caa a22 4500 467938776 CHVBK 20180406153005.0 cr unu---uuuuu 170328e20061201xx s 000 0 eng 10.1007/s10822-006-9085-8 doi (NATIONALLICENCE)springer-10.1007/s10822-006-9085-8 Feature-map vectors: a new class of informative descriptors for computational drug discovery [Elektronische Daten] [Gregory Landrum, Julie Penzotti, Santosh Putta] In order to develop robust machine-learning or statistical models for predicting biological activity, descriptors that capture the essence of the protein-ligand interaction are required. In the absence of structural information from X-ray or NMR experiments, deriving informative descriptors can be difficult. We have developed feature-map vectors (FMVs), a new class of descriptors based on chemical features, to address this challenge. FMVs, which are derived from the conformational models of a few actives, are low dimensional, problem specific, and highly interpretable. By using shape-based alignments and scoring with chemical features, FMVs can combine information about a molecule's shape and the pharmacophores it can match. In five validation studies, bag classifiers built using FMVs have shown high enrichments for identifying actives for five diverse targets: CDK2, 5-HT3, DHFR, thrombin, and ACE. The interpretability of these descriptors has been demonstrated for CDK2 and 5-HT3, where the method automatically discovers the standard literature pharmacophore. Springer Science+Business Media, LLC, 2007 Chemical features nationallicence Descriptor nationallicence Machine learning nationallicence Molecular shape nationallicence Pharmacophores nationallicence Landrum Gregory Novartis Institutes For BioMedical Research, CH-4002, Basel, Switzerland aut Penzotti Julie 16th Ave NE, 5731, 98105, Seattle, WA, USA aut Putta Santosh Telik Inc., 3165 Porter Drive, 94304, Palo Alto, CA, USA aut Journal of Computer-Aided Molecular Design Kluwer Academic Publishers 20/12(2006-12-01), 751-762 0920-654X 20:12<751 2006 20 10822 https://doi.org/10.1007/s10822-006-9085-8 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s10822-006-9085-8 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Landrum Gregory Novartis Institutes For BioMedical Research, CH-4002, Basel, Switzerland aut NATIONALLICENCE 700 1- Penzotti Julie 16th Ave NE, 5731, 98105, Seattle, WA, USA aut NATIONALLICENCE 700 1- Putta Santosh Telik Inc., 3165 Porter Drive, 94304, Palo Alto, CA, USA aut NATIONALLICENCE 773 0- Journal of Computer-Aided Molecular Design Kluwer Academic Publishers 20/12(2006-12-01), 751-762 0920-654X 20:12<751 2006 20 10822 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer