Healthcare analytics, AI solutions for biological big data, providing an AI platform for the biotech, life sciences, medical and pharmaceutical industries, as well as for related technological approaches, i.e., curation and text analysis with machine learning and other activities related to AI applications to these industries.
Background: To date, antiangiogenic therapy has failed to improve overall survival in cancer patients when used in the adjuvant setting (local-regional disease with no detectable systemic metastasis). The presence of lymph node metastases worsens prognosis, however their reliance on angiogenesis for growth has not been reported.
Methods: Here, we introduce a novel chronic lymph node window (CLNW) model to facilitate new discoveries in the growth and spread of lymph node metastases. We use the CLNW in multiple models of spontaneous lymphatic metastases in mice to study the vasculature of metastatic lymph nodes (n = 9–12). We further test our results in patient samples (n = 20 colon cancer patients; n = 20 head and neck cancer patients). Finally, we test the ability of antiangiogenic therapy to inhibit metastatic growth in the CLNW. All statistical tests were two-sided.
Results: Using the CLNW, we reveal the surprising lack of sprouting angiogenesis during metastatic growth, despite the presence of hypoxia in some lesions. Treatment with two different antiangiogenic therapies showed no effect on the growth or vascular density of lymph node metastases (day 10: untreated mean = 1.2%, 95% confidence interval [CI] = 0.7% to 1.7%; control mean = 0.7%, 95% CI = 0.1% to 1.3%; DC101 mean = 0.4%, 95% CI = 0.0% to 3.3%; sunitinib mean = 0.5%, 95% CI = 0.0% to 1.0%, analysis of variance P = .34). We confirmed these findings in clinical specimens, including the lack of reduction in blood vessel density in lymph node metastases in patients treated with bevacizumab (no bevacizumab group mean = 257 vessels/mm2, 95% CI = 149 to 365 vessels/mm2; bevacizumab group mean = 327 vessels/mm2, 95% CI = 140 to 514 vessels/mm2, P = .78).
Conclusion: We provide preclinical and clinical evidence that sprouting angiogenesis does not occur during the growth of lymph node metastases, and thus reveals a new mechanism of treatment resistance to antiangiogenic therapy in adjuvant settings. The targets of clinically approved angiogenesis inhibitors are not active during early cancer progression in the lymph node, suggesting that inhibitors of sprouting angiogenesis as a class will not be effective in treating lymph node metastases.
Introduction
Although antiangiogenic therapy is standard of care for several advanced (metastatic) cancers, all phase III clinical trials of antiangiogenic therapy to date have failed in the adjuvant setting.[1–4] The presence of lymph node metastases—the most common form of cancer dissemination—dictates treatment decisions,[5,6] however their reliance on angiogenesis for growth has not been reported. Furthermore, observations from preclinical and clinical studies suggest that lymph node metastases and primary tumors can respond differently to the same therapeutic regimen.[7–9] The clinical relevance of lymph node metastases has been the subject of debate for many years. Some argue that the presence of lymph node metastasis only demonstrates the ability of the cancer to metastasize and that disease in the lymph node is inconsequential.[10,11] The strong predictive power of lymph node metastases has led others to hypothesize that cancer cells in the lymph node can exit and spread to distant metastatic sites.[12,13] These advocates argue disease in lymph nodes needs to be treated in order to prevent distant metastasis and ultimately eradicate disease from the patient.[14,15] Likely the answer lies in between, depending where on the spectrum of progression to distant metastasis the cancer is diagnosed.[16]These issues highlight our fundamental lack of understanding of the biology of how metastatic cancer cells grow in a lymph node and affect the overall prognosis for the patient, limiting our ability to discover effective adjuvant therapy to treat lymph node metastases.
We and others have previously shown that antiangiogenic therapy did not stop the seeding or growth of lymph node metastases,[9,17,18] but no mechanism of failure has been determined. Nonsprouting angiogenesis mechanisms to sustain tumor growth, such as vessel co-option and intussusception, have been implicated in the growth of lung, liver, and brain metastases[19] and are thought to play a role in resistance to antiangiogenic therapy.[20] Based on these findings, we hypothesized that early growth of lymph node metastases is not dependent on sprouting angiogenesis.
Although reports show reduced vascular density in lymph node metastases compared with corresponding primary tumors and surrounding normal lymph node,[17,21,22] these data do not describe the degree of angiogenesis or whether the vessels are functional. Here, we introduce a novel model to longitudinally image the formation and growth of metastatic tumors in lymph nodes and reveal the surprising lack of sprouting angiogenesis, despite the presence of hypoxia in some lesions. Treatment with two different therapies designed to target sprouting angiogenesis showed no effect on the growth or vascular density of lymph node metastases in our models. These data are corroborated in clinical specimens and further add to mechanisms for the failure of antiangiogenic treatments in adjuvant settings.[1–4,20]
….
Intravital Multiphoton Microscopy
Intravital multiphoton microscopy was carried out as described previously on a custom-built multiphoton microscope.[25] Details of the imaging equipment, imaging protocols, and image analysis can be found in the Supplementary Methods http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1 (available online).
….
Longitudinal Imaging of the Formation of Spontaneous Lymph Node Metastases Using a Novel Chronic Lymph Node Window
Holding back our understanding of the biology of lymph node metastasis is our inability to longitudinally monitor spontaneous lymph node metastases. Inspired by pioneering intravital microscopy of the lymph node,[30–35] we developed a chronic lymph node window (CLNW)—a modification of the mammary fat pad chamber[23,24]—to create a CLNW that allows intravital imaging for up to 14 days with minimal morphological, cellular or biochemical changes in the inguinal lymph node (Figure 1, A and B; Supplementary Figure 1,http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1 available online).
Using multiphoton microscopy in the CLNW, we were able to serially image various stages of the growth of spontaneous metastasis in the lymph node from murine SCCVII squamous cell carcinoma[36,37]transduced with green fluorescence protein (SCCVII-GFP) (Figure 1C). Initially, cancer cells remain in or near the subcapsular sinus as individual cells (Figure 1C). Later, small aggregates of a few cancer cells form near the subcapsular sinus, which then grow into metastatic lesions that invade deeper into the lymph node (Figure 1C). This sequence was also observed in syngeneic MCa-P0008 breast cancer and B16F10 melanoma cells lines (Supplementary Figure 2,http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1 available online).
Recent genomic studies suggest that metastatic cells within lymph nodes consist of multiple clones.[38,39]To investigate this concept, we transduced SCCVII and SCCVII-GFP cells with a red fluorescence protein (DsRed), producing three different colors of cells (red, green, and red+green) that were mixed in equal proportions to form primary tumors. Single cells of multiple colors disseminated from the multicolor primary tumor and grew in the subcapsular sinus (Figure 1D). The metastatic lesions that subsequently formed contained all three colors with great spatial heterogeneity (Figure 1D), suggesting that lymph node metastases form from multiple cells. These findings were reproduced when using an equal mix of 4T1-DsRed and 4T1-GFP mammary carcinoma cells implanted in the mammary fat pad. In contrast, more than 80% of detected lung metastases from these 4T1 tumors were single color (Figure 1E).
The Role of the Existing Lymph Node Vascular Supply in Supporting the Growth of Lymph Node Metastases
Next, we directly measured for the first time whether angiogenesis is occurring in lymph node metastases by using intravital multiphoton microscopy to make longitudinal measurements in our CLNW. In early stages, metastatic cells resided in the lymph node sinus, away from blood vessels (Figure 2A). These metastatic tumor cells eventually invaded the lymph node cortex, growing closer to functional lymph node blood vessels and presumably utilizing the nutrient supply of these pre-existing vessels (Figure 2A). We found that the tumor cells started to access host lymph node blood vessels when they invaded approximately 50 to 100 μm into the cortex (Figure 2, B and C). Although the tumor invaded deeper into the node (day 6 mean depth = 43 μm, 95% CI = 24 to 61 μm; day 12 mean depth = 131 μm, 95% CI = 71 to 191 μm, P = .01), blood vessels did not invade toward the surface of the lymph node (day 6 mean depth = 52 μm, 95% CI = 49 to 55 μm; day 20 mean depth = 58 μm, 95% CI = 41 to 75 μm,P = .38), as would be expected for tumor-induced sprouting angiogenesis. These data provide the first direct evidence of the lack of sprouting angiogenesis during the growth of metastatic lesions in the lymph node.
Figure 2.
Intravital imaging of lymph node metastases and the native lymph node vasculature. A) Representative time course of images from a single metastatic lymph node, showing cancer cells (SCCVII, green) and blood vessels (TRITC-dextran, red) at three different depths in tissue. The image was created using multiphoton microscopy, and second harmonic generation was used to highlight fibrillar collagen (blue) in the lymph node capsule. The images are created from maximum intensity projections of 25 μm of tissue from inside the lymph node. In day 40 images, the red signal is background signal from the accumulation of TRITC-dextran as a result of the five intravenous injections over the course of the metastatic growth. Yellow arrows identify individual cancer cells. Yellow circles identify areas in which many cancer cells are found in the subcapsular sinus. White arrows identify blood vessels in the metastatic lesion. Purple, green and light blue arrows identify features in the lymph node vasculature that can be used to identify the same region in the mouse over the multiday experiment. White line marks edge of lymph node. Scale bars = 100 μm. B) A vertical image reconstruction showing the tumor cells (SCCVII, green) initially growing above the blood vessels (red). C) Measurements of the maximum depth of tumor cell invasion (SCCVII) and the minimum depth of blood vessels. Data are presented as mean ± 95% confidence interval.
Immunofluorescent staining for CD31 (Figure 3A) showed that the vessel density in lymph nodes with micrometastases from SCCVII tumors (Figure 3B) and macrometastases (lesions greater than 500 microns in one dimension) from 4T1 tumors (Figures 3E; Supplementary Figure 3A,http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1 available online) were not increased compared with those of control (from naïve mice with no tumor implantation) and contralateral nodes. The vessel density inside metastatic lesions was lower than the surrounding lymph node tissue (vessel density: SCCVII: metastatic lesion = 1.0%, 95% CI = 0.0% to 2.0%; nontumor area = 7.0%, 95% CI = 1.0% to 13.0%, P = .04; 4T1: metastatic lesion = 4.0%, 95% CI = 1.0% to 7.0%; nontumor area = 10.0%, 95% CI = 5.0% to 15.0%, P = .04) (Figure 3, C and F). To indicate sprouting angiogenesis, Ki67—a marker of cell proliferation—showed no difference in endothelial cell proliferation in micrometastatic lymph nodes (SCCVII) (Figure 3D; Supplementary Figure 4,http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1 available online) and a reduction in endothelial cell proliferation in macrometastatic lymph nodes (4T1) (Figure 3G; Supplementary Figure 3B, http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1 available online) in comparison with control and contralateral nodes. Vessel density in the metastatic lesions was not related to lesion size (Supplementary Figure 3C, http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1 available online). These data further indicate that sprouting angiogenesis is not induced in the lymph node at this stage of cancer progression.
Figure 3.
Immunohistochemical analysis of lymph node blood vessels and metastases. A) Representative sections of control (from non–tumor bearing mice), contralateral, and tumor-draining lymph nodes with micrometastases (SCCVII, green). Vessels were stained with CD31 (red) and nuclei with DAPI (blue).Scale bars = 300 μm. B) Quantification of CD31+ area per lymph node area in control, contralateral, and micrometastatic lymph nodes. C) In micrometastatic lymph nodes, quantification of CD31+ area per tissue area comparing tumor areas with nontumor areas. D) Costaining for CD105 and Ki67 measured blood vessel proliferation in micrometastatic lymph nodes. E) Using a different tumor model (4T1) that formed macrometastasis in the lymph node (greater than 500 μm in one direction), we measured CD31+ area in micrometastatic or macrometastatic lymph nodes, compared with control or contralateral nodes. F) The vascular area of macrometastatic lesions was measured in tumor areas and nontumor lymph node tissue. G) Costaining for CD31 and Ki67 measured blood vessel proliferation in macrometastatic lymph nodes. Data are presented as mean ± 95% confidence interval. Statistical significance was tested by one-way analysis of variance with Tukey’s Honestly Significant Difference post hoc test (B, D, E, G) or two-tailed paired Student’s t test (C, F).
In contrast, LYVE-1 staining for lymphatic vessels showed an increase in lymphatic vascular area (vessel density: SCCVII: control = 5.0%, 95% CI = 3.0% to 7.0%; contralateral = 8.0%, 95% CI = 6.0% to 10.0%; metastatic = 10.0%, 95% CI = 6.0% to 14.0%; control vs metastatic P = .03; 4T1: control = 5.0%, 95% CI = 2.0% to 8.0%; contralateral = 9.0%, 95% CI = 6.0% to 12.0%; nonmetastatic tumor draining = 22.0%, 95% CI = 18.0% to 26.0%; metastatic = 4.0%, 95% CI = 1.0% to 7.0%; control vs nonmetastatic tumor draining P < .001) and proliferating lymphatic endothelial cells in draining lymph nodes from SCCVII and 4T1 tumors (Supplementary Figures 5 and 6,http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1 available online), consistent with previous reports.[40–43] Interestingly, the lymphatic vascular area was greater in the contralateral and nonmetastatic tumor-draining lymph nodes of 4T1-bearing mice compared with lymph nodes with macrometastatic lesions (P < .001) (Supplementary Figure 6,http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1 available online), suggesting that the presence of cancer cells causes the lymphatic vasculature to regress. When compared with lymph nodes from tumor-naïve animals, contralateral lymph nodes show greater lymphatic vascular density (SCCVII: P = .04; 4T1: P < .001), suggesting that contralateral lymph nodes are also affected by the presence of the primary tumor, as others have reported.[44]
Although lesions growing in the subcapsular sinus of the lymph node showed markers for hypoxia (Figure 4, A–D), sprouting angiogenesis was not induced in these lesions and they remained avascular. Metastatic lesions that invaded the lymph node parenchyma where functional nodal blood vessels reside had only focally heterogeneous areas positive for hypoxia markers (Figure 4, A, C, and E). These data suggest that growing metastatic lesions can utilize the existing lymph node vasculature in order to meet their metabolic demand. Whether this demand or hypoxia drives cancer cell invasion of the lymph node remains unknown.
Figure 4.
Hypoxia in lymph node metastases. A) Representative images of pimonidazole staining for hypoxia (green) and perfused lectin staining for functional blood vessels (red) in lymph node metastases from 4T1 mammary carcinoma (cytokeratin, blue). The top panels show a lesion in the subcapsular sinus that is hypoxic and has no perfused blood vessels in the lesion. The bottom panels show a lesion in the parenchyma of the lymph node with perfused blood vessels and no hypoxia. Dashed line shows edge of the lymph node. Scale bars = 100 μm. B) Higher magnification of pimonidazole staining in metastatic lymph node showing colocalization of cytokeratin and pimonidazole. Contralateral lymph node is non–tumor bearing. Dashed line shows edge of the lymph node. Scale bars = 50 μm. C) Quantification of pimonidazole and perfused vessel staining in metastatic lesions in the subcapsular sinus and lymph node parenchyma. Data are presented as mean ± 95% confidence interval. Statistical significance was tested by two-tailed unpaired Student’s t test. D and E) Staining for CAIX, a marker of the cellular response to hypoxia, and CD31-positive blood vessels shows similar results to pimonidazole staining. Dashed line shows the outline of the metastatic lesions. Scale bars = 636 μm.
Hypoxia generally induces the production of vascular endothelial growth factor (VEGF). However, VEGF levels in control, contralateral, and metastatic lymph nodes were not different (4T1: control = 0.3 pg VEGF/mg protein, 95% CI = 0.2 to 0.4 pg VEGF/mg protein; contralateral = 0.4 pg VEGF/mg protein, 95% CI = 0.3 to 0.5 pg VEGF/mg protein; metastatic = 0.5 pg VEGF/mg protein, 95% CI = 0.2 to 0.8 pg VEGF/mg protein; Figure 5A; SCCVII: control = 0.4 pg VEGF/mg protein, 95% CI = 0.3 to 0.5 pg VEGF/mg protein; contralateral = 0.4 pg VEGF/mg protein, 95% CI = 0.3 to 0.5 pg VEGF/mg protein; metastatic = 0.4 pg VEGF/mg protein, 95% CI = 0.3 to 0.5 pg VEGF/mg protein; Figure 5B; and E0771: control = 0.3 pg VEGF/mg protein, 95% CI = 0.2 to 0.4 pg VEGF/mg protein; contralateral = 0.4 pg VEGF/mg protein, 95% CI = 0.3 to 0.5 pg VEGF/mg protein; metastatic = 0.4 pg VEGF/mg protein, 95% CI = 0.3 to 0.5 pg VEGF/mg protein; Figure 5C; all P values > .05 for each ANOVA containing these three lymph nodes types). Furthermore, levels of VEGF-C and VEGF-D were lower in metastatic and nonmetastatic tumor draining lymph nodes when compared with naïve lymph nodes (Supplementary Figure 6, C and D, http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1 available online). Next, we screened for transcriptional changes in sprouting angiogenesis-related genes in lymph nodes with metastasis when compared with naïve lymph nodes. No pro-angiogenesis related genes were upregulated in metastatic lymph nodes, but thrombospondin-1 (Thbs-1) and TIMP-1—both of which are antiangiogenic—were upregulated (Figure 5D). We confirmed no change in Vegf levels (control = 0.24 VEGF/GAPDH, 95% CI = 0.06 to 0.42 VEGF/GAPDH; metastatic = 0.16 VEGF/GAPDH, 95% CI = 0.04 to 0.28 VEGF/GAPDH, P = .37) and the elevation in Thbs-1 in lymph node metastasis by quantitative polymerase chain reaction (qPCR) (control = 0.10 THBS-1/GAPDH, 95% CI = 0.05 to 0.15 THBS-1/GAPDH; metastatic = 0.38 THBS-1/GAPDH, 95% CI = 0.23 to 0.53 THBS-1/GAPDH; P = .001) (Figure 5E). Thrombospondin-1 (TSP-1) was specifically located surrounding the blood vessels of control, contralateral, and metastatic lymph nodes (Figure 5F), further defining the nonangiogenic phenotype associated with these vessels. Taken together, these data describe an environment lacking prosprouting angiogenesis stimuli and abundant in antiangiogenesis molecules, suggesting metastatic lesions in the lymph node do not induce nor rely upon sprouting angiogenesis during their early growth.
Figure 5.
Molecular signature of quiescent lymph node vasculature. A-C) Levels of vascular endothelial growth factor (VEGF) protein were measured in metastatic lymph nodes containing 4T1 (A), SCCVII (B), or E0771 (C) and compared with control and contralateral lymph nodes. D) Quantitative polymerase chain reaction (qPCR) transcriptional array for angiogenesis-related genes compared the transcriptional profile of a diaeresis lymph node to a tumor-bearing lymph node. Differentially transcribed genes were defined as having more than a four-fold change and a P value under .01 when comparing metastatic lymph nodes to diaeresis lymph nodes. E) Confirmation of the qPCR transcriptional array for the Vegf and Thbs1 genes. *P < .05. F) Dual immunofluorescence staining for CD31 (red) and TSP-1 (green) showed distinctive TSP-1 staining surrounding the blood vessels in diaeresis, contralateral, and metastatic lymph nodes. Scale bars = 100μm. Data are presented as mean ± 95% confidence interval. Statistical significance was tested by one-way analysis of variance with Tukey’s Honestly Significant Difference post hoc test (A, B, and C) and two-tailed unpaired Student’s t test (E).
Blood Vessel Density in Metastatic Lymph Nodes From Colon Cancer and Head and Neck Cancer Patients
To confirm these findings in clinical specimens in a cancer where angiogenesis inhibitors have shown efficacy, we stained lymph nodes from 20 colon cancer patients with lymphatic metastasis for CD31 (Figure 6A; Supplementary Figure 7A, http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1available online). These patients did not have metastases on initial staging and went directly for surgical resection with no prior cancer-directed treatments (eg, chemotherapy, radiation therapy). We found that blood vessel densities in metastatic lymph nodes and large metastatic lesions where lymph node tissue was completely replaced with tumor cells were on average lower than those of tumor-negative lymph nodes (nonmetastatic- = 220 blood vessels/mm2, 95% CI = 172 to 268 blood vessels/mm2; metastatic = 135 blood vessels/mm2, 95% CI = 113 to 157 blood vessels/mm2; lymph node replaced by cancer = 104 blood vessels/mm2, 95% CI = 75 to 133 blood vessels/mm2; comparisons of either group of tumor-bearing to nonmetastatic lymph nodes: P < .001) (Figure 6, B and C). Furthermore, the vessel density inside metastatic lesions was statistically significantly lower than in the remaining lymph node tissue (metastatic lesion = 148 blood vessels/mm2, 95% CI = 124 to 172 blood vessels/mm2; nontumor area = 115 blood vessels/mm2, 95% CI = 95 to 135 blood vessels/mm2, P = .03) (Figure 6, D and E). Accordingly, TSP-1 staining was also found to associate with lymph node blood vessels and to surround the gland-like structures formed by the cancer cells (Supplementary Figure 7B,http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1 available online), further suggesting that these vessels were not undergoing sprouting angiogenesis. Finally, the density of CD31-positive vessels was not dependent on the lesion size in the section, showing that vessel densities of macrometastases (clinically classified as lesions larger than 2mm in one direction[45]]) are the same as in micrometastases (Figure 6F). Blood vessel density and TSP-1 staining in specimens from head and neck cancer patients were similar to those from colon cancer patients (Supplementary Figure 7, C–G,http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1 available online). Taken together, these data from two different patient populations support the concept that the growth of metastatic lesions in the lymph nodes is not dependent upon sprouting angiogenesis.
Figure 6.
Vascular density in metastatic lymph nodes from colon cancer patients. A) Representative images of nonmetastatic (n = 19) and metastatic (n = 39) lymph nodes as well as lymph node tumors in which no normal lymph node tissue remained (n = 9). The sections were stained with CD31 (brown) to identify blood vessels. Scale bars = 200 μm. Images of whole lymph node sections can be found in Supplementary Figure 7 (available online). B) The number of vessels per area as determined by CD31 staining was measured in metastatic lymph nodes and in lymph node tumors in which no normal lymph node tissue remained and compared with nonmetastatic lymph nodes. C) The fraction of lymph node area composed of CD31-positive vessels was similarly measured in metastatic lymph nodes and in lymph node tumors in which no normal lymph node tissue remained and compared with nonmetastatic lymph nodes. *P value was determined by Tukey’s Honestly Significant Difference post hoc test of analysis of variance model. D and E) Within a metastatic lymph node, vascular density (D) and vessel area fraction (E) were measured in the tumor and the nontumor area. * P value was determined by paired Student’s t test.F) Vessel density was not dependent on the lesion size. Data are presented as mean ± 95% confidence interval throughout figure.
Growth of Lymph Node Metastases With Antiangiogenic Treatment
To directly measure the response of lymph node metastases to antiangiogenic therapy in the CLNW, we began treatment when micrometastases were between 100 and 125 μm in diameter (5–10×10–3 mm3)—the stage when we found blood vessels surrounding lymph node metastases—with either a monoclonal VEGF receptor (VEGFR)-2–blocking antibody (DC101, ImClone Systems) or the pan-VEGFR small-molecule tyrosine kinase inhibitor sunitinib. We chose agents with differential mechanisms of VEGF pathway inhibition—monoclonal antibody vs tyrosine kinase inhibitor (TKI)—to understand whether our findings were agent specific. Measuring lymph node blood vessels using the CLNW and longitudinal multiphoton microscopy, the growth of lymph node metastases (Figure 7, A–C) and functional blood vessel volume density remained at similar levels during treatment with either DC101 or sunitinib when compared with untreated controls (vessel density: day 10: untreated = 1.2%, 95% CI = 0.7% to 1.7%; control = 0.7%, 95% CI = 0.1% to 1.3%; DC101 = 0.4%, 95% CI = 0.0% to 3.3%; sunitinib = 0.5%, 95% CI = 0.0% to 1.0%; ANOVA P = .34) (Figure 7D). These direct measurements, supported by previous endpoint studies,[9,17] suggest that inhibitors of sprouting angiogenesis as a class of drugs will not be effective in inhibiting the early phase of lymph node metastasis. In contrast, sunitinib—a pan-VEGF receptor TKI—reduced the elevated lymphatic vessel density found in early metastatic lymph nodes compared with PBS control (Supplementary Figure 8, http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1 available online).
Figure 7.
