Posts Tagged ‘immune inhibitory checkpoints’

Yet another Success Story: Machine Learning to predict immunotherapy response

Curator and Reporter: Dr. Premalata Pati, Ph.D., Postdoc

Immune-checkpoint blockers (ICBs) immunotherapy appears promising for various cancer types, offering a durable therapeutic advantage. Only a number of cases with cancer respond to this therapy. Biomarkers are required to adequately predict the responses of patients. This article evaluates this issue utilizing a system method to characterize the immune response of the anti-tumor based on the entire tumor environment. Researchers build mechanical biomarkers and cancer-specific response models using interpretable machine learning that predict the response of patients to ICB.

The lymphatic and immunological systems help the body defend itself by combating. The immune system functions as the body’s own personal police force, hunting down and eliminating pathogenic baddies.

According to Federica Eduati, Department of Biomedical Engineering at TU/e, “The immune system of the body is quite adept at detecting abnormally behaving cells. Cells that potentially grow into tumors or cancer in the future are included in this category. Once identified, the immune system attacks and destroys the cells.”

Immunotherapy and machine learning are combining to assist the immune system solve one of its most vexing problems: detecting hidden tumorous cells in the human body.

It is the fundamental responsibility of our immune system to identify and remove alien invaders like bacteria or viruses, but also to identify risks within the body, such as cancer. However, cancer cells have sophisticated ways of escaping death by shutting off immune cells. Immunotherapy can reverse the process, but not for all patients and types of cancer. To unravel the mystery, Eindhoven University of Technology researchers used machine learning. They developed a model to predict whether immunotherapy will be effective for a patient using a simple trick. Even better, the model outperforms conventional clinical approaches.

The outcomes of this research are published on 30th June, 2021 in the journal Patterns in an article entitled “Interpretable systems biomarkers predict response to immune-checkpoint inhibitors”.

The Study

  • Characterization of the tumor microenvironment from RNAseq and prior knowledge
  • Multi-task machine-learning models for predicting antitumor immune responses
  • Identification of cancer-type-specific, interpretable biomarkers of immune responses
  • EaSIeR is a tool to predict biomarker-based immunotherapy response from RNA-seq

“Tumor also contains multiple types of immune and fibroblast cells which can play a role in favor of or anti-tumor, and communicates among themselves,” said Oscar Lapuente-Santana, a researcher doctoral student in the computational biology group. “We had to learn how complicated regulatory mechanisms in the micro-environment of the tumor affect the ICB response. We have used RNA sequencing datasets to depict numerous components of the Tumor Microenvironment (TME) in a high-level illustration.”

Using computational algorithms and datasets from previous clinical patient care, the researchers investigated the TME.

Eduati explained

While RNA-sequencing databases are publically available, information on which patients responded to ICB therapy is only available for a limited group of patients and cancer types. So, to tackle the data problem, we used a trick.

All 100 models learned in the randomized cross-validation were included in the EaSIeR tool. For each validation dataset, we used the corresponding cancer-type-specific model: SKCM for the melanoma Gide, Auslander, Riaz, and Liu cohorts; STAD for the gastric cancer Kim cohort; BLCA for the bladder cancer Mariathasan cohort; and GBM for the glioblastoma Cloughesy cohort. To make predictions for each job, the average of the 100 cancer-type-specific models was employed. The predictions of each dataset’s cancer-type-specific models were also compared to models generated for the remaining 17 cancer types.

From the same datasets, the researchers selected several surrogate immunological responses to be used as a measure of ICB effectiveness.

Lapuente-Santana stated

One of the most difficult aspects of our job was properly training the machine learning models. We were able to fix this by looking at alternative immune responses during the training process.

Some of the researchers employed the machine learning approach given in the paper to participate in the “Anti-PD1 Response Prediction DREAM Challenge.”

DREAM is an organization that carries out crowd-based tasks with biomedical algorithms. “We were the first to compete in one of the sub-challenges under the name cSysImmunoOnco team,” Eduati remarks.

The researchers noted,

We applied machine learning to seek for connections between the obtained system-based attributes and the immune response, estimated using 14 predictors (proxies) derived from previous publications. We treated these proxies as individual tasks to be predicted by our machine learning models, and we employed multi-task learning algorithms to jointly learn all tasks.

The researchers discovered that their machine learning model surpasses biomarkers that are already utilized in clinical settings to evaluate ICB therapies.

But why are Eduati, Lapuente-Santana, and their colleagues using mathematical models to tackle a medical treatment problem? Is this going to take the place of the doctor?

Eduati explains

Mathematical models can provide an overview of the interconnection between individual molecules and cells and at the same time predicting a particular patient’s tumor behavior. This implies that immunotherapy with ICB can be personalized in a patient’s clinical setting. The models can aid physicians with their decisions about optimum therapy, it is vital to note that they will not replace them.

