Archive for the ‘BioIT: BioInformatics, NGS, Clinical & Translational, Pharmaceutical R&D Informatics, Clinical Genomics, Cancer Informatics’ Category

18th Annual 2019 BioIT, Conference & Expo, April 16-18, 2019, Boston, Seaport World Trade Center, Track 5 Next-Gen Sequencing Informatics – Advances in Large-Scale Computing



Leaders in Pharmaceutical Business Intelligence (LPBI) Group

represented by Founder & Director, Aviva Lev-Ari, PhD, RN will cover this event in REAL TIME using Social Media





2:00 – 6:30 Main Conference Registration Open



5:00 – 7:00 Welcome Reception in the Exhibit Hall with Poster Viewing



7:30 am Registration Open and Morning Coffee


9:45 Coffee Break in the Exhibit Hall with Poster Viewing


Waterfront 3

10:50 Chairperson’s Remarks

David LaBrosse, Director, Genomics, Research, Life Sciences & Healthcare, NetApp

11:00 Long Read Sequencing

Justin Zook, PhD, Researcher, National Institute of Standards and Technology

11:20 NovoGraph: Loading 7 Human Genomes into Graphs

Evan Biederstedt, Computational Biologist, Memorial Sloan Kettering Cancer Center

11:40 Building a Usable Human Pangenome: A Human Pangenomics Hackathon Run by NCBI at UCSC

Ben Busby, PhD, Scientific Lead, NCBI Hackathons Group, National Center for Biotechnology Information (NCBI)

netapp12:00 pm Co-Presentation: Faster Genomic Data

Michael Hultner, PhD, Senior Vice President, Strategy; General Manager, US Operations, PetaGene

David LaBrosse, Director, Genomics, Research, Life Sciences & Healthcare, NetApp

Genetic testing demand is driving up the volume of genomic data that must be processed, analyzed, and stored. Gigabyte-scale genome sample files and terabyte- to petabyte-scale cohort data sets must be moved from data generation to processing to analysis sites, historically a slow, arduous process. NetApp and PetaGene will describe compression and data transfer technologies that overcome I/O bottlenecks to accelerate the movement of genomic data and reduce the time to process and analyze it.

12:30 Session Break

12:40 Luncheon Presentation I: Deep Phenotypic and Genomic Analysis of UK Biobank Data on the WuXi NextCODE Platform

Saliha Yilmaz, PhD, Research Geneticist, WuXi NextCODE

The increasing size and complexity of genetic and phenotypic data to include hundreds of thousands of participants poses a significant challenge for data storage and analysis. We demonstrate use of the GOR database and query language underlying our platform to mine UK Biobank and other datasets for efficient phenotype selection, GWAS and PheWAS, and to archive and query the results.

Seven-Bridges-rectangular1:10 NEW: Luncheon Co-Presentation II: Optimizing Drug Discovery and Development with Data-Driven Insights

Christian Frech, PhD, Associate Director, Scientific Operations, Seven Bridges

Serhat Tetikol, Research & Development Engineer, Seven Bridges

1:40 Session Break

Waterfront 3

1:50 Chairperson’s Remarks

Jeffrey Rosenfeld, PhD, Manager of the Biomedical Informatics Shared Resource and Assistant Professor of Pathology, Rutgers Cancer Institute of NJ

1:55 AbbVie’s Target and Genomics Compilation (ATGC): A Target Knowledge Platform

Rishi Gupta, PhD, Senior Research Scientist, Information Research, AbbVie, Inc.

Author: Anne-Sophie Barthelet, Scientific Developer, Discngine

ATGC is a web-based platform that allows AbbVie scientists to gather relevant information to make accurate decisions on target ID, target validation, biomarker selection and drug discovery. This platform provides in-depth information on several key pieces of information such as gene expression, RNA expression, protein expression, mouse knockout studies, etc. for each target. This talk focuses on key aspects of this application including application architecture, currently available tool sets and how various pieces of information are provided to the user.

2:25 Self Service Data Visualization and Exploration at Genentech Research

Kiran Mukhyala, Senior Software Engineer, Bioinformatics and Computational Biology, Genentech Research and Early Development

Genomic data requires specialized infrastructure to enable data exploration and analysis at scale. We built an integrated, modular, end-to-end gene expression analysis platform implementing data import, storage, processing, analysis and visualization. The multi-layered architecture of the platform supports general, high-level applications for self-service analytics, as well as infrastructure for prototyping, incubating and integrating scientist-driven innovations. The platform coexists with other in-house and commercial software to provide a wide range of genomic data analysis and visualization options for Research scientists.

