IMPROVE, the latest project to come out of NCI-DOE’s Joint Design of Advanced Computing Solutions for Cancer program, focuses on improving deep learning models to predict the efficacy of cancer treatments.

While progress has been made in formulating and training artificial intelligence and machine learning models to predict drug response, challenges remain in recognizing and understanding new innovations in drug response data models. IMPROVE has been created to address these challenges via two inter-related objectives, or ‘aims’:

Aim 1: Develop protocols for comparing cancer therapeutic response deep learning models and identify attributes that contribute to prediction performance with the goal of IMPROVING future models.

Aim 2: Develop protocols for designing drug and therapeutic screening experiments to generate data for IMPROVING deep learning model performance.