%0 Journal Article %1 Brown2021-om %A Brown, Benjamin P %A Mendenhall, Jeffrey %A Geanes, Alexander R %A Meiler, Jens %D 2021 %I American Chemical Society (ACS) %J J. Chem. Inf. Model. %K topic_lifescience %N 2 %P 603--620 %T General purpose structure-based drug discovery neural network score functions with human-interpretable pharmacophore maps %V 61 %X The BioChemical Library (BCL) is an academic open-source cheminformatics toolkit comprising ligand-based virtual high-throughput screening (vHTS) tools such as quantitative structure-activity/property relationship (QSAR/QSPR) modeling, small molecule flexible alignment, small molecule conformer generation, and more. Here, we expand the capabilities of the BCL to include structure-based virtual screening. We introduce two new score functions, BCL-AffinityNet and BCL-DockANNScore, based on novel distance-dependent signed protein-ligand atomic property correlations. Both metrics are conventional feed-forward dropout neural networks trained on the new descriptors. We demonstrate that BCL-AffinityNet is one of the top performing score functions on the comparative assessment of score functions 2016 affinity prediction and affinity ranking tasks. We also demonstrate that BCL-AffinityNet performs well on the CSAR-NRC HiQ I and II test sets. Furthermore, we demonstrate that BCL-DockANNScore is competitive with multiple state-of-the-art methods on the docking power and screening power tasks. Finally, we show how our models can be decomposed into human-interpretable pharmacophore maps to aid in hit/lead optimization. Altogether, our results expand the utility of the BCL for structure-based scoring to aid small molecule discovery and design. BCL-AffinityNet, BCL-DockANNScore, and the pharmacophore mapping application, as well as the remainder of the BCL cheminformatics toolkit, are freely available with an academic license at the BCL Commons site hosted on http://meilerlab.org/.

@article{Brown2021-om, abstract = {The BioChemical Library (BCL) is an academic open-source cheminformatics toolkit comprising ligand-based virtual high-throughput screening (vHTS) tools such as quantitative structure-activity/property relationship (QSAR/QSPR) modeling, small molecule flexible alignment, small molecule conformer generation, and more. Here, we expand the capabilities of the BCL to include structure-based virtual screening. We introduce two new score functions, BCL-AffinityNet and BCL-DockANNScore, based on novel distance-dependent signed protein-ligand atomic property correlations. Both metrics are conventional feed-forward dropout neural networks trained on the new descriptors. We demonstrate that BCL-AffinityNet is one of the top performing score functions on the comparative assessment of score functions 2016 affinity prediction and affinity ranking tasks. We also demonstrate that BCL-AffinityNet performs well on the CSAR-NRC HiQ I and II test sets. Furthermore, we demonstrate that BCL-DockANNScore is competitive with multiple state-of-the-art methods on the docking power and screening power tasks. Finally, we show how our models can be decomposed into human-interpretable pharmacophore maps to aid in hit/lead optimization. Altogether, our results expand the utility of the BCL for structure-based scoring to aid small molecule discovery and design. BCL-AffinityNet, BCL-DockANNScore, and the pharmacophore mapping application, as well as the remainder of the BCL cheminformatics toolkit, are freely available with an academic license at the BCL Commons site hosted on http://meilerlab.org/.}, added-at = {2024-09-10T11:56:37.000+0200}, author = {Brown, Benjamin P and Mendenhall, Jeffrey and Geanes, Alexander R and Meiler, Jens}, biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/29d1dc328045415fe289e9366c6efe7a5/scadsfct}, copyright = {http://pubs.acs.org/page/policy/authorchoice\_ccbyncnd\_termsofuse.html}, interhash = {66e39e5d1a9fad94b97c10ec0c138ca0}, intrahash = {9d1dc328045415fe289e9366c6efe7a5}, journal = {J. Chem. Inf. Model.}, keywords = {topic_lifescience}, language = {en}, month = feb, number = 2, pages = {603--620}, publisher = {American Chemical Society (ACS)}, timestamp = {2024-09-10T14:02:01.000+0200}, title = {General purpose structure-based drug discovery neural network score functions with human-interpretable pharmacophore maps}, volume = 61, year = 2021 }