Accurate Identification of Covalently Ligandable Cysteines Using CCSite
- 12 August 2026
- journal article
- Published by American Chemical Society (ACS) in Journal of Medicinal Chemistry
- Vol. 69 (16) , 20037-20049
Abstract
Targeted covalent inhibition is an important strategy in modern drug discovery, with cysteine being the most common residue targeted for covalent ligands. Accurate identification of covalently ligandable cysteines is therefore essential, especially for traditionally “undruggable” targets. However, structure-based methods depend on available and reliable protein structures, while sequence-based methods remain scarce and require further improvement. Here, we present CCSite, a protein language model-based framework for discovering covalently ligandable cysteines from protein sequences. It uniquely integrates low-rank adaptation of ESM Cambrian (LoRA-ESMC) with a cysteine-centered encoder-decoder module to capture local microenvironment features and long-range contextual information. Benchmarking and independent evaluation showed that CCSite achieved competitive performance without requiring 3D structures. Moreover, a real-world application revealed that CCSite was capable of prospectively identifying experimentally validated covalent cysteines, and a large-scale screen of human pathogenic X-to-Cys mutations further identified over 2,000 neo-cysteines as covalently ligandable candidates for future covalent drug development.Keywords
Funding Information
- National Natural Science Foundation of China (22220102001)
- National Natural Science Foundation of China (82373790)
- National Natural Science Foundation of China (82404511)
- China Postdoctoral Science Foundation (2025M773525)
- Natural Science Foundation of Zhejiang Province (RG25H300001)
- Science and Technology Department of Zhejiang Province (2026C01039)
- National Key Research and Development Program of China (2024YFA1307503)
- Graduate Program in Physics at UNIFAL-MG (HR202502095)
- Graduate Program in Physics at UNIFAL-MG (HR202502098)
This publication has 52 references indexed in Scilit:
- Accurate Identification of Protein Binding Sites for All Drug Modalities Using ALLSitesAdvanced Science, 2025
- TopCysteineDB: A Cysteinome-wide Database Integrating Structural and Chemoproteomics Data for Cysteine Ligandability PredictionJournal of Molecular Biology, 2025
- MMFuncPhos: A Multi‐Modal Learning Framework for Identifying Functional Phosphorylation Sites and Their Regulatory TypesAdvanced Science, 2025
- DrugMap: A quantitative pan-cancer analysis of cysteine ligandabilityCell, 2024
- Proteome-wide structural analysis identifies warhead- and coverage-specific biases in cysteine-focused chemoproteomicsCell Chemical Biology, 2023
- How good are AlphaFold models for docking-based virtual screening?iScience, 2022
- Implications of disease-related mutations at protein–protein interfacesCurrent Opinion in Structural Biology, 2021
- Recent Advances in Selective and Irreversible Covalent Ligand Development and ValidationCell Chemical Biology, 2019
- Vaccinia virus proteolysis—a reviewReviews in Medical Virology, 2006
- Protein Flexibility in Ligand Docking and Virtual Screening to Protein KinasesJournal of Molecular Biology, 2004