Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Deep neural network modeling identifies biomarkers of response to immune-checkpoint therapy.

ABSTRACT: Immunotherapy has shown significant promise as a treatment for cancer, such as lung cancer and melanoma. However, only 10%-30% of the patients respond to treatment with immune checkpoint blockers (ICBs), underscoring the need for biomarkers to predict response to immunotherapy. Here, we developed DeepGeneX, a computational framework that uses advanced deep neural network modeling and feature elimination to reduce single-cell RNA-seq data on ∼26,000 genes to six of the most important genes (CCR7, SELL, GZMB, WARS, GZMH, and LGALS1), that accurately predict response to immunotherapy. We also discovered that the high LGALS1 and WARS-expressing macrophage population represent a biomarker for ICB therapy nonresponders, suggesting that these macrophages may be a target for improving ICB response. Taken together, DeepGeneX enables biomarker discovery and provides an understanding of the molecular basis for the model's predictions.

SUBMITTER: Kang Y

PROVIDER: S-EPMC9044175 | biostudies-literature | 2022 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Deep neural network modeling identifies biomarkers of response to immune-checkpoint therapy.

Kang Yuqi Y Vijay Siddharth S Gujral Taranjit S TS

iScience 20220409 5

Immunotherapy has shown significant promise as a treatment for cancer, such as lung cancer and melanoma. However, only 10%-30% of the patients respond to treatment with immune checkpoint blockers (ICBs), underscoring the need for biomarkers to predict response to immunotherapy. Here, we developed DeepGeneX, a computational framework that uses advanced deep neural network modeling and feature elimination to reduce single-cell RNA-seq data on ∼26,000 genes to six of the most important genes (<i>CC ...[more]

PMID: 35494249

Similar Datasets

TME-NET: an interpretable deep neural network for predicting pan-cancer immune checkpoint inhibitor responses.

Project description:Immunotherapy with immune checkpoint inhibitors (ICIs) is increasingly used to treat various tumor types. Determining patient responses to ICIs presents a significant clinical challenge. Although components of the tumor microenvironment (TME) are used to predict patient outcomes, comprehensive assessments of the TME are frequently overlooked. Using a top-down approach, the TME was divided into five layers-outcome, immune role, cell, cellular component, and gene. Using this structure, a neural network called TME-NET was developed to predict responses to ICIs. Model parameter weights and cell ablation studies were used to investigate the influence of TME components. The model was developed and evaluated using a pan-cancer cohort of 948 patients across four cancer types, with Area Under the Curve (AUC) and accuracy as performance metrics. Results show that TME-NET surpasses established models such as support vector machine and k-nearest neighbors in AUC and accuracy. Visualization of model parameter weights showed that at the cellular layer, Th1 cells enhance immune responses, whereas myeloid-derived suppressor cells and M2 macrophages show strong immunosuppressive effects. Cell ablation studies further confirmed the impact of these cells. At the gene layer, the transcription factors STAT4 in Th1 cells and IRF4 in M2 macrophages significantly affect TME dynamics. Additionally, the cytokine-encoding genes IFNG from Th1 cells and ARG1 from M2 macrophages are crucial for modulating immune responses within the TME. Survival data from immunotherapy cohorts confirmed the prognostic ability of these markers, with p-values <0.01. In summary, TME-NET performs well in predicting immunotherapy responses and offers interpretable insights into the immunotherapy process. It can be customized at https://immbal.shinyapps.io/TME-NET.

| S-EPMC11337220 | biostudies-literature

In-depth profiling of tumor tissue derived from malignant pleural mesothelioma patients identifies potential biomarkers predicting response to immune-checkpoint inhibitor therapy.

Project description: Not available

| S-EPMC11298826 | biostudies-literature

Molecular imaging biomarkers for immune checkpoint inhibitor therapy.

Project description:Immune checkpoint inhibitors (ICIs) have substantially changed the field of oncology over the past few years. ICIs offer an alternative treatment strategy by exploiting the patients' immune system, resulting in a T cell mediated anti-tumor response. These therapies are effective in multiple different tumor types. Unfortunately, a substantial group of patients do not respond to ICIs. Molecular imaging, using single-photon emission computed tomography (SPECT) and positron emission tomography (PET), can provide non-invasive whole-body visualization of tumor and immune cell characteristics and might support patient selection or response evaluations for ICI therapies. In this review, recent studies with 18F-fluorodeoxyglucose-PET imaging, imaging of immune checkpoints and imaging of immune cells will be discussed. These studies are until now mainly exploratory, but the first results suggest that molecular imaging biomarkers could have a role in the evaluation of ICI therapy.

| S-EPMC6993216 | biostudies-literature

Biomarkers of therapeutic response with immune checkpoint inhibitors.