Furthermore, the model aids in determining which biological mechanisms are relevant for the biological response.

The researchers noted

Another advantage of our concept is that it does not need a dataset with known patient responses to immunotherapy for model training.

Further testing is required before these findings may be implemented in clinical settings.

Main Source:

Lapuente-Santana, Ó., van Genderen, M., Hilbers, P. A., Finotello, F., & Eduati, F. (2021). Interpretable systems biomarkers predict response to immune-checkpoint inhibitorsPatterns, 100293. https://www.cell.com/patterns/pdfExtended/S2666-3899(21)00126-4

Other Related Articles published in this Open Access Online Scientific Journal include the following:

Inhibitory CD161 receptor recognized as a potential immunotherapy target in glioma-infiltrating T cells by single-cell analysis

Reporter: Dr. Premalata Pati, Ph.D., Postdoc


Immunotherapy may help in glioblastoma survival

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


Deep Learning for In-silico Drug Discovery and Drug Repurposing: Artificial Intelligence to search for molecules boosting response rates in Cancer Immunotherapy: Insilico Medicine @John Hopkins University

Reporter: Aviva Lev-Ari, PhD, RN


Machine Learning (ML) in cancer prognosis prediction helps the researcher to identify multiple known as well as candidate cancer diver genes

Curator and Reporter: Dr. Premalata Pati, Ph.D., Postdoc


AI System Used to Detect Lung Cancer

Reporter: Irina Robu, PhD


Cancer detection and therapeutics

Curator: Larry H. Bernstein, MD, FCAP


Read Full Post »

Deep Learning for In-silico Drug Discovery and Drug Repurposing: Artificial Intelligence to search for molecules boosting response rates in Cancer Immunotherapy: Insilico Medicine @John Hopkins University, Volume 2 (Volume Two: Latest in Genomics Methodologies for Therapeutics: Gene Editing, NGS and BioInformatics, Simulations and the Genome Ontology), Part 1: Next Generation Sequencing (NGS)

Deep Learning for In-silico Drug Discovery and Drug Repurposing: Artificial Intelligence to search for molecules boosting response rates in Cancer Immunotherapy: Insilico Medicine @John Hopkins University

Reporter: Aviva Lev-Ari, PhD, RN

Insilico Medicine –>>> transcriptome-based pathway perturbation analysis

Insilico Medicine, Inc. is a bioinformatics company located at the Emerging Technology Centers at the Johns Hopkins University Eastern campus in Baltimore with R&D resources in Belgium, Russia, and Poland hiring talent through hackathons and competitions. It utilizes advances in genomics, big data analysis and deep learning for in silico drug discovery and drug repurposing for aging and age-related diseases. The company pursues internal drug discovery programs in cancer, Parkinson’s, Alzheimer’s, sarcopenia and geroprotector discovery. Through its Pharmaceutical Artificial Intelligence division the company provides advanced machine learning services to biotechnology, pharmaceutical, and skin care companies.


Brief company video: https://www.youtube.com/watch?v=l62jlwgL3v8.

Insilico Medicine develops a new approach to concomitant cancer immunotherapy

Artificial intelligence to search for molecules boosting response rates in cancer immunotherapy





  • Some of the most promising drugs for cancer therapy called checkpoint inhibitors often result in complete remissions, however, a majority of patients fail cancer immunotherapy with antibodies targeting immune checkpoints, such as CTLA-4 or programmed death-1 (PD-1).
  • Insilico Medicine developed a set of pathway-based signatures of response to popular checkpoint inhibitors
  • Using these markers and a deep learned drug scoring engine Insilico Medicine identified 12 leads that may help increase response to cancer immunotherapy and is seeking industry partnerships to test these leads

Thursday, July 14, 2016, Baltimore, MD — Recent advances in cancer immunotherapy demonstrated complete remission in multiple tumor types including melanoma and lung cancers. Almost every major pharmaceutical company operating in oncology space started multiple programs in immuno-oncology with thousands of clinical trials underway. Immuno-oncology is now a very broad field ranging from treatment of a patient with an engineered antibody to genome editing of patient’s immune cells. Genetic mutations accruing from the inherent genomic instability of tumor cells present neo-antigens that are recognized by the immune system. Cross-presentation of tumor antigens at the immune synapse between antigen-presenting dendritic cells and T lymphocytes can potentially activate an adaptive antitumor immune response, however, tumors continuously evolve to counteract and ultimately defeat such immune surveillance by co-opting and amplifying mechanisms of immune tolerance to evade elimination by the immune system. This prerequisite for tumor progression is enabled by the ability of cancers to produce negative regulators of immune response.

Cancer immunotherapy is currently focused on targeting immune inhibitory checkpoints that control T cell activation, such as CTLA-4 and PD-1. Monoclonal antibodies that block these immune checkpoints (commonly referred to as immune checkpoint inhibitors) can unleash antitumor immunity and produce durable clinical responses in a subset of patients with advanced cancers, such as melanoma and non-small-cell lung cancer. However, these immunotherapeutics are currently constrained by their inability to induce clinical responses in the vast majority of patients and the frequent occurrence of immune-related adverse events. A key limitation of checkpoint inhibitors is that they narrowly focus on modulating the immune synapse but do not address other key molecular determinants that may also be responsible for immune dysfunction.

Immunoresistance often ensues as a result of the concomitant activation of multiple, often overlapping signaling pathways. Therefore, inhibition of multiple, cross-talking pathways involved in survival control with combination therapy is usually more effective in decreasing the likelihood that cancer cells will develop therapeutic resistance than with single agent therapy. While research efforts are now focused on identifying new inhibitory mechanisms that could be targeted to achieve responses in patients with refractory cancers and provide durable and adaptable cancer control, there are outstanding challenges in determining what combination of immunotherapies and conventional therapies will prove beneficial against each tumor type.

“Immunotherapy is the most promising area in oncology resulting in cures, but we need to identify effective combinations of both established methods and new drugs developed specifically to boost response rates. At Insilico Medicine we developed a new method for screening, scoring and personalizing small molecules that may boost response rates to PD-1, PD-L1, CTLA4 and other checkpoint inhibitors. We can identify effective combinations of both established methods and new drugs developed specifically to boost response rates to immunotherapy”, said Artem Artemov, director of computational drug repurposing at Insilico Medicine.

Insilico Medicine, Inc. is one of the leaders in transcriptome-based pathway perturbation analysis. It is also a pioneer in applying cutting edge artificial intelligence techniques to biological and medical data analysis, particularly focused on in silico screening for new compounds against cancer and known drugs which can be repurposed against different cancers. One of the major programs currently ongoing at Insilico Medicine is evaluation of the transcriptional responses to multiple checkpoint inhibitors and analyzing the pathway-level differences in patients who respond and fail to respond to clinically approved checkpoint inhibitors. This novel computational approach is aimed at identifying new drug candidates which can be used in combination with immunotherapy to unleash durable antitumor effect against several types of cancers.

Recently, scientists at Insilico Medicine performed a large in silico screening of compounds that can be administered in combination with anti-PD1 immunotherapy to increase response rates. The researchers collected transcriptomic data from tumors of patients who either responded or failed to respond to standard immunotherapy, using both publically available and internally generated data. Next, they used differential pathway activation analysis and deep learning based approaches to identify transcriptomic signatures predicting the success of immunotherapy in a particular tumor type.

Finally, they analyzed drug-induced transcriptomic effects to screen for the drugs that can robustly drive transcriptomes of tumor cells from non-responsive state to the state responsive to immunotherapy. In other words, researchers developed approach that can predict whether drug of interest would induce a transcriptional signature that characterizes those patients that respond to cancer immunotherapy in non-respondents. This method allows personalizing these drugs to individual patients and specific checkpoint inhibitors. Among the top-scoring drugs, they found several compounds known to increase response rates in combination with cancer immunotherapy. One of the top-scoring compounds included a naturally-occurring substance marketed as a natural product.

The current list of top-scoring leads that may increase response rates to checkpoint inhibitors included 12 small molecules identified using signaling pathway perturbation analysis and annotated using a deeply learned drug scoring system. Insilico Medicine is currently open for partnerships which will allow further testing and validation of the discovered compounds ex vivo on cell cultures established from tumors which respond and failed to respond to immunotherapy, as well as in mice with patient-derived tumor xenografts. This approach may greatly reduce the costs of preclinical trials and significantly shorten the timeframe from a drug prediction to validation and marketing. The compounds, after preclinical and clinical validation, may improve cancer care and dramatically increase the lifespan of cancer patients.

A panel of leads for concomitant immunotherapy is part of a large number of leads developed using DeepPharma™, artificially-intelligent drug discovery engine, which includes a large number of molecules predicted to be effective antineoplastic agents, metabolic regulators, CVD and CNS lead, senolytics and ED drugs. Recently Insilico Medicine published several seminal papers demonstrating proof of concept of utilizing deep learning techniques to predict pharmacological properties of small molecules using transcriptional response data utilizing deep neural networks for biomarker development. “Deep Learning Applications for Predicting Pharmacological Properties of Drugs and Drug Repurposing Using Transcriptomic Data,” a paper published in Molecular Pharmaceuticals received the American Chemical Society Editors’ Choice Award. Another recent collaboration with Biotime, Inc resulted in a launch of Embryonic.AI, deep learned predictor of differentiation state of the sample.



Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.



Read Full Post »