What is the IMPROVE project?

IMPROVE aims to establish methodology to systematically and rigorously compare supervised learning models. To this end, IMPROVE has four components:

1. IMPROVE Framework: standardized scaffolding for machine learning models, written in Python

2. IMPROVE Evaluation Schemes: workflows to evaluated and compare models

3. IMPROVE Benchmark Datasets: a collection of standardized data for each application to allow for benchmarking of models

4. IMPROVE Community Curated Models: models for each application from the scientific communitity that have been curated into the IMPROVE framework

IMPROVE can be applied to a variety of supervised learning models. We have begun with the Drug Response Prediction problem, standardizing community models that predict pan-cancer, pan-drug, single drug response for precision oncology with a standardized benchmark dataset.

For more information

• Background
• Future Directions
• Acknowledgments

Access the code base https://github.com/JDACS4C-IMPROVE/

References

1. A. Partin et al. “Deep learning methods for drug response prediction in cancer: Predominant and emerging trends”, Frontiers in Medicine, Section Prediction Oncology, 2023