In Need of Bias Control - New publication in Journal of Chemical Information and Modeling
27. März 2019
Machine Learning gained a lot of attention in many areas of research right now. Not surprisingly, this is also the case on Drug Discovery. In the recent JCIM Special Issue Machine Learning in Drug Discovery, we present a study on the risk of learning non-causal bias when applying ML in structure-based design. Using ML algorithms require much care to estimate their ability to generalize and predict. All the details can be found here.