Antiangiogenic therapy in the early growth of lymph node metastases. A) Representative intravital multiphoton microscopy images of spontaneous lymph node metastases treated with vehicle control, sunitinib, or the blocking monoclonal anti–VEGFR-2 antibody DC101. Tumor cells are shown in green and blood vessels in red. Scale bars = 200 μm. B) Primary tumors were of equal size at the time treatment began, when the lymph node micrometastases were 5–10×10–3 mm3. C) The growth rate of the metastatic tumor in the lymph node was measured during antiangiogenesis therapy. D) The vessel density in metastatic lesions in the lymph node was measured during antiangiogenesis therapy. Biological replicates: untreated n = 15 (C), 12 (D), control (IgG = 2, PBS = 4) n = 6, sunitinib = 6, DC101 = 5. Data are presented as mean ± 95% confidence interval. Statistical significance was tested by one-way analysis of variance with Tukey’s Honestly Significant Difference post hoc test (B and C) and two-tailed unpaired Student’s t test (D and E).
Blood Vessel Density of Lymph Node Metastasis From Patients Treated With Bevacizumab
Finally, we identified rectal cancer patients that received neoadjuvant chemoradiation and bevacizumab and a comparator cohort of rectal cancer patients who received only neoadjuvant chemoradiation, as previously described.[46,47] Despite downstaging of the primary tumor after neoadjuvant therapy, lymph node metastases were often found at the time of surgery and pathological evaluation. Comparing lymph node metastases from 10 patients in each group, we found no difference in the vessel density in lymph node metastases (no bevacizumab group mean = 257 vessels/mm2, 95% CI = 149 to 365 vessels/mm2; bevacizumab group mean = 327 vessels/mm2, 95% CI = 140 to 514 vessels/mm2, P = .78) (Figure 8, A and B). The vascular density in the tumor lesions specifically was also not different between the groups (no bevacizumab group mean = 307 blood vessels/mm2, 95% CI = 186 to 428 vessels/mm2; bevacizumab group mean = 318 blood vessels/mm2, 95% CI = 118 to 518 vessels/mm2, P = .60) (Figure 8, C and D). Metastatic lymph nodes showed lower vascular density than nonmetastatic nodes after neoadjuvant therapy (Figure 8, A and B), independent of whether bevacizumab was used. Finally, lymphatic vessel density was not different in metastatic and nonmetastatic lymph nodes when comparing patients who received bevacizumab to those who did not (Supplementary Figure 8, D and E, http://jnci.oxfordjournals.org/content/107/9/djv155/suppl/DC1 available online). These data provide the first clinical evidence for the lack of response of lymph node metastasis to antiangiogenic therapy.
Figure 8.
Vascular density in lymph node metastases in rectal cancer patients treated with bevacizumab. The number of CD31+ vessels per area (A) and the fraction of lymph node area composed of CD31+ vessels(B) were measured in nonmetastatic and metastatic lymph nodes in colorectal cancer (CRC) patients that received neoadjuvant chemoradiation (No Bev.) or neoadjuvant chemoradiation with bevacizumab (Bev.).P value was determined by two-tailed unpaired Student’s t test. C and D) Within the tumor area of metastatic lymph nodes, we measured vascular density (C) and vessel area fraction (D) in rectal cancer patients that received neoadjuvant chemoradiation (No Bev.) or neoadjuvant chemoradiation with bevacizumab (Bev.). P value was determined by two-tailed unpaired Student’s t test. Data are presented as mean ± 95% confidence interval.
Discussion
The main concept driving antiangiogenic therapy has been the hypothesis that tumors depend on new blood vessel growth. A critical observation made by longitudinal intravital microscopy in the CLNW is that metastatic lesions did not induce sprouting angiogenesis as they grew, in spite of the presence of hypoxia. Lesions that invaded into the blood vessel–rich lymph node parenchyma showed reduced hypoxia, suggesting that cancer cells survive in the lymph node by utilizing the existing lymph node vascular supply. The lack of VEGF, VEGF-C, and VEGF-D, along with the presence of TSP-1 surrounding lymph node blood vessels, provides a mechanism behind the lack of sprouting angiogenesis observed in lymph node metastases. A limitation of the use of longitudinal intravital microscopy is the limited imaging depth of 300 μm by multiphoton microscopy in the CLNW. To balance this, we used histological techniques, which allow full lymph node depth to be characterized but are limited in their ability to monitor the kinetic changes occurring as metastatic lesions grow in the lymph node. Using these complimentary techniques allowed better characterization of the growth of lymphatic metastases.
Our data show lymph node lymphangiogenesis is an early event in the natural history of cancer progression, in agreement with previous studies.[40,41,43] However, decreased lymphatic vessel density was found in macrometastatic lymph nodes, suggesting that the presence of the cancer cells in the lymph node causes lymphatic vessel regression. Furthermore, bevacizumab did not statistically significantly affect the lymphatic vasculature in patients. These data suggest that late intervention with antiangiogenic or antilymphangiogenic therapies after lymphatic vessel regression has begun in patients will show no effect on lymph node lymphatic vessels.
In patients, the observation that large metastatic lesions do not exhibit increased vascular density relative to those with micrometastases further suggests that sprouting angiogenesis is not required to sustain the growth of lymph node metastases. A limitation of our data is that we estimated lesion size based on the two-dimensional area available in the histological sections, so we are likely underestimating the size of the lesion. An additional limitation of our study is that we cannot rule out the contribution from different modes of new blood vessel formation in lymph node metastasis such as vasculogenesis, intussusception, vessel co-option, vascular mimicry, and tumor cell differentiation into endothelial cells.[20] The mechanisms of these alternative processes are not clearly defined, although VEGF and endothelial proliferation have been shown to contribute to these processes.[48–51] Our preclinical and clinical data, however, show that inhibitors targeting primarily sprouting angiogenesis will not inhibit the growth of metastases in the lymph node.
Predicted by recent genomic data,[38,39,52] we provide direct evidence that lymph node metastasis forms from multiple cells that disseminate from the primary tumor and suggest a fundamental difference in their formation compared with hematogenous metastases. Cancer cells that invade lymphatic vessels travel to the draining lymph node where they enter in locations defined by afferent lymphatic vessels. As such, lymph node metastasis can be reinforced by the continual arrival of new cells as they gain a foothold in their new microenvironment, leading to the spatially heterogeneous lesions imaged here and the genetically heterogeneous lesions documented previously.[38,39,52,53] In contrast, cells that metastasize through the blood spread out to different locations in an organ by the branching vasculature, leading to a higher probability of individually homogenous lesions. One can thus speculate that targeting a single genetic trait, unless ubiquitous in the primary tumor, may not be effective in eradicating lymph node metastases and any subsequent spread to distant sites.[39]
Using multiple spontaneous metastasis models, we show the first direct evidence that sprouting angiogenesis is not required in lymph node lesions during early metastatic growth. The lack of sprouting angiogenesis in lymph node metastases suggests an additional explanation for the poor outcomes of antiangiogenic therapy in adjuvant settings. As the lymph node is able to metabolically support rapid cellular expansion during an active immune response, it seems the existing vasculature of the lymph node is also able to support the growth of a nascent metastasis. Thus, the mechanisms of angiogenesis and the targets of clinically approved drugs are not active during this early step in cancer progression, suggesting that inhibitors of sprouting angiogenesis as a class will not be effective in treating lymph node metastases. Our novel preclinical models provide opportunities to uncover strategies to better control and eradicate disease in lymph nodes in metastatic cancer patients.
Gene Mutation Signals Poor Prognosis for Pancreatic Tumors
NASHVILLE, Tennessee — For patients with pancreatic neuroendocrine tumors, the presence of recently identified mutations in two key genes is a prognostic factor for poor outcome, researchers report.
“We found loss of nuclear expression in about 23% of the tumors that we studied, and this loss of expression was associated with worse tumors from the outset,” lead investigator Michelle Heayn, MD, a second-year pathology resident at the University of Pittsburgh Medical Center, told Medscape Medical News.
Pancreatic tumors with neuroendocrine histology frequently respond to chemotherapy and have a more favorable prognosis than the more common pancreatic adenocarcinomas. However, the mutations are associated with worse disease-free and disease-specific survival.
The results of the study were presented here at the College of American Pathologists 2015 Meeting.
The mutations — in the alpha-thalassemia mental retardation syndrome X-linked gene (ATRX) and the death-domain-associated protein gene (DAXX) — cause loss of expression of the proteins coded by ATRX and DAXX, Dr Heayn explained.
We found loss of nuclear expression in about 23% of the tumors that we studied.
To test whether these mutations had any prognostic significance, Dr Heayn and her colleagues used immunolabeling in surgically resected pancreatic neuroendocrine tumors from 303 patients. They then correlated the findings with patient demographics, pathologic features, disease-free survival, and disease-specific survival. Follow-up ranged from 1.6 to 18.8 years.
Of the 303 tumors, 69 (23%) had mutations in one or both genes. Tumors with a gene mutation had a larger mean diameter than tumors with intact gene expression (5.0 vs 2.4 cm), as well as a significantly higher histologic grade, more lymphovascular and perineural invasion, a more advanced T stage, greater lymph node involvement, more synchronous metastases, and more frequent disease recurrence (P < .01 for all comparisons).
In addition, the mutations were associated with shorter mean disease-free survival (5.6 vs 17.2 years;P < .01) and shorter mean disease-specific survival (12.5 vs 17.7 years; P = .01).
On multivariate analysis that controlled for patient and tumor factors, the mutations were a significant predictor of shorter disease-free survival (P < .01), independent of tumor size, stage, histology, lymphovascular or perineural invasion, and lymph node status.
Dr Heayn and her colleagues are currently exploring whether there is an association between metastatic pancreatic cancer and these genetic mutations.
Metastatic Pancreatic Cancer
Patients with these mutations in their tumors should be followed more closely for recurrence or disease progression, Dr Heayn said. And in this subset of patients, there is the possibility of new targeted therapies.
These findings are very important, said Safia Salaria, MD, from the Vanderbilt University Medical Center in Nashville.
“There is so much heterogeneity in these tumors, and currently we are just using clinicopathologic features and the WHO-recommended Ki-67 labelling and white count,” she told Medscape Medical News.
“If we have something that can be an adjunct to that — immunohistochemistry to determine the loss of these genes — it’s definitely going to be something that will help us, especially in low-grade tumors,” she explained.
Staining for the expression of the genes could also help pathologists identify patients who are at higher risk for disease recurrence or metastasis but don’t have metastases at the time of primary resection, Dr Salaria said.
Microbiome May Predict Colon Cancer Tumor Mutational Status
BALTIMORE — Analysis of the microbiome surrounding colon cancer tumors could be used as a noninvasive screening test that is more sensitive and specific than fecal occult blood testing, according to the results of a new study.
“This is something that could be critical in colon cancer, because each tumor may have a different mutational landscape with different genes mutated, and that might have an effect on the microbiome,” said Ran Blekhman, PhD, from the University of Minnesota in Minneapolis.
The results of the study were presented here at the American Society of Human Genetics 2015.
Dr Blekhman and his colleagues looked at the genetic differences between healthy colon cells and tumor cells from adults with colorectal cancer, and found that specific tumor mutations are associated with the presence of specific bacteria in the gut.
For example, in people with an APC gene mutation, there is a strong association between familial adenomatous polyposis, a hereditary cancer syndrome, and an abundance of Fusobacterium, said Dr Blekhman.
He pointed out that his lab is the first to analyze the correlation between specific tumor mutations and the composition of the tumor microbiome.
More Mutations, More Diversity
The investigators used whole-exome sequencing to assess the protein-coding regions of tumors and microbiome profiling to characterize the microbiota in tumor biopsy specimens and normal colon tissue samples from 44 adults with colon cancer.
They found that the more mutations, the more varied the bacterial species in the tumor microbiome.
And for certain genes, there was a correlation between somatic mutations and changes in the abundance of specific microbes.
Other evidence of the correlation between bacteria and tumor was seen at the pathway level.
Loss-of-function mutations were detected in tumor glucose transport pathways and were strongly correlated with higher levels of energy utilization in the microbiome, said Dr Blekhman. This suggests that the tumor and the bacteria in its neighborhood are competing for bodily resources.
The investigators created a risk index that evaluated the correlation between microbes and each of several known tumor driver mutations. The index was able to accurately predict the presence of a loss-of-function mutation in ZFN717, a gene encoding for a zinc finger nuclease, part of a family of enzymes involved in DNA repair.
These findings suggest that it is possible to genetically classify tumors from fecal samples alone. Theoretically, this means that manipulation of the tumor microenvironment could be used to prevent or treat colon cancer, Dr Blekhman explained.
This study addresses, in part, the problem of “hidden heritability,” said Chris Gunter, PhD, from Emory University School of Medicine in Atlanta.
“If you look at cancer-sequencing studies now, they identify something like 10 possible driver mutations. We have not yet managed to predict what all the drivers and passengers will be,” she told Medscape Medical News.
“If this type of work can help us narrow down the list, that should add to our understanding of how cancer develops,” she said.
Notes On Tumor Heterogeneity: Targets and Mechanisms, from the 2015 AACR Meeting in Philadelphia PA
Reporter: Stephen J. Williams, Ph.D.
The following contain notes from the Sunday April 19, 2015 AACR Meeting (Pennsylvania Convention Center, Philadelphia PA) 1 PM Major Symposium Session on Tumor Heterogeneity: Targets and Mechanism chaired by Dr. Charles Swanton.
Tumor heterogeneity is a common feature of many malignancies, especially the solid tumors and can drive the evolution and adaptation of the growing tumor, complicating therapy and resulting in therapeutic failure, including resistance. This session at AACR described the mechanisms, both genetic and epigenetic, which precipitate intratumor heterogeneity and how mutational processes and chromosomal instability may impact the tumor progression and the origin of driver events during tumor evolution. Finally the session examined possible therapeutic strategies to take advantage of, and overcome, tumor evolution. The session was chaired by Dr. Charles Swanton. For a more complete description of his work, tumor heterogeneity, and an interview on this site please click on the link below:
This paper described the longitudinal Whole Genome Sequencing (WGS) study of a 35 year old female whose primary glioblastoma (GBM) was followed through temozolomide treatment and ultimately recurrence.
In 2008 patient was diagnosed with primary GBM (three biopsies of unrelated sites were Grade II and Grade IV; temozolomide therapy for three years then relapse in 2011
WGS of 2 areas of primary tumor showed extensive mutational and copy number heterogeneity; was able to identify clonal TP53 mutations and clonal IDH1 mutation in primary tumor with different patterns of clonality based on grade
Amplifications on chromosome 4 and 12 (PDGFRA, KIT, CDK4)
After three years of temozolomide multiple translocations found in chromosome 4 and 12 (6 translocations)
Clonal IDH1 R132H mutation in primary tumor only at very low frequency in recurrent tumor
The WGS on recurrent tumor (sequencing took ONLY 9 days from tumor resection to sequence results) showed mutation cluster in KIT/PDGFRA.PI3K.mTOR axis so patient treated with imatinib
However despite rapid sequencing and a personalized approach based on WGS results, tumor progressed and patient died shortly: tumor evolution is HUGE hurdle for personalized medicine
As Dr. Swanton stated:
“we are underestimating the frequency of polyclonal evolution”
analyzed nine cancer types to determine the subclonal frequencies of driver events, to time mutational processes during cancer evolution, and to identify drivers of subclonal expansions.
identified later subclonal “actionable” mutations, including BRAF (V600E), IDH1 (R132H), PIK3CA (E545K), EGFR (L858R), and KRAS (G12D), which may compromise the efficacy of targeted therapy approaches.
> 20% of IDH1 mutations in glioblastomas, and 15% of mutations in genes in the PI3K (phosphatidylinositol 3-kinase)–AKT–mTOR (mammalian target of rapamycin) signaling axis across all tumor types were subclonal
Mutations in the RAS–MEK (mitogen-activated protein kinase kinase) signaling axis were less likely to be subclonal than mutations in genes associated with PI3K-AKT-mTOR signaling
Branched chain can converge on single resistance mechanism; clonal resistance (for example to PI3K inhibitors can get multiple PTEN mutations in various metastases
Targeting Tumor Heterogeneity
Identify high risk occupants (have to know case history)
Mutational landscape interferes with anti-PD1 therapies
Low frequency mutations affect outcome
Notes from Dr. Catherine J. Wu, Dana-Farber Cancer Institute: The evolutionary landscape of CLL: Therapeutic implications
Clonal evolution a key feature of cancer progression and relapse
Hypothesis: evolutionary dynamics (heterogeneity) in chronic lymphocytic leukemia (CLL) contributes to variations in response and disease “tempo”
Used whole exome sequencing and copy number data of 149 CLL cases to discover early and late cancer drivers: clonal patterns (Landau et. al, Cell 2013); some drivers correspond to poor clinical outcome
Methylation studies suggest that there is epigenetic heterogeneity which may drive CLL clonal evolution
Developing methodology to integrate WES to determine mutations with immunogenic potential for development of personalized immunotherapy for CLL and other malignancies
McGranahan N, Favero F, de Bruin EC, Birkbak NJ, Szallasi Z, Swanton C: Clonal status of actionable driver events and the timing of mutational processes in cancer evolution. Science translational medicine 2015, 7(283):283ra254.
Other related articles on Tumor Heterogeneity were published in this Open Access Online Scientific Journal, include the following:
This update was performed by the following methods:
A. GPT 5 Text analysis and Reasoning
B. Insertion of Knowledge Graph on topic Curation of Genomic Analysis from Non Small Cell Lung Cancer Studies from Nodus Labs using InfraNodus software
C. Domain Knowledge Expert evaluation of the Update outcomes
This article has the following Structure:
Part A: Introduction to LLM, Knowledge Graph software InfraNodus, ChatGPT5 and Background Information on curated material for Test Case
Part B: InfraNodus Analysis of manual curation and Knowledge Graph Creation
Part C: Chat GPT 5 Analysis of Manually Curated Material
Part D: Curation entitled Multiple Lung Cancer Genomic Projects Suggest New Targets, Research Directions for Non-Small Cell Lung Cancer originally published on 09/05/2014
Results of Article Update with GPT 5
1. GPT5 alone was not able to understand the goal of the article, namely to determine knowledge gaps in a particular research area involving 5 genomic studies on lung cancer patients
2. GPT5 alone was not able to group concepts or comonalities between biological pathways unless supplied with a manually curated list of KEGG pathways from a list of mutated genes. However this precluded any effect that fusion proteins had on the analysis and so GPT5 would only concentrate on mutated genes commonly found in literature
3. GPT was not able to access some of the open Access databases like NCBI Gene Ontology database
Results of Article Update with KnowledgeGraph presentation to GPT 5
4. As the Knowledge Graph understood the importance of fusion proteins and transversions, the knowledgegraph augmented the GPT analysis and so enriched the known pathways as well as could correctly identify the less represented pathways in the knowledge graph
5. This led to the identification of many novel signaling pathways not identified in the original analysis, and was able to perform this task with ease and speed
6. GPT with InfraNodus Analysis was able to propose pertinent questions for future research (the goal of the original curation) such as:
How does the interaction between [[EGFR]] mutations and sex-specific gene alterations, including [[RBM10]], influence treatment outcomes in lung adenocarcinoma?
How does the intersection of mutational patterns from smoking influence pathway activation in NSCLC, and can identifying these interactions improve targeted therapy development?
Novelty in comparison to Original article published on 09/05/2014
7. it appears that manual curation is necessary to assist in the building of relevant knowledge graphs in the biomedical fields to augment generative AI analysis
8. by itself, generative AI is not optimized for inference of higher concepts from biomedical text, and therefore, at this point, requires the input from human curators developing domain-specific knowledge graphs
9. The combination of ChatGPT5 and Knowledge graphs of this manually curated biomedical text added a further layer of complexity of gaps of knowledge not seen in the original curations including the need to study noncanonical signaling pathways like WNT and Hedgehog in smoker versus nonsmoker cohorts of lung cancer patients
A Comparison of Manual Expert-Curative and an LLM-based analysis of Knowledge Gaps in Non Small Lung Cancer Whole Exome Sequencing Studies and a Use Case Example of Chat GPT 5
Part A: Introduction to LLM, Knowledge Graph software InfraNodus, ChatGPT5 and Background Information on curated material for Test Case
The development of Large Language Models (LLMs), together with development of knowledge graphs, have facilitated the ability to analyze text and determine the relationships among the various concepts contained within series of texts. These concepts and relationships can be visualized, and new insights inferred from these visualizations. As a result, this type of analysis suggests new directions and lines of research.
Alternatively, these types of visualizations can also reveal gaps in knowledge which should be addressed. A new type of LLM and visualization tools have been developed to understand the gaps in knowledge in biomedical text.
Nodus Labs InfrNodus AI Knowledge Graph Software Tools Allow Text Relationship Visualization and Integrated AI Functionality
Infranodus makes knowlegde graphs from text and then is able to visualize the relationships between concepts (or nodes). In doing so, the tool also highlights the various knowledge gaps (or large differences between nodes) which can be used to investigate new hypotheses and research directions of previously univestigated relationships between concepts. This generates new research questions, in which these gaps can be used as prompts in the software’s integrated AI tool. The AI tool, much like a GPT, returns recommendations for research to be conducted in the area.
In addition, the InfraNodus software can detect if text is too biased on a particular concept or conclusion, and using a GPT3 or GPT4, can determine if the nodes are too dispersed and will recommend which gaps should be focused on.
The software can upload any biomedical text in various formats
A full demonstration is on their website but a good summary is found on their Youtube site at
Previously we had manually curated and analyzed the knowledge gaps from a series of publications on whole exome sequencing of biopsied tumors from cohorts of non small lung cancer patients. This curation (from 2016) is seen in the lower half of this updated link below and I separated with a bar and highlighted in Yellow as Text for AI Analysis.
Govindan R, Ding L, Griffith M, Subramanian J, Dees ND, Kanchi KL, Maher CA, Fulton R, Fulton L, Wallis J et al: Genomic landscape of non-small cell lung cancer in smokers and never-smokers. Cell 2012, 150(6):1121-1134.
Imielinski M, Berger AH, Hammerman PS, Hernandez B, Pugh TJ, Hodis E, Cho J, Suh J, Capelletti M, Sivachenko A et al: Mapping the hallmarks of lung adenocarcinoma with massively parallel sequencing. Cell 2012, 150(6):1107-1120.
Peifer M, Fernandez-Cuesta L, Sos ML, George J, Seidel D, Kasper LH, Plenker D, Leenders F, Sun R, Zander T et al: Integrative genome analyses identify key somatic driver mutations of small-cell lung cancer. Nature genetics 2012, 44(10):1104-1110.
were performed.
The purpose of this analysis was to uncover biological functions related to the sets of mutated genes with limited research publications in the area of non small cell lung cancer. The identification of such biological functions would represent a gap in knowledge in this disease. In addition, this analysis attempted to find new lines of research or potential new biotargets to investigate for lung cancer therapy.
However this manual method is time consuming and may miss relationships not defined in a GO ontology or gene knowledgebases.
Therefore we turned to an AI-driven approach:
Using InfraNodus ability to develop a knowledge graph based on our curation and determine if the AI platform could infer knowledge gaps
Utilize Chat GPT5 to analyze the same curated set to determine if OpenAI analysis would lead to the similar analysis from curated material
Determine if combining a knowledge graph within GPT would lead to a higher level of analysis
See below (Part D) of this update for the curated studies which were included in this analysis and the text which was entered into both InfraNodus and Chat GPT5.
As a summary, it seems that manual curation is necessary to assist in the building of relevant knowledge graphs in the biomedical fields to augment generative AI analysis. In addition, it appears that , by itself, generative AI is not optimized for inference of higher concepts from biomedical text, and therefore, at this point, requires the input from human curators developing domain-specific knowledge graphs.
Part B. InfraNodus Analysis of manual curation and Knowledge Graph Creation
Methods:
Text of the curation was copied and directly pasted into the text analysis module of InfraNodus. There was no editing of words however genes in the curation were linked to their GeneCard entry. GeneCards is a database run by the Weizmann Institute. InfraNodus utilizes a combination of LLMs and its own GraphRAG system to provide insights from text analysis. While it leverages various models, including those from OpenAI and Anthropic, it’s not limited to a single LLM. Instead, InfraNodus integrates these models within its GraphRAG framework, which enhances their capabilities by adding a relational understanding of the context through a knowledge graph.
InfraNodus then autogenerates a knowledge graph and returns entities and relationships between entities. InfraNodus offers the opportunity to modify the knowledge graph however for this analysis we used the first graph InfraNodus generated. Inspection of this graph (as shown below) was deemed reasonable.
Results
The knowledge graph of the input text is shown below:
InfraNodus generated Knowledge Graph of 5 WES Non Smal Cell Lung Cancer studies involving smokers and non smokers
Four main concepts were returned: tumors, genes, literature, and mutations.
A snapshot of the Analysis window is given below. It should be noted that InfraNodus felt there needed to be more connections between Pathway and Mutational Patterns.
An InfraNodus reposrt with Knowlege Graph on Whole Exome Sequencing studies in NSCLC to determine mutational spectrum in smokers versus non smokers
alk clinical [[egfr]] mutational pathway [[paper]] found key literature study [[genomic]] reveal [[transversion]]
Top relations / ngrams:
1) [[lung]] [[tumors]]
2) alk fusion
3) link function
4) eml alk
5) function [[gene_ontology]]
Modulary: 0.47
Relations:
InfraNodus identified 744 relations between entities (nodes)
A list of some of the more frequent are given here:
source
target
occurrences
weight
betweenness
[[lung]]
[[tumors]]
8
24
0.4676
analysis
pathway
5
12
0.2291
significantly
[[genes]]
5
9
0.1074
significantly
[[mutated]]
4
12
0.0281
[[mutated]]
[[genes]]
4
12
0.0847
[[transversion]]
high
3
12
0.0329
[[smoking]]
history
3
10
0.0352
study
identify
3
9
0.2051
mutational
pattern
3
9
0.0921
[[rbm10]]
[[mutations]]
3
8
0.1776
literature
analysis
3
7
0.2218
[[egfr]]
[[mutations]]
3
7
0.2139
[[transversion]]
group
3
7
0.0259
enriched
cohort
3
6
0.0219
[[whole_exome_sequencing]]
[[tumors]]
3
6
0.3485
identify
[[genes]]
3
6
0.2268
including
analysis
3
5
0.1985
alteration
[[genes]]
3
4
0.1298
[[tumors]]
analysis
3
4
0.5192
alk
fusion
2
15
0.0671
link
function
2
14
0.0269
function
[[gene_ontology]]
2
13
0.0054
Notice how the betweenness or importance of connection of disparate concepts vary but are high between concepts like tumors and analysis, or lung and tumor, however many important linked concepts like alk and fusion may have low betweenness but are mentioned frequently and have a much higher weight or closeness to each other. Gene-mutations-transversions-smoking seem to have a high correspondence to each other
Genetic Alterations: identify, [[genes]], study:The recent comprehensive studies on lung adenocarcinoma have significantly advanced our understanding of the genetic landscape by identifying key mutations and their intricate interactions. Notably, EGFR and RBM10 exhibit distinct mutational patterns, with RBM10 inactivations being notably enriched in male cohorts. This gender-linked enrichment underscores a potential differential oncogenic pathway involving ERBB2 and RB1 alterations.Moreover, these projects emphasize the quest to map significant gene alterations within lung adenocarcinoma. The identification of such genes not only corroborates prior reports but also expands upon them by highlighting new connections between mutation signatures and clinical factors like smoking history. These findings are crucial as they can inform future therapeutic targeting strategies, ensuring that personalized treatment approaches consider both gender-specific genomic enrichments and mutation-driven tumorigenesis pathways elucidated through rigorous analyses.elaborate
questions generated using AI to help you explore “alk, clinical, [[egfr]], mutational, pathway, [[paper]], found, key, literature, study, [[genomic]], reveal, [[transversion]]…”:How do mutational patterns, specifically EGFR mutations and transversions related to smoking history, influence the effectiveness of targeted therapies in NSCLC patients?elaborate
ideas generated using AI to help you explore “alk, clinical, [[egfr]], mutational, pathway, [[paper]], found, key, literature, study, [[genomic]], reveal, [[transversion]]…”:Develop a predictive model that utilizes genomic data and smoking history to forecast patient response to targeted therapies. This model would identify key mutational signatures linked to EGFR and other genes, highlighting the impact of smoking-induced transversions on drug efficacy.elaborate
Project Notes
”
The recent comprehensive studies on lung adenocarcinoma have significantly advanced our understanding of the genetic landscape by identifying key mutations and their intricate interactions. Notably, EGFR and RBM10 exhibit distinct mutational patterns, with RBM10 inactivations being notably enriched in male cohorts. This gender-linked enrichment underscores a potential differential oncogenic pathway involving ERBB2 and RB1 alterations.
Moreover, these projects emphasize the quest to map significant gene alterations within lung adenocarcinoma. The identification of such genes not only corroborates prior reports but also expands upon them by highlighting new connections between mutation signatures and clinical factors like smoking history. These findings are crucial as they can inform future therapeutic targeting strategies, ensuring that personalized treatment approaches consider both gender-specific genomic enrichments and mutation-driven tumorigenesis pathways elucidated through rigorous analyses.”
<ConceptualGateways>
alk
clinical
[[egfr]]
mutational
pathway
[[paper]]
found
key
literature
study
[[genomic]]
reveal
[[transversion]]
</ConceptualGateways>
How do mutational patterns, specifically EGFR mutations and transversions related to smoking history, influence the effectiveness of targeted therapies in NSCLC patients?
The report from the NCI Bulletin outlines significant advancements in understanding lung cancer through genome sequencing projects. These studies have revealed a plethora of genetic and epigenetic alterations across various forms of lung tumors, including adenocarcinomas, squamous cell carcinomas, and small cell lung cancers. Notably, some identified alterations could be targeted by existing therapies, providing potential new avenues for treatment.Dr. Meyerson emphasizes the complexity of these genetic changes, highlighting that distinct mechanisms inactivating genes can vary between tumors. The report also notes gaps in knowledge regarding non-coding DNA alterations, which comprise a major part of the human genome.Key findings include:1. Comprehensive genomic analyses revealing unique driver mutations in lung adenocarcinoma, such as those affecting MET and ERBB2, alongside significant mutations in known cancer drivers like TP53 and KRAS.2. A classification system based on genomic data enabling more accurate patient stratification—achieving a 75% classification rate of lung cancer subtypes.3. Smoking history is shown to influence mutational patterns significantly, with smokers exhibiting a higher incidence of point mutations compared to never-smokers.Moreover, the integration of genomic data and pathway analysis highlighted recurrent mutations across various pathways related to tumorigenesis, suggesting new therapeutic targets and underscoring the importance of personalized medicine approaches that factor in gender-specific mutation distributions.This synthesis of findings not only corroborates earlier studies but also extends our understanding of the interplay between genomic alterations, smoking habits, and clinical outcomes in lung cancer. Future research is needed to explore the implications of these findings further and to develop targeted therapies that leverage the identified genetic alterations.
Tumor Genomics
Genetic Alterations
Pathway Analysis
Mutation Patterns
Main Ideas Summary from Infranodus:
The report from the NCI Bulletin highlights significant developments in lung cancer genomics through five genome sequencing projects. These studies have uncovered various genetic and epigenetic alterations across multiple forms of lung cancer, including adenocarcinomas, squamous cell cancers, and small cell lung cancers. Notably, these alterations may correspond to existing drugs, offering new avenues for targeted therapy.
Key findings include the identification of unique mutations in genes like NF1, MET, and ERBB2, with particular attention to smoking’s role in mutational patterns. The analysis shows that smokers exhibit a higher incidence of specific point mutations, marking a distinct divergence in mutation profiles compared to never-smokers.
The research also emphasizes the need for continued exploration of the data to link mutation signatures with clinical outcomes, particularly regarding gender-specific differences in mutation prevalence. Emerging insights suggest that pathways involving MYC and alterations in splicing factors could be vital targets for future therapeutic strategies.
Overall, the studies collectively underscore an urgent need for integrating genomic data into clinical practice, which can lead to more personalized treatment approaches for lung cancer patients by considering both the genetic landscape of tumors and their histories, such as smoking exposure. The ongoing efforts to map gene alterations within lung adenocarcinoma not only reinforce existing knowledge but also reveal new potential therapeutic targets that can significantly impact patient outcomes.
Questions to Explore from InfraNodus:
How does the interaction between [[EGFR]] mutations and sex-specific gene alterations, including [[RBM10]], influence treatment outcomes in lung adenocarcinoma?
How does the intersection of mutational patterns from smoking influence pathway activation in NSCLC, and can identifying these interactions improve targeted therapy development?
Part C: Chat GPT 5 Analysis of Manually Curated Material
Now let us see how Chat GPT5 analyzed the same material.
Methods
Nice — I’ll work from the KEGG-pathway list shown in your text (the table of pathways with PubMed counts) and call out major KEGG pathways that are not represented there.
Important caveat: “Not represented in the table” below means not listed in the KEGG-pathway hits shown in your pasted literature analysis, not that these pathways never play a role in lung cancer. Absence from that table can reflect lack of reporting in the specific WES/WGS studies or the PubMed keyword search used — it’s not proof the pathway is uninvolved biologically.
The above Important caveat was very important because it showed that ChatGPT5 could understand what my experimental goals were, or at least understood the problem I was presenting to ChatGPT5!
Major KEGG pathways missing from the provided KEGG list
(However Note that GPT did NOT take into account the mutational spectrum of the studies or the gene lists supplied in the curation)
These are commonly cited cancer-related KEGG pathways that do not appear in the table you gave:
Wnt signaling pathway
Notch signaling pathway
Hedgehog signaling pathway
TGF-beta signaling pathway
Hippo signaling pathway
p53 signaling pathway — (note: TP53 is mutated in many tumors, so p53 biology is implicated in the text, but “p53 signaling” does not appear in that KEGG hits table)
Autocrine/paracrine inflammation/chemokine signaling beyond the one low-count entry (general cytokine networks other than the single “cytokine–cytokine receptor interaction” hit)
Signal transduction modules sometimes separate in KEGG:g. Calcium signaling was listed in your table, but other modules like cGMP–PKG signaling or PKA/PKC broader signaling networks are not.
Quick summary
The KEGG table in your text highlights many cancer and receptor-tyrosine/MAPK/PI3K related pathways (cell cycle, MAPK, ErbB, JAK-STAT, focal adhesion, etc.). What’s not listed are numerous developmental morphogen pathways (Wnt/Notch/Hedgehog/TGF-β/Hippo), many DNA-repair and core metabolic pathways, canonical apoptosis/autophagy/ubiquitin pathways, and broad adaptive-immune signaling pathways.
If you want, I can:
(A) cross-check this against the full KEGG pathway list and produce a definitive “KEGG universe → present vs absent in your table” spreadsheet, or
(B) prioritize which of the missing pathways you’d most want investigated in lung tumor sequencing data and suggest genes to look for.
Which follow-up would you prefer?
Now taking out the KEGG list I gave GPT in order to force GPT to do a similar but unbiased analysis
From the studies you’ve shared, we can identify which KEGG pathways are under-represented (i.e., appear less frequently altered than expected) in the altered genes in lung cancer.
To do this, we note that the researchers used KEGG and other pathway analysis tools (PathScan, literature curation, proteomics) to see which biological pathways the mutated genes mapped to.
While many well-known cancer pathways were found to be activated (MAPK, PI3K-AKT, mTOR, cell cycle, oxidative stress, etc.), a few key pathways were reported as unexpectedly low in mutation frequency despite their known role in cancer biology.
KEGG Pathways Under-Represented in Altered Genes in Lung Cancer
From the descriptions in Papers 1–5, these are the main pathways that appear under-represented:
MAPK signaling pathway
Normally, MAPK is a major cancer driver pathway. In this dataset, MAPK activity was high in proteomics, but many tumors lacked mutations in MAPK pathway genes.
This means MAPK activation is often non-mutational (possibly via upstream signaling, epigenetic changes, or ligand activation), so in mutation-based KEGG enrichment it is under-represented.
PI3K-Akt signaling pathway
Like MAPK, the PI3K-Akt pathway was highly activated in proteomics, but often without mutations in PI3K pathway genes.
Under-represented in gene mutation lists, despite strong functional activation.
mTOR signaling pathway
Functional activation was observed (especially when STK11 was mutated), but most tumors had no mTOR-pathway gene mutations.
Under-represented when looking only at altered genes.
JAK-STAT signaling pathway
Mentioned as novel pathway alterations in some tumors, but in KEGG enrichment analysis, JAK-STAT genes did not appear as a dominant mutated group—implying low mutation frequency compared to other cancer types.
Oxidative phosphorylation & metabolic pathways
While oxidative stress response genes (e.g., KEAP1) were sometimes mutated, the oxidative phosphorylation KEGG pathway itself did not emerge as mutation-enriched, suggesting functional changes occur via other mechanisms (e.g., hypoxia signaling).
While some epigenetic regulators (ARID1A, CREBBP, EP300, MLL) were mutated, KEGG’s “Chromatin remodeling” and “Histone modification” groupings were less represented than expected given the role of epigenetics in lung cancer, indicating epigenetic dysregulation is often non-mutational.
Why They Are Under-Represented
Proteomics revealed activation without DNA mutation (e.g., ligand-driven activation, phosphorylation cascades).
Epigenetic or post-translational modifications can activate pathways without altering the coding sequence.
Tumor heterogeneity: some pathways are only altered in subsets of tumors and thus don’t reach statistical enrichment.
Limitations of mutation-based KEGG analysis: pathways that are activated downstream or by non-coding alterations are missed.
✅ Summary Table
Pathway (KEGG ID)
Representation in Mutated Genes
Reason for Under-Representation
hsa04010 MAPK signaling
Low
Activated via non-mutational mechanisms
hsa04151 PI3K-Akt signaling
Low
Functional activation w/o gene mutations
hsa04150 mTOR signaling
Low
Activation often via upstream STK11 loss or growth factor signaling
hsa04630 JAK-STAT signaling
Low
Rarely mutated, altered mostly via cytokine/growth factor changes
hsa00190 Oxidative phosphorylation
Low
Functional metabolic shift via hypoxia & ROS stress, not mutations
Chromatin remodeling / histone modification
Low
Mostly altered via epigenetic changes, not coding mutations
If you want, I can cross-reference the exact KEGG IDs and run a quick gene-to-pathway mapping using the genes listed in the reports so we can get a precise statistical under-representation list. That way it’s backed by an enrichment p-value rather than just qualitative observation.
I tried to re-run the KEGG-backed analysis you requested, but the KEGG REST endpoints/web pages aren’t reachable from my browsing tool right now (the web.run calls to KEGG returned an internal/safety error). I can’t produce a properly-sourced, KEGG-ID–backed enrichment report unless I can successfully query KEGG (or a comparable pathway service) for the exact pathway membership.
Two clear, immediate options — tell me which you prefer and I’ll proceed right away:
Option 1 — Proceed with a KEGG-backed run using an alternate route (recommended)
I’ll attempt a small number of web.run search queries (to public pathway tools that mirror KEGG membership, e.g., g:Profiler / Reactome / Enrichr / DAVID) and then follow links to KEGG pathway pages. This often works even when direct KEGG REST calls fail. It will take a few web.run calls and I’ll cite the pages used. (If you want me to prefer a particular service — e.g., g:Profiler, Enrichr, DAVID — say so; otherwise I’ll pick g:Profiler as it’s robust.)
Option 2 — Run an immediate local (best-effort) analysis without web lookups
I’ll map the genes you listed to likely KEGG pathways from internal knowledge, run hypergeometric enrichment using a standard human background (20,000 genes), and give a ranked list of under-represented KEGG pathways with p-values — but I must be clear this is approximate (I cannot provide verified KEGG IDs or exact pathway sizes).
If you pick Option 1, I’ll start the web lookups now and produce the KEGG-ID mapped, statistically precise under-representation list with citations.
If you pick Option 2, I’ll run the approximation immediately and give results plus a confidence caveat.
Which do you want?
Sources
Ask ChatGPT
You said:
Use Option 1 to Proceed with a KEGG-backed run using an alternate route
ChatGPT said:
Thought for 37s
Thanks — I followed Option 1 trying to do a KEGG-backed run, but hit the same problem: my web tool (web.run) can reach g:Profiler/KEGG reliably in some contexts but it failed for the programmatic queries I attempted (internal / non-retryable errors). Because you explicitly requested a KEGG-backed run, I tried an alternate route (g:Profiler web query) and the site blocked the automated call.
Rather than leave you waiting, I made a transparent, reproducible best-effort analysis right now so you have immediate, concrete results — but please read the very important limitations below before using these numbers: (GPT having problems accessing material behind firewalls and paywalls)
What I did (short)
I extracted a conservative set of 48 unique genes from the papers you supplied (recurrent drivers, fusion partners, and the druggable gene list). Gene list used (48 genes):
TP53, KRAS, EGFR, STK11, KEAP1, SMARCA4, RBM10, NF1, MET, ERBB2, RIT1, BRAF, PIK3CA, PTEN, ARID1A, U2AF1, CREBBP, EP300, MLL, ALK, ROS1, DACH1, CFTR, RELN, ABCB5, HGF, JAK2, JAK3, HDAC2, HDAC6, HDAC9, BIRC6, ITGB1, ITGB3, MMP2, PRKCB, PIK3CG, TERT, MMP14, AURKC, ERBB4, FGFR1, EML4, SIK2, ZFHX4, EPHA3, EPHA7, SLIT2.
Because direct KEGG lookups failed, I mapped those genes to a short list of common KEGG pathways by manual curation (based on canonical pathway membership knowledge) and used conservative, literature-style approximate pathway sizes (number of genes in that KEGG pathway) to compute exact hypergeometric lower-tail p-values (i.e., probability of observing as few or fewer genes in the pathway than we did — an under-representation test).
I computed exact hypergeometric probabilities (sum of combinations) with a standard human gene background of N = 20,000. All calculations were executed programmatically (so no hand-approximate combinatorics).
Important limitations (please read)
This is NOT a true KEGG-backed run. I could not fetch KEGG pathway membership lists or KEGG IDs because the web tool could not access the KEGG/g:Profiler APIs in this session. (more GPT issues with access to data)
I used manually mapped genes → pathways (conservative, but not exhaustive) and approximate pathway sizes (estimates). Because both gene membership and exact pathway sizes matter a lot for enrichment statistics, the p-values below are illustrative only — they are useful to prioritize where to retry a proper KEGG query, but should not be taken as authoritative.
The correct, defensible way to produce what you asked is to re-run this on g:Profiler/Enrichr/DAVID (or download KEGG GMTs) so pathway membership and KEGG IDs are exact. I can do that as soon as the web tool can access those services (or you can paste exact KEGG gene sets if you prefer).
Results — immediate best-effort under-representation test
For each pathway I show: pathway size (K, approximate), number of genes from your list found in that pathway (k), and the hypergeometric lower-tail p-value P(X ≤ k) (probability of seeing k or fewer pathway genes by chance). Lower p-values (e.g., < 0.05) would suggest significant under-representation.
Interpretation: none of the pathways above reach statistical significance for under-representation under the assumptions I used. The closest to a (moderate) signal is oxidative phosphorylation where we observed 0 genes from the list (p ≈ 0.73) — but that p-value is still far from being significant (p < 0.05 would be needed). In short: no pathway is robustly under-represented in this small gene set using the conservative approximations above.
What I recommend (next steps to get the exact KEGG-ID–backed answer you originally asked for)
Allow me to retry the web-backed run (g:Profiler / Enrichr / DAVID) — I’ll re-run the enrichment and return:
gene → exact KEGG IDs mapping,
KEGG pathway sizes (exact K),
over- and under-representation p-values (Fisher/hypergeometric), and
multiple-testing corrected q-values (Benjamini–Hochberg). (This requires the web tool to be able to reach g:Profiler/KEGG; I already tried and the call failed. If you want, I’ll attempt again immediately.)
If you prefer not to rely on the web tool, you can paste your final canonical gene list (e.g., a CSV of the exact genes you want analyzed) and I will run a conservative local analysis like the above but I will be explicit that KEGG IDs and pathway sizes are approximations.
If you’d like, I can also send you the exact code/notebook I used for the above best-effort run so you (or your bioinformatics person) can re-run it locally against an up-to-date KEGG GMT file.
If you want me to retry the web-backed run now, say “Retry web run now” and I’ll immediately attempt g:Profiler/Enrichr again and produce the precise KEGG-ID–backed enrichment with citations. If you prefer I proceed without web access (i.e., run a local approximation on a larger set of genes or with different pathway groupings), tell me what gene list to use and I’ll compute immediately.
Top of Form
Bottom of Form
Done — I created a bar chart showing estimated PubMed article counts (prior to 2018) for “lung cancer” mentions of the pathways we discussed: MAPK, PI3K-Akt, mTOR, JAK-STAT, and Oxidative phosphorylation.
Important caveats (please read)
I could not access PubMed programmatically from this session (the web tool failed on PubMed/NCBI requests), so the numbers used are illustrative estimates, not exact counts.
If you need exact PubMed counts (filtered to publications before 2018), I can re-run the web-backed PubMed queries and regenerate the graph as soon as web access to NCBI is available — just say “Retry PubMed queries” and I’ll attempt that immediately.
Re-run the exact PubMed queries and update the chart with real counts, or
Expand the chart to include more pathways (e.g., chromatin modifiers, spliceosome, cell cycle), or
Provide the code/notebook used so you can run it locally against PubMed.
Here’s the expanded bar chart with additional pathways — Spliceosome, Chromatin remodeling / histone modification, ECM / focal adhesion, and Cell cycle — alongside the original set.
Would you like me to now replace these illustrative numbers with exact PubMed counts (filtered to before 2018) by running targeted PubMed searches?
Yes — even though the dataset and pathway lists we discussed focused mostly on signaling, metabolic, and genomic alterations, there is a clear immune component to lung cancer supported by both your provided text and the broader literature. (Now note that GPT noticed a clear literature coverage of cell cycle in lung cancer however it is claiming there was evidence of an immune component in the literature before 2018).
Evidence from your provided studies (Note GPT is using recent evidence not just restricting to periods before 2018)
Pathways with immune relevance
JAK-STAT signaling (detected in the analysis)
Central to cytokine signaling, immune cell activation, and inflammatory responses in the tumor microenvironment.
Altered JAK-STAT can drive immune evasion or chronic inflammation that promotes tumor growth.
RTK/RAS/RAF pathway indirectly affects immune signaling by altering cytokine/chemokine secretion from tumor cells.
ROS1-ALK fusions
These can alter the tumor’s immunogenic profile; your text notes they may create epitopes that make tumors amenable to immunotherapy.
Shown in cited literature to be less chemosensitive but potentially sensitive to immune-based approaches when certain epitopes are exposed.
Also exhibit HSP90 chaperone dependence, which links to immune stress response pathways.
Tumor heterogeneity and immune escape
The genomic heterogeneity reported (monoclonal vs biclonal tumors) suggests different subclones may evade immune surveillance differently — a hallmark of tumor–immune system interaction.
From broader lung cancer research
Even when not highlighted in mutation frequency lists, immune-related processes in lung cancer are driven by:
Tumor-infiltrating lymphocytes (TILs) and their exhaustion profiles.
Immune checkpoints (PD-1/PD-L1, CTLA-4) — a major therapeutic target in NSCLC.
Inflammatory cytokine networks (many driven via JAK-STAT, NF-κB, MAPK cross-talk).
Neoantigen load (especially in smokers, due to high mutation rates) that can trigger immune recognition — unless suppressed by tumor-mediated immunosuppression.
Conclusion
Yes — there is an immune component to lung cancer. It may not appear as strongly in mutation-based KEGG under-representation analysis (because immune evasion is often mediated by gene expression, epigenetics, and tumor–immune interactions rather than recurrent coding mutations), but immune signaling pathways like JAK-STAT and cytokine-related signaling are still altered and clinically relevant.
(Remember our initial test was to see if GPT could do our manual curative analysis without relying on current information!)
That’s why immune checkpoint inhibitors (anti–PD-1, anti–PD-L1, anti–CTLA-4) are now standard-of-care in many lung cancer treatment regimens (The evidence that led to immune checkpoint inhibitors was not based just on JAK-STAT or cytokine signaling).
Now Let Us See What Happens When a Knowledge Graph from InfraNodus is Imported into Chat GPT5
The import of a knowledge graph as a CSV from InfraNodus into ChatGPT5 is rather straightforward as can directly upload into the GPT interface.
ChatGPT was prompted with: “based on the imported knowledge graph tell me what Gene ontology biologic functions are missing?”
ChatGPT said:
Your imported graph isn’t labeled with standard Gene Ontology (GO) IDs or names, so I can’t directly map it to “biological process” terms yet.
The next step is to align your node name column with the official GO Biological Process ontology and then report which expected functions are missing.
I can:
Pull the latest GO Biological Process list.
Match your nodes against it.
Output the GO BP terms absent from your network.
Do you want me to fetch the current GO BP ontology from the Gene Ontology database and run that comparison?
You said:
based on the imported knowledge graph tell me what KEGG processes are missing?
ChatGPT said:
To identify which KEGG processes are missing from your imported knowledge graph, the first step is to retrieve an up-to-date list of KEGG human pathways and then compare that against the nodes present in your graph. Here’s how I can help:
Fetch the current list of KEGG human pathways
I can pull the latest catalog of KEGG pathways for Homo sapiens, which includes major metabolic routes (e.g., purine metabolism, glycolysis) as well as signaling pathways (e.g., JAK-STAT, Wnt, PI3K-Akt) KEGG+1.
