Publications and Presentations

Practical Applications of Deep Learning to Impute Heterogeneous Drug Discovery Data

This article outlines practical applications of deep learning on drug discovery data. It introduces some of the research behind our Cerella technology.


When looking to apply artificial intelligence in drug discovery, one of the main challenges is around the lack of abundant quality data. This is due to the time and cost of experiments, alongside potential experimental errors. This paper describes Alchemite™, the cutting-edge deep learning method underpinning our Cerella platform, and its success in making predictions even faced with sparse, noisy data. It can impute data across a range of drug discovery projects, from activity to ADME endpoints with excellent accuracy, even when combining data across uncorrelated endpoints and projects with different chemical spaces.

Citation details

B. W. J. Irwin, J. Levell, T. M. Whitehead, M. D. Segall, G. J. Conduit, J. Chem. Inf. Model. 2020, 60, 6, 2848–2857
DOI: 10.1021/acs.jcim.0c00443

Find out more

Visit the journal webpage to read the full peer-reviewed article, via the button below. Alternatively, you can discover more about deep learning imputation by watching some of our Cerella videos.


Discover Cerella™

Cerella™ is a unique artificial intelligence platform which supports medicinal chemists and other discovery scientists, escalating the success rate 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 deliver results, seamlessly integrate with your med chem software platforms and help you and your colleagues increase the success rate of your projects.