Your browser doesn't support javascript.
loading
A Bayesian machine learning approach for drug target identification using diverse data types.
Madhukar, Neel S; Khade, Prashant K; Huang, Linda; Gayvert, Kaitlyn; Galletti, Giuseppe; Stogniew, Martin; Allen, Joshua E; Giannakakou, Paraskevi; Elemento, Olivier.
Afiliación
  • Madhukar NS; Institute for Computational Biomedicine, Dept. of Physiology and Biophysics, Weill Cornell Medical College, New York, NY, 10065, USA.
  • Khade PK; Caryl and Israel Englander Institute for Precision Medicine, Weill Cornell Medical College, New York, NY, 10065, USA.
  • Huang L; Meyer Cancer Center, Weill Cornell Medical College, New York, NY, 10065, USA.
  • Gayvert K; Tri-Institutional Training Program in Computational Biology and Medicine, New York, NY, 10065, USA.
  • Galletti G; OneThree Biotech Inc, Astoria, NY, 11106, USA.
  • Stogniew M; Division of Hematology and Medical Oncology, Department of Medicine, Weill Cornell Medical College, New York, NY, 10065, USA.
  • Allen JE; Institute for Computational Biomedicine, Dept. of Physiology and Biophysics, Weill Cornell Medical College, New York, NY, 10065, USA.
  • Giannakakou P; Caryl and Israel Englander Institute for Precision Medicine, Weill Cornell Medical College, New York, NY, 10065, USA.
  • Elemento O; Meyer Cancer Center, Weill Cornell Medical College, New York, NY, 10065, USA.
Nat Commun ; 10(1): 5221, 2019 11 19.
Article en En | MEDLINE | ID: mdl-31745082
Drug target identification is a crucial step in development, yet is also among the most complex. To address this, we develop BANDIT, a Bayesian machine-learning approach that integrates multiple data types to predict drug binding targets. Integrating public data, BANDIT benchmarked a ~90% accuracy on 2000+ small molecules. Applied to 14,000+ compounds without known targets, BANDIT generated ~4,000 previously unknown molecule-target predictions. From this set we validate 14 novel microtubule inhibitors, including 3 with activity on resistant cancer cells. We applied BANDIT to ONC201-an anti-cancer compound in clinical development whose target had remained elusive. We identified and validated DRD2 as ONC201's target, and this information is now being used for precise clinical trial design. Finally, BANDIT identifies connections between different drug classes, elucidating previously unexplained clinical observations and suggesting new drug repositioning opportunities. Overall, BANDIT represents an efficient and accurate platform to accelerate drug discovery and direct clinical application.
Asunto(s)
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Teorema de Bayes / Sistemas de Liberación de Medicamentos / Descubrimiento de Drogas / Reposicionamiento de Medicamentos / Aprendizaje Automático Tipo de estudio: Diagnostic_studies Límite: Humans Idioma: En Revista: Nat Commun Asunto de la revista: BIOLOGIA / CIENCIA Año: 2019 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Reino Unido
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Teorema de Bayes / Sistemas de Liberación de Medicamentos / Descubrimiento de Drogas / Reposicionamiento de Medicamentos / Aprendizaje Automático Tipo de estudio: Diagnostic_studies Límite: Humans Idioma: En Revista: Nat Commun Asunto de la revista: BIOLOGIA / CIENCIA Año: 2019 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Reino Unido