A semi-supervised learning framework for quantitative structure-activity regression modelling

no code implementations • 7 Jan 2020 • Oliver P Watson, Isidro Cortes-Ciriano, James A Watson

Supervised learning models, also known as quantitative structure-activity regression (QSAR) models, are increasingly used in assisting the process of preclinical, small molecule drug discovery.

Drug Discovery regression +1

Reliable Prediction Errors for Deep Neural Networks Using Test-Time Dropout

no code implementations • 12 Apr 2019 • Isidro Cortes-Ciriano, Andreas Bender

Here, we present a framework to compute reliable errors in prediction for Neural Networks using Test-Time Dropout and Conformal Prediction.

Conformal Prediction Decision Making +2

Deep Confidence: A Computationally Efficient Framework for Calculating Reliable Errors for Deep Neural Networks

no code implementations • 24 Sep 2018 • Isidro Cortes-Ciriano, Andreas Bender

While controlling for prediction confidence is essential to increase the trust, interpretability and usefulness of virtual screening models in drug discovery, techniques to estimate the reliability of the predictions generated with deep learning networks remain largely underexplored.

Conformal Prediction Drug Discovery