2:55 Exploring and Visualizing Single-cell RNA Sequencing Data

Michael DeRan, PhD, Scientific Consultant, Diamond Age Data Science

Recent advances in single-cell RNA sequencing (scRNA-seq) technology have made this powerful method accessible to many researchers, but have not brought with them a clear, simple workflow for data analysis. As the number of scRNA-seq datasets has increased, so too has the number of analysis tools available; for those looking to perform their first scRNA-seq analysis the range of options can seem daunting. In working with our clients, I have had the opportunity to apply many different tools to scRNA-seq data from a variety of tissues and organisms. I have used this experience to select a set of tools that are flexible and suitable to many common scRNA-seq analysis tasks. In this talk I will introduce popular tools and methods for identifying cell populations, assessing differential expression and visualizing biological processes. I will discuss common pitfalls encountered in analyzing this data and make recommendations that anyone can use in their own analysis.

3:25 Refreshment Break in the Exhibit Hall with Poster Viewing, Meet the Experts: Bio-IT World Editorial Team, and Book Signing with Joseph Kvedar, MD, Author, The Internet of Healthy Things℠ (Book will be available for purchase onsite)

Waterfront 3

4:00 Comparison of Different Approaches for Clinical Cancer Sequencing

Jeffrey Rosenfeld, PhD, Manager of the Biomedical Informatics Shared Resource and Assistant Professor of Pathology, Rutgers Cancer Institute of NJ

The sequencing of tumors is important for guiding the treatment of cancer patients. While it is agreed that there is a need to perform sequencing of the tumor, there are a wide variety of approaches ranging from paired whole genome tumor-normal sequencing to tumor-only small panel sequencing with many intermediate possibilities. Each of the approaches has a different cost and associated benefit. I will present a comparison of different methods and their efficacy for guiding cancer treatment.

4:30 Integrated NGS Analysis to Accelerate Disease Understanding for Drug Discovery

Helen Li, Director- Research IT – Biologics & Informatics, Eli Lilly and Company

5:00 Identification of Cancer Biomarker Genes

Maryam Nazarieh, PhD, Postdoctoral Researcher, Center for Bioinformatics, Universität des Saarlandes, Saarbrücken, Germany

Identification of biomarker genes plays a crucial role in disease detection and treatment. Computational approaches enhance the insights derived from experiments and reduce the efforts of biologists and experimentalists to identify biomarker genes which play key roles in complex diseases. This is essentially achieved through prioritizing a set of genes with certain attributes (1). Here, I propose a set of transcription factors that make the largest strongly connected component of the pluripotency network in embryonic stem cells as the global regulators that control differentiation process determining cell fate. This component can be controlled by a set of master regulatory genes.  The regulatory mechanisms underlying stem cells inspired us to formulate the problem where a set of master regulatory genes in regulatory networks is identified with two combinatorial optimization problems namely as minimum dominating set and minimum connected dominating set in weakly and strongly connected components. The developed methods were applied to regulatory cancer networks to identify disease-associated genes and anti-cancer drug targets in breast cancer and hepatocellular carcinoma.  As not all the nodes in the solutions are critical, a prioritization method was developed named TopControl to rank a set of candidate genes which relate to a certain disease based on systematic analysis of the genes that are differentially expressed in tumor and normal conditions. To this purpose, the NGS data were utilized taken from The Cancer Genome Atlas for matched tumor and normal samples of liver hepatocellular carcinoma (LIHC) and breast invasive carcinoma (BRCA) datasets. Moreover, the topological features were demonstrated in regulatory networks surrounding differentially expressed genes that were highly consistent in terms of using the output of several analysis tools. We present several web servers and software packages that are publicly available at no cost. The Cytoscape plugin of minimum connected dominating set identifies a set of key regulatory genes in a user provided regulatory network based on a heuristic approach. The ILP formulations of minimum dominating set and minimum connected dominating set return the optimal solutions for the aforementioned problems. Our source code is publicly available. The web servers TFmiR and TFmiR2 construct disease-, tissue-, process-specific networks for the sets of deregulated genes and miRNAs provided by a user. They highlight topological hotspots and offer detection of three- and four-node FFL motifs as a separate web service for both organisms mouse and human. 1) Maryam Nazarieh, Understanding regulatory mechanisms underlying stem cells helps to identify cancer biomarkers. Ph.D. thesis, Saarland University, Saarbrücken, Germany (2018).

5:30 Best of Show Awards Reception in the Exhibit Hall with Poster Viewing


Read Full Post »

Reporter and Curator: Dr. Sudipta Saha, Ph.D.


Gender of a person can affect the kinds of cancer-causing mutations they develop, according to a genomic analysis spanning nearly 2,000 tumours and 28 types of cancer. The results show striking differences in the cancer-causing mutations found in people who are biologically male versus those who are biologically female — not only in the number of mutations lurking in their tumours, but also in the kinds of mutations found there.


