BipotentR

BipotentR identifies cancer cell-specific regulators that modulate tumor immunity and oncogenic pathways to discover immune-metabolic antitumor drug targets.

Key Features:

• Multiomics Integration: Integrates multiomics data to identify candidate immune-metabolic regulators influencing both tumor immunity and oncogenic pathways.
• Machine Learning and Deep Neural Networks: Applies machine learning and deep neural network approaches for predictive modeling and feature discovery.
• Patient Stratification: Stratifies melanoma patients by predicted response to anti-PD-1 therapy using model-derived biomarkers.
• Candidate Identification: Identified 38 candidate immune-metabolic regulators for evaluation as potential drug targets.
• Pathway Versatility: Applies analyses to immune-metabolic pathways as well as angiogenesis and growth suppressor evasion pathways.
• ESRRA Detection: Identifies Estrogen-Related Receptor Alpha (ESRRA) as activated in immunotherapy-resistant tumors.
• Functional Validation (reported): Reports tumor-suppressive effects of identified targets via energy metabolism suppression, cytokine induction, proinflammatory macrophage polarization, and antigen-presentation stimulation.

Scientific Applications:

• Drug Target Discovery: Discovery of immune-metabolic regulators as candidate antitumor drug targets that concurrently modulate tumor immunity and oncogenic signaling.
• Biomarker Development: Development of predictive biomarkers for anti-PD-1 therapy response in melanoma.
• Pathway Analysis for Therapeutics: Analysis of angiogenesis, growth suppressor evasion, and ESRRA-associated mechanisms to inform therapeutic strategy development.

Methodology:

In silico analysis of multiomics data and predictive modeling using machine learning and deep neural networks.