Project description:Immune checkpoint inhibitors (ICPIs) have revolutionized the treatment paradigm of a wide range of malignancies with durable responses seen in even advanced, refractory cancers. Unfortunately, only a small proportion of patients with cancer derive meaningful benefit to ICPI therapy, and its use is also limited by significant immune and financial toxicities. Thus, there is a critical need for the development of biomarkers to reliably predict response to ICPI therapy. Only a few biomarkers are validated and approved for use with currently Food and Drug administration (FDA)-approved ICPIs. The development and broad application of biomarkers is limited by the lack of complete understanding of the complex interactions of tumor-host environment, the effect of immunotherapies on these already complex interactions, a lack of standardization and interpretation of biomarker assays across tumor types. Despite these challenges, the field of identifying predictive biomarkers is evolving at an unprecedented pace leaving the clinician responsible for identifying the patients that may derive optimal benefit from ICPIs. In this review, we provide clinicians with a current and practical update on the key, clinically relevant biomarkers of response to ICPIs. We categorize the current and emerging biomarkers of response to ICPIs in four major categories that govern anticancer response-the inflamed tumor, tumor antigens, immune suppression, and overall host environment.

| S-EPMC8267267 | biostudies-literature

Interpretable systems biomarkers predict response to immune-checkpoint inhibitors.

Project description:Cancer cells can leverage several cell-intrinsic and -extrinsic mechanisms to escape immune system recognition. The inherent complexity of the tumor microenvironment, with its multicellular and dynamic nature, poses great challenges for the extraction of biomarkers of immune response and immunotherapy efficacy. Here, we use RNA-sequencing (RNA-seq) data combined with different sources of prior knowledge to derive system-based signatures of the tumor microenvironment, quantifying immune-cell composition and intra- and intercellular communications. We applied multi-task learning to these signatures to predict different hallmarks of immune responses and derive cancer-type-specific models based on interpretable systems biomarkers. By applying our models to independent RNA-seq data from cancer patients treated with PD-1/PD-L1 inhibitors, we demonstrated that our method to Estimate Systems Immune Response (EaSIeR) accurately predicts therapeutic outcome. We anticipate that EaSIeR will be a valuable tool to provide a holistic description of immune responses in complex and dynamic systems such as tumors using available RNA-seq data.

| S-EPMC8369166 | biostudies-literature

Genetic and Epigenetic Biomarkers of Immune Checkpoint Blockade Response.

Project description:Checkpoint inhibitor therapy constitutes a promising cancer treatment strategy that targets the immune checkpoints to re-activate silenced T cell cytotoxicity. In recent pivotal trials, immune checkpoint blockade (ICB) demonstrated durable responses and acceptable toxicity, resulting in the regulatory approval of 8 checkpoint inhibitors to date for 15 cancer indications. However, up to ~85% of patients present with innate or acquired resistance to ICB, limiting its clinical utility. Current response biomarker candidates, including DNA mutation and neoantigen load, immune profiles, as well as programmed death-ligand 1 (PD-L1) expression, are only weak predictors of ICB response. Thus, identification of novel, more predictive biomarkers that could identify patients who would benefit from ICB constitutes one of the most important areas of immunotherapy research. Aberrant DNA methylation (5mC) and hydroxymethylation (5hmC) were discovered in multiple cancers, and dynamic changes of the epigenomic landscape have been identified during T cell differentiation and activation. While their role in cancer immunosuppression remains to be elucidated, recent evidence suggests that 5mC and 5hmC may serve as prognostic and predictive biomarkers of ICB-sensitive cancers. In this review, we describe the role of epigenetic phenomena in tumor immunoediting and other immune evasion related processes, provide a comprehensive update of the current status of ICB-response biomarkers, and highlight promising epigenomic biomarker candidates.

| S-EPMC7019273 | biostudies-literature

Modelling of Immune Checkpoint Network Explains Synergistic Effects of Combined Immune Checkpoint Inhibitor Therapy and the Impact of Cytokines in Patient Response.