Liver tumours from women were more likely to carry mutations caused by a faulty system of DNA mending called mismatch repair, for instance. And men with any type of cancer were more likely to exhibit DNA changes thought to be linked to a process that the body uses to repair DNA with two broken strands. These biases could point researchers to key biological differences in how tumours develop and evolve across sexes.


The data add to a growing realization that sex is important in cancer, and not only because of lifestyle differences. Lung and liver cancer, for example, are more common in men than in women — even after researchers control for disparities in smoking or alcohol consumption. The source of that bias, however, has remained unclear.

In 2014, the US National Institutes of Health began encouraging researchers to consider sex differences in preclinical research by, for example, including female animals and cell lines from women in their studies. And some studies have since found sex-linked biases in the frequency of mutations in protein-coding genes in certain cancer types, including some brain cancers and advanced melanoma.


But the present study is the most comprehensive study of sex differences in tumour genomes so far. It looks at mutations not only in genes that code for proteins, but also in the vast expanses of DNA that have other functions, such as controlling when genes are turned on or off. The study also compares male and female genomes across many different cancers, which can allow researchers to pick up on additional patterns of DNA mutations, in part by increasing the sample sizes.


Researchers analysed full genome sequences gathered by the International Cancer Genome Consortium. They looked at differences in the frequency of 174 mutations known to drive cancer, and found that some of these mutations occurred more frequently in men than in women, and vice versa. When they looked more broadly at the loss or duplication of DNA segments in the genome, they found 4,285 sex-biased genes spread across 15 chromosomes.


There were also differences found when some mutations seemed to arise during tumour development, suggesting that some cancers follow different evolutionary paths in men and women. Researchers also looked at particular patterns of DNA changes. Such patterns can, in some cases, reflect the source of the mutation. Tobacco smoke, for example, leaves behind a particular signature in the DNA.


Taken together, the results highlight the importance of accounting for sex, not only in clinical trials but also in preclinical studies. This could eventually allow researchers to pin down the sources of many of the differences found in this study. Liver cancer is roughly three times as common in men as in women in some populations, and its incidence is increasing in some countries. A better understanding of its aetiology may turn out to be really important for prevention strategies and treatments.




Read Full Post »

Reporter and Curator: Dr. Sudipta Saha, Ph.D.


Protein kinase C (PKC) isozymes function as tumor suppressors in increasing contexts. These enzymes are crucial for a number of cellular activities, including cell survival, proliferation and migration — functions that must be carefully controlled if cells get out of control and form a tumor. In contrast to oncogenic kinases, whose function is acutely regulated by transient phosphorylation, PKC is constitutively phosphorylated following biosynthesis to yield a stable, autoinhibited enzyme that is reversibly activated by second messengers. Researchers at University of California San Diego School of Medicine found that another enzyme, called PHLPP1, acts as a “proofreader” to keep careful tabs on PKC.


The researchers discovered that in pancreatic cancer high PHLPP1 levels lead to low PKC levels, which is associated with poor patient survival. They reported that the phosphatase PHLPP1 opposes PKC phosphorylation during maturation, leading to the degradation of aberrantly active species that do not become autoinhibited. They discovered that any time an over-active PKC is inadvertently produced, the PHLPP1 “proofreader” tags it for destruction. That means the amount of PHLPP1 in patient’s cells determines his amount of PKC and it turns out those enzyme levels are especially important in pancreatic cancer.


This team of researchers reversed a 30-year paradigm when they reported evidence that PKC actually suppresses, rather than promotes, tumors. For decades before this revelation, many researchers had attempted to develop drugs that inhibit PKC as a means to treat cancer. Their study implied that anti-cancer drugs would actually need to do the opposite — boost PKC activity. This study sets the stage for clinicians to one day use a pancreatic cancer patient’s PHLPP1/PKC levels as a predictor for prognosis, and for researchers to develop new therapeutic drugs that inhibit PHLPP1 and boost PKC as a means to treat the disease.


The ratio — high PHLPP1/low PKC — correlated with poor prognoses: no pancreatic patient with low PKC in the database survived longer than five-and-a-half years. On the flip side, 50 percent of the patients with low PHLPP1/high PKC survived longer than that. While still in the earliest stages, the researchers hope that this information might one day aid pancreatic diagnostics and treatment. The researchers are next planning to screen chemical compounds to find those that inhibit PHLPP1 and restore PKC levels in low-PKC-pancreatic cancer cells in the lab. These might form the basis of a new therapeutic drug for pancreatic cancer.




Read Full Post »

Immunoediting can be a constant defense in the cancer landscape

Reporter and Curator: Dr. Sudipta Saha, Ph.D.


