no code implementations • 25 Mar 2022 • Carl Poelking, Gianni Chessari, Christopher W. Murray, Richard J. Hall, Lucy Colwell, Marcel Verdonk
In this study we derive ML models from over 50 fragment-screening campaigns to introduce two important elements that we believe are absent in most -- if not all -- ML studies of this type reported to date: First, alongside the observed hits we use to train our models, we incorporate true misses and show that these experimentally validated negative data are of significant importance to the quality of the derived models.