Biological and Medicinal Chemistry

JAEGER – Hunting for Antimalarials with Generative Chemistry

Authors

Abstract

Recent advances in generative modeling allow designing novel compounds through deep neural networks. One such neural network model, the Junction Tree Variational Auto- Encoder (JT-VAE), excels at proposing chemically valid structures. Based on JT-VAE, we built a generative modeling approach (JAEGER) for finding novel chemical matter with desired bioactivity. Using JAEGER, we designed compounds to inhibit malaria. To prioritize the compounds for synthesis, we used the in-house Profile-QSAR (pQSAR) program, a massively-multitask bioactivity model based on 12,000 Novartis assays. Based on the pQSAR activity predictions, we selected, synthesized, and experimentally profiled two compounds. Both compounds exhibited low nanomolar activity in a malaria proliferation assay as well as a biochemical assay measuring activity against PI(4)K, which is an essential kinase that regulates intracellular development in malaria. The compounds also showed low activity in a cytotoxicity assay. Our findings show that JAEGER is a viable approach for finding novel active compounds for drug discovery.

Content

Thumbnail image of jaeger_paper.pdf

Supplementary material

Thumbnail image of jaeger_SI.pdf
Supplementary Material
Supplementary Figures and Supplementary Note