There are many considerations in the cancer immunoediting landscape of defense and regulation in the cancer hallmark biology. The cancer hallmark biology in concert with key controls of the HLA compatibility affinity mechanisms are pivotal in architecting a unique patient-centric therapeutic application. Selection of random immune products including neoantigens, antigens, antibodies and other vital immune elements creates a high level of uncertainty and risk of undesirable immune reactions. Immunoediting is a constant process. The human innate and adaptive forces can either trigger favorable or unfavorable immunoediting features. Cancer is a multi-disease entity. There are multi-factorial initiators in a certain disease process. Namely, environmental exposures, viral and / or microbiome exposure disequilibrium, direct harm to DNA, poor immune adaptability, inherent risk and an individual’s own vibration rhythm in life.


When a human single cell is crippled (Deranged DNA) with mixed up molecular behavior that is the initiator of the problem. A once normal cell now transitioned into full threatening molecular time bomb. In the modeling and creation of a tumor it all begins with the singular molecular crisis and crippling of a normal human cell. At this point it is either chop suey (mixed bit responses) or a productive defensive and regulation response and posture of the immune system. Mixed bits of normal DNA, cancer-laden DNA, circulating tumor DNA, circulating normal cells, circulating tumor cells, circulating immune defense cells, circulating immune inflammatory cells forming a moiety of normal and a moiety of mess. The challenge is to scavenge the mess and amplify the normal.


Immunoediting is a primary push-button feature that is definitely required to be hit when it comes to initiating immune defenses against cancer and an adaptation in favor of regression. As mentioned before that the tumor microenvironment is a “mixed bit” moiety, which includes elements of the immune system that can defend against circulating cancer cells and tumor growth. Personalized (Precision-Based) cancer vaccines must become the primary form of treatment in this case. Current treatment regimens in conventional therapy destroy immune defenses and regulation and create more serious complications observed in tumor progression, metastasis and survival. Commonly resistance to chemotherapeutic agents is observed. These personalized treatments will be developed in concert with cancer hallmark analytics and immunocentrics affinity and selection mapping. This mapping will demonstrate molecular pathway interface and HLA compatibility and adaptation with patientcentricity.



Read Full Post »

Immunotherapy may help in glioblastoma survival

Reporter and Curator: Dr. Sudipta Saha, Ph.D.


Glioblastoma is the most common primary malignant brain tumor in adults and is associated with poor survival. But, in a glimmer of hope, a recent study found that a drug designed to unleash the immune system helped some patients live longer. Glioblastoma powerfully suppresses the immune system, both at the site of the cancer and throughout the body, which has made it difficult to find effective treatments. Such tumors are complex and differ widely in their behavior and characteristics.


A small randomized, multi-institution clinical trial was conducted and led by researchers at the University of California at Los Angeles involved patients who had a recurrence of glioblastoma, the most common central nervous system cancer. The aim was to evaluate immune responses and survival following neoadjuvant and/or adjuvant therapy with pembrolizumab (checkpoint inhibitor) in 35 patients with recurrent, surgically resectable glioblastoma. Patients who were randomized to receive neoadjuvant pembrolizumab, with continued adjuvant therapy following surgery, had significantly extended overall survival compared to patients that were randomized to receive adjuvant, post-surgical programmed cell death protein 1 (PD-1) blockade alone.


Neoadjuvant PD-1 blockade was associated with upregulation of T cell– and interferon-γ-related gene expression, but downregulation of cell-cycle-related gene expression within the tumor, which was not seen in patients that received adjuvant therapy alone. Focal induction of programmed death-ligand 1 in the tumor microenvironment, enhanced clonal expansion of T cells, decreased PD-1 expression on peripheral blood T cells and a decreasing monocytic population was observed more frequently in the neoadjuvant group than in patients treated only in the adjuvant setting. These findings suggest that the neoadjuvant administration of PD-1 blockade enhanced both the local and systemic antitumor immune response and may represent a more efficacious approach to the treatment of this uniformly lethal brain tumor.


Immunotherapy has not proved to be effective against glioblastoma. This small clinical trial explored the effect of PD-1 blockade on recurrent glioblastoma in relation to the timing of administration. A total of 35 patients undergoing resection of recurrent disease were randomized to either neoadjuvant or adjuvant pembrolizumab, and surgical specimens were compared between the two groups. Interestingly, the tumoral gene expression signature varied between the two groups, such that those who received neoadjuvant pembrolizumab displayed an INF-γ gene signature suggestive of T-cell activation as well as suppression of cell-cycle signaling, possibly consistent with growth arrest. Although the study was not powered for efficacy, the group found an increase in overall survival in patients receiving neoadjuvant pembrolizumab compared with adjuvant pembrolizumab of 13.7 months versus 7.5 months, respectively.


