New machine learning techniques boost predictions for virtual drug screening with less data

A novel way of using kernel methods in biomedical data analysis has been developed by researchers at the Eric and Wendy Schmidt Center at the Broad Institute of MIT and Harvard University, who published a paper in Nature Communications about the wide range of applications for kernel methods including virtual drug screening.

Senior author of the paper, principal investigator in the Abdul Latif Jameel Clinic for Machine Learning in Health (Jameel Clinic), Caroline Uhler, describes the team's transfer learning framework, which predicts drug efficacy in cancer care.

"Before our paper, there was no transfer learning method for kernel methods that could scale to the large datasets of most interest in the biomedical field and beyond. We've shown for the first time that transfer learning using kernels in these settings is possible and I think that is really exciting," says Caroline.