comboSC

comboSC optimizes personalized tumor combination therapy by analyzing single-cell RNA sequencing data to stratify tumor and immune microenvironments and to prioritize synergistic drug and small-molecule combinations.

Key Features:

• Single-Cell Transcriptome Utilization: Leverages single-cell RNA sequencing (scRNA-seq) to characterize individual tumor cells and their surrounding immune microenvironments.
• Stratification and Evaluation: Performs quantitative evaluation and stratification of personalized immune microenvironments to identify context-specific therapeutic targets.
• Integration with Immune Checkpoint Inhibitors: Identifies small molecules and drug combinations that can be paired with immune checkpoint inhibitors to modulate anti-tumor immune responses.
• Bipartition Graph Optimization: Employs bipartition graph optimization to prioritize potential drug combinations from a large candidate space.
• Validation and Application: Validates predictions using literature evidence, clinical trial data mining, perturbation of patient-derived cell line data, and in vivo sample testing, and was applied to 119 single-cell transcriptome datasets across 15 cancer types.

Scientific Applications:

• Personalized combination therapy prediction: Predicts synergistic drug and small-molecule combinations tailored to individual patients' tumor and immune profiles derived from scRNA-seq.
• Prioritization to reduce screening space: Prioritizes candidate combinations to reduce experimental screening time and focus validation efforts on high-confidence therapies.

Methodology:

Analyzes scRNA-seq data for quantitative immune microenvironment evaluation and stratification, applies bipartition graph optimization to prioritize drug combinations, and mines literature and clinical trial data for validation evidence.