In this small pilot study, neoadjuvant PD-1 blockade followed by surgical resection was associated with intratumoral T-cell activation and inhibition of tumor growth as well as longer survival. How the drug works in glioblastoma has not been totally established. The researchers speculated that giving the drug before surgery prompted T-cells within the tumor, which had been impaired, to attack the cancer and extend lives. The drug didn’t spur such anti-cancer activity after the surgery because those T-cells were removed along with the tumor. The results are very important and very promising but would need to be validated in much larger trials.




Read Full Post »

eProceeding 2019 Koch Institute Symposium – 18th Annual Cancer Research Symposium – Machine Learning and Cancer, June 14, 2019, 8:00 AM-5:00 PM ET MIT Kresge Auditorium, 48 Massachusetts Ave, Cambridge, MA


Aviva Lev-Ari, PhD, RN,

Founder and Director of LPBI Group will be in attendance covering the event in REAL TIME






8:00–9:00 Coffee Break Registration


9:00 –9:10 Introductory Remarks Tyler Jacks Koch Institute, MIT Phillip Sharp Koch Institute, MIT

  • INTERDISCIPLINARY research at the interface of Cancer with other disciplines, this year CS, ML,

9:10–10:30 Machine Learning in Cancer Research: The Need and the Opportunity

Moderator: Phillip Sharp, Nobel Laureate 

  • ML and cancer @MIT over a decade under discussion, ML & Cancer in research is embryonic
  • REENGINEERING Healthcare using ML: understand disease, treating it
  • MIT Stephen A. Schwarzman College of Computing, AI and Healthcare – an MIT commitment of a $MILLION

James P. Allison MD Anderson Cancer Center, Nobel Laureate FOR CURE OF CANCER, THE ONLY ONE

Immune checkpoint blockade in cancer therapy: Historical perspective, new opportunities, and prospects for cures

  • long survival on ipilimumab – Lung cancer pleural effusion
  • CTLA-4Blockade – attenuated or Terminate Proliferation vs unrestrained Proliferation – APC
  • PD-1 – Ipi/Nivo vs. Ipi in metastatic Melanoma – 10 years survival after initial three years
  • FDA Approved CTLA-4 and Anti-PD-1 for a dozen indication
  • CD4, CD8, NKT – CHeckpoint blockage modulates MC38 infiltrating T cell population frequency
  • Cellular mechanism interaction
  • T cell differentiation is complex – negative costimulation regulate T cell differentiation
  • comprehensive profiling of peripheral T cell arising
  • Expansion of phynotype – distinct gene expression
  • Transcription loss of PD-1 expands CD8 T cells
  • Nuanced Model – T cell differentiation
  • Role of T cells in Immunotherapy

Aviv Regev Broad Institute; Koch Institute, MIT

Cell atlases as roadmaps to cancer

  • Experimental data and computation data
  • Tumors: a complex cellular ecosystem
  • Genetic pathology, Combination therapy Genetic variants and
  • Components vs Programs (regulatory, pathways, tissue modules, disease road map)
  • ML Applications: Immunotherapy in melanoma
  • Learning an single cell profiling and spatial organization – massively parallel cell profiling
  • malignant cells from T cell cold tumors
  • T cell T cell CD8 Malignant: Resistant
  • Computational search predicts CDK4/6 as program regulators
  • the resistance program is reversed abemaciclib sensitized to B16
  • Resistance to immunotherapy in Melanoma
  • Generalize across types of cancers – Resistance to treatment
  • Atlas for Synovial sarcoma has anti-tumor activity in its immune environment
  • Melanoma vs Synovial sarcoma (SS18-SSX fusion directly controls the core oncogenic program
  • Target the core oncogenic program therapeutically
  • IFN from CD8 T NF repress the program
  • Insi2Vec: Define a cell by intrinsic and extrinsic and spatial features: generalize across patient samples in melanoma
  • Identifying key patio-molecular archetypes
  • Expanding to full Transcriptome
  • Emerging toolbox for spatial genomics: Protein, RNA,
  • Compressed sensing,

Regina Barzilay MIT Computer Science and Artificial Intelligence Laboratory; Koch Institute,

MIT How machine learning changes cancer research

  • ML & Clinical Oncology
  • Data Science perspective – Raw Data to Cure: Extract information
  • NLP – penetration of deepLearning @MGH
  • Drug discovery – New molecules
  • MIT – ML in drug discovery
  • Risk models: age, family history, prior breast procedures breast density
  • High risk and Breast density
  • Myth #1: DEMOCRATIZATION OF AI – deep learning and customization
  • Myth @2: Bias – Deep Learning allows across population studies
  • Myth #3: Black-Box Architecture 0 @MIT Interpretable models
  • J-Clinic @MIT – ML and Healthcare Hospitals are recruited to use the algorithms

11:00–12:25 Machine Learning to Decipher Cellular and Molecular Mechanisms in Cancer

