Imputation of Assay Bioactivity Data using Deep Learning
T. M. Whitehead, B. W. J. Irwin, P. Hunt, M. D. Segall, G. J. Conduit, J. Chem. Inf. Model., 2019, 59(3) pp. 1197-1204
This article describes a novel deep learning neural network method and its application for the imputation of assay pIC50 values. These deep learning methods underpin our Cerella™ technology, part of our Augmented Chemistry® suite.
We describe a novel deep learning neural network method and its application for the imputation of 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 a preprint version of this paper as a PDF via the button below. Alternatively, visit the journal webpage to read the final published version of this article.
INTERESTED IN AI FOR DRUG DISCOVERY?
Cerella is a unique artificial intelligence platform which supports medicinal chemists and other discovery scientists. It escalates success rates and advances small molecule drug discovery, from working with early hits to nominating preclinical candidates.
Cerella’s AI platform is proven to overcome limitations in drug discovery data, confidently delivering results and seamlessly integrating with your med chem software platforms.
Cerella is part of our Augmented Chemistry suite of software and services, which bring ground-breaking artificial intelligence technologies that continuously learn from all available data to supplement your experience and skills.