Project description:After the success of the new generation of immune therapies, immune checkpoint receptors have become one important center of attention of molecular oncologists. The initial success and hopes of anti-programmed cell death protein 1 (anti-PD1) and anti-cytotoxic T-lymphocyte-associated protein 4 (anti-CTLA4) therapies have shown some limitations since a majority of patients have continued to show resistance. Other immune checkpoints have raised some interest and are under investigation, such as T cell immunoglobulin and ITIM (immunoreceptor tyrosine-based inhibition motif) domain (TIGIT), inducible T-cell costimulator (ICOS), and T cell immunoglobulin and mucin domain-containing protein 3 (TIM3), which appear as promising targets for immunotherapy. To explore their role and study possible synergetic effects of these different checkpoints, we have built a model of T cell receptor (TCR) regulation including not only PD1 and CTLA4, but also other well studied checkpoints (TIGIT, TIM3, lymphocyte activation gene 3 (LAG3), cluster of differentiation 226 (CD226), ICOS, and tumour necrosis factor receptors (TNFRs)) and simulated different aspects of T cell biology. Our model shows good correspondence with observations from available experimental studies of anti-PD1 and anti-CTLA4 therapies and suggest efficient combinations of immune checkpoint inhibitors (ICI). Among the possible candidates, TIGIT appears to be the most promising drug target in our model. The model predicts that signal transducer and activator of transcription 1 (STAT1)/STAT4-dependent pathways, activated by cytokines such as interleukin 12 (IL12) and interferon gamma (IFNG), could improve the effect of ICI therapy via upregulation of Tbet, suggesting that the effect of the cytokines related to STAT3/STAT1 activity is dependent on the balance between STAT1 and STAT3 downstream signalling.

| S-EPMC7761568 | biostudies-literature

Identifying biomarkers to predict immune-checkpoint therapy response-is it a reality or a distant dream?

Project description: Not available

| S-EPMC11651762 | biostudies-literature

Exploring histological predictive biomarkers for immune checkpoint inhibitor therapy response in non-small cell lung cancer.

Project description:Treatment challenges persist in advanced lung cancer despite the development of therapies beyond the traditional platinum-based chemotherapy. The early 2000s marked a shift to tyrosine kinase inhibitors targeting epidermal growth factor receptor, ushering in personalized genetic-based treatment. A further significant advance was the development of immune checkpoint inhibitors (ICIs), especially for non-small cell lung cancer. These target programmed death-ligand 1 (PD-L1) and cytotoxic T lymphocyte antigen 4, which enhanced the immune response against tumor cells. However, not all patients respond, and immune-related toxicities arise. This review emphasizes identifying biomarkers for ICI response prediction. While PD-L1 is a widely used, validated biomarker, its predictive accuracy is imperfect. Investigating tumor-infiltrating lymphocytes, tertiary lymphoid structure, and emerging biomarkers such as high endothelial venule, Human leukocyte antigen class I, T-cell immunoreceptors with Ig and ITIM domains, and lymphocyte activation gene-3 counts is promising. Understanding and exploring additional predictive biomarkers for ICI response are crucial for enhancing patient stratification and overall care in lung cancer treatment.

| S-EPMC10948248 | biostudies-literature

TG468: a text graph convolutional network for predicting clinical response to immune checkpoint inhibitor therapy.

Project description:Enhancing cancer treatment efficacy remains a significant challenge in human health. Immunotherapy has witnessed considerable success in recent years as a treatment for tumors. However, due to the heterogeneity of diseases, only a fraction of patients exhibit a positive response to immune checkpoint inhibitor (ICI) therapy. Various single-gene-based biomarkers and tumor mutational burden (TMB) have been proposed for predicting clinical responses to ICI; however, their predictive ability is limited. We propose the utilization of the Text Graph Convolutional Network (GCN) method to comprehensively assess the impact of multiple genes, aiming to improve the predictive capability for ICI response. We developed TG468, a Text GCN model framing drug response prediction as a text classification task. By combining natural language processing (NLP) and graph neural network techniques, TG468 effectively handles sparse and high-dimensional exome sequencing data. As a result, TG468 can distinguish survival time for patients who received ICI therapy and outperforms single gene biomarkers, TMB and some classical machine learning models. Additionally, TG468's prediction results facilitate the identification of immune status differences among specific patient types in the Cancer Genome Atlas dataset, providing a rationale for the model's predictions. Our approach represents a pioneering use of a GCN model to analyze exome data in patients undergoing ICI therapy and offers inspiration for future research using NLP technology to analyze exome sequencing data.

| S-EPMC10886443 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data