Moderator: Matthew Vander

Heiden Michael Angelo Stanford University

Comprehensive enumeration of immune cells in solid tumors using Multiplexed ion beam imaging (MIBI)

  • Tissue imaging – high dimensional, multiplexing: high sensitivity, dynamic range,
  • GI Tissue selection – Immunofluorescence (IF)  fluorophores – elemental reporters and mass spectrometry  Label antibody,
  • Immune populations in triple negative breast cancer
  • Patient stratification survival
  • mixed tumor: Immune cells, non immune cells – response to PD-1
  • Single cell: imaging data trained by nuclear interior ( nuclei only, , segmentation channel using DeepCell v1.0
  • TB granulomas,
  • Cell type identification with deep learning – No downstream
  • 3D Segmentation Melanoma
  • Assays and Ion sources

Olga Troyanskaya Princeton University

Decoding cancer genomes with deep learning

  • genome to phenotype – BIG genomics data to understand human disease
  • exosome – non coding region
  • gene regulation affected by genome for gene expression
  • sequence specific
  • Interpreting a genome: predicting the effect of any mutation: coding variant vs non-coding variance – regulatory code, transcription marks, DeepSEA – model learns from one genome interactions of biochemical level models, variants motives cell type
  • Interpreting a Genome: predicting the effect of any mutation: Noncoding variant effect in ASD from WGS data
  • DeNovo mutations: How impactful are these mutations in Autism patients – to % not explained by sequencing
  • DeepSEA identifies significant noncoding regulatory mutation burden in ASD
  • Cell-type specific expression models capture tissue-specific
  • ExPecto-prioritized putative casual GWAS variants
  • HumanBase Networks best model selected are

Dana Pe’er Sloan Kettering Institute

Manifolds underlying plasticity in development, regeneration and cancer

  • Asynchronous Nature of Cells
  • Single cell transitional states, homeostatic
  • Representing population structure as a neighbor graph: each node is a cell connected to a neighborhood – diffusion components Magic: Using structure for data recovery
  • PALANTIR: a probabilistic model for cell fate
  • Learn differentiation trajectories/pseudo-time ordering
  • Computing Differentiation probabilities stochastic process – branch
  • The gut tube comprises cells of two distinct regions
  • mammal cell plasticity – endodermal organ identities in space
  • VE cells express key organ lineage regulators similarly to DE cell
  • Uncovering unappreciated lineage relationship
  • Lung adenocarcinoma – tumor – 10% are cancer cell the rest are not therefore – they are ORGANS
  • Primary tumor exhibit epithelial progenitor cells
  • Pancreatic Ductal Adenocarcinoma – ductal Metaplasia
  • Immune ecosystem reprogrammed
  • Leptomeningeal niche — iron binding – adopt environment and prevent iron from the immune system
  • Tumor plasticity – Mutation Kras + injury to cause pancreatic cancer


Peter Sorger Harvard Medical School

Measuring and modeling variability in drug response in cells, tissues and clinical trials

  • combination therapy and drug synergy
  • Re-digitalization of 300 clinical trials
  • combination immunotherapy: Assumption each patient benefits from both = synergy
  • vs the assumption of NO interaction: each Patient benefit from ONE or the Other
  • Novartis PDX models
  • Gastric Cancer PDXs
  • Three way combination drug therapy – a deeper look at RAF and MEK inhibitors in BRAF mutant melanoma
  • Pharmacology of ‘reconstituted pulses” independent action
  • Heterogeneous response – sophisticated stratification of patients Four biopsy vs Three Biopsy
  • Highly multiplexed, high resolution image of FFPE specimens
  • Assaying the effects of multiple possible
  • Cancer Precision Medicine per NCI
  • Precision medicine based on therapeutic response at sisngel cell level
  • Pharmacological synergy is over emphsized – time sensitivity prevent the interactions expected

12:30–2:00 Lunch Break

2:00–3:00 Big Data, Computation and the Future of Health Care

Moderator: Susan Hockfield

Jay Bradner Novartis Institutes for BioMedical Research

  • AI is a Tool in all phases of drug discovery integrated analysis of epigenetics
  • strategy for investment in 400 Scientists, big data
  • monitoring of Clinical Trial around the  World
  • generative chemistry – 100 years of discovery in chemistry
  • validation models – bring trials to patients – distributed model of participation
  • catalyst – ML in biological experimentation
  • Published 700 articles per year at Novartis by 400 scientists
  • Population Data sets
  • IN 5 YEARS MASSIVE data will dominate molecule selection in Drug delivery

Aine Hanly VP Amgen

  • 17% improvement in survival rate in 50 years
  • Data infrastructure investment paid off
  • Partnerships, interoperability in EMR

Clifford Hudis American Society of Clinical Oncology (ASCO)