Compare with your knowledge graph nodes
Once I have that KEGG list, I’ll match it against your graph’s node name entries. Any pathway names or identifiers (like hsa04110 for “Cell cycle”) not present in your graph would be flagged as missing.
Deliver the findings
I’ll provide you with:
A list of KEGG processes present in your graph
A list of those missing, enabling you to fill in gaps or trigger further investigation
Does that sound good? If you’d like, please share a sample or the full list of your graph’s node name entries, especially if they include KEGG-style labels or pathway names—it’ll help speed up the matching process.
Sources
You said:
Fetch the current list of KEGG human pathways and compare with my knowledge graph nodes and provide me with a list of KEGG processes present and a list of KEGG processes missing.
ChatGPT said:
I’ve fetched the current list of KEGG human pathways (hsa) and compared it to the nodes in your imported knowledge graph. Here’s what we can do next—and what I need from you to complete the analysis:
KEGG Human Pathway List
Below are just a few highlights from the complete KEGG human pathway list (retrieved via KEGG REST /list/pathway/hsa) rest.kegg.jp:
hsa00010 – Glycolysis / Gluconeogenesis
hsa00020 – Citrate cycle (TCA cycle)
hsa01100 – Metabolic pathways
hsa04010 – MAPK signaling pathway
hsa04151 – PI3K-Akt signaling pathway
hsa04910 – Insulin signaling pathway
hsa05200 – Pathways in cancer
…plus hundreds more spanning metabolism, genetic information processing, organismal systems, disease, and more.
You can view the full list in the KEGG API or in your local copy if you’ve grabbed it via /list/pathway/hsa.
What I Need From You
To identify which KEGG pathways are present or missing in your graph, please provide the list of node names (or IDs) from your knowledge graph that correspond to KEGG pathways. For example, this might include:
KEGG identifiers like hsa04110
Pathway names like “Cell cycle” or “Glycolysis / Gluconeogenesis”—ideally matching exact KEGG naming
With those node names in hand, I can:
Match them against the official KEGG list.
Generate two clear lists:
Present in your graph
Missing from your graph (i.e., not represented)
If you can share your node set (even a sample if too large), we can proceed immediately. Let me know when you’re ready!
Sources
You said:
based on my knowledge graph I uploaded, is there any relation between lung cancer and the immune system?
ChatGPT said:
In the knowledge graph you uploaded, there aren’t any nodes explicitly labeled with immune-related terms (like “immune,” “T cell,” “macrophage,” “cytokine,” etc.) that directly link to lung cancer concepts.
That means your graph doesn’t appear to contain an obvious connection between lung cancer and the immune system—at least not through explicitly named immune processes or cell types.
If you want, I can run a broader search for indirect immune-related concepts (e.g., inflammation, checkpoint pathways like PD-1/PD-L1, MHC) to see if they’re present but labeled differently.
You said:
Based on my knowledge graph I uploaded is there any relation between lung cancer and inflammation or genes related to inflammation?
ChatGPT said:
Your uploaded knowledge graph doesn’t contain any nodes that explicitly mention inflammation or common inflammation-related genes (e.g., TNF, interleukins, NF-κB, COX-2, JAK/STAT, chemokines).
So based on the current data, there’s no recorded link between lung cancer and inflammation in your network—either directly or via inflammation-related genes.
If you want, I can try mapping your existing nodes to KEGG’s inflammation and immune-related pathways to catch indirect associations that aren’t obvious from node names alone.
You said:
Are there any nodes in my graph that maps to KEGG inflammation and immune-related pathways?
ChatGPT said:
Here’s what I discovered regarding KEGG immune- and inflammation-related pathways, and how they relate (or don’t) to the nodes in your uploaded knowledge graph:
Key KEGG Immune-Related Pathways
KEGG organizes numerous human pathways under the “Immune System” category, including:
From your graph’s node name entries, I didn’t see any nodes that correspond to the KEGG immune or inflammation pathways listed above. There are no direct matches like:
“Toll-like receptor signaling”
“Chemokine signaling”
“Antigen processing and presentation”
“Th1 cell differentiation,” etc.
So, based solely on node names, none of the canonical KEGG immune or inflammation pathways appear to be represented in your graph.
Next Steps to Explore Potential Indirect Links
Even if those pathways aren’t explicitly named, your graph might still include immune- or inflammation-related genes under alternate labels. If you’d like, I can help:
Search for common immune-related genes in your graph (e.g., TLR4, NLRP3, interleukins, NF-κB) to spot indirect associations;
Perform pathway mapping, using tools like KEGG Mapper or Reactome, to see if the gene set from your graph corresponds to any immune-related pathways—even if they’re not explicitly named.
Would you like me to proceed with one of those approaches to dig deeper?
Sources
You said:
Search for common immune-related genes in my graph and pathways using KEGG Mapper
ChatGPT said:
Your uploaded knowledge graph doesn’t contain any nodes that match common immune-related genes from the KEGG immune and inflammation pathways list—at least not under standard gene symbols like IL6, TNF, TLR4, STAT3, etc.
This means KEGG Mapper wouldn’t find direct immune pathway hits from your current node set unless those genes are present under alternate labels or embedded inside other entity names.
If you want, I can:
Expand the search to look for partial matches (e.g., “IL-6” or “interleukin 6” instead of strictly “IL6”)
Try mapping all your nodes to KEGG to see if indirect immune pathway associations appear
You said:
Based on the above analysis and my knowledge graph would you say investigating the role of the immune system in lung cancer would uncover interesting therapeutic targets?
ChatGPT said:
Thought for 9s
Short answer: Yes — very likely.
Even though your uploaded graph does not currently show immune or inflammation nodes, independent evidence strongly supports that the immune system and inflammatory programs are central to lung-cancer biology and have already yielded major therapeutic targets (and will likely yield more). PMC+1
Why I say that (big points, with sources):
Immune checkpoint therapy (anti-PD-1/PD-L1, anti-CTLA-4) is an established, practice-changing class of treatments in non-small cell lung cancer (NSCLC) — i.e., the immune axis is clinically actionable in lung cancer. PMCAACR Journals
The tumor immune microenvironment (TIME) — infiltrating T cells, myeloid cells, cytokines and stromal factors — strongly influences lung cancer progression and patient outcome, and is a major focus for biomarker/target discovery. PMC+1
Chronic inflammation (IL-1, IL-6, TNF, NF-κB, STAT3 and related signaling) promotes tumor initiation/progression and shapes the microenvironment in lung cancer; those pathways are plausible therapeutic targets or combinatorial partners with immunotherapy. FrontiersPMC
Beyond PD-1/PD-L1, many immune/TME components are under active translational study (co-inhibitory/activating receptors, cytokines, myeloid suppressor cells, TME remodeling) — so there’s real opportunity for new targets or combination strategies. NatureBioMed Central
What this means for your graph / next steps I recommend (practical, doable):
Expand node matching to include gene name variants and immune terms (e.g., IL6, IL-6, interleukin 6, PDCD1, PD-1, CD274, PD-L1, TLR4, NFKB1, STAT3) — you may have immune hits under alternate labels. I can do this mapping for you and return matches.
Map your gene set (all nodes that are genes/keywords) to pathway databases (KEGG, Reactome) and to immune gene lists — that will reveal indirect associations even if pathway names aren’t nodes. I can run KEGG Mapper / Reactome mapping and give a present/missing report.
If you have expression / mutation / clinical metadata, do: (a) differential expression / mutation enrichment for immune genes, (b) deconvolution to estimate immune cell infiltration, (c) network-neighborhood expansion to find immune neighbors — each can point to actionable targets.
Prioritize candidate targets by combining evidence: presence in your graph, pathway membership, druggability, and clinical relevance (e.g., known checkpoint ligands, cytokines, myeloid regulators).
Would you like me to (A) run a relaxed search of your graph for immune/inflammation gene name variants now, and then (B) map any hits to KEGG/Reactome so we can produce a ranked list of immune-related targets and pathways? If yes I’ll start immediately and return the matched nodes + pathway hits.
Sources
Short answer: Yes — very likely.
Even though your uploaded graph does not currently show immune or inflammation nodes, independent evidence strongly supports that the immune system and inflammatory programs are central to lung-cancer biology and have already yielded major therapeutic targets (and will likely yield more). (PMC)
Why I say that (big points, with sources):
Immune checkpoint therapy (anti-PD-1/PD-L1, anti-CTLA-4) is an established, practice-changing class of treatments in non-small cell lung cancer (NSCLC) — i.e., the immune axis is clinically actionable in lung cancer. (PMC, AACR Journals)
The tumor immune microenvironment (TIME) — infiltrating T cells, myeloid cells, cytokines and stromal factors — strongly influences lung cancer progression and patient outcome, and is a major focus for biomarker/target discovery. (PMC)
Chronic inflammation (IL-1, IL-6, TNF, NF-κB, STAT3 and related signaling) promotes tumor initiation/progression and shapes the microenvironment in lung cancer; those pathways are plausible therapeutic targets or combinatorial partners with immunotherapy. (Frontiers, PMC)
Beyond PD-1/PD-L1, many immune/TME components are under active translational study (co-inhibitory/activating receptors, cytokines, myeloid suppressor cells, TME remodeling) — so there’s real opportunity for new targets or combination strategies. (Nature, BioMed Central)
What this means for your graph / next steps I recommend (practical, doable):
Expand node matching to include gene name variants and immune terms (e.g., IL6, IL-6, interleukin 6, PDCD1, PD-1, CD274, PD-L1, TLR4, NFKB1, STAT3) — you may have immune hits under alternate labels. I can do this mapping for you and return matches.
Map your gene set (all nodes that are genes/keywords) to pathway databases (KEGG, Reactome) and to immune gene lists — that will reveal indirect associations even if pathway names aren’t nodes. I can run KEGG Mapper / Reactome mapping and give a present/missing report.
If you have expression / mutation / clinical metadata, do: (a) differential expression / mutation enrichment for immune genes, (b) deconvolution to estimate immune cell infiltration, (c) network-neighborhood expansion to find immune neighbors — each can point to actionable targets.
Prioritize candidate targets by combining evidence: presence in your graph, pathway membership, druggability, and clinical relevance (e.g., known checkpoint ligands, cytokines, myeloid regulators).
Would you like me to (A) run a relaxed search of your graph for immune/inflammation gene name variants now, and then (B) map any hits to KEGG/Reactome so we can produce a ranked list of immune-related targets and pathways? If yes I’ll start immediately and return the matched nodes + pathway hits.
Based on the uploaded knowledge graph would there be any plausible reason to develop PD-L1 inhibitors for treatment of lung cancer?
ChatGPT said:
Thought for a few seconds
Short answer: Not from the uploaded graph alone.
Your current knowledge graph contains no node matching PD-L1 (CD274) or close synonyms (PD-L1, PDL1, PDCD1LG1/2) and—more broadly—no explicit immune/inflammation gene nodes were found. So, based solely on the graph you uploaded there’s no direct evidence in that dataset that would, by itself, justify developing PD-L1 inhibitors.
That said — important context and why the answer is still “probably yes” in real biology:
Clinically, PD-1/PD-L1 blockade is already an established, effective therapy in many lung cancers (especially NSCLC). The absence of PD-L1 in your graph likely reflects a gap in the data you uploaded (labels, scope, or data sources), not a biological counterargument.
Rationale for PD-L1 targeting typically depends on features that your graph currently lacks: PD-L1 (CD274) expression on tumor or immune cells, presence of PD-1 on T cells, tumor mutational burden/neoantigens, and evidence of T cell infiltration or an immunosuppressive microenvironment. None of those features appear in your nodes.
If you want to pursue PD-L1 as a target for this dataset, here are concrete next steps I recommend (I can do these for you):
Search the graph for PD-L1 synonyms and related immune genes (CD274, PDCD1, PDCD1LG2, PD1, PDL1, PD-L2, CD8A, CTLA4, etc.) — I’ll run a relaxed search (IL-6 vs IL6, hyphens, full names) to catch alternate labels.
Map all gene nodes to standard gene symbols (HGNC) and then run pathway mapping (KEGG/Reactome) to reveal immune pathway hits even if pathway names aren’t nodes.
If you have expression or mutation metadata (linked to nodes), check: PD-L1 expression levels, TMB/neoantigen load, and immune-deconvolution signatures — these are strong predictors of benefit from PD-1/PD-L1 therapies.
Network neighborhood expansion: find genes directly connected to known immune regulators — that can reveal indirect immune associations missed by exact-name matching.
If no immune content is present, consider integrating orthogonal data (TCGA expression for lung cancer, published PD-L1 expression datasets) to augment the graph and inform target prioritization.
Summary and Discussions: The goal of our original curation was to determine if gaps of knowledge exists between five whole exome studies on mutational spectrum in non small cell lung cancer (NSCLC) and if differences in mutational spectrum in smokers versus non-smokers. Our manual curation involved a process in which individual genes and mutations were analayzed for literature coverage in Pubmed and if the potential affected pathways were also being investigated in lung cancer research (what we called a literomics approach). Our manual analysis (as of 2016) revealed while many mutated genes were involved in the well researched fields of Cell Cycle, there were substantial gaps in knowledge of the role of the immune system in lung cancer, especially given the mutational spectrum seen in these studies. We had also noticed a number of fusion proteins which may be interesting for further (post 2016) investigation. This involved some inference into the use of ALK inhibitors and a suggestion of noncanonical pathways of EGFR to smoker versus nonsmoker patients, based on differences in mutational spectrum and KEGG analysis.
Using both an AI tool to generate knowledge graphs and gain insights into knowledge gaps (InfraNodus) and a generative AI new tool (Chat GPT5) we attempted to determine if our inital analysis in 2016 using more labor intensive manual curation methods could be similar to results that both AI tools could infer. It is interesting to note that InfraNodus generated knowledge graphs could generate concepts and relationships pertinent to lung cancer, mutational spectrum and gave some interesting insights into the importance of transversions, especially relating to fusion proteins. InfraNodus did not see much relations to immune functions however to further probe this we asked the same question to GPT5 in two different formats: with text alone and text with uploaded knowledge graph. Surprisingly Chat GPT had some issues retrieving data from certain online open access databases such as NCBI GO but better luck with the KEGG database. However GPT, being trained on the most recent data inferred there must be an immune component of lung cancer, although it admitted this was from recent studies; not the studies we supplied to it. When we narrowed down GPT to look at studies before 2018 there was similarities in the relations and lack of relations we had found in our previous manual method. We then supplied GPT with our knowledge graph and forced GPT to focus on our knowledge graph from older studies. Under these constraints GPT correctly admitted there were no links between the immune system and lung cancer mutational specrum although it did give some interesting insights into the role of fusion proteins and reactive oxygen signaling. After our intial curation, one of our experts Dr. Larry Bernstein had noticed that KEAP1 and 2 showed genetic alterations in the studies, as he suggested there were differences in redox signaling between smokers and nonsmokers. KEAP1 and 2 are intracellular redox sensors.
Therefore it is possible that GPT alone, including the new 5 version, may not be as effective in complex inference into biomedical literature analysis, and a human expert curated knowledge graph incorporated into GPT analysis returns better inference and more novel insights than either modality alone.
For further reading on Artificial Intelligence, Machine Learning and Immunotherapy on this Open Access Scientific Journal please read these articles:
Part D: Curation entitled Multiple Lung Cancer Genomic Projects Suggest New Targets, Research Directions for Non-Small Cell Lung Cancer originally published on 09/05/2014
Note the text below this point was used for all AI-based text analsysis
summarizes the clinical importance of five new lung cancer genome sequencing projects. These studies have identified genetic and epigenetic alterations in hundreds of lung tumors, of which some alterations could be taken advantage of using currently approved medications.
The reports, all published this month, included genomic information on more than 400 lung tumors. In addition to confirming genetic alterations previously tied to lung cancer, the studies identified other changes that may play a role in the disease.
“All of these studies say that lung cancers are genomically complex and genomically diverse,” said Dr. Matthew Meyerson of Harvard Medical School and the Dana-Farber Cancer Institute, who co-led several of the studies, including a large-scale analysis of squamous cell lung cancer by The Cancer Genome Atlas (TCGA) Research Network.
Some genes, Dr. Meyerson noted, were inactivated through different mechanisms in different tumors. He cautioned that little is known about alterations in DNA sequences that do not encode genes, which is most of the human genome.
Four of the papers are summarized below, with the first described in detail, as the Nature paper used a multi-‘omics strategy to evaluate expression, mutation, and signaling pathway activation in a large cohort of lung tumors. A literature informatics analysis is given for one of the papers. Please note that links on GENE names usually refer to the GeneCard entry.
Paper 1. Comprehensive genomic characterization of squamous cell lung cancers[1]
The Cancer Genome Atlas Research Network Project just reported, in the journal Nature, the results of their comprehensive profiling of 230 resected lung adenocarcinomas. The multi-center teams employed analyses of
microRNA
Whole Exome Sequencing including
Exome mutation analysis
Gene copy number
Splicing alteration
Methylation
Proteomic analysis
Summary:
Some very interesting overall findings came out of this analysis including:
High rates of somatic mutations including activating mutations in common oncogenes
Newly described loss of function MGA mutations
Sex differences in EGFR and RBM10 mutations
driver roles for NF1, MET, ERBB2 and RITI identified in certain tumors
differential mutational pattern based on smoking history
splicing alterations driven by somatic genomic changes
MAPK and PI3K pathway activation identified by proteomics not explained by mutational analysis = UNEXPLAINED MECHANISM of PATHWAY ACTIVATION
however, given the plethora of data, and in light of a similar study results recently released, there appears to be a great need for additional mining of this CGAP dataset. Therefore I attempted to curate some of the findings along with some other recent news relevant to the surprising findings with relation to biomarker analysis.
Makeup of tumor samples
230 lung adenocarcinomas specimens were categorized by:
Subtype
33% acinar
25% solid
14% micro-papillary
9% papillary
8% unclassified
5% lepidic
4% invasive mucinous
Gender
Smoking status
81% of patients reported past of present smoking
The authors note that TCGA samples were combined with previous data for analysis purpose.
A detailed description of Methodology and the location of deposited data are given at the following addresses:
Gender and Smoking Habits Show different mutational patterns
WES mutational analysis
a) smoking status
– there was a strong correlations of cytosine to adenine nucleotide transversions with past or present smoking. In fact smoking history separated into transversion high (past and previous smokers) and transversion low (never smokers) groups, corroborating previous results.
→ mutations in groups Transversion High Transversion Low
TP53, KRAS, STK11, EGFR, RB1, PI3CA
KEAP1, SMARCA4 RBM10
b) Gender
Although gender differences in mutational profiles have been reported, the study found minimal number of significantly mutated genes correlated with gender. Notably:
EGFR mutations enriched in female cohort
RBM10 loss of function mutations enriched in male cohort
Although the study did not analyze the gender differences with smoking patterns, it was noted that RBM10 mutations among males were more prevalent in the transversion high group.
Whole exome Sequencing and copy number analysis reveal Unique, Candidate Driver Genes
Whole exome sequencing revealed that 62% of tumors contained mutations (either point or indel) in known cancer driver genes such as:
KRAS, EGFR, BRMF, ERBB2
However, authors looked at the WES data from the oncogene-negative tumors and found unique mutations not seen in the tumors containing canonical oncogenic mutations.
Unique potential driver mutations were found in
TP53, KEAP1, NF1, and RIT1
The genomics and expression data were backed up by a proteomics analysis of three pathways:
MAPK pathway
mTOR
PI3K pathway
…. showing significant activation of all three pathways HOWEVER the analysis suggested that activation of signaling pathways COULD NOT be deduced from DNA sequencing alone. Phospho-proteomic analysis was required to determine the full extent of pathway modification.
For example, many tumors lacked an obvious mutation which could explain mTOR or MAPK activation.
Altered cell signaling pathways included:
Increased MAPK signaling due to activating KRAS
Higher mTOR due to inactivating STK11 leading to increased proliferation, translation
Pathway analysis of mutations revealed alterations in multiple cellular pathways including:
Reduced oxidative stress response
Nucleosome remodeling
RNA splicing
Cell cycle progression
Histone methylation
Summary:
Authors noted some interesting conclusions including:
MET and ERBB2 amplification and mutations in NF1 and RIT1 may be unique driver events in lung adenocarcinoma
Possible new drug development could be targeted to the RTK/RAS/RAF pathway
MYC pathway as another important target
Cluster analysis using multimodal omics approach identifies tumors based on single-gene driver events while other tumor have multiple driver mutational events (TUMOR HETEROGENEITY)
Paper 2. A Genomics-Based Classification of Human Lung Tumors[2]
3,726 point mutations and more than 90 indels in the coding sequence
Smokers with lung cancer show 10× the number of point mutations than never-smokers
Novel lung cancer genes, including DACH1, CFTR, RELN, ABCB5, and HGF were identified
Tumor samples from males showed high frequency of MYCBP2 MYCBP2 involved in transcriptional regulation of MYC.
Variant allele frequency analysis revealed 10/17 tumors were at least biclonal while 7/17 tumors were monoclonal revealing majority of tumors displayed tumor heterogeneity
Novel pathway alterations in lung cancer include cell-cycle and JAK-STAT pathways
14 fusion proteins found, including ROS1-ALK fusion. ROS1-ALK fusions have been frequently found in lung cancer and is indicative of poor prognosis[4].
Novel metabolic enzyme fusions
Alterations were identified in 54 genes for which targeted drugs are available. Drug-gable mutant targets include: AURKC, BRAF, HGF, EGFR, ERBB4, FGFR1, MET, JAK2, JAK3, HDAC2, HDAC6, HDAC9, BIRC6, ITGB1, ITGB3, MMP2, PRKCB, PIK3CG, TERT, KRAS, MMP14
Table. Validated Gene-Fusions Obtained from Ref-Seq Data
Note: Gene columns contain links for GeneCard while Gene function links are to the gene’s GO (Gene Ontology) function.
There has been a recent literature on the importance of the EML4-ALK fusion protein in lung cancer. EML4-ALK positive lung tumors were found to be les chemo sensitive to cytotoxic therapy[5] and these tumor cells may exhibit an epitope rendering these tumors amenable to immunotherapy[6]. In addition, inhibition of the PI3K pathway has sensitized EMl4-ALK fusion positive tumors to ALK-targeted therapy[7]. EML4-ALK fusion positive tumors show dependence on the HSP90 chaperone, suggesting this cohort of patients might benefit from the new HSP90 inhibitors recently being developed[8].
Table. Significantly mutated genes (point mutations, insertions/deletions) with associated function.
Table. Literature Analysis of pathways containing significantly altered genes in NSCLC reveal putative targets and risk factors, linkage between other tumor types, and research areas for further investigation.
Note: Significantly mutated genes, obtained from WES, were subjected to pathway analysis (KEGG Pathway Analysis) in order to see which pathways contained signicantly altered gene networks. This pathway term was then used for PubMed literature search together with terms “lung cancer”, “gene”, and “NOT review” to determine frequency of literature coverage for each pathway in lung cancer. Links are to the PubMEd search results.
KEGG pathway Name
# of PUBMed entries containing Pathway Name, Gene ANDLung Cancer
A few interesting genetic risk factors and possible additional targets for NSCLC were deduced from analysis of the above table of literature including HIF1-α, mIR-31, UBQLN1, ACE, mIR-193a, SRSF1. In addition, glioma, melanoma, colorectal, and prostate and lung cancer share many validated mutations, and possibly similar tumor driver mutations.
please click on graph for larger view
Paper 4. Mapping the Hallmarks of Lung Adenocarcinoma with Massively Parallel Sequencing[9]
Exome and genome characterization of somatic alterations in 183 lung adenocarcinomas
12 somatic mutations/megabase
U2AF1, RBM10, and ARID1A are among newly identified recurrently mutated genes
Structural variants include activating in-frame fusion of EGFR
Epigenetic and RNA deregulation proposed as a potential lung adenocarcinoma hallmark
Summary
Lung adenocarcinoma, the most common subtype of non-small cell lung cancer, is responsible for more than 500,000 deaths per year worldwide. Here, we report exome and genome sequences of 183 lung adenocarcinoma tumor/normal DNA pairs. These analyses revealed a mean exonic somatic mutation rate of 12.0 events/megabase and identified the majority of genes previously reported as significantly mutated in lung adenocarcinoma. In addition, we identified statistically recurrent somatic mutations in the splicing factor gene U2AF1 and truncating mutations affecting RBM10 and ARID1A. Analysis of nucleotide context-specific mutation signatures grouped the sample set into distinct clusters that correlated with smoking history and alterations of reported lung adenocarcinoma genes. Whole-genome sequence analysis revealed frequent structural rearrangements, including in-frame exonic alterations within EGFR and SIK2 kinases. The candidate genes identified in this study are attractive targets for biological characterization and therapeutic targeting of lung adenocarcinoma.
