Learning from human and chemical languages to predict biological function
Kosonocky, C. W.; Kaderabkova, N.; Kim, K.; Mahmood, A. J. S.; Dunmyre, A.; Woolley, P.; Xing, K.; Winkler, D.; Babu, T.; Kaderabek, F.; Sessler, J. L.; Anslyn, E. V.; Marcotte, E. M.; Zhang, Y. J.; Ellington, A. D.; Mavridou, D. A. I.
Show abstract
Understanding how molecular structure encodes biological function remains a grand challenge in drug discovery. Here, we present PubCheF-1, a deep learning model that predicts literature-derived biological function directly from chemical structure. PubCheF-1 was trained on a dataset linking molecules to labels derived from the scientific articles in which they appear, a strategy that connects disparate compounds through the language used to describe their functionalities. When tasked with identifying inhibitors of {beta}-lactamases, including enzymes considered largely refractory to inhibition, PubCheF-1 predicted structurally distinct compounds that collectively have activity against all {beta}-lactamase classes. Furthermore, hit compounds directly bind the enzyme active site, restore antibiotic efficacy in multidrug-resistant high-priority pathogens, and demonstrate potent activity in animal infection models. Together, these findings establish that machine learning-based prediction of biological function derived from the language of scientific literature allows the identification of bioactive molecules at high hit rates, thereby accelerating therapeutic discovery.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Community assessment of cancer drug combination screens identifies strategies for synergy prediction 95%
- First fully-automated AI/ML virtual screening cascade implemented at a drug discovery centre in Africa 95%
- In silico discovery of nanobody binders to a G-protein coupled receptor using AlphaFold-Multimer 95%
Similar papers in this journal
- TrustAffinity: accurate, reliable and scalable out-of-distribution protein-ligand binding affinity prediction using trustworthy deep learning 95%
- Efficient protein structure generation with sparse denoising models 94%
- PSICHIC: physicochemical graph neural network for learning protein-ligand interaction fingerprints from sequence data 93%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.