  • 75% of communication is by FAX still
  • White cell data count – convert data structure on EMR
  • Data in the Cloud for sharing
  • 165 Million in US — employer covers health cost
  • ACCESS to 2,000 clinical trials for repurposing

Constance Lehman Massachusetts General Hospital

  • Pathway – Screening mammograms is run via the algorithm, report generated, Radiologist accept or reject the mobile presented
  • more domains need AI and specialties of Medicine
  • Development and implementation then dissemination to multiple sites
  • In 1000 mammogram only 8 cancers detected

David Schenkein GOOGLE Venture (GV)

  • Regeneron, Geisinger Health System, Amgen – Big data repositories are built
  • Clinical Trials and big data
  • delivery side: AI: Pathology and Radiology, early diagnostics:
  • AI in MDs Offices to record the entire sessions
  • diagnostics – Foundation Medicine diagnostics had difficult time to prove improvement to justify reimbursement


3:00–3:15 Break


3:15–4:40 Machine Learning into the Clinic


Moderator: Sangeeta Bhatia, Koch Institute, MIT

Tommi S. Jaakkola MIT Computer Science and Artificial Intelligence Laboratory

Machine learning for drug design

  • Automation arises from data
  • How much data is enough? assay size vs all spectrum
  • MIT Consortium on Drug Discovery: 13 Pharma, chemistry Department, Chemical Engineering Department, CSMIT Consortium on Pharmaceutical Discovery
  • multi-resolution representations
  • substructures with precision attachment – what atoms are underlined
  • predicting molecular properties
  • programmatic optimization – machine translation problem in analogy – learn the mapping principles from examples
  • Example comparisons – Programmatic optimization – Success %
  • Understanding: Accuracy- interpretable, statistical constraints inserted
  • integrations with biology and cancer research
  • Automating Drug Design – learn from exampl

Andrew Beck PathAI

Artificial intelligence for pathology: From discovery to AI-powered companion diagnostics

  • Pathologic diagnosis informs all subsequent medical decisions
  • Discordance among pathologists is common in interpretation of breast biopsy
  • Discordance among pathologists is common in interpretation of skin biopsy – melanoma
  • Discordance among pathologists is common in interpretation across all fields: NSCLC, bladder,
  • AI – deep learning is driving major advances in computer vision
  • Reduce errors training set vs validation set
  • computer vision vs Human eye – machine learning is BETTER
  • Labeled and counting data standardization requires work with the community of Pathologists
  • Automatic interpretation of cells and tissues
  • Immuno-oncology
  • TisSue and cellular phenologies – Pathological phenotypes
  • BMS – CD8 continuum – Phenotype : Identify stromal and parenchymal CD8 infalmmation
  • AI project with Novartis

Brian Wolpin Dana-Farber Cancer Institute

Early detection of pancreatic cancer

  • ML for Pancreatic Cancer Early detection
  • Metabolic alterations: Muscle wasting, subcutaneous adipose
  • Automated Peripheral Tissue Segmentation
  • 30,000 scans: changes by race, age, : Image-Based Risk Modeling within Large Health Systems

longitudinal Cohorts: Risk Factors

  • Diabetes related to pancreatic cancer
  • risk for weight and Diabetes
  • Medication: Start and Stopped: NSAIDs, Tylenol, H2 Blocker, PPI, anti- HTN,
  • ML – early detection: altered systemic metabolism

Stephen Friend University of Oxford

From complex to complicated problems: What are the known unknowns, and unknown unknowns in using wearables to forecast symptom transitions

  • Pattern recognition for prognosis NEJM 20 years took since Breast cancer started to benefit from pattern recognition
  • Participants-Centered
  • 10M smart watches
  • APPLE – many studies Smart watch – 15,000 participants donate data via their watch – large scale ALERT based on data analysis
  • Inter-individual Diversity
  • Personal Health Assistant
  • all day sensing & recording
  • Health Assessment – signals to Symptoms
  • Deep Learning – multiple stages of non-linear feature transformation
  • Vector Institute – data analysis was done [Pregnancy]
  • Forecasting – binary labels: Well or Sick, intra and inter-individual longitudinal
  • 4YouandMe  – Foundation
  • Wearables for Cancer patients

4:40–4:45 Closing Remarks Phillip Sharp Koch Institute, MIT



Machine Learning and Cancer

The 18th Annual Koch Institute Summer Symposium on June 14, 2019 at MIT’s Kresge Auditorium will focus on Machine Learning and Cancer.