Paper 5. Integrative genome analyses identify key somatic driver mutations of small-cell lung cancer[10]
Highlights
Whole exome and transcriptome (RNASeq) sequencing 29 small-cell lung carcinomas
High mutation rate 7.4 protein-changing mutations/million base pairs
Inactivating mutations in TP53 and RB1
Functional mutations in CREBBP, EP300, MLL, PTEN, SLIT2, EPHA7, FGFR1 (determined by literature and database mining)
The mutational spectrum seen in human data also present in a Tp53-/- Rb1-/- mouse lung tumor model
Curator Graphical Summary of Interesting Findings From the Above Studies
The above figure (please click on figure) represents themes and findings resulting from the aforementioned studies including
questions which will be addressed in Future Postson this site.
UPDATED 10/10/2021
The following article uses RNASeq to screen lung adenocarcinomas for fusion proteins in patients with either low or high tumor mutational burden. Findings included presence of MET fusion proteins in addition to other fusion proteins irrespective if tumors were driver negative by DNASeq screening.
High Yield of RNA Sequencing for Targetable Kinase Fusions in Lung Adenocarcinomas with No Mitogenic Driver Alteration Detected by DNA Sequencing and Low Tumor Mutation Burden
Source:
High Yield of RNA Sequencing for Targetable Kinase Fusions in Lung Adenocarcinomas with No Mitogenic Driver Alteration Detected by DNA Sequencing and Low Tumor Mutation Burden
RymaBenayed, MichaelOffin, KerryMullaney, PurvilSukhadia, KellyRios, PatriceDesmeules, RyanPtashkin, HelenWon, JasonChang, DarraghHalpenny, Alison M.Schram, Charles M.Rudin, David M.Hyman, Maria E.Arcila, Michael F.Berger, AhmetZehir, Mark G.Kris, AlexanderDrilon and MarcLadanyi
Purpose: Targeted next-generation sequencing of DNA has become more widely used in the management of patients with lung adenocarcinoma; however, no clear mitogenic driver alteration is found in some cases. We evaluated the incremental benefit of targeted RNA sequencing (RNAseq) in the identification of gene fusions and MET exon 14 (METex14) alterations in DNA sequencing (DNAseq) driver–negative lung cancers.
Experimental Design: Lung cancers driver negative by MSK-IMPACT underwent further analysis using a custom RNAseq panel (MSK-Fusion). Tumor mutation burden (TMB) was assessed as a potential prioritization criterion for targeted RNAseq.
Results: As part of prospective clinical genomic testing, we profiled 2,522 lung adenocarcinomas using MSK-IMPACT, which identified 195 (7.7%) fusions and 119 (4.7%) METex14 alterations. Among 275 driver-negative cases with available tissue, 254 (92%) had sufficient material for RNAseq. A previously undetected alteration was identified in 14% (36/254) of cases, 33 of which were actionable (27 in-frame fusions, 6 METex14). Of these 33 patients, 10 then received matched targeted therapy, which achieved clinical benefit in 8 (80%). In the 32% (81/254) of DNAseq driver–negative cases with low TMB [0–5 mutations/Megabase (mut/Mb)], 25 (31%) were positive for previously undetected gene fusions on RNAseq, whereas, in 151 cases with TMB >5 mut/Mb, only 7% were positive for fusions (P < 0.0001).
Conclusions: Targeted RNAseq assays should be used in all cases that appear driver negative by DNAseq assays to ensure comprehensive detection of actionable gene rearrangements. Furthermore, we observed a significant enrichment for fusions in DNAseq driver–negative samples with low TMB, supporting the prioritization of such cases for additional RNAseq.
Translational Relevance
Inhibitors targeting kinase fusions have shown dramatic and durable responses in lung cancer patients, making their comprehensive detection critical. Here, we evaluated the incremental benefit of targeted RNA sequencing (RNAseq) in the identification of gene fusions in patients where no clear mitogenic driver alteration is found by DNA sequencing (DNAseq)–based panel testing. We found actionable alterations (kinase fusions or MET exon 14 skipping) in 13% of cases apparently driver negative by previous DNAseq testing. Among the driver-negative samples tested by RNAseq, those with low tumor mutation burden (TMB) were significantly enriched for gene fusions when compared with the ones with higher TMB. In a clinical setting, such patients should be prioritized for RNAseq. Thus, a rational, algorithmic approach to the use of targeted RNA-based next-generation sequencing (NGS) to complement large panel DNA-based NGS testing can be highly effective in comprehensively uncovering targetable gene fusions or oncogenic isoforms not just in lung cancer but also more generally across different tumor types.
Wake Up and Smell the Fusions: Single-Modality Molecular Testing Misses Drivers
by Kurtis D.Davies and Dara L.Aisner
Abstract
Multitarget assays have become common in clinical molecular diagnostic laboratories. However, all assays, no matter how well designed, have inherent gaps due to technical and biological limitations. In some clinical cases, testing by multiple methodologies is needed to address these gaps and ensure the most accurate molecular diagnoses.
In this issue of Clinical Cancer Research, Benayed and colleagues illustrate the growing need to consider multiple molecular testing methodologies for certain clinical specimens (1). The rapidly expanding list of actionable molecular alterations across cancer types has resulted in the wide adoption of multitarget testing approaches, particularly those based on next-generation sequencing (NGS). NGS-based assays are commonly viewed as “one-stop shops” to detect a vast array of molecular variants. However, as Benayed and colleagues discuss, even well-designed and highly vetted NGS assays have inherent gaps that, under certain circumstances, are ideally addressed by analyzing the sample using an alternative approach.
In the article, the authors examined a cohort of lung adenocarcinoma patient samples that had been deemed “driver- negative” via MSK-IMPACT, an FDA-cleared test that is widely considered by experts in the field to be one of the best examples of a DNA-based large gene panel NGS assay (2). Of 589 driver-negative cases, 254 had additional material amenable for a different approach: RNA-based NGS designed specifically for gene fusion and oncogenic gene isoform detection. After accounting for quality control failures, 232 samples were successfully sequenced, and, among these, 36 samples (representing an astonishing 15.5% of tested cases) were found to be positive for a driver gene fusion or oncogenic isoform that had not been detected by DNA-based NGS. The real-world value derived from this orthogonal testing schema was more than theoretical, with 8 of 10 (80%) patients demonstrating clinical benefit when treated according to the alteration identified via the RNA-based approach.
To detect gene rearrangements that lead to oncogenic gene fusions (and to detect mutations and insertions/deletions that lead to MET exon 14 skipping), MSK-IMPACT employs hybrid capture-based enrichment of selected intronic regions from genomic DNA. While this approach has proven to be successful in a variety of settings, there are associated limitations that were determined in this study to underlie the discrepancies between MSK-IMPACT and the RNA-based assay. First, some introns that are involved in clinically actionable rearrangement events are very large, thus requiring substantial sequencing capital that can represent a disproportionate fraction of the assay. Despite the ability via NGS to perform sequencing at a large scale, this sequencing capacity is still finite, and thus decisions must be made to sacrifice coverage of certain large genomic regions to ensure sufficient sequencing depth for other desired genomic targets. In the case of MSK-IMPACT (and most other DNA-based NGS assays), certain important introns in NTRK3 and NRG1 are not included in covered content, simply because they are too large (>90 Kb each). The second primary problem with DNA-based analysis of introns is that they often contain highly repetitive elements that are extremely difficult to assess via NGS due to their recurring presence across the genome. Attempts to sequence these regions are largely unfruitful because any sequencing data obtained cannot be specifically aligned/mapped to the desired targeted region of the genome (3). This is particularly true for intron 31 of ROS1, because it contains two repetitive long interspersed nuclear elements, and many DNA-based assays, including MSK-IMPACT, poorly cover this intron (4). In this study by Benayed and colleagues, the most common discrepant alteration was fusion involving ROS1, which accounted for 10 of 36 (28%) cases. At least six of these, those that demonstrated fusion to ROS1 exon 32, were likely directly explained by incomplete intron 31 sequencing. RNA-based analysis is able to overcome the above described limitations owing to the simple fact that sequencing is focused on exons post-splicing and the need to sequence introns is entirely avoided (Fig. 1).
Schematic representation of underlying genomic complexities that can lead to false-negative gene fusion results in DNA-based NGS analysis. In some cases, RNA-based approaches may overcome the limitations of DNA-based testing.
Lack of sufficient intronic coverage could not account for all of the discrepancies between DNA-based and RNA-based analysis however. Six samples in the cohort were found to be positive for MET exon 14 skipping based on RNA. In five of these, genomic alterations in MET introns 13 or 14 were observed, however they did not conform to canonical splice site alterations and thus were not initially called (although this was addressed by bioinformatics updates). In RNA-based testing, however, determination of exon skipping is simplified such that, regardless of the specific genomic alteration that interferes with splicing, absence of the exon in the transcript is directly observed (5). In another two of the discrepant cases, tumor purity was observed to be low in the sample, meaning that the expected variant allele frequency (VAF) for a genomic event would also likely be low, potentially below detectable levels. However, overexpression of the fusions at the transcript level was theorized to compensate for low VAF (Fig. 1). Additional explanations for discordant findings between the assays included sample-specific poor sequencing in selected introns and complex rearrangements that hindered proper capture (Fig. 1).
The take home message from Benayed and colleagues is simply this: there is no perfect assay that will detect 100% of the potential actionable alterations in patient samples. Even an extremely well designed, thoroughly vetted, and FDA-cleared assay such as MSK-IMPACT will have inherent and unavoidable “holes” due to intrinsic limitations. The solution to this dilemma, as adeptly described by Benayed and colleagues, is additional testing using a different approach. While in an ideal world every clinical tumor sample would be tested by multiple modalities to ensure the most comprehensive clinical assessment, the reality is that these samples are often scant and testing is fiscally burdensome (and often not reimbursed). Therefore, algorithms to determine which samples should be reflexed to secondary assays after testing with a primary assay are critical for maximizing benefit. In this study, the first algorithmic step was lack of an identified driver (because activated oncogenic drivers tend to exist exclusively of each other), which amounted to 23% of samples tested with the primary assay. In addition, the authors found a significantly higher rate of actionable gene fusions in samples with a low (<5 mut/Mb) tumor mutational burden, meaning that this metric, which was derived from the primary assay, could also be used to help inform decision making regarding additional testing. While this scenario is somewhat specific to lung cancer, similar approaches could be prescribed on a cancer type–specific basis.
These findings should be considered a “wake-up call” for oncologists in regard to the ordering and interpretation of molecular testing. It is clear from these and other published findings that advanced molecular analysis has limitations that require nuanced technical understanding. As this arena evolves, it is critical for oncologists (and trainees) to gain an increased comprehension of how to identify when the “gaps” in a test might be most clinically relevant. This requires a level of technical cognizance that has been previously unexpected of clinical practitioners, yet is underscored by the reality that opportunities for effective targeted therapy can and will be missed if the treating oncologist is unaware of how to best identify patients for whom additional testing is warranted. This study also highlights the mantra of “no test is perfect” regardless of prestige of the testing institution, number of past tests performed, or regulatory status. NGS, despite its benefits, does not mean all-encompassing. It is only through the adaptability of laboratories to utilize knowledge such as is provided by Benayed and colleagues that advances in laboratory medicine can be quickly deployed to maximize benefits for oncology patients.
Govindan R, Ding L, Griffith M, Subramanian J, Dees ND, Kanchi KL, Maher CA, Fulton R, Fulton L, Wallis J et al: Genomic landscape of non-small cell lung cancer in smokers and never-smokers. Cell 2012, 150(6):1121-1134.
Takeuchi K, Soda M, Togashi Y, Suzuki R, Sakata S, Hatano S, Asaka R, Hamanaka W, Ninomiya H, Uehara H et al: RET, ROS1 and ALK fusions in lung cancer. Nature medicine 2012, 18(3):378-381.
Morodomi Y, Takenoyama M, Inamasu E, Toyozawa R, Kojo M, Toyokawa G, Shiraishi Y, Takenaka T, Hirai F, Yamaguchi M et al: Non-small cell lung cancer patients with EML4-ALK fusion gene are insensitive to cytotoxic chemotherapy. Anticancer research 2014, 34(7):3825-3830.
Yoshimura M, Tada Y, Ofuzi K, Yamamoto M, Nakatsura T: Identification of a novel HLA-A 02:01-restricted cytotoxic T lymphocyte epitope derived from the EML4-ALK fusion gene. Oncology reports 2014, 32(1):33-39.
Workman P, van Montfort R: EML4-ALK fusions: propelling cancer but creating exploitable chaperone dependence. Cancer discovery 2014, 4(6):642-645.
Imielinski M, Berger AH, Hammerman PS, Hernandez B, Pugh TJ, Hodis E, Cho J, Suh J, Capelletti M, Sivachenko A et al: Mapping the hallmarks of lung adenocarcinoma with massively parallel sequencing. Cell 2012, 150(6):1107-1120.
Peifer M, Fernandez-Cuesta L, Sos ML, George J, Seidel D, Kasper LH, Plenker D, Leenders F, Sun R, Zander T et al: Integrative genome analyses identify key somatic driver mutations of small-cell lung cancer. Nature genetics 2012, 44(10):1104-1110.
Other posts on this site which refer to Lung Cancer and Cancer Genome Sequencing include:
This is an up-to-date article about the significance of mutations found in 12 major types of cancer.
Word Cloud by Daniel Menzin
UPDATED 4/24/2020 The genomic landscape of pediatric cancers: Curation of WES/WGS studies shows need for more data
Mutational landscape and significance across 12 major cancer types
Cyriac Kandoth1*, Michael D. McLellan1*, Fabio Vandin2, Kai Ye1,3, Beifang Niu1, Charles Lu1, et al.
1The Genome Institute, Washington University in St Louis, Missouri 63108, USA. 2Department of Computer Science, Brown University, Providence, Rhode Island 02912, USA. 3Department of Genetics, Washington University in St Louis, Missouri 63108, USA. 4Department of Medicine, Washington University in St Louis, Missouri 63108, USA. 5Siteman Cancer Center, Washington University in St Louis, Missouri 63108, USA. 6Department of Mathematics, Washington University in St Louis, Missouri 63108, USA.
The Cancer Genome Atlas (TCGA) has used the latest sequencing and analysis methods to identify somatic variants across thousands of tumours. Here we present data and analytical results for point mutations and small insertions/deletions from 3,281 tumours across 12 tumour typesas part of the TCGA Pan-Cancer effort. We illustrate
Using the integrated data sets, we identified 127 significantly mutated genes from well-knownand emerging cellular processes in cancer.
(for example, mitogen-activated protein kinase, phosphatidylinositol-3-OH kinase,Wnt/b-catenin and receptor tyrosine kinase signalling pathways, and cell cycle control)
(for example, histone, histone modification, splicing, metabolism and proteolysis)
The average number of mutations in these significantly mutated genes varies across tumour types;
most tumours have two to six, indicating that the number of driver mutations required during oncogenesis is relatively small.
Mutations in transcriptional factors/regulators show tissue specificity, whereas
histone modifiers are often mutated across several cancer types.
Clinical association analysis identifies genes having a significant effect on survival, and
investigations of mutations with respect to clonal/subclonal architecture delineate their temporal orders during tumorigenesis.
Taken together, these results lay the groundwork for developing new diagnostics and individualizing cancer treatment
Introduction
The advancement of DNA sequencing technologies now enables the processing of thousands of tumours of many types for systematic mutation discovery. This expansion of scope, coupled with appreciable progress in algorithms1–5, has led directly to characterization of significant functional mutations, genes and pathways6–18. Cancer encompasses more than 100 related diseases19, making it crucial to understand the commonalities and differences among various types and subtypes. TCGA was founded to address these needs, and its large data sets are providing unprecedented opportunities for systematic, integrated analysis.
We performed a systematic analysis of 3,281 tumours from 12 cancer types to investigate underlying mechanisms of cancer initiation and progression. We describe variable mutation frequencies and contexts and their associations with environmental factors and defects in DNA repair. We identify 127 significantlymutated genes (SMGs) from diverse signalling and enzymatic processes. The finding of a TP53-driven breast, head and neck, and ovarian cancer cluster with a dearth of other mutations in SMGs suggests common therapeutic strategies might be applied for these tumours. We determined interactions among mutations and correlated mutations in BAP1, FBXW7 and TP53 with detrimental phenotypes across several cancer types. The subclonal structure and transcription status of underlying somatic mutations reveal the trajectory of tumour progression in patients with cancer.
Standardization of mutation data
Stringent filters (Methods) were applied to ensure high quality mutation calls for 12 cancer types: breast adenocarcinoma (BRCA), lung adenocarcinoma (LUAD), lung squamous cell carcinoma (LUSC), uterine corpus endometrial carcinoma (UCEC), glioblastoma multiforme (GBM), head and neck squamous cell carcinoma (HNSC), colon and rectal carcinoma (COAD, READ),bladder urothelial carcinoma (BLCA), kidney renal clear cell carcinoma (KIRC), ovarian serous carcinoma (OV) and acute myeloid leukaemia (LAML; conventionally called AML) (Supplementary Table 1). A total of 617,354 somatic mutations, consisting of
15,141 frameshift insertions/deletions (indels) and
3,538 inframe indels,
were included for downstream analyses (Supplementary Table 2).
Distinct mutation frequencies and sequence context
Figure 1a shows that AML has the lowest median mutation frequency and LUSC the highest (0.28 and 8.15 mutations per megabase (Mb), respectively). Besides AML, all types average over 1 mutation per Mb, substantially higher than in pediatric tumours20. Clustering21 illustrates that
mutation frequencies for KIRC, BRCA, OV and AML are normally distributed within a single cluster, whereas
other types have several clusters (for example, 5 and 6 clusters in UCEC and COAD/ READ, respectively) (Fig. 1a and Supplementary Table 3a, b).
In UCEC, the largest patient cluster has a frequency of approximately 1.5 mutations per Mb, and
the cluster with the highest frequency is more than 150 times greater.
Multiple clusters suggest that factors other than age contribute to development in these tumours14,16. Indeed,
there is a significant correlation between high mutation frequency and DNA repair pathway genes (for example, PRKDC, TP53 and MSH6) (Supplementary Table 3c). Notably,
PRKDC mutations are associated with high frequency in BLCA, COAD/READ, LUAD and UCEC, whereas
TP53 mutations are related with higher frequencies in AML, BLCA, BRCA, HNSC, LUAD, LUSC and UCEC (all P < 0.05).
Mutations in POLQ and POLE associate with high frequencies in multiple cancer types; POLE association in UCEC is consistent with previous observations14.
Comparison of spectra across the 12 types (Fig. 1b and Supplementary Table 3d) reveals that LUSC and LUAD contain increased C>A transversions, a signature of cigarette smoke exposure10. Sequence context analysis across 12 types revealed
the largest difference being in C>T transitions and C>G transversions (Fig. 1c).
The frequency of thymine 1-bp (base pair)upstream of C>G transversions is markedly higher in BLCA, BRCA and HNSC than in other cancer types (Extended Data Fig. 1). GBM, AML, COAD/READ and UCEC have similar contexts in that
the proportions of guanine 1 base downstreamof C>T transitions are between
59% and 67%, substantially higher than the approximately 40% in other cancer types.
Higher frequencies of transition mutations at CpG in gastrointestinal tumours, including colorectal, were previously reported22. We found three additional cancer types (GBM, AML and UCEC) clustered in the C>T mutation at CpG, consistent with previous findings of
aberrant DNA methylation in endometrial cancer23 and glioblastoma24.
BLCA has a unique signature for C>T transitions compared to the other types (enriched for TC) (Extended Data Fig. 1).
Significantly mutated genes
Genes under positive selection, either in individual or multiple tumour types, tend to display higher mutation frequencies above background. Our statistical analysis3, guided by expression data and curation (Methods), identified 127 such genes (SMGs; Supplementary Table 4). These SMGs are involved in a wide range of cellular processes, broadly classified into 20 categories (Fig. 2), including
The identification of MAPK, PI(3)K and Wnt/ -catenin signaling pathways is consistent with classical cancer studies. Notably, newer categories (for example, splicing, transcription regulators, metabolism, proteolysis and histones) emerge as exciting guides for the development of new therapeutic targets. Genes categorized as histone modifiers (Z = 0.57), PI(3)K signalling (Z = 1.03), and genome integrity (Z = 0.66) all relate to more than one cancer type, whereas
transcription factor/regulator (Z = 0.40), TGF- signalling (Z = 0.66), and Wnt/ -catenin signalling (Z = 0.55) genes tend to associate with single types (Methods).
Notably, 3,053 out of 3,281 total samples (93%) across the Pan-Cancer collection had at least one non-synonymous mutation in at least one SMG. The average number of point mutations and small indels in these genes varies across tumour types, with the highest (,6 mutations per tumour) in UCEC, LUAD and LUSC, and the lowest (,2 mutations per tumour) in AML, BRCA, KIRC and OV. This suggests that the numbers of both cancer-related genes (only 127 identified in this study) and cooperating driver mutations required during oncogenesis are small (most cases only had 2–6) (Fig. 3), although large-scale structural rearrangements were not included in this analysis.
Common mutations
The most frequently mutated gene in the Pan-Cancer cohort is TP53 (42% of samples). Its mutations predominate in serous ovarian (95%) and serous endometrial carcinomas (89%) (Fig. 2). TP53mutations are also associated with basal subtype breast tumours. PIK3CA is the second most commonly mutated gene, occurring frequently (>10%) in most cancer types except OV, KIRC, LUAD and AML. PIK3CA mutations frequented UCEC (52%) and BRCA (33.6%), being specifically enriched in luminal subtype tumours. Tumours lacking PIK3CA mutations often had mutations inPIK3R1, with the highest occurrences in UCEC (31%) and GBM (11%) (Fig. 2).
Many cancer types carried mutations in chromatin re-modelling genes. In particular, histone-lysine N-methyltransferase genes (MLL2 (also known as KMT2D), MLL3 (KMT2C) and MLL4 (KMT2B)) cluster in bladder, lung and endometrial cancers, whereas the lysine (K)-specific demethylase KDM5C is prevalently mutated in KIRC (7%). Mutations in ARID1A are frequent in BLCA, UCEC, LUAD and LUSC, whereas mutations inARID5B predominate in UCEC (10%) (Fig. 2).
Fig. 1. | Distribution of mutation frequencies across 12 cancer types.
Dashed grey and solid white lines denote average across cancer types and median for each type, respectively. b, Mutation spectrum of six transition (Ti) and transversion (Tv) categories for each cancer type. c, Hierarchically clustered mutation context (defined by the proportion of A, T, C and G nucleotides within ±2bp of variant site) for six mutation categories. Cancer types correspond to colours in a. Colour denotes degree of correlation: yellow (r = 0.75) and red (r = 1).
Fig. 2. The 127 SMGs from 20 cellular processes in cancer identified in and Pan-Cancer are shown, with the highest percentage in each gene among 12 (not shown)
Fig. 3. | Distribution of mutations in 127 SMGs across Pan-Cancer cohort.
Box plot displays median numbers of non-synonymous mutations, with outliers shown as dots. In total, 3,210 tumours were used for this analysis (hypermutators excluded).
Figure 4 | Unsupervised clustering based on mutation status of SMGs. Tumours having no mutation or more than 500 mutations were excluded. A mutation status matrix was constructed for 2,611 tumours. Major clusters of mutations detected in UCEC, COAD, GBM, AML, KIRC, OV and BRCA were highlighted.
Complete gene list shown in Extended Data Fig. 3. (not shown)
Figure 5 | Driver initiation and progression mutations and tumour clonal mutation is in the subclone
Survival Analysis
We examined which genes correlate with survival using the Cox proportional hazards model, first analysing individual cancer types using age and gender as covariates; an average of 2 genes (range: 0–4) with mutation frequency 2% were significant (P<_0.05) in each type (Supplementary Table 10a and Extended Data Fig. 6). KDM6A and ARID1A mutations correlate with better survival in BLCA (P = 0.03, hazard ratio (HR) = 0.36, 95% confidence interval (CI): 0.14–0.92) and UCEC (P = 0.03, HR = 0.11, 95% CI: 0.01–0.84), respectively, but mutations in SETBP1, recently identified with worse prognosis in atypical chronic myeloid leukaemia (aCML)31, have a significant detrimental effect in HNSC (P = 0.006, HR = 3.21, 95% CI: 1.39–7.44). BAP1 strongly correlates with poor survival (P = 0.00079, HR = 2.17, 95% CI: 1.38–3.41) in KIRC. Conversely, BRCA2 mutations (P = 0.02, HR = 0.31, 95% CI: 0.12–0.85) associate with better survival in ovarian cancer, consistent with previous reports32,33; BRCA1 mutations showed positive correlation with better survival, but did not reach significance here.
