Publications and Presentations

Experimental Validation of Predictive Models in a Series of Novel Antimalarials

Experimental Validation of Predictive Models in a Series of Novel Antimalarials

E. G. Tse, L. Aithani, M. Anderson, J. Cardoso-Silva, G. Cincilla, G. J. Conduit, M. Galushka, D. Guan, I. Hallyburton, B. W. J. Irwin, K. Kirk, A. M. Lehane, J. C. R. Lindblom, R. Lui, S. Matthews, J. McCulloch, A. Motion, H. L. Ng, M. Öeren, M. N. Robertson, V. Spadavecchio, V. A. Tatsis, W. P. van Hoorn, A.D. Wade, T. M. Whitehead, P. Willis, and M. H. Todd, J. Med. Chem. 2021, 64, 22, 16450–16463

DOI: 10.1021/acs.jmedchem.1c00313

This article outlines an open drug discovery competition, help by the Open Malaria Consortium. Optibrium entered in collaboration with Intellegens. We developed potential anti-malarials by combining our Cerella™ technology and StarDrop™ drug discovery software. We achieved second place with a compound flagged by Cerella. An unusual compound structure, our entry would not have been considered by human scientists alone, showing the usefulness of our machine learning methods.

An Open Drug Discovery Competition: Experimental Validation of Predictive Models in a Series of Novel Antimalarials

Abstract

The Open Source Malaria (OSM) consortium develops compounds that kill the human malaria parasite, Plasmodium falciparum, by targeting PfATP4, an essential ion pump on the parasite surface. The structure of PfATP4 has not yet been determined.

Here, we describe a public competition created to develop a predictive model for the identification of PfATP4 inhibitors, thereby reducing project costs associated with the synthesis of inactive compounds. Competition participants saw all entries as they were submitted. The final round featured private sector entrants specializing in machine learning methods. Here, using the best-performing predictive models, novel inhibitors were generated, of which several were synthesized and evaluated against the parasite. Half possessed biological activity, with one featuring a motif that the human chemists familiar with this series would have dismissed as “ill-advised”. Since all data and participant interactions remain in the public domain, this research project “lives” and may be improved by others.

Download the article from the journal webpage via the button below. Alternatively, find out more about AI-guided design of antimalarials by watching our webinar. Ben Irwin and Matthew Segall (Optibrium) and Professor Matthew Todd (University College London) describe how Optibrium’s team deployed the cutting-edge AI technologies of Augmented Chemistry® in the Open Source Malaria (OSM) initiative, using predictive models to design active compounds against a novel target in Plasmodium falciparum.

 

INTERESTED IN AI/ML FOR DRUG DISCOVERY?

Discover Cerella™

Cerella™ is a unique artificial intelligence platform, supporting 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.