Your browser doesn't support javascript.
loading
Assigning confidence to molecular property prediction.
Nigam, AkshatKumar; Pollice, Robert; Hurley, Matthew F D; Hickman, Riley J; Aldeghi, Matteo; Yoshikawa, Naruki; Chithrananda, Seyone; Voelz, Vincent A; Aspuru-Guzik, Alán.
Afiliación
  • Nigam A; Chemical Physics Theory Group, Department of Chemistry, University of Toronto, Toronto, Canada.
  • Pollice R; Department of Computer Science, University of Toronto, Toronto, Canada.
  • Hurley MFD; Chemical Physics Theory Group, Department of Chemistry, University of Toronto, Toronto, Canada.
  • Hickman RJ; Department of Computer Science, University of Toronto, Toronto, Canada.
  • Aldeghi M; Department of Chemistry, Temple University, Philadelphia, USA.
  • Yoshikawa N; Chemical Physics Theory Group, Department of Chemistry, University of Toronto, Toronto, Canada.
  • Chithrananda S; Department of Computer Science, University of Toronto, Toronto, Canada.
  • Voelz VA; Chemical Physics Theory Group, Department of Chemistry, University of Toronto, Toronto, Canada.
  • Aspuru-Guzik A; Department of Computer Science, University of Toronto, Toronto, Canada.
Expert Opin Drug Discov ; 16(9): 1009-1023, 2021 09.
Article en En | MEDLINE | ID: mdl-34126827
Introduction: Computational modeling has rapidly advanced over the last decades. Recently, machine learning has emerged as a powerful and cost-effective strategy to learn from existing datasets and perform predictions on unseen molecules. Accordingly, the explosive rise of data-driven techniques raises an important question: What confidence can be assigned to molecular property predictions and what techniques can be used?Areas covered: The authors discuss popular strategies for predicting molecular properties, their corresponding uncertainty sources and methods to quantify uncertainty. First, the authors' considerations for assessing confidence begin with dataset bias and size, data-driven property prediction and feature design. Next, the authors discuss property simulation via computations of binding affinity in detail. Lastly, they investigate how these uncertainties propagate to generative models, as they are usually coupled with property predictors.Expert opinion: Computational techniques are paramount to reduce the prohibitive cost of brute-force experimentation during exploration. The authors believe that assessing uncertainty in property prediction models is essential whenever closed-loop drug design campaigns relying on high-throughput virtual screening are deployed. Accordingly, considering sources of uncertainty leads to better-informed validations, more reliable predictions and more realistic expectations of the entire workflow. Overall, this increases confidence in the predictions and, ultimately, accelerates drug design.
Asunto(s)
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Diseño de Fármacos / Aprendizaje Automático Tipo de estudio: Prognostic_studies / Risk_factors_studies Límite: Humans Idioma: En Revista: Expert Opin Drug Discov Año: 2021 Tipo del documento: Article País de afiliación: Canadá Pais de publicación: Reino Unido

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Diseño de Fármacos / Aprendizaje Automático Tipo de estudio: Prognostic_studies / Risk_factors_studies Límite: Humans Idioma: En Revista: Expert Opin Drug Discov Año: 2021 Tipo del documento: Article País de afiliación: Canadá Pais de publicación: Reino Unido