Both fields are undergoing dramatic changes, and their integration holds great promise for cancer research, diagnostics, and therapeutics. Cancer treatment and research have advanced rapidly with an increasing reliance on data-driven decisions. The volume, complexity, and diversity of research and clinical data—from genomics and single-cell molecular and image-based profiles to histopathology, clinical imaging, and medical records—far surpasses the capacity of individual scientists and physicians. However, they offer a remarkable opportunity to new approaches for data science and machine learning to provide holistic and intelligible interpretations to trained experts and patients alike. These advances will make it possible to provide far better diagnostics, discover possible chemical pathways for de novo synthesis of therapeutic compounds, predict accurately the risk of individuals for development of specific cancers years before metastatic spread, and determine the combination of agents that will stimulate immune rejection of a tumor or selectively induce the death of all cells in a tumor.

The symposium will address these issues through three sessions:

  • Machine Learning in Cancer Research: the Need and the Opportunity
  • Machine Learning to Decipher Cellular and Molecular Mechanisms in Cancer
  • Machine Learning into the Clinic

Sessions will be followed by a panel discussion of broadly informed experts moderated by MIT President Emerita Susan Hockfield.

Introductory remarks will be given by symposium co-chairs and Koch Institute faculty members Regina Barzilay, Aviv Regev and Phillip Sharp.


Keynote Speakers | Machine Learning in Cancer Research: the Need and the Opportunity

James P. Allison, PhD

MD Anderson Cancer Center

Regina Barzilay, PhD

MIT Computer Science and Artificial Intelligence Lab, Koch Institute for Integrative Cancer Research at MIT

Aviv Regev, PhD

Broad Institute, Koch Institute for Integrative Cancer Research at MIT


Session Speakers

Michael R. Angelo, MD, PhD

Stanford Unviersity

Andrew Beck


Stephen H. Friend, MD, PhD

Sage Bionetworks

Tommi Jaakkola, PhD

MIT Computer Science and Artificial Intelligence Lab

Dana Pe’er, PhD

Memorial Sloan Kettering Cancer Center

Peter Sorger, PhD

Harvard Medical School

Olga Troyanskaya, PhD

Princeton University

Brian Wolpin, MD

Dana-Farber Cancer Institute


Panel Discussion | Big Data, Computation and the Future of Health Care

James (Jay) Bradner, MD


Clifford A. Hudis, MD

American Society of Clinical Oncology

Constance D. Lehman, MD, PhD

Massachusetts General Hospital

Norman (Ned) Sharpless, MD

National Cancer Institute


Moderator: Susan Hockfield, PhD

Koch Institute for Integrative Cancer Research at MIT

[if gte mso 9]>


From: 2019 Koch Institute Symposium <>

Reply-To: <>

Date: Tuesday, March 12, 2019 at 11:30 AM

To: Aviva Lev-Ari <>

Subject: Invitation to the 2019 Koch Institute Symposium – Machine Learning and Cancer

Read Full Post »

Hypertriglyceridemia: Evaluation and Treatment Guideline

Reporter and Curator: Dr. Sudipta Saha, Ph.D.


Severe and very severe hypertriglyceridemia increase the risk for pancreatitis, whereas mild or moderate hypertriglyceridemia may be a risk factor for cardiovascular disease. Individuals found to have any elevation of fasting triglycerides should be evaluated for secondary causes of hyperlipidemia including endocrine conditions and medications. Patients with primary hypertriglyceridemia must be assessed for other cardiovascular risk factors, such as central obesity, hypertension, abnormalities of glucose metabolism, and liver dysfunction. The aim of this study was to develop clinical practice guidelines on hypertriglyceridemia.

The diagnosis of hypertriglyceridemia should be based on fasting levels, that mild and moderate hypertriglyceridemia (triglycerides of 150–999 mg/dl) be diagnosed to aid in the evaluation of cardiovascular risk, and that severe and very severe hypertriglyceridemia (triglycerides of >1000 mg/dl) be considered a risk for pancreatitis. The patients with hypertriglyceridemia must be evaluated for secondary causes of hyperlipidemia and that subjects with primary hypertriglyceridemia be evaluated for family history of dyslipidemia and cardiovascular disease.

The treatment goal in patients with moderate hypertriglyceridemia should be a non-high-density lipoprotein cholesterol level in agreement with National Cholesterol Education Program Adult Treatment Panel guidelines. The initial treatment should be lifestyle therapy; a combination of diet modification, physical activity and drug therapy may also be considered. In patients with severe or very severe hypertriglyceridemia, a fibrate can be used as a first-line agent for reduction of triglycerides in patients at risk for triglyceride-induced pancreatitis.

Three drug classes (fibrates, niacin, n-3 fatty acids) alone or in combination with statins may be considered as treatment options in patients with moderate to severe triglyceride levels. Statins are not be used as monotherapy for severe or very severe hypertriglyceridemia. However, statins may be useful for the treatment of moderate hypertriglyceridemia when indicated to modify cardiovascular risk.




Read Full Post »

« Newer Posts - Older Posts »