New NCI-DOE Collaboration Project, IMPROVE, Seeks Deep Learning Model Approaches

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.

An RFP focused on Aim 1 calls on the scientific research community, including computational scientists, data scientists, cancer researchers, and bioinformaticists, to submit their proposal for improving model comparison. The submission deadline is May 9, 2022.

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

An RFI for Aim 2 seeks input related to experimental setup for drug screening studies on cancer models; treatment modalities available for screening experiments; scalability of cancer models and compounds; and cost and time estimates to generate drug screening data for cancer models and compounds. Responses are due by April 15, 2022, at 5:00 p.m. ET.


Vote below about this page’s helpfulness.

Enter the characters shown in the image.