Your browser doesn't support javascript.
loading
Is Multitask Deep Learning Practical for Pharma?
Ramsundar, Bharath; Liu, Bowen; Wu, Zhenqin; Verras, Andreas; Tudor, Matthew; Sheridan, Robert P; Pande, Vijay.
Afiliación
  • Ramsundar B; Department of Computer Science, Stanford University , Stanford, California 94305, United States.
  • Liu B; Department of Chemistry, Stanford University , Stanford, California 94305, United States.
  • Wu Z; Department of Chemistry, Stanford University , Stanford, California 94305, United States.
  • Verras A; Chemistry Capabilities and Screening, Merck & Co., Inc. , 2000 Galloping Hill Road, Kenilworth, New Jersey 07033, United States.
  • Tudor M; Chemistry Capabilities and Screening, Merck & Co., Inc. , 770 Sumneytown Pike, West Point, Pennsylvania 19846, United States.
  • Sheridan RP; Chemistry Capabilities and Screening, Merck & Co., Inc. , 2000 Galloping Hill Road, Kenilworth, New Jersey 07033, United States.
  • Pande V; Department of Chemistry, Stanford University , Stanford, California 94305, United States.
J Chem Inf Model ; 57(8): 2068-2076, 2017 08 28.
Article en En | MEDLINE | ID: mdl-28692267
Multitask deep learning has emerged as a powerful tool for computational drug discovery. However, despite a number of preliminary studies, multitask deep networks have yet to be widely deployed in the pharmaceutical and biotech industries. This lack of acceptance stems from both software difficulties and lack of understanding of the robustness of multitask deep networks. Our work aims to resolve both of these barriers to adoption. We introduce a high-quality open-source implementation of multitask deep networks as part of the DeepChem open-source platform. Our implementation enables simple python scripts to construct, fit, and evaluate sophisticated deep models. We use our implementation to analyze the performance of multitask deep networks and related deep models on four collections of pharmaceutical data (three of which have not previously been analyzed in the literature). We split these data sets into train/valid/test using time and neighbor splits to test multitask deep learning performance under challenging conditions. Our results demonstrate that multitask deep networks are surprisingly robust and can offer strong improvement over random forests. Our analysis and open-source implementation in DeepChem provide an argument that multitask deep networks are ready for widespread use in commercial drug discovery.
Asunto(s)

Texto completo: 1 Base de datos: MEDLINE Asunto principal: Descubrimiento de Drogas / Aprendizaje Automático Idioma: En Revista: J Chem Inf Model Asunto de la revista: INFORMATICA MEDICA / QUIMICA Año: 2017 Tipo del documento: Article

Texto completo: 1 Base de datos: MEDLINE Asunto principal: Descubrimiento de Drogas / Aprendizaje Automático Idioma: En Revista: J Chem Inf Model Asunto de la revista: INFORMATICA MEDICA / QUIMICA Año: 2017 Tipo del documento: Article