We extended our survival analysis across cancer types, restricting our attention to the subset of 97 SMGs whose mutations appeared in 2% of patients having survival data in 2 tumour types. Taking type, age and gender as covariates, we found 7 significant genes: BAP1, DNMT3A, HGF, KDM5C, FBXW7, BRCA2 and TP53 (Extended Data Table 1). In particular,BAP1 was highly significant (P = 0.00013, HR = 2.20, 95% CI: 1.47–3.29, more than 53 mutated tumours out of 888 total), with mutations associating with detrimental outcome in four tumour typesand notable associations in KIRC(P = 0.00079), consistent with a recent report28, and in UCEC(P = 0.066). Mutations in several other genes are detrimental, including DNMT3A (HR = 1.59), previously identified with poor prognosis in AML34, and KDM5C(HR = 1.63), FBXW7 (HR = 1.57) and TP53(HR = 1.19).TP53 has significant associations with poor outcome in KIRC (P = 0.012), AML(P = 0.0007) and HNSC (P = 0.00007). Conversely, BRCA2(P = 0.05, HR = 0.62, 95% CI: 0.38 to 0.99) correlates with survival benefit in six types, including OV and UCEC (Supplementary Table 10a, b).IDH1 mutations are associated with improved prognosis across the Pan-Cancer set (HR = 0.67, P = 0.16) and also in GBM (HR = 0.42, P = 0.09) (Supplementary Table 10a, b), consistent with previous work.35
Driver mutations and tumour clonal architecture
To understand the temporal order of somatic events, we analysed the variant allele fraction (VAF) distribution of mutations in SMGs across AML, BRCA and UCEC (Fig. 5a and Supplementary Table 11a) and other tumour types (Extended Data Fig. 7). To minimize the effect of copy number alterations, we focused on mutations in copy neutral segments. Mutations in TP53 have higher VAFs on average in all three cancer types, suggesting early appearance during tumorigenesis.
It is worth noting that copy neutral loss of heterozygosity is commonly found in classical tumour suppressors such as TP53, BRCA1, BRCA2 and PTEN, leading to increased VAFs in these genes. In AML, DNMT3A (permutation test P = 0), RUNX1 (P = 0.0003) and SMC3 (P = 0.05) have significantly higher VAFs than average among SMGs (Fig. 5a and Supplementary Table 11b). In breast cancer, AKT1, CBFB, MAP2K4, ARID1A, FOXA1 and PIK3CA have relatively high average VAFs. For endometrial cancer, multiple SMGs (for example, PIK3CA, PIK3R1, PTEN, FOXA2 and ARID1A) have similar median VAFs. Conversely, KRAS and/or NRAS mutations tend to have lower VAFs in all three tumour types (Fig. 5a), suggesting NRAS (for example, P = 0 in AML) and KRAS (for example, P = 0.02 in BRCA) have a progression role in a subset of AML, BRCA and UCEC tumours. For all three cancer types, we clearly observed a shift towards higher expression VAFs in SMGs versus non-SMGs, most apparent in BRCA and UCEC (Extended Data Fig. 8a and Methods).
Previous analysis using whole-genome sequencing (WGS) detected subclones in approximately 50% of AML cases15,36,37; however, analysis is difficult using AML exome owing to its relatively few coding mutations. Using 50 AML WGS cases, sciClone (http://github.com/ genome/sciclone) detected DNMT3A mutations in the founding clone for 100% (8 out of 8) of cases and NRAS mutations in the subclone for 75% (3 out of 4) of cases (Extended Data Fig. 8b). Among 304 and 160 of BRCA and UCEC tumours, respectively, with enough coding mutations for clustering, 35% BRCA and 44% UCEC tumours contained subclones. Our analysis provides the lower bound for tumour heterogeneity, because only coding mutations were used for clustering. In BRCA, 95% (62 out of 65) of cases contained PIK3CA mutations in the founding clone, whereas 33% (3 out of 9) of cases had MLL3 mutations in the subclone. Similar patterns were found in UCEC tumours, with 96% (65 out of 68) and 95% (62 out of 65) of tumours containing PIK3CA and PTEN mutations, respectively, in the founding clone, and 9% (2 out of22) ofKRAS and 14% (1 out of 7) ofNRAS mutations in the subclone (Extended Data Fig. 8b and Supplementary Table 12).
Mutation context (-2 to +2 bp) was calculated for each somatic variant in each mutation category, and hierarchical clustering was then performed using the pairwise mutation context correlation across all cancer types. The mutational significance in cancer (MuSiC)3 package was used to identify significant genes for both individual tumour types and the Pan-Cancer collective. An R function ‘hclust’ was used for complete-linkage hierarchical clustering across mutations and samples, and Dendrix30 was used to identify sets of approximately mutual exclusive mutations. Cross-cancer survival analysis was based on the Cox proportional hazards model, as implemented in the R package ‘survival’ (http://cran.r-project.org/web/ packages/survival/), and the sciClone algorithm (http://github.com/genome/sci-clone) generated mutation clusters using point mutations from copy number neutral segments. A complete description of the materials and methods used to generate this data set and its results is provided in the Methods.
References (20 of 38)
Larson, D. E. et al. SomaticSniper: identification of somatic point mutations in whole genome sequencing data. Bioinformatics 28, 311–317 (2012).
Koboldt, D. C. et al. VarScan 2: somatic mutation and copy number alteration discovery in cancer by exome sequencing. Genome Res. 22, 568–576 (2012).
Dees, N. D. et al. MuSiC: Identifying mutational significance in cancer genomes. Genome Res. 22, 1589–1598 (2012).
Roth, A. et al. JointSNVMix: a probabilistic model for accurate detection of somatic mutations in normal/tumour paired next-generation sequencing data. Bioinformatics 28, 907–913 (2012).
Cibulskis, K. et al. Sensitive detection of somatic point mutations in impure and heterogeneous cancer samples. Nature Biotechnol. 31, 213–219 (2013).
Jones, S. et al. Core signaling pathways in human pancreatic cancers revealed by global genomic analyses. Science 321, 1801–1806 (2008).
Parsons, D. W. et al. An integrated genomic analysis of human glioblastoma multiforme. Science 321, 1807–1812 (2008).
Sjo¨blom, T. etal. The consensuscodingsequences of human breast and colorectal cancers. Science 314, 268–274 (2006).
The Cancer Genome Atlas Research Network. Comprehensive genomic characterization defines human glioblastoma genes and core pathways. Nature 455, 1061–1068 (2008).
Ding, L. et al. Somatic mutations affect key pathways in lung adenocarcinoma. Nature 455, 1069–1075 (2008).
Wood, L. D. etal. The genomic landscapesof human breast and colorectal cancers. Science 318, 1108–1113 (2007).
The Cancer Genome Atlas Research Network. Integrated genomic analyses of ovarian carcinoma. Nature 474, 609–615 (2011).
The Cancer Genome Atlas Network. Comprehensive molecular portraits of human breast tumours. Nature 490, 61–70 (2012).
Cancer Genome Atlas Research Network. Integrated genomic characterization of endometrial carcinoma. Nature 497, 67–73 (2013).
The Cancer Genome Atlas Research Network. Genomic and epigenomic landscapes of adult de novo acute myeloid leukemia. N. Engl. J. Med. 368, 2059–2074 (2013).
The Cancer Genome Atlas Network. Comprehensive molecular characterization of human colon and rectal cancer. Nature 487, 330–337 (2012).
Ellis, M. J. et al. Whole-genome analysis informs breast cancer response to aromatase inhibition. Nature 486, 353–360 (2012).
The Cancer Genome Atlas Research Network. Comprehensive molecular characterization of clear cell renal cell carcinoma. Nature 499, 43–49 (2013).
Hanahan, D. & Weinberg, R. A. The hallmarks of cancer. Cell 100, 57–70 (2000).
Downing, J. R. et al. The Pediatric Cancer Genome Project. Nature Genet. 44, 619–622 (2012).
UPDATED 4/24/2020 The genomic landscape of pediatric cancers: Curation of WES/WGS studies shows need for more data
The past decade has witnessed a major increase in our understanding of the genetic underpinnings of childhood cancer. Genomic sequencing studies have highlighted key differences between pediatric and adult cancers. Whereas many adult cancers are characterized by a high number of somatic mutations, pediatric cancers typically have few somatic mutations but a higher prevalence of germline alterations in cancer predisposition genes. Also noteworthy is the remarkable heterogeneity in the types of genetic alterations that likely drive the growth of pediatric cancers, including copy number alterations, gene fusions, enhancer hijacking events, and chromoplexy. Because most studies have genetically profiled pediatric cancers only at diagnosis, the mechanisms underlying tumor progression, therapy resistance, and metastasis remain poorly understood. We discuss evidence that points to a need for more integrative approaches aimed at identifying driver events in pediatric cancers at both diagnosis and relapse. We also provide an overview of key aspects of germline predisposition for cancer in this age group.
Approximately 300,000 children from infancy to age 14 are diagnosed with cancer worldwide every year (1). Some of the cancer types affecting the pediatric population are also seen in adolescents and young adults (AYA), but it has become increasingly clear that cancers in the latter age group have unique biological characteristics that can affect prognosis and therapy (2). Pediatric and AYA cancer patients present with a heterogeneous set of diseases that can be broadly subclassified as leukemias, brain tumors, and non–central nervous system (CNS) solid tumors. These subgroups contain numerous distinct clinical entities, many of which are still poorly characterized from a molecular standpoint.
Recent large-scale genomic analyses have increased our understanding of the genetic drivers of pediatric cancer and have helped to identify new clinically relevant subtypes. These studies have also underscored the distinct nature of the genetic alterations in pediatric and AYA cancers versus adult cancers. Of particular note, the number of somatic mutations in most pediatric cancers is substantially lower than that in adult cancers (3, 4). Exceptions are tumors in children who carry germline mutations that compromise repair of DNA damage (5). For many pediatric cancers, driver events are conditioned on the developmental stage in which the tumor arises. For example, a mutation occurring in one developmental compartment (e.g., a muscle stem cell) may lead to cancer, whereas the same mutation in another compartment does not (6). Pediatric cancer genomes are also characterized by specific patterns of copy number alterations and structural alterations [chromoplexy (7), chromothripsis (8)] that are prognostic indicators in several cancer subtypes. Gene fusion events have long been recognized as oncogenic drivers in many pediatric cancers; however, advanced sequencing technologies have revealed that the number of fusion partners is greater than previously thought, and that previously undetected gene rearrangements may also function as drivers. Finally, germline mutations in a wide spectrum of genes that predispose to cancer appear to play a greater role in pediatric cancer than previously appreciated (9, 10).
Somatic alterations in pediatric cancers
Genome landscape studies
Early large-scale sequencing studies of pediatric cancers identified novel driver genes while also underscoring the overall low mutational burden (11–14). Whole exome sequencing studies of Wilms tumor, T-cell acute lymphoblastic leukemia (TALL), and acute myeloid leukemia (CML) identified some recurring mutations such as
FLT3-IDT
WT1
NUP98-NST1 gene fusion
however many of the driver genes were subtype specific. Other fusion events were seen (by RNASeq) such as
EWS-FL1
Bcr-Abl
MYB-QK1
as well as multiple epigenetic events such as methylations.
REFERENCES
E. Steliarova-Foucher, M. Colombet, L. A. G. Ries, F. Moreno, A. Dolya, F. Bray, P. Hesseling, H. Y. Shin, C. A. Stiller, IICC-3 contributors, International incidence of childhood cancer, 2001-10: A population-based registry study. Lancet Oncol. 18, 719–731 (2017). 10.1016/S1470-2045(17)30186-9pmid:28410997
2. V. Tricoli, D. G. Blair, C. K. Anders, W. A. Bleyer, L. A. Boardman, J. Khan, S. Kummar, B. Hayes-Lattin, S. P. Hunger, M. Merchant, N. L. Seibel, M. Thurin, C. L. Willman, Biologic and clinical characteristics of adolescent and young adult cancers: Acute lymphoblastic leukemia, colorectal cancer, breast cancer, melanoma, and sarcoma. Cancer 122, 1017–1028 (2016). 10.1002/cncr.29871pmid:26849082
3. S. Lawrence, P. Stojanov, P. Polak, G. V. Kryukov, K. Cibulskis, A. Sivachenko, S. L. Carter, C. Stewart, C. H. Mermel, S. A. Roberts, A. Kiezun, P. S. Hammerman, A. McKenna, Y. Drier, L. Zou, A. H. Ramos, T. J. Pugh, N. Stransky, E. Helman, J. Kim, C. Sougnez, L. Ambrogio, E. Nickerson, E. Shefler, M. L. Cortés, D. Auclair, G. Saksena, D. Voet, M. Noble, D. DiCara, P. Lin, L. Lichtenstein, D. I. Heiman, T. Fennell, M. Imielinski, B. Hernandez, E. Hodis, S. Baca, A. M. Dulak, J. Lohr, D.-A. Landau, C. J. Wu, J. Melendez-Zajgla, A. Hidalgo-Miranda, A. Koren, S. A. McCarroll, J. Mora, B. Crompton, R. Onofrio, M. Parkin, W. Winckler, K. Ardlie, S. B. Gabriel, C. W. M. Roberts, J. A. Biegel, K. Stegmaier, A. J. Bass, L. A. Garraway, M. Meyerson, T. R. Golub, D. A. Gordenin, S. Sunyaev, E. S. Lander, G. Getz, G. Getz, Mutational heterogeneity in cancer and the search for new cancer-associated genes. Nature 499, 214–218 (2013). 10.1038/nature12213pmid:23770567
B. Vogelstein, N. Papadopoulos, V. E. Velculescu, S. Zhou, L. A. Diaz Jr.., K. W. Kinzler, Cancer genome landscapes. Science 339, 1546–1558 (2013). 10.1126/science.1235122pmid:23539594
5. B. Campbell, N. Light, D. Fabrizio, M. Zatzman, F. Fuligni, R. de Borja, S. Davidson, M. Edwards, J. A. Elvin, K. P. Hodel, W. J. Zahurancik, Z. Suo, T. Lipman, K. Wimmer, C. P. Kratz, D. C. Bowers, T. W. Laetsch, G. P. Dunn, T. M. Johanns, M. R. Grimmer, I. V. Smirnov, V. Larouche, D. Samuel, A. Bronsema, M. Osborn, D. Stearns, P. Raman, K. A. Cole, P. B. Storm, M. Yalon, E. Opocher, G. Mason, G. A. Thomas, M. Sabel, B. George, D. S. Ziegler, S. Lindhorst, V. M. Issai, S. Constantini, H. Toledano, R. Elhasid, R. Farah, R. Dvir, P. Dirks, A. Huang, M. A. Galati, J. Chung, V. Ramaswamy, M. S. Irwin, M. Aronson, C. Durno, M. D. Taylor, G. Rechavi, J. M. Maris, E. Bouffet, C. Hawkins, J. F. Costello, M. S. Meyn, Z. F. Pursell, D. Malkin, U. Tabori, A. Shlien, Comprehensive Analysis of Hypermutation in Human Cancer. Cell 171, 1042–1056.e10 (2017). 10.1016/j.cell.2017.09.048pmid:29056344
6. Chen, A. Pappo, M. A. Dyer, Pediatric solid tumor genomics and developmental pliancy. Oncogene 34, 5207–5215 (2015). 10.1038/onc.2014.474pmid:25639868
S. C. Baca, D. Prandi, M. S. Lawrence, J. M. Mosquera, A. Romanel, Y. Drier, K. Park, N. Kitabayashi, T. Y. MacDonald, M. Ghandi, E. Van Allen, G. V. Kryukov, A. Sboner, J.-P. Theurillat, T. D. Soong, E. Nickerson, D. Auclair, A. Tewari, H. Beltran, R. C. Onofrio, G. Boysen, C. Guiducci, C. E. Barbieri, K. Cibulskis, A. Sivachenko, S. L. Carter, G. Saksena, D. Voet, A. H. Ramos, W. Winckler, M. Cipicchio, K. Ardlie, P. W. Kantoff, M. F. Berger, S. B. Gabriel, T. R. Golub, M. Meyerson, E. S. Lander, O. Elemento, G. Getz, F. Demichelis, M. A. Rubin, L. A. Garraway, Punctuated evolution of prostate cancer genomes. Cell 153, 666–677 (2013). 10.1016/j.cell.2013.03.021pmid:23622249
P. J. Stephens, C. D. Greenman, B. Fu, F. Yang, G. R. Bignell, L. J. Mudie, E. D. Pleasance, K. W. Lau, D. Beare, L. A. Stebbings, S. McLaren, M.-L. Lin, D. J. McBride, I. Varela, S. Nik-Zainal, C. Leroy, M. Jia, A. Menzies, A. P. Butler, J. W. Teague, M. A. Quail, J. Burton, H. Swerdlow, N. P. Carter, L. A. Morsberger, C. Iacobuzio-Donahue, G. A. Follows, A. R. Green, A. M. Flanagan, M. R. Stratton, P. A. Futreal, P. J. Campbell, Massive genomic rearrangement acquired in a single catastrophic event during cancer development. Cell 144, 27–40 (2011). 10.1016/j.cell.2010.11.055pmid:21215367
D. W. Parsons, A. Roy, Y. Yang, T. Wang, S. Scollon, K. Bergstrom, R. A. Kerstein, S. Gutierrez, A. K. Petersen, A. Bavle, F. Y. Lin, D. H. López-Terrada, F. A. Monzon, M. J. Hicks, K. W. Eldin, N. M. Quintanilla, A. M. Adesina, C. A. Mohila, W. Whitehead, A. Jea, S. A. Vasudevan, J. G. Nuchtern, U. Ramamurthy, A. L. McGuire, S. G. Hilsenbeck, J. G. Reid, D. M. Muzny, D. A. Wheeler, S. L. Berg, M. M. Chintagumpala, C. M. Eng, R. A. Gibbs, S. E. Plon, Diagnostic Yield of Clinical Tumor and Germline Whole-Exome Sequencing for Children With Solid Tumors. JAMA Oncol. 2, 616 (2016). 10.1001/jamaoncol.2015.5699pmid:26822237
J. Zhang, M. F. Walsh, G. Wu, M. N. Edmonson, T. A. Gruber, J. Easton, D. Hedges, X. Ma, X. Zhou, D. A. Yergeau, M. R. Wilkinson, B. Vadodaria, X. Chen, R. B. McGee, S. Hines-Dowell, R. Nuccio, E. Quinn, S. A. Shurtleff, M. Rusch, A. Patel, J. B. Becksfort, S. Wang, M. S. Weaver, L. Ding, E. R. Mardis, R. K. Wilson, A. Gajjar, D. W. Ellison, A. S. Pappo, C.-H. Pui, K. E. Nichols, J. R. Downing, Germline Mutations in Predisposition Genes in Pediatric Cancer. N. Engl. J. Med. 373, 2336–2346 (2015). 10.1056/NEJMoa1508054pmid:26580448
T. J. Pugh, O. Morozova, E. F. Attiyeh, S. Asgharzadeh, J. S. Wei, D. Auclair, S. L. Carter, K. Cibulskis, M. Hanna, A. Kiezun, J. Kim, M. S. Lawrence, L. Lichenstein, A. McKenna, C. S. Pedamallu, A. H. Ramos, E. Shefler, A. Sivachenko, C. Sougnez, C. Stewart, A. Ally, I. Birol, R. Chiu, R. D. Corbett, M. Hirst, S. D. Jackman, B. Kamoh, A. H. Khodabakshi, M. Krzywinski, A. Lo, R. A. Moore, K. L. Mungall, J. Qian, A. Tam, N. Thiessen, Y. Zhao, K. A. Cole, M. Diamond, S. J. Diskin, Y. P. Mosse, A. C. Wood, L. Ji, R. Sposto, T. Badgett, W. B. London, Y. Moyer, J. M. Gastier-Foster, M. A. Smith, J. M. Guidry Auvil, D. S. Gerhard, M. D. Hogarty, S. J. M. Jones, E. S. Lander, S. B. Gabriel, G. Getz, R. C. Seeger, J. Khan, M. A. Marra, M. Meyerson, J. M. Maris, The genetic landscape of high-risk neuroblastoma. Nat. Genet. 45, 279–284 (2013). 10.1038/ng.2529pmid:23334666
J. R. Downing, R. K. Wilson, J. Zhang, E. R. Mardis, C.-H. Pui, L. Ding, T. J. Ley, W. E. Evans, The Pediatric Cancer Genome Project. Nat. Genet. 44, 619–622 (2012). 10.1038/ng.2287pmid:22641210
St. Jude Children’s Research Hospital–Washington University Pediatric Cancer Genome Project, Somatic histone H3 alterations in pediatric diffuse intrinsic pontine gliomas and non-brainstem glioblastomas. Nat. Genet. 44, 251–253 (2012). 10.1038/ng.1102pmid:22286216
J. Zhang, L. Ding, L. Holmfeldt, G. Wu, S. L. Heatley, D. Payne-Turner, J. Easton, X. Chen, J. Wang, M. Rusch, C. Lu, S.-C. Chen, L. Wei, J. R. Collins-Underwood, J. Ma, K. G. Roberts, S. B. Pounds, A. Ulyanov, J. Becksfort, P. Gupta, R. Huether, R. W. Kriwacki, M. Parker, D. J. McGoldrick, D. Zhao, D. Alford, S. Espy, K. C. Bobba, G. Song, D. Pei, C. Cheng, S. Roberts, M. I. Barbato, D. Campana, E. Coustan-Smith, S. A. Shurtleff, S. C. Raimondi, M. Kleppe, J. Cools, K. A. Shimano, M. L. Hermiston, S. Doulatov, K. Eppert, E. Laurenti, F. Notta, J. E. Dick, G. Basso, S. P. Hunger, M. L. Loh, M. Devidas, B. Wood, S. Winter, K. P. Dunsmore, R. S. Fulton, L. L. Fulton, X. Hong, C. C. Harris, D. J. Dooling, K. Ochoa, K. J. Johnson, J. C. Obenauer, W. E. Evans, C.-H. Pui, C. W. Naeve, T. J. Ley, E. R. Mardis, R. K. Wilson, J. R. Downing, C. G. Mullighan, The genetic basis of early T-cell precursor acute lymphoblastic leukaemia. Nature 481, 157–163 (2012). 10.1038/nature10725pmid:22237106
CRACKING THE CODE OF HUMAN LIFE: Recent Advances in Genomic Analysis and Disease – Part IIC
Author: Larry H. Bernstein, MD, FCAP, Triplex Medical Science
Article 1.4 CRACKING THE CODE OF HUMAN LIFE: Recent Advances in Genomics Analysis and Disease – Part IIC
Part I: The Initiation and Growth of Molecular Biology and Genomics – Part I From Molecular Biology to Translational Medicine: How Far Have We Come, and Where Does It Lead Us?
Part IIB. “CRACKING THE CODE OF HUMAN LIFE: The Birth of BioInformatics & Computational Genomics” lays the manifold multivariate systems analytical tools that has moved the science forward to a groung that ensures clinical application.
Part IIC. “CRACKING THE CODE OF HUMAN LIFE: Recent Advances in Genomic Analysis and Disease “ will extend the discussion to advances in the management of patients as well as providing a roadmap for pharmaceutical drug targeting.
This final paper of Part II concludes a thorough review of the scientific events leading to the discovery of the human genome, the purification and identification of the components of the chromosome and the DNA structure and role in regulation of embryogenesis, and potential targets for cancer.
The first two articles, Part IIA, Part IIB, go into some depth to elucidate the problems and breakthoughs encountered in the Human Genome Project, and the construction of a 3-D model necessary to explain interactions at a distance.
Part IIC, the final article, is entirely concerned with clinical application of this treasure trove of knowledge to resolving diseases of epigenetic nature in the young and the old, chronic inflammatory diseases, autoimmune diseases, infectious disease, gastrointestinal disorders, neurological and neurodegenerative diseases, and cancer.
Recently, large studies have identified some of the genetic basis for important common diseases such as heart disease and diabetes, but most of the genetic contribution to them remains undiscovered. Now researchers at the University of Massachusetts Amherst led by biostatistician Andrea Foulkes have applied sophisticated statistical tools to existing large databases to reveal substantial new information about genes that cause such conditions as high cholesterol linked to heart disease.
Foulkes says, “This new approach to data analysis provides opportunities for developing new treatments.” It also advances approaches
to identifying people at greatest risk for heart disease. Another important point is that our method is straightforward to use with freely
available computer software and can be applied broadly to advance genetic knowledge of many diseases.
The new analytical approach she developed with cardiologist Dr. Muredach Reilly at the University of Pennsylvania and others is called “Mixed modeling of Meta-Analysis P-values” or MixMAP. Because it makes use of existing public databases, the powerful new method
represents a low-cost tool for investigators.
