Dataset Information

Machine learning reveals genetic modifiers of the immune microenvironment of cancer.

ABSTRACT: Heritability in the immune tumor microenvironment (iTME) has been widely observed yet remains largely uncharacterized. Here, we developed a machine learning approach to map iTME modifiers within loci from genome-wide association studies (GWASs) for breast cancer (BrCa) incidence. A random forest model was trained on a positive set of immune-oncology (I-O) targets, and then used to assign I-O target probability scores to 1,362 candidate genes in linkage disequilibrium with 155 BrCa GWAS loci. Cluster analysis of the most probable candidates revealed two subfamilies of genes related to effector functions and adaptive immune responses, suggesting that iTME modifiers impact multiple aspects of anticancer immunity. Two of the top ranking BrCa candidates, LSP1 and TLR1, were orthogonally validated as iTME modifiers using BrCa patient biopsies and comparative mapping studies, respectively. Collectively, these data demonstrate a robust and flexible framework for functionally fine-mapping GWAS risk loci to identify translatable therapeutic targets.

SUBMITTER: Riley-Gillis B

PROVIDER: S-EPMC10470213 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning reveals genetic modifiers of the immune microenvironment of cancer.

Riley-Gillis Bridget B Tsaih Shirng-Wern SW King Emily E Wollenhaupt Sabrina S Reeb Jonas J Peck Amy R AR Wackman Kelsey K Lemke Angela A Rui Hallgeir H Dezso Zoltan Z Flister Michael J MJ

iScience 20230809 9

Heritability in the immune tumor microenvironment (iTME) has been widely observed yet remains largely uncharacterized. Here, we developed a machine learning approach to map iTME modifiers within loci from genome-wide association studies (GWASs) for breast cancer (BrCa) incidence. A random forest model was trained on a positive set of immune-oncology (I-O) targets, and then used to assign I-O target probability scores to 1,362 candidate genes in linkage disequilibrium with 155 BrCa GWAS loci. Clu ...[more]

PMID: 37664640

Similar Datasets

Project description:BackgroundOvarian cancer (OC) is a globally prevalent malignancy with significant morbidity and mortality, yet its heterogeneity poses challenges in treatment and prognosis. Recognizing the crucial role of the tumor microenvironment (TME) in OC progression, this study leverages integrative multi-omics and machine learning to uncover TME-associated prognostic biomarkers, paving the way for more personalized therapeutic interventions.MethodsEmploying a rigorous multi-omics approach, this study analyzed single-cell RNA sequencing (scRNA-seq) data from OC and normal tissue samples, including high-grade serous OC (HGSOC) from the Gene Expression Omnibus (GEO: GSE184880) and The Cancer Genome Atlas (TCGA) OC cohort, utilizing the Seurat package to annotate 700 TME-related genes. A prognostic model was developed using the least absolute shrinkage and selection operator (LASSO) regression and independently validated against similarly composed HGSOC datasets. Comprehensive gene expression and immune cell infiltration analyses were conducted, employing advanced algorithms like xCell to delineate the immune landscape of HGSOC.ResultsOur investigation unveiled distinctive immune cell infiltration patterns and gene expression profiles within the TME of HGSOC. Notably, the prevalence of exhausted CD8+ T cells in high-risk patient samples emerged as a critical finding, underscoring the dualistic nature of the immune response in OC. The developed prognostic model, incorporating immune cell markers, exhibited robust predictive accuracy for patient outcomes, showing significant correlations with immunotherapy responses and drug sensitivities.ConclusionsThis study presents a groundbreaking exploration of the OC TME, offering vital insights into its molecular intricacies. By systematically deciphering the TME-associated gene signatures, the research illuminates the potential of these biomarkers in refining patient prognosis and guiding treatment strategies. Our findings underscore the necessity for personalized medicine in OC treatment, potentially enhancing patient survival rates and quality of life. This study marks a significant stride in understanding and combatting the complexities of OC.

Project description:BackgroundProstate cancer (PCa) incidence and mortality rates are rising, necessitating precise prognostic tools to guide personalized treatment. Dysregulation of programmed cell death pathways in tumor suppression and cancer development has garnered increasing attention, providing a new research direction for identifying biomarkers and potential therapeutic targets.MethodsIntegrating multiple database resources, we constructed and optimized a prognostic signature based on the expression of programmed cell death-related genes (PCDRG) using ten machine learning algorithms. Model performance and prognostic effects were further evaluated. We analyzed the relationships between signature and clinicopathological features, somatic mutations, drug sensitivity, and the tumor immune microenvironment, and constructed a nomogram. The expression level of PCDRGs were evaluated and compared.ResultsOf 1560 PCDRGs, 149 were differentially expressed in PCa, with 34 associated with biochemical recurrence. The PCDRG-derived index (PCDI), constructed using the random forest algorithm, exhibited optimal prognostic performance, successfully stratifying PCa patients into two groups with significant prognostic differences. Patients with high PCDI scores exhibited poorer survival and lower immunotherapy benefit. PCDI was closely associated with the infiltration of specific immune cells, particularly positive correlations with macrophages and T helper cells, and negative correlations with neutrophils, suggesting that PCDI may influence the tumor immune microenvironment, thereby affecting patient prognosis and treatment response. PCDI was associated with age, pathological stage, somatic mutations, and drug sensitivity. The PCDI-based nomogram demonstrated excellent performance in predicting biochemical recurrence in PCa patients. Finally, the differential expression of these PCDRGs was verified based on cell lines and PCa patient expression profile data.ConclusionThis study developed an effective prognostic indicator for prostate cancer, PCDI, using machine learning approaches. PCDI reflects the link between aberrant programmed cell death pathways and disease progression and treatment response.

Dataset Information

Machine learning reveals genetic modifiers of the immune microenvironment of cancer.

Publications

Machine learning reveals genetic modifiers of the immune microenvironment of cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets