cancerdp

cancerdp prioritizes anticancer drugs using genomic-feature-based models to predict growth inhibition across cancer cell lines for genotype-driven drug selection.

Key Features:

• Genomic Feature Analysis: Integrates genomic data including frequent mutations, gene expression levels, and copy number variations to assess drug responses of 24 anticancer drugs across cancer cell lines.
• Drug Efficacy Prediction: Implements models that predict growth inhibition of cell lines by anticancer drugs with reported correlation coefficients between predicted and actual outcomes ranging from 0.43 to 0.78.
• Tissue-Specific Drug Preferences: Captures tissue-origin-dependent differences in drug efficacy to highlight drugs that preferentially inhibit cell lines derived from particular tissues.
• Personalized Medicine Application: Uses genomic-feature-driven predictions to prioritize drugs aligned with individual genetic profiles for genotype-informed therapy selection.

Scientific Applications:

• Drug Resistance Mechanisms: Enables investigation of associations between altered genomic characteristics and resistance to anticancer drugs.
• Therapeutic Target and Biomarker Identification: Supports identification of genomic alterations correlated with drug sensitivity that may serve as biomarkers or targets.
• Genotype-Driven Therapy Prioritization: Facilitates prioritization of anticancer drugs tailored to specific genetic profiles of cancer cell lines or patient-derived samples.

Methodology:

Uses a genomic-features-based modeling approach that leverages frequent mutations, gene expression levels, and copy number variations to predict growth inhibition of cancer cell lines by 24 anticancer drugs, reporting prediction versus observation correlations of 0.43–0.78.