Your browser doesn't support javascript.
loading
Predicting With Confidence: Using Conformal Prediction in Drug Discovery.
Alvarsson, Jonathan; Arvidsson McShane, Staffan; Norinder, Ulf; Spjuth, Ola.
Afiliação
  • Alvarsson J; Department of Pharmaceutical Biosciences and Science for Life Laboratory, Uppsala University, Box 591, SE-75124, Uppsala, Sweden.
  • Arvidsson McShane S; Department of Pharmaceutical Biosciences and Science for Life Laboratory, Uppsala University, Box 591, SE-75124, Uppsala, Sweden.
  • Norinder U; Department of Pharmaceutical Biosciences and Science for Life Laboratory, Uppsala University, Box 591, SE-75124, Uppsala, Sweden; Department of Computer and Systems Sciences, Stockholm University, Box 7003, SE-16407, Kista, Sweden; MTM Research Centre, School of Science and Technology, Örebro Univer
  • Spjuth O; Department of Pharmaceutical Biosciences and Science for Life Laboratory, Uppsala University, Box 591, SE-75124, Uppsala, Sweden. Electronic address: ola.spjuth@farmbio.uu.se.
J Pharm Sci ; 110(1): 42-49, 2021 01.
Article em En | MEDLINE | ID: mdl-33075380
One of the challenges with predictive modeling is how to quantify the reliability of the models' predictions on new objects. In this work we give an introduction to conformal prediction, a framework that sits on top of traditional machine learning algorithms and which outputs valid confidence estimates to predictions from QSAR models in the form of prediction intervals that are specific to each predicted object. For regression, a prediction interval consists of an upper and a lower bound. For classification, a prediction interval is a set that contains none, one, or many of the potential classes. The size of the prediction interval is affected by a user-specified confidence/significance level, and by the nonconformity of the predicted object; i.e., the strangeness as defined by a nonconformity function. Conformal prediction provides a rigorous and mathematically proven framework for in silico modeling with guarantees on error rates as well as a consistent handling of the models' applicability domain intrinsically linked to the underlying machine learning model. Apart from introducing the concepts and types of conformal prediction, we also provide an example application for modeling ABC transporters using conformal prediction, as well as a discussion on general implications for drug discovery.
Assuntos
Palavras-chave

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Descoberta de Drogas / Aprendizado de Máquina Idioma: En Ano de publicação: 2021 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Descoberta de Drogas / Aprendizado de Máquina Idioma: En Ano de publicação: 2021 Tipo de documento: Article