Researchers have developed a new machine learning approach called D2ML for direct-to-biology small molecule screening. This method is designed to handle the unique challenges of D2B data, such as uncertain concentrations, to improve predictions and guide the discovery of more effective compounds. D2ML models can predict activity from single-point screens and relative potency across targets, even with crude dose-response assays. In experiments, D2ML guided the selection of new compounds that demonstrated improved potency and selectivity compared to existing molecules. AI
IMPACT Enhances AI's role in drug discovery by improving the efficiency and effectiveness of small molecule screening.
RANK_REASON The cluster contains a research paper detailing a new machine learning model and methodology. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →