Your browser doesn't support javascript.
loading
Practical Model Selection for Prospective Virtual Screening.
Liu, Shengchao; Alnammi, Moayad; Ericksen, Spencer S; Voter, Andrew F; Ananiev, Gene E; Keck, James L; Hoffmann, F Michael; Wildman, Scott A; Gitter, Anthony.
Afiliación
  • Liu S; Department of Computer Sciences , University of Wisconsin-Madison , Madison , Wisconsin 53706 , United States.
  • Alnammi M; Morgridge Institute for Research , Madison , Wisconsin 53715 , United States.
  • Ericksen SS; Department of Computer Sciences , University of Wisconsin-Madison , Madison , Wisconsin 53706 , United States.
  • Voter AF; Morgridge Institute for Research , Madison , Wisconsin 53715 , United States.
  • Ananiev GE; Small Molecule Screening Facility , University of Wisconsin Carbone Cancer Center , Madison , Wisconsin 53792 , United States.
  • Keck JL; Department of Biomolecular Chemistry , University of Wisconsin School of Medicine and Public Health , Madison , Wisconsin 53706 , United States.
  • Hoffmann FM; Small Molecule Screening Facility , University of Wisconsin Carbone Cancer Center , Madison , Wisconsin 53792 , United States.
  • Wildman SA; Department of Biomolecular Chemistry , University of Wisconsin School of Medicine and Public Health , Madison , Wisconsin 53706 , United States.
  • Gitter A; Small Molecule Screening Facility , University of Wisconsin Carbone Cancer Center , Madison , Wisconsin 53792 , United States.
J Chem Inf Model ; 59(1): 282-293, 2019 01 28.
Article en En | MEDLINE | ID: mdl-30500183
Virtual (computational) high-throughput screening provides a strategy for prioritizing compounds for experimental screens, but the choice of virtual screening algorithm depends on the data set and evaluation strategy. We consider a wide range of ligand-based machine learning and docking-based approaches for virtual screening on two protein-protein interactions, PriA-SSB and RMI-FANCM, and present a strategy for choosing which algorithm is best for prospective compound prioritization. Our workflow identifies a random forest as the best algorithm for these targets over more sophisticated neural network-based models. The top 250 predictions from our selected random forest recover 37 of the 54 active compounds from a library of 22,434 new molecules assayed on PriA-SSB. We show that virtual screening methods that perform well on public data sets and synthetic benchmarks, like multi-task neural networks, may not always translate to prospective screening performance on a specific assay of interest.
Asunto(s)

Texto completo: 1 Banco de datos: MEDLINE Asunto principal: Evaluación Preclínica de Medicamentos / Simulación del Acoplamiento Molecular / Aprendizaje Automático Tipo de estudio: Diagnostic_studies / Prognostic_studies / Risk_factors_studies / Screening_studies Idioma: En Revista: J Chem Inf Model Asunto de la revista: INFORMATICA MEDICA / QUIMICA Año: 2019 Tipo del documento: Article País de afiliación: Estados Unidos

Texto completo: 1 Banco de datos: MEDLINE Asunto principal: Evaluación Preclínica de Medicamentos / Simulación del Acoplamiento Molecular / Aprendizaje Automático Tipo de estudio: Diagnostic_studies / Prognostic_studies / Risk_factors_studies / Screening_studies Idioma: En Revista: J Chem Inf Model Asunto de la revista: INFORMATICA MEDICA / QUIMICA Año: 2019 Tipo del documento: Article País de afiliación: Estados Unidos