Premium
Modeling Choices for Virtual Screening Hit Identification
Author(s) -
Bergeron Charles,
Krein Michael,
Moore Gregory,
Breneman Curt M.,
Bennett Kristin P.
Publication year - 2011
Publication title -
molecular informatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.481
H-Index - 68
eISSN - 1868-1751
pISSN - 1868-1743
DOI - 10.1002/minf.201100092
Subject(s) - pubchem , computer science , identification (biology) , virtual screening , support vector machine , machine learning , in silico , exploit , cheminformatics , data mining , variety (cybernetics) , drug discovery , chemical database , artificial intelligence , computational biology , bioinformatics , biochemistry , chemistry , botany , computer security , gene , biology
Making suitable modeling choices is crucial for successful in silico drug design, and one of the most important of these is the proper extraction and curation of data from qHTS screens, and the use of optimized statistical learning methods to obtain valid models. More specifically, we aim to learn the top‐1 % most potent compounds against a variety of targets in a procedure we call virtual screening hit identification (VISHID). To do so, we exploit quantitative high‐throughput screens (qHTS) obtained from PubChem, descriptors derived from molecular structures, and support vector machines (SVM) for model generation. Our results illustrate how an appreciation of subtle issues underlying qHTS data extraction and the resulting SVM models created using these data can enhance the effectiveness of solutions and, in doing so, accelerate drug discovery.