Using deep learning to model drug-target engagement

LSP investigators are contributing to and benefiting from the rapid advances in deep learning that are revolutionizing data analysis, protein structure prediction, and our ability to invent new drugs.

The contemporary approach towards inventing targeted therapies commonly aims to identify highly selective inhibitors that block the action of specific disease genes. In the case of multi-gene families, such as kinases, it is increasingly evident that approved drugs commonly inhibit multiple proteins, and this poly-pharmacology is essential to their mechanism of action. To better understand the spectrum of proteins that drugs bind, we are investigating drugs that target multi-enzyme families (kinases, deubiquitinases, and bromodomain inhibitors), using cell-based assays, mass spectrometry, and deep learning (a type of machine learning and artificial intelligence). Predicting structure and docking using deep learning plays an increasingly important role, and members of our lab are actively building on recent successes in this area (AlphaFold, for example). This project is actively recruiting individuals interested in ML/AI, protein structure prediction, and chemical biology.

Associated with:

The Center for Cancer Systems Pharmacology (CCSP) studies the responsiveness and resistance of human tumors to anticancer drugs as well as the adverse effects that they cause. Part of the National Cancer Institute Center for Cancer Systems Biology Consortium.

Selected Publications:

AlQuraishi M. End-to-End Differentiable Learning of Protein Structure. Cell Syst. 2019 Apr 24;8(4):292-301.e3. PMCID: PMC6513320.

AlQuraishi M, Sorger PK. Differentiable biology: using deep learning for biophysics-based and data-driven modeling of molecular mechanisms. Nat Methods. 2021 Oct;18(10):1169–1180. PMID: 34608321.

Chowdhury R, Bouatta N, Biswas S, Floristean C, Kharkar A, Roy K, Rochereau C, Ahdritz G, Zhang J, Church GM, Sorger PK, AlQuraishi M. Single-sequence protein structure prediction using a language model and deep learning. Nat Biotechnol. 2022 Nov;40(11):1617–1623. PMID: 36192636

Liu C, Kutchukian P, Nguyen ND, AlQuraishi M, Sorger PK. A Hybrid Structure-Based Machine Learning Approach for Predicting Kinase Inhibition by Small Molecules. J Chem Inf Model. 2023 Aug 18; PMID: 37595065

Back to Projects