Predictive modeling codes for CTD-squared BeatAML DREAM Challenge.
The goal of this challenge is to define patient subpopulations tailored to individual treatments by discovering (genomic and transcriptomic) biomarkers of drug sensitivity, as evaluated on an unpublished cohort of patients from the BeatAML project. Specifically, there are two sub-challenges:
- Sub-Challenge 1 (SC1): Predict quantitative ex vivo drug sensitivity [represented by area under the dose response curve (AUC) values] to targeted and chemotherapeutic agents based on genomic variants, gene expression, and clinical data.
- Sub-Challenge 2 (SC2): Predict clinical response [represented as days of survival after inclusion in the study] based on ex vivo drug sensitivity data, genomic variants, gene expression, and clinical data.