MixMAP draws on a principled statistical modeling framework and the vast array of summary data now available from genetic association
studies to formally test at a new, locus-level, association.
While that traditional statistical method looks for one unusual “needle in a haystack” as a possible disease signal, Foulkes and colleagues’
new method uses knowledge of DNA regions in the genome that are likely to
contain several genetic signals for disease variation clumped together in one region.
Thus, it is able to detect groups of unusual variants rather than just single SNPs, offering a way to “call out” gene
regions that have a consistent signal above normal variation.
The LPA gene codes for apolipoprotein(a), which, when linked with low-density lipoprotein particles, forms lipoprotein(a) [Lp(a)] —
a well-studied molecule associated with coronary artery disease (CAD). The Lp(a) molecule has both atherogenic and thrombogenic effects in vitro , but the extent to which these translate to differences in how atherothrombotic disease presents is unknown.
LPA contains many single-nucleotide polymorphisms, and 2 have been identified by previous groups as being strongly associated with
levels of Lp(a) and, as a consequence, strongly associated with CAD.
However, because atherosclerosis is thought to be a systemic disease, it is unclear to what extent Lp(a) leads to atherosclerosis in other arterial beds (eg, carotid, abdominal aorta, and lower extremity),
as well as to other thrombotic disorders (eg, ischemic/cardioembolic stroke and venous thromboembolism).
Such distinctions are important, because therapies that might lower Lp(a) could potentially reduce forms of atherosclerosis beyond the coronary tree.
To answer this question, Helgadottir and colleagues compiled clinical and genetic data on the LPA gene from thousands of previous
participants in genetic research studies from across the world. They did not have access to Lp(a) levels, but by knowing the genotypes for
2 LPA variants, they inferred the levels of Lp(a) on the basis of prior associations between these variants and Lp(a) levels. [1]
Their studies included not only individuals of white European descent but also a significant proportion of black persons, in order to
widen the generalizability of their results.
Their main findings are that LPA variants (and, by proxy, Lp(a) levels) are associated with
CAD,
peripheral arterial disease,
abdominal aortic aneurysm,
number of CAD vessels,
age at onset of CAD diagnosis, and
large-artery atherosclerosis-type stroke.
They did not find an association with
cardioembolic or small-vessel disease-type stroke;
intracranial aneurysm;
venous thrombosis;
carotid intima thickness; or,
in a small subset of individuals, myocardial infarction.
English: Structure of the LPA protein. Based on PyMOL rendering of PDB 1i71. (Photo credit: Wikipedia)
Micrograph of an artery that supplies the heart with significant atherosclerosis and marked luminal narrowing. Tissue has been stained using Masson’s trichrome. (Photo credit: Wikipedia)
Scientists at the Gladstone Institutes have revealed the precise order and timing of hundreds of genetic “switches” required to construct a fully
functional heart from embryonic heart cells — providing new clues into the genetic basis for some forms of congenital heart disease.
In a study being published online today in the journal Cell, researchers in the laboratory of Gladstone Senior Investigator Benoit Bruneau, PhD,
employed stem cell technology, next-generation DNA sequencing and computing tools to piece together the instruction manual, or “genomic
blueprint” for how a heart becomes a heart. These findings offer renewed hope for combating life-threatening heart defects such as arrhythmias (irregular heart beat) and ventricular septal defects (“holes in the heart”).
They approach heart formation with a wide-angle lens by
looking at the entirety of the genetic material that gives heart cells their unique identity.
The news comes at a time of emerging importance for the biological process called “epigenetics,” in which a non-genetic factor impacts a cell’s genetic
makeup early during development — but sometimes with longer-term consequences. All of the cells in an organism contain the same DNA, but the
epigenetic instructions encoded in specific DNA sequences give the cell its identity. Epigenetics is of particular interest in heart formation, as the
incorrect on-and-off switching of genes during fetal development can lead to congenital heart disease — some forms of which may not be apparent until adulthood.
the scientists took embryonic stem cells from mice and reprogrammed them into beating heart cells by mimicking embryonic development in a petri dish. Next, they extracted the DNA from developing and mature heart cells, using an advanced gene-sequencing technique called ChIP-seq that lets scientists “see” the epigenetic signatures written in the DNA.
Map of Heart Disease Death Rates in US White Males from 2000-2004 (Photo credit: Wikipedia)
Estimated propability of death or non-fatal myocardial-infarction over one year corresponding ti selectet values of the individual scores. Ordinate: individual score, abscissa: Propability of death or non-fatal myocardial infarction in 1 year (in %) (Photo credit: Wikipedia)
simply finding these signatures was only half the battle — we next had to decipher which aspects of heart formation they encoded
To do that, we harnessed the computing power of the Gladstone Bioinformatics Core. This allowed us to take the mountains of data collected from
gene sequencing and organize it into a readable, meaningful blueprint for how a heart becomes a heart.”
For each of the above datasets, an upstream analysis from the identified transcription factors correctly identified the stimulus. IPA’s tools were very
easy to use and the
analysis time for the above experiments was less than one minute.
The performance, speed, and ease of use can only be characterized as very good, perhaps leading to breakthroughs when extended and used creatively. Ingenuity’s new transcription factor analysis tool in IPA, coupled with Ingenuity’s established upstream grow tools, should be strongly considered for every lab analyzing differential expression data.
NF-E2-related factor 2 (Nrf2) is an important transcription factor that
activates the expression of cellular detoxifying enzymes.
Nrf2 expression is largely regulated through the association of Nrf2 with Kelch-like ECH-associated protein 1 (Keap1), which
results in cytoplasmic Nrf2 degradation.
Conversely, little is known concerning the regulation of Keap1 expression. Until now, a regulatory role for microRNAs (miRs) in controlling Keap1 gene expression had not been characterized. By using miR array-
based screening, we observed miR-200a silencing in breast cancer cells and
demonstrated that upon re-expression, miR-200a
targets the Keap1 3′-untranslated region (3′-UTR), leading to Keap1 mRNA degradation. Loss of this regulatory mechanism may
contribute to the dysregulation of Nrf2 activity in breast cancer. Previously, we have identified epigenetic repression of miR-200a
in breast cancer cells. Here, we find that treatment with epigenetic therapy, the histone deacetylase inhibitor suberoylanilide hydroxamic acid, restored miR-200a expression and reduced Keap1 levels. This reduction in Keap1 levels corresponded with
Nrf2 nuclear translocation
and activation of Nrf2-dependent NAD(P)H-quinone oxidoreductase 1 (NQO1) gene transcription.
Moreover, we found that Nrf2 activation inhibited the anchorage-independent growth of breast cancer cells. Finally, our in vitro observations were confirmed in a model of carcinogen-induced mammary hyperplasia in vivo. In conclusion, our study demonstrates
that miR-200a regulates the Keap1/Nrf2 pathway in mammary epithelium, and we find that epigenetic therapy can restore miR-200a
regulation of Keap1 expression,
reactivating the Nrf2-dependent antioxidant pathway in breast cancer.
Nuclear factor-like 2 (erythroid-derived 2, also known as NFE2L2 or Nrf2, is a transcription factor that in humans is encoded by the NFE2L2 gene.[1]) NFE2L2 induces the expression of various genes including those that encode for several antioxidant enzymes, and it may play a physiological role in the regulation of oxidative stress. Investigational drugs that target NFE2L2 are of interest as potential therapeutic interventions for
oxidative-stress related pathologies.
4. Highly active zinc finger nucleases by extended modular assembly
Zinc finger nucleases (ZFNs) are important tools for genome engineering. Despite intense interest by many academic groups,
the lack of robust non-commercial methods has hindered their widespread use. The modular assembly (MA) of ZFNs from
publicly-available one-finger archives provides a rapid method to create proteins that can recognize a very broad spectrum of DNA sequences.
However, three- and four-finger arrays often fail to produce active nucleases. Efforts to improve the specificity of the one-finger archives have not increased the success rate above 25%, suggesting that the MA method might
be inherently inefficient due to its insensitivity to context-dependent effects.
Here we present the first systematic study on the effect of array length on ZFN activity. ZFNs composed of six-finger MA arrays produced mutations at 15 of 21 (71%) targeted
loci in human and mouse cells. A novel Drop-Out Linker scheme was used to rapidly assess three- to six-finger combinations,
demonstrating that shorter arrays could improve activity in some cases. Analysis of 268 array variants revealed that half of
MA ZFNs of any array composition that exceed an ab initio
B-score cut-off of 15 were active.
MA ZFNs are able to target more DNA sequences with higher success rates than other methods.
These insightful reviews are based on the strategic data and insights from Thomson Reuters Cortellis™ for Competitive Intelligence. (A Review of April-June 2012).
The majority of diseases are complex and multi-factorial, involving multiple genes interacting with environmental factors. At the genetic level,
information from genome-wide association studies that elucidate common patterns of genetic variation across various human populations,
in addition to profiling, technologies can be utilized in discovery research to provide snapshots of genes and expression profiles that are controlled
by the same regulatory mechanism and are altered between healthy and diseased states.
The characterization of genes that are abnormally expressed in disease tissues could further be employed as
diagnostic markers,
prognostic indicators of efficacy and/or toxicity, or as
targets for therapeutic intervention.
As the defining catalyst that exponentially paved the way for personalized medicine, information from the published genome sequence revealed that much of the genetic variations in humans are concentrated in about 0.1 percent of the over 3 billion base pairs in the haploid DNA. Most of these variations involve substitution of a single nucleotide for another at a given location in the genetic sequence, known as single nucleotide polymorphism (SNP).
Combinations of linked SNPs aggregate together to form haplotypes and
together these serve as markers for locating genetic variations in DNA sequences.
SNPs located within the protein-coding region of a gene or within the control regions of DNA that regulate a gene’s activity could
have a substantial effect on the encoded protein and thus influence phenotypic outcomes.
Analyzing SNPs between patient population cohorts could highlight specific genotypic variations which can be correlated with specific phenotypic variations in disease predisposition and drug responses.
Prior to the genomic revolution, many of the established therapies were directed against less than 500 drug targets, with many of the top selling drugs acting on well defined protein pathways. However, the sequencing of the human genome has massively expanded the pool of molecular targets that could be exploited in unmet medical needs and currently, of the approximately 22,300 protein-coding genes in the human code, it has been estimated that up to 3000 are druggable. Furthermore, genomic technologies such as
high-throughput sequencing
and transcription profiling,
can be used to identify and validate biologically relevant target molecules, or can be applied to cell-based and mice disease models or directly to in vivo human tissues,
helping to correlate gene targets with phenotypic traits of complex diseases.
This is particularly important, as
insufficient validation of target gene/proteins in complex diseases may be a contributing factor in the decline in R&D productivity.
Personalized medicine no doubt is already having a tremendous impact on drug development pipelines. According to a study conducted by the Tufts Center for the Study of Drug Development, more than 90 percent of biopharmaceutical companies now utilize at least some
genomics-derived targets in their drug discovery programs.
However, pipeline analysis from Cortellis for Competitive Intelligence suggests that there is still a scientific gap that has resulted in difficulty optimizing these novel genomic targets into the clinical R&D portfolios of major pharmaceutical companies, particularly outside the oncology field. Selected examples of personalized medicine product candidates in clinical development include (see TABLE 4).
Mutations in Melanomaare in regions that control genes, not in the genes themselves. The mutations are exactly the type caused by exposure to ultraviolet light. The findings are reported in two papers in http://Science.com/ScienceExpress/
The findings do not suggest new treatments, but they help explain how melanomas – and possibly – other cancers – develop and what drives their growth. This is a modification found in the “dark matter”, according to Dr. Levi A. Garraway, the 99 percent of DNA in a region that regulates genes. A small control region was mutated in 7 out of 10 of the tumors, commonly of one or two tiny changes. A German Team led by Rajiv Kumar (Heidelberg) and Dirk Schadendorf (Essen) looked at a family whose members tended to get melanomas. Their findings indicate that those inherited with the mutations might be born with cells that have taken the first step toward cancer.
The mutations spur cells to make telomerase, that keeps the cells immortal by preventing them from losing the ends of their chromosome, the telomere. Abundant telomerase occurs in 90 percent of cancers, according to Immaculata De Vivo at Harvard Medical School.
The importance of the findings is that the mechanism of telomerase involvement in cancer is now within view. But it is not clear how to block the telomerase production in cancer cells.
A slight mutation in the matched nucleotides can lead to chromosomal aberrations and unintentional genetic rearrangement. (Photo credit: Wikipedia)
Comment
This discussion addresses the issues raised about the direction to follow in personalized medicine. Despite the amount of work necessary to bring the clarity that is sought after, the experiments and experimental design is most essential.
The arrest of ciliogenesis in ovarian cancer cell lines compared to wild type (WT) ovarian epithelial cells, and
The link to suppressing ciliogenesis by AURA protein and CHFR at the base of the cilium, which disappears at mitosis or with proliferation.
There is no accumulation by upregulation of PDGF under starvation by the cancer cells compared to the effect in WT OSE.
Here we have a systematic combination of signaling events tied to changes in putative biomarkers that occur synchronously in Ov cancer cell lines.
These changes are identified with changes in
proliferation,
loss of ciliary structure, and
proliferation.
In this described scenario,
WT OSE cells would be arrested, and
it appears that they would take the path to apoptosis (under starvation).
Even without more information, this cluster is what one wants to have in a “syndromic classification”. The information used to form the classification entails the identification of strong‘signaling-related’ biomarkers. The Gli2 peptide has to be part of this.
In principle, a syndromic classification would be ideally expected to have no less than 64 classes. If the classification is “weak”, then the class frequencies would be close to what one would expect in the WT OSE. In this case, in reality,
several combinatorial classes would have low frequency, and
others would be quite high.
This obeys the classification rules established by feature identification, and the information gain described by Solomon Kullback and extended by Akaike.
Does this have to be the case for all different cancer types? I don’t think so. The cells are different in ontogenesis. In this case, even the WT OSE have mesenchymal features and so, are not fully directed to epithelial expression. This happens to be the case in actual anatomic expression of the ovary. On the other hand, one would expect shared features of the
ovary,
testes,
thyroid,
adrenals, and
pituitary.
There is biochemical expression in terms of their synthetic function – TPN organs. I would have to put the liver into that broad class. Other organs – skeletal muscle & heart – transform substrate into energy or work. (Where you might also put intestinal smooth muscle).
They have to have different biomarker expressions, even though they much less often don’t form neoplasms. (Bone is not just a bioenergetic force. It is maintained by muscle action. It forms sarcomas. But there has to be a balance between bone removal by osteoclasts and refill by osteoblasts.)
Viewpoint: What we have learned
The Watson-Crick model proposed in 1953 is limited for explaining fully genome effects
The Pauling triplex model may have been prescient because of a more full anticipation of molecular bonding variants
A more adequate triple-helix model has been proposed and is consistent with a compact genome in the nucleus
The structure of the genome is not as we assumed – based on the application of Fractal Geometry. Current body of evidence is building that can reveal a more complete view of genome function.
transcription
cell regulation
mutations
Summary
I have just completed a most comprehensive review of the Human Genome Project. There are key research collaborations, problems in deciphering the underlying structure of the genome, and there are also both obstacles and insights to elucidating the complexity of the final model.
This is because of frequent observations of molecular problems in folding and other interactions between nucleotides that challenge the sufficiency of the original DNA model proposed by Watson and Crick. This has come about because of breakthrough innovation in technology and in computational methods.
Radoslav Bozov •
Molecular biology and growth was primarily initiated on biochemical structural paradigms aiming to define functional spatial dynamics of molecules via assignation of various types of bondings – covalent and non-covalent – hydrogen, ionic , dipole-dipole, hydrophobic interactions.
Lab techniques based on z/m paradigm allowed separation, isolation and identification of bio substances with a general marker identity finding correlation between physiological/cellular states.
The development of electronic/x-ray technologies allowed zooming in nano space without capturing time.
NMR technology identified the existence of space topology of initial and final atomic states giving a highly limited light on time – energy axis of atomic interactions.
Sequence technology and genomic perturbations shed light on uncertainty of genomic dynamics and regulators of functional ever expanding networks.
Transition state theory coupled to structural complexity identification and enzymatic mechanisms ran up parallel to work on various phenomena of strings of nucleotides (oligomers and polymers) – illusion/observation of constructing models on the dynamics of protein-dna-rna interference.
The physical energetic constrains of biochemistry were inapplicable in open biological systems. Biologists have accepted observation as a sole driver towards re-evaluating models.
The separation of matter and time constrains emerged as deviation of energy and space constrains transforming into the full acceptance of code theory of life. One simple thing was left unnoticed over time –
the amount of information of quantum matter within a single codon is larger than that of a single amino acid. This violated all physical laws/principles known to work with a limited degree of certainty.
The limited amount of information analyzed by conventional sequence identity led to the notion of applicability of statistical measures of and PCR technology. Mutations were identified over larger scale of data.
Quantum chemistry itself is being limited due discrete space/energy constrains, thus it transformed into concepts/principles in biology that possess highly limited physical values whatsoever.
The central dogma is partially broken as a result of
regulatory constrains
epigenetic phenomena and
iRNA.
Large scale code computational data run into uncertainty of the processes of evolution and its consequence of signaling transformation. All drugs were ‘lucky based’ applicability and/or discovery with largely unpredictable side effect over time.
Other Related articles on this Open Access Online Sceintific Journal include the following:
Rewriting the Mathematics of Tumor Growth[1]; Teams Use Math Models to Sort Drivers from Passengers[2]: Two JNCI Reviews by Mike Martin Regarding Genomics, Cancer, and Mutation
Curator: Stephen J. Williams, Ph.D.
WordCloud Image Produced by Adam Tubman
Word Cloud By Danielle Smolyar
Recently, there has been extensive interest in the cancer research and oncology community on detecting those mutations responsible for the initiation and propagation of a neoplastic cell (driver mutations) versus those mutations that are randomly (or by selective pressures) acquired due to the genetic instability of the transformed cell. The impact of either type of mutation has been a topic for debate, with a recent article showing that some passenger mutations may actually be responsible for tumor survival. In addition many articles, highlighted on this site (and referenced below) in recent years have described the importance of classifying driver and passenger mutations for the purposes of more effective personalized medicine strategies directed against tumors. Two review articles by Mike Martin in the Journal of the National Cancer Institute (JCNI) shed light on the current efforts and successes to discriminate between these passenger and driver mutations and determine impact of each type of mutation to tumor growth. However, as described in the associated article, the picture is not as clear cut as previously thought and highlights some revolutionary findings. In Rewriting the Mathematics of Tumor Growth, researchers discovered that driver mutations may confer such a small growth advantage that, multiple mutations, including the so called passenger mutations are necessary in order to sustain tumor growth. In fact, much experimental evidence has suggested at least six defined genetic events may be necessary for the in-vitro transformation of human cells. The following table shows some of the genetic events required for in-vitro transformation in cell culture systems.
3 for anchorage independence (cyclin D1, dnp53, EGFR),Cyclin D1+dnp53 for immortalization
HOSE
6
CDK4, cyclin D, hTERT plus combination of either P53DD, myrAkt, and H-ras or P53DD, H-ras, c-myc Bcl2
(f)Sasaki(Kiyono)
5
HOSE
3
hTERTSV40 earlyH-ras orK-ras
(g)Liu(Bast)
2hTERT+ SV40 early
HOSE
3
Large ThTERTH-ras orc-erB-2
(h)Kusakari(Fujii)
2hTERT+large T
Rat
Fibroblasts
2
Large TH-ras
(i)Hirakawa
Did not analyze
Fibroblasts
2
Large TH-ras
(d)Rangarajan(Weinberg)
Large T
Mouse
MOSEIn p53-/- background
3
c-mycK-rasAkt
(j)Orsulic
Pig
Fibroblasts
6
p53DDhTERTCDK4H-ras c-myccyclin D1
(k)Adam(Counter)
5 need all butp53DD
Note: priming means events required to immortalize but not fully transform. * Note that both ability to form colonies in soft agarose and subsequently tested for tumor formation in immunocompromised mice.
a. Hahn, W. C., Counter, C. M., Lundberg, A. S., Beijersbergen, R. L., Brooks, M. W., and Weinberg, R. A. (1999) Creation of human tumour cells with defined genetic elements, Nature400, 464-468.
b. Kendall, S. D., Linardic, C. M., Adam, S. J., and Counter, C. M. (2005) A network of genetic events sufficient to convert normal human cells to a tumorigenic state, Cancer Res65, 9824-9828.
c. Sun, B., Chen, M., Hawks, C. L., Pereira-Smith, O. M., and Hornsby, P. J. (2005) The minimal set of genetic alterations required for conversion of primary human fibroblasts to cancer cells in the subrenal capsule assay, Neoplasia7, 585-593.
d. Rangarajan, A., Hong, S. J., Gifford, A., and Weinberg, R. A. (2004) Species- and cell type-specific requirements for cellular transformation, Cancer Cell6, 171-183.
e. Goessel, G., Quante, M., Hahn, W. C., Harada, H., Heeg, S., Suliman, Y., Doebele, M., von Werder, A., Fulda, C., Nakagawa, H., Rustgi, A. K., Blum, H. E., and Opitz, O. G. (2005) Creating oral squamous cancer cells: a cellular model of oral-esophageal carcinogenesis, Proc Natl Acad Sci U S A102, 15599-15604.
f. Sasaki, R., Narisawa-Saito, M., Yugawa, T., Fujita, M., Tashiro, H., Katabuchi, H., and Kiyono, T. (2009) Oncogenic transformation of human ovarian surface epithelial cells with defined cellular oncogenes,Carcinogenesis30, 423-431.
g. Liu, J., Yang, G., Thompson-Lanza, J. A., Glassman, A., Hayes, K., Patterson, A., Marquez, R. T., Auersperg, N., Yu, Y., Hahn, W. C., Mills, G. B., and Bast, R. C., Jr. (2004) A genetically defined model for human ovarian cancer, Cancer Res64, 1655-1663.
h. Kusakari, T., Kariya, M., Mandai, M., Tsuruta, Y., Hamid, A. A., Fukuhara, K., Nanbu, K., Takakura, K., and Fujii, S. (2003) C-erbB-2 or mutant Ha-ras induced malignant transformation of immortalized human ovarian surface epithelial cells in vitro, Br J Cancer89, 2293-2298.
i. Hirakawa, T., and Ruley, H. E. (1988) Rescue of cells from ras oncogene-induced growth arrest by a second, complementing, oncogene, Proc Natl Acad Sci U S A85, 1519-1523.
j. Orsulic, S., Li, Y., Soslow, R. A., Vitale-Cross, L. A., Gutkind, J. S., and Varmus, H. E. (2002) Induction of ovarian cancer by defined multiple genetic changes in a mouse model system, Cancer Cell1, 53-62.
k. Adam, S. J., Rund, L. A., Kuzmuk, K. N., Zachary, J. F., Schook, L. B., and Counter, C. M. (2007) Genetic induction of tumorigenesis in swine, Oncogene26, 1038-1045.
However it may be argued that the aforementioned experimental examples were produced in cell lines with a more stable genome than that which is seen in most tumors and had used traditional assays of transformation, such as growth in soft agarose and tumorigenicity in immunocompromised mice, as endpoints of transformation, and not representative of the tumor growth seen in the clinical setting.
Therefore Bert Vogelstein, M.D., along with collaborators around the world developed a model they termed the “sequential driver mutation theory”, in which they describe that driver mutations multiply over time with each mutation “slightly increasing the tumor growth rate through a process that depends on three factors”:
Driver mutation rate
The 0.4% selective growth advantage
Cell division time
This model was based on a combination of experimental data and computer simulations of gliobastoma multiforme and pancreatic adenocarcinoma. Most tumor models follow a Gompertz kinetics, which show how tumor growth is exponential but eventually levels off over time.
This new theory shows though that a tumor cell with only one driver mutation can only grow so much, until a second driver mutation is required. Using data for the COSMIC database (Catalog of Somatic Mutations in Cancer) together with analysis software CHASM (Cancer-specific High-throughput Annotation of Somatic Mutations) the researchers analyzed 713 mutations sequenced from 14 glioma patients and 562 mutations in nine pancreatic adenocarcinomas, revealing at least 100 tumor suppressor genes and 100 oncogenes altered. Therefore, the authors suggested these may be possible driver mutations, or at least mutations required for the sustained growth of these tumors. Applying this new model to data obtained from Dr. Giardiello’s publication concerning familial adenopolypsis in New England Journal of medicine in 19993 and 2000, the sequential driver mutation model predicted age distribution of FAP patients, number and size of polyps, and polyp growth rate than previous models. This surprising number of required driver mutations for full transformation was also verified in a study led by University of Texas Southwestern Medical Center biologist Jerry Shay, Ph.D., who noted “this team’s surprise nearly 45% of all colorectal candidate oncogenes (65 mutations) drove malignant proliferation”[3].
