Targeted covalent inhibition is a powerful therapeutic modality in the drug discoverer’s toolbox. Recent advances in covalent drug discovery, in particular, targeting cysteines, have led to significant breakthroughs for traditionally challenging targets such as mutant KRAS, which is implicated in diverse human cancers. However, identifying cysteines for targeted covalent inhibition is a difficult task, as experimental and in silico tools have shown limited accuracy. Using the recently released CovPDB and CovBinderInPDB databases, we have trained and tested interpretable machine learning (ML) models to identify cysteines that are liable to be covalently modified (i.e., “ligandable” cysteines). We explored myriad physicochemical features (pKa, solvent exposure, residue electrostatics, etc.) and protein–ligand pocket descriptors in our ML models. Our final logistic regression model achieved a median F1 score of 0.73 on held-out test sets. When tested on a small sample of holo proteins, our model also showed reasonable performance, accurately predicting the most ligandable cysteine in most cases. Taken together, these results indicate that we can accurately predict potential ligandable cysteines for targeted covalent drug discovery, privileging cysteines that are more likely to be selective rather than purely reactive. We release this tool to the scientific community as CovCysPredictor.

The oxidation status of N-terminal cysteines directly dictates protein stability via arginylation and proteasomal degradation. However, only a handful of proteins have been shown to be regulated via t...

Using reactivity-based metabolomics, methylglyoxal and its main metabolite lactoylglutathione were found to react rapidly with cysteines to generate l-lactoylated and d-lactoylated thioesters, suggest...

A deep mapping of the human zinc-binding cysteine proteome (ZnCPT) defines thousands of zinc-binding protein cysteines across major domains of biology and discovers glutathione reductase as zinc-targetable cancer vulnerability.

Montaño et al. generate an integrated proteomic and cysteine reactivity resource for the NCI-60 cancer cell line panel, offering quantitative data on over 12,000 proteins and 36,000 cysteines to enabl...

A deep mapping of the human zinc-binding cysteine proteome (ZnCPT) defines thousands of zinc-binding protein cysteines across major domains of biology and discovers glutathione reductase as zinc-targetable cancer vulnerability.

A deep mapping of the human zinc-binding cysteine proteome (ZnCPT) defines thousands of zinc-binding protein cysteines across major domains of biology and discovers glutathione reductase as zinc-targetable cancer vulnerability.

Through the Astrocyte Neuron Lactate Shuttle, astrocyte-derived lactate fuels the high-energy demand

Development of targeted covalent inhibitors and covalent ligand-first approaches have emerged as a powerful strategy in drug design, with cysteines be…