This paper was printed in the Journal of Chemical Information and Modeling. Whitehead et al. J. Chem. Inf. Model (2019) 59(3), pp 1197–1204.

Abstract

We describe a novel deep learning neural network method and its application to impute assay pIC₅₀ values. Unlike conventional machine learning approaches, this method is trained on sparse bioactivity data as input, typical of that found in public and commercial databases, enabling it to learn directly from correlations between activities measured in different assays.

In two case studies on public domain data sets we show that the neural network method outperforms traditional quantitative structure-activity relationship (QSAR) models and other leading approaches. Furthermore, by focussing on only the most confident predictions the accuracy is increased to R² > 0.9 using our method, as compared to R² = 0.44 when reporting all predictions.

You can download this paper as a PDF

This article was published in the online edition of Drug Discovery Today; February 2019

Matthew Segall, Tamsin Mansley, Peter Hunt, Edmund Champness

Abstract

Successful drug discovery requires knowledge and experience across many disciplines and no current ‘artificial intelligence’ method can replace expert scientists. However, computers can recall much more information than any individual or team and facilitate transfer of knowledge across disciplines. We’ll discuss how knowledge relating to chemistry and the biological and physicochemical properties required for a successful compound can be captured. Furthermore, we’ll illustrate how, by combining and applying this knowledge computationally, a much broader range of optimisation strategies can be rigorously explored, and the results presented in an intuitive way for consideration by the experts.

You can download the article as a PDF