However, some investigators do not believe the model is complex enough to account for other factors involved in oncogenesis, such as epigenetic factors like methylation and acetylation. In addition the review also discusses host and tissue factors which may complicate the models, such as location where a tumor develops. However, most of the investigators interviewed for this review agreed that focusing on this long-term progression of the disease may give us clues to other potential druggable targets.
Teams Use Math Models to Sort Drivers From Passengers
A related review from Mike Martin in JNCI [2] describes a statistical method, published in 2009 Cancer Informatics[4], which distinguishes chromosomal abnormalities that can drive oncogenesis from passenger abnormalities. Chromosomal abnormalities, such as deletions, additions, and translocations are common in cancer. For instance, the well-known Philadelphia chromosome, a translocation between chromosome 9 and 22 which results in the BCR-ABL tyrosine kinase fusion protein is the molecular basis of chronic myelogenous leukemia.
In the report, Eytan Domany, Ph.D., from Weizmann Institute and several colleagues from University of Lausanne, University of Haifa and the Broad Institute were analyzing chromosomal aberrations in a subset of medulloblastoma, which had more gain and losses in chromosomes than had been attributed to the disease. Using a statistical method they termed a “volumetric sieve”, the investigators were able to identify driver versus passenger aberrations based on three filters:
Fraction of patients with the abnormality
Length of DNA involved in the aberrant chromosome
Abnormality’s copy number
Another method to sort the most “important” chromosomal aberrations from less relevant alterations is termed GISTIC[5], as the website describes is: a tool to identify genes targeted by somatic copy-number alterations (SCNAs) that drive cancer growth (at the Broad Institute website http://www.broadinstitute.org/software/cprg/?q=node/31). The method allows for comparison across multiple tumors so noise is eliminated and improves consistency of analysis. This method had been successfully used to determine driver aberrations is mesotheliomas, leukemias, and identify new oncogenes in adenocarcinomas of the lung and squamous cell carcinoma of the esophagus.
Main references for the two Mike Martin articles are as follows:
3. Eskiocak U, Kim SB, Ly P, Roig AI, Biglione S, Komurov K, Cornelius C, Wright WE, White MA, Shay JW: Functional parsing of driver mutations in the colorectal cancer genome reveals numerous suppressors of anchorage-independent growth. Cancer research 2011, 71(13):4359-4365.
4. Shay T, Lambiv WL, Reiner-Benaim A, Hegi ME, Domany E: Combining chromosomal arm status and significantly aberrant genomic locations reveals new cancer subtypes. Cancer informatics 2009, 7:91-104.
This discussion will identify the huge expansion of genomic technology in the search for biopharmacotherapeutic targets that continue to be explored involving different levels and interacting signaling pathways. There are several methods of analyzing gene expression that will be discussed. Great primary emphasis required investigation of combinations of mutations expressed in different cancer types. James Watson has proposed a major hypothesis that expresses the need to focus on “central” “driver mutations” that correspond with the regulation of gene expression, cell proliferation, and cell metabolism eith a critical rejection of antioxiant benefits. What hasn’t been know is why drug resistance develops and whether the cellular migration and aerobic glycolysis can be redirected after cell metastasis occurs. I attempt to bring out the complexities of current efforts.
.Introduction
This discussion is a continuation of a previous discussion on the role of genomics if discovery of therapeutic targets for cancer, each somewhat different, but all related to:
The reversal of carcinoma by targeting a key driver of multiple signaling pathways that activate cell proliferation
Pinpointing a stage in a multistage process at which tumor progression links to changes in morphology from basal cells to invasive carcinoma with changes in polarity and loss of glandular architecture
Reversal of the carcinoma through using a small molecule that either is covalently bound to a nanoparticle delivery system that blocks or reverses tumor development
Synthesis of a small molecule that interacts with the translation of the genome either by substitution of a key driver molecule or by blocking at the mRNAstage of translation
Blocking more than one signaling pathway that are links to carcinogenesis and cellular proliferation and invasion
Difficulty of the problem
A problem expressed by James Watson is that the investigations that are ongoing
are following a pathway that is not driven by attacking the “primary” driver of carcinogenesis.
He uses the Myc gene as an example, as noted in the previous discussion. The problem may be more complicated than he envisions.
The most consistent problem in chemotherapy, irrespective of the design and the target has been cancer remission for a short time followed by recurrence, and then
switching to another drug, or combination chemotherapy.
It is common to “clean” the field at the time of resection using radiotherapy before chemotherapy.
But the goal is understood to be “palliation”, not cure.
This raises a serious issue in the hypothesis posed by Watson. The issue is
whether there is a core locus of genetic regulation that is common to carcinogenesis irrespective of tissue metabolic expression.
This is supported by the observation that tissue specific express is lost in cancer cells by de-differentiation.
In 1967Otto Warburgpublished his view in a paper “The prime cause and prevention of cancer”.
There are primary and secondary causes of all diseases
plague – primary: plague bacillus
plague – secondary: filth, rats, and fleas
cancer, above all diseases,
has countless seconday causes
primary – replacement of respiration of oxygen in normal body tissue by fermentation of glucose with conversion from obligate aerobic to anaerobic, as in bacterial cells
The cornerstone to understanding cancer is in study of the energetics of life
This thinking came out of decades of work in the Dahlem Institute Kaiser Wilhelm pre WWII and Max Planck Institute after WWII, supported by the Rockefeller Foundation.
The oxygen- and hydrogen-transferring enzymes were discovered and isolated.
The methods were elegant for that time, using a manometer that improved on the method used by Haldane, that did not allow the leakage of O2 or CO2.
The interest was initiated by the increased growth of Sea Urchin eggs after fertization, which turned out to be not comparable to the rapid growth of cancer cells.
Warburg used both normal and cancer tissue and measured the utilization of O2. He found
that the normal tissue did not accumulate lactic acid.
Cancer tissue generated lactic acid
the rate of O2 consumption the same as normal tissue, but
the rate of lactate formation far exceeded any tissue, except the retina.
Hematopoietic cells of bone marrow develop aerobic glycolysis when exposed to a low oxygen condition.
He then followed on an observation by Otto Meyerhoff (Embden-Myerhoff cycle) that in muscle
the consumption of one molecule of oxygen generates two molecules of lactate, but in aerobic glycolysis, the relationship disappears.
He expressed the effectiveness of respiration by the ‘Meyerhoff quotient’.
He found that cancer cells didn’t have a quotient of ‘2’
The role of the allosteric enzyme phosphofructokinase (PFK) not then known, would tie together the glycolytic and gluconeogenic pathways.
He used a heavy metal ion chelator ethylcarbylamine to
sever the link and turn on aerobic glycolysis.
The explanation for this was provided years later by the work fleshed out by Lynen, Bucher, Lowry, Racker, and Sols.
The rate-limiting enzyme, PFK is regulated by the concentrations of ATP, ADP, and inorganic phosphate. The ethylcarbylamide was an ‘uncoupler’ of oxidative phosphorylation.
Warburg understood that when normal cells switched to aerobic glycolysis
it is a re-orientation of normal cell expression.
this provides the basis for the inference that neoplastic cells become more like each other than their cell of origin.
embryonic cells can be transformed into cancer cells under hypoxic conditions
re-exposure to higher oxygen did not cause reversion back to normal cells.
Warburg publically expressed the rejected view in 1954 (at age 83) that restriction of chemical wastes, food additives, and air pollution would substantially reduce cancer rates.
His emphasis on the impairment of respiration was inadequate.
the prevailing view today is loss of controlled growth of normal cells in cancer cells.
The Human Genome Project, driven by Francis Collins at NIH, and by Craig Venter at the Institute for Genome Research (TIGR) had parallel projects to map the human chromosome, completed in 2003. It originally aimed to map the nucleotides contained in a human haploid reference genome (more than three billion). TIGR was the first complete genomic sequencing of a free living organism, Haemophilus influenzae, in 1995. This used a shotgun sequencing technique pioneered earlier, but which had never been used for a whole bacterium.
Venter broke away from the HGP and started Celera in 1998 because of resistance to the shotgun sequency method, and his team completed the genome sequence in three years – seven years’ less time than the HGP timetable (using the gene of Dr. Venter). TIGR eventually sequenced and analyzed more than 50 microbial genomes. Its bioinformatics group developed
pioneering software algorithms that were used to analyze these genomes,
including the automatic gene finder GLIMMER and
the sequence alignment program MUMmer.
In 2002, Venter created and personally funded theJ. Craig Venter Institute (JCVI) Joint Technology Center (JTC), which specialized in high throughput sequencing. The JTC, in the top ranks of scientific institutions worldwide, sequenced nearly 100 million base pairs of DNA per day for its affiliated institutions (JCVI) .
He received his his Ph.D. degree in physiology and pharmacology from the University of California, San Diego in 1975 under biochemist Nathan O. Kaplan. A full professor at the State University of New York at Buffalo, he joined the National Institutes of Health in 1984. There he learned of a technique for rapidly identifying all of the mRNAs present in a cell and began to use it to identify human brain genes. The short cDNA sequence fragments discovered by this method are called expressed sequence tags (ESTs), a name coined by Anthony Kerlavage at TIGR.
Venter believed that shotgun sequencing was the fastest and most effective way to get useful human genome data. There was a belief that shotgun sequencing was less accurate than the clone-by-clone method chosen by the HGP, but the technique became widely accepted by the scientific community and is still the de facto standard used today.
An article has been discussed by Dr. Tilda Barilya on use of a sensitive fluorescent probe in the near IR spectrum at > 700 nm to identify malignant ovarian cells in-vivo in abdominal exploration by tagging an overexpressed FR-α (folate-FITA)
The author makes the point that:
In ovarian cancer, the FR-α appears to constitute a good target because it is overexpressed in 90–95% of malignant tumors, especially serous carcinomas.
Targeting ligand, folate, is attractive as it is nontoxic, inexpensive and relatively easily conjugated to a fluorescent dye to create a tumor-specific fluorescent contrast agent.
The report is identified as “ the first in-human proof-of-principle of the use of intraoperative tumor-specific fluorescence imaging in staging and debulking surgery for ovarian cancer using the systemically administered targeted fluorescent agent folate-FITC.”
While this does invoke possibilities for prognosis, the decision to perform the surgery, whether laparoscopic or open, is late in the discovery process. However, it does suggest the possibility that the discovery and the treatment might be combined if the biomarker itself had the fluorescence to identify the overexpression, but it also is combined with a tag to block the overexpession. This hypothetical possibility is now expressed below. http://pharmaceuticalintelligence.com/2013/01/19/ovarian-cancer-and-fluorescence-guided-surgery-a-report/
can achieve much greater control over where new genes are inserted
According to Feng Zhang, this is an improvement beyond splicing the gene in specific locations and insertion of complexes difficult to assemble known as transcription activator-like effector nucleases (TALENs).
The researchers create DNA-editing complexes
using naturally occurring bacterial protein-RNA systems
that recognize and snip viral DNA, including
a nuclease called Cas9 bound to short RNA sequences.
they target specific locations in the genome, and
when they encounter a match, Cas9 cuts the DNA.
This approach can be used either to
disrupt the function of a gene or
to replace it with a new one.
To replace the gene, a DNA template for the new gene has to be copied into the genome after the DNA is cut. The method is also very precise —
if there is a single base-pair difference between the RNA targeting sequence and the genome sequence, Cas9 is not activated.
In its first iteration, it appears comparable in efficiency to what zinc finger nucleases and TALENs have to offer.
The research team has deposited the necessary genetic components with a nonprofit called Addgene, and they have also created a website with tips and tools for using this new technique.
The above story is reprinted from materials provided by Massachusetts Institute of Technology. The original article was written by Anne Trafton.
Le Cong, F. Ann Ran, David Cox, Shuailiang Lin, Robert Barretto, Naomi Habib, Patrick D. Hsu, Xuebing Wu, Wenyan Jiang, Luciano Marraffini, and Feng Zhang. Multiplex Genome Engineering Using CRISPR/Cas Systems. Science, 3 January 2013 DOI: 10.1126/science.1231143. http://Science.com. Editing genome with high precision: New method to insert multiple genes in specific locations, delete defective genes. ScienceDaily. Retrieved January 20, 2013, from http://www.sciencedaily.com /releases/2013/01/130103143205.htm?goback=%2Egde_4346921_member_205356312.
The information needed for the production of a mature protein is encoded in segments called exons .
In the splicing process, the non-coding segments of the RNA (introns) are spliced from the pre-mRNA and
the exons are joined together.
Alternative splicing is when a specific ”scene” (or exon) is either inserted or deleted from the movie (mRNA), thus changing its meaning.
Over 90 percent of the genes in our genome undergo alternative splicing of one or more of their exons, and
the resulting changes in the proteins encoded by these different mRNAs are required for normal function.
the normal process of alternative splicing is altered in cancer, and
”bad” protein forms are generated that aid cancer cell proliferation and survival.
The researchers reported in online Cell Reports that breast cancer cells
change the alternative splicing of an important enzyme, calledS6K1, which is
a protein involved in the transmission of information into the cell.
when this happens, breast cancer cells start to produce shorter versions of this enzyme and
these shorter versions transmit signals ordering the cells to grow, proliferate, survive and invade other tissues (otherwise proliferation is suppressed)
The application to biotherapeutics would be to ”reverse” the alternative splicing of S6K1 in cancer cells back to the normal situation as a novel anti-cancer therapy.
With a new approach, researchers may rapidly distinguish the range of
genetic changes that are causally linked to cancer (i.e. “driver” mutations)
versus those with limited impact on cancer progression.
This study published in the prestigious journal Genes & Development could pave the way to design more targeted treatment against different cancer types, based on the specific cancer-linked mutations present in the patient, an advance in the development of personalized medicine.
Signaling pathways involved in tumour formation are conserved from fruit flies to humans. In fact, about 75 percent of known human disease genes have a recognizable match in the genome of fruit flies.
Leveraging on their genetic similarities, Dr Hector Herranz, a post-doctorate from the Dr. Stephen Cohen’s team developed an innovative strategy to genetically screen the whole fly genome for “cooperating” cancer genes.
These genes appear to have little or no impact on cancer.
However, they cooperate with other cancer genes, so that
the combination causes aggressive cancer, which
neither would cause alone.
In this study, the team was specifically looking for genes that
could cooperate with EGFR “driver” mutation,
a genetic change commonly associated with breast and lung cancers in humans.
SOCS5 (reported in this paper) is one of the several new “cooperating” cancer genes to be identified.
Already, there are indications that levels of SOCS5 expression are
reduced in breast cancer, and
patients with low levels of SOCS5 have poor prognosis.”
The IMCB team is preparing to explore the use of SOCS5 as a biomarker in diagnosis for cancer. http://genes&development.com
‘Altered cellular metabolism is a hallmark of cancer,’ says Dr Patrick Pollard, in the Nuffield Department of Clinical Medicine at Oxford. Most cancer cells get the energy they need predominantly through a high rate of glycolysis, allowing cancer cells deal with the low oxygen levels that tend to be present in a tumour.
But whether dysfunctional metabolism causes cancer, as Warburg believed, or is something that happens afterwards is a different question. In the meantime, gene studies rapidly progressed and indicated that genetic changes occur in cancer.
DNA mutations spring up all the time in the body’s cells, but
most are quickly repaired.
Alternatively the cell might shut down or be killed off (apoptosis) before any damage is caused. However, the repair machinery is not perfect.
If changes occur that bypass parts of the repair machinery or sabotage it,
the cell can escape the body’s normal controls on growth and
DNA changes can begin to accumulate as the cell becomes cancerous.
Patrick believes certain changes in cells can’t always be accounted for by ‘genetics.’
He is now collaborating with Professor Tomoyoshi Soga’s large lab at Keio University in Japan, which has been at the forefront of developing the technology for metabolomics research over the past couple of decades.
The Japanese lab’s ability to
screen samples for thousands of compounds and metabolites at once, and
the access to tumour material and cell and animal models of disease
enables them to probe the metabolic changes that occur in cancer.
There is reason to believe that
dysfunctional cell metabolism is important in cancer.
genes with metabolic functions are associated with some cancers
changes in the function of a metabolic enzyme have been implicated in the development of gliomas.
These results have led to the idea that some metabolic compounds, or metabolites, when they accumulate in cells, can cause changes to metabolic processes and set cells off on a path towards cancer.
Patrick Pollard and colleagues have now published a perspective article in the journal Frontiers in Molecular and Cellular Oncology that proposes fumarate as such an ‘oncometabolite’. Fumarate is a standard compound involved in cellular metabolism.
The researchers summarize evidence that shows how
accumulation of fumarate when an enzyme goes wrong affects various biological pathways in the cell.
It shifts the balance of metabolic processes and disrupts the cell in ways that could favour development of cancer.
Patrick and colleagues write in their latest article that the shift in focus of cancer research to include cancer cell metabolism ‘has highlighted how woefully ignorant we are about the complexities and interrelationships of cellular metabolic pathways’.
Using genome-wide Chromatin Interaction Analysis with Paired-End-Tag sequencing (ChIA-PET),
mapped long-range chromatin interactions associated with RNA polymerase II in human cells
uncovered widespread promoter-centered intragenic, extragenic, and intergenic interactions.
These interactions further aggregated into higher-order clusters
proximal and distal genes were engaged through promoter-promoter interactions.
most genes with promoter-promoter interactions were active and transcribed cooperatively
some interacting promoters could influence each other implying combinatorial complexity of transcriptional controls.
Comparative analyses of different cell lines showed that
cell-specific chromatin interactions could provide structural frameworks for cell-specific transcription,
and suggested significant enrichment of enhancer-promoter interactions for cell-specific functions.
genetically-identified disease-associated noncoding elements were spatially engaged with corresponding genes through long-range interactions.
Overall, our study provides insights into transcription regulation by
three-dimensional chromatin interactions for both housekeeping and
Transcriptional regulation is a complex process that requires the integrated action of many multi-protein complexes.
The way in which a living cell coordinates the action of these complexes in time and space is still poorly understood.
nuclear pores, well known for their role in 3′ processing and export of transcripts, also participate in the control of transcriptional initiation.
nuclear pores interface with the well-described machinery that regulates initiation.
This work led to the discovery that
specific nucleoporins are required for binding of the repressor protein Mig1 to its site in target promoters.
Nuclear pores are involved in repressing, as well as activating, transcription.
Here we discuss in detail the main models explaining our result and consider what each implies about the roles that nuclear pores play in the regulation of gene expression.
(M Burton, M Thomassen, Q Tan, and TA Kruse.) Cancer Informatics 2012:11 193–217 doi: 10.4137/CIN.S10375
The popularity of a large number of microarray applications has in cancer research led to the development of predictive or prognostic gene expression profiles. However, the diversity of microarray platforms has made the full validation of such profiles and their related gene lists across studies difficult and, at the level of classification accuracies, rarely validated in multiple independent datasets. Frequently, while the individual genes between such lists may not match, genes with same function are included across such gene lists. Development of such lists does not take into account the fact that
genes can be grouped together as metagenes (MGs) based on common characteristics such as pathways, regulation, or genomic location.
In this study we compared the performance of either metagene- or single gene-based feature sets and classifiers using random forest and two support vector machines for classifier building. The performance
within the same dataset,
feature set validation performance, and
validation performance of entire classifiers in strictly independent datasets
were assessed by
10 times repeated 10-fold cross validation,
leave-one-out cross validation, and
one-fold validation, respectively.
To test the significance of the performance difference between MG- and SG-features/classifiers, we used a repeated down-sampled binomial test approach.
MG- and SG-feature sets are transferable and perform well for training and testing prediction of metastasis outcome
in strictly independent data sets, both
between different and
within similar microarray platforms, while
classifiers had a poorer performance when validated in strictly independent datasets.
The study showed that MG- and SG-feature sets perform equally well in classifying independent data. Furthermore, SG-classifiers significantly outperformed MG-classifier
when validation is conducted between datasets using similar platforms, while
no significant performance difference was found when validation was performed between different platforms.
Prediction of metastasis outcome in lymph node–negative patients by MG- and SG-classifiers showed that SG-classifiers performed significantly better than MG-classifiers when validated in independent data based on the same microarray platform as used for developing the classifier. However, the MG- and SG-classifiers had similar performance when conducting classifier validation in independent data based on a different microarray platform. The latter was also true when only validating sets of MG- and SG-features in independent datasets, both between and within similar and different platforms.
to identify the differentially expressed miRNAs in the serum of children with RB in comparison with the normal age matched serum,
to analyze its concurrence with the existing RB tumor miRNA profile,
to identify its novel gene targets specific to RB, and
to study the expression of a few of the identified oncogenic miRNAs in the advanced stage primary RB patient’s serum sample.
MiRNA profiling performed on 14 pooled serum from children with advanced RB and 14 normal age matched serum samples
21 miRNAs found to be upregulated (fold change > 2.0, P < 0.05) and
24 downregulated (fold change > 2.0, P < 0.05).
Intersection of 59 significantly deregulated miRNAs identified from RB tumor profiles with that of miRNAs detected in serum profile revealed that
33 miRNAs had followed a similar deregulation pattern in RB serum.
Later we validated a few of the miRNAs (miRNA 17-92) identified by microarray in the RB patient serum samples (n = 20) by using qRT-PCR.
Expression of the oncogenic miRNAs, miR-17, miR-18a, and miR-20a by qRT-PCR was significant in the serum samples
exploring the potential of serum miRNAs identification as noninvasive diagnosis.
Moreover, from miRNA gene target prediction, key regulatory genes of
cell proliferation,
apoptosis, and
positive and negative regulatory networks
involved in RB progression were identified in the gene expression profile of RB tumors.
Therefore, these identified miRNAs and their corresponding target genes could give insights on
potential biomarkers and key events involved in the RB pathway.
Computational Design of Targeted Inhibitors of Polo-Like Kinase 1 ( lk1).
(KS Jani and DS Dalafave) Bioinformatics and Biology Insights 2012:6 23–31.doi: 10.4137/BBI.S8971.
Down regulation of Plk1 has been shown to inhibit tumor progression.
Most kinase inhibitors interact with the ATP binding site on Plk1, which is highly conserved.
This makes the development of Plk1-specific inhibitors challenging, since different kinases have similar ATP sites.
However, Plk1 also contains a unique region called the polo-box domain (PBD), which is absent from other kinases.
the PBD site was used as a target for designed Plk1 putative inhibitors.
Common structural features of several experimentally known Plk1 ligands were first identified.
The findings were used to design small molecules that specifically bonded Plk1.
Drug likeness and possible toxicities of the molecules were investigated.
Molecules with no implied toxicities and optimal drug likeness values were used for docking studies.
Several molecules were identified that made stable complexes only with Plk1 and LYN kinases, but not with other kinases.
One molecule was found to bind exclusively the PBD site of Plk1.
Possible utilization of the designed molecules in drugs against cancers with over expressed Plk1 is discussed.
Conclusions
The previous discussions reviewed the status of an evolving personalized medicine multicentered and worldwide enterprise. It is also clear from these reports that the search for targeted drugs matched to a cancer profile or signature has identified several approaches that show great promise.
We know considerably more about metabolic pathways and linked changes in transcription that occur in neoplastic development.
There are several methods used to do highly accurate insertions in gene sequences that are linked to specific metabolic changes, and
some may have significant implications for therapeutics, if
the link is a change that is associated with a driver mutation
the link can be identified by a fluorescent or other probe
the link is tied to a mRNA or peptide product that is a biomarker measured in the circulation
We have probes to genetic links to the control of many and interacting signaling pathways.
We know more about transcription through mRNA.
We are closer to the possibility that metabolic substrates, like ‘fumarate’ (a key intermediate in the TCA cycle), may provide a means to reverse regulate the neoplastic cells.
We may also find metabolic channels that drive the cells from proliferation to apoptosis or normal activity.
Summary
This discussion identified the huge expansion of genomic technology in the investigation of biopharmacotherapeutic targets that have been identified involving different levels and interacting signaling pathways. There are several methods of analyzing gene expression, and a primary emphasis is given to combinations of mutations expressed in different cancer types. There is a major hypothesis that expresses the need to focus on “central” “driver mutations” that correspond with the regulation of gene expression, cell proliferation, and cell metabolism. What hasn’t been know is why drug resistance develops and whether the cellular migration and aerobic glycolysis can be redirected after cell metastasis occurs.
.
A slight mutation in the matched nucleotides can lead to chromosomal aberrations and unintentional genetic rearrangement. (Photo credit: Wikipedia)
Deutsch: Regulation der Phosphofructokinase (Photo credit: Wikipedia)
Other posts related to this discussion were published on this Open Source Online Scientific Journal from Leaders in Pharmaceutical Business Intelligence:
2012pharmaceutical
sjwilliamspa
