Covalent small-molecule ligands have re-emerged as powerful tools in drug discovery, offering prolonged target engagement, enhanced potency, and the ability to modulate proteins once considered undruggable. However, the rational design and virtual screening (VS) of covalent ligands remain challenging. Many docking tools cannot accurately model the energetics of covalent bond formation, often requiring more rigorous quantum mechanical (QM) or semi-empirical QM calculations for reliable predictions. Despite these limitations, the computational landscape is rapidly evolving. An increasing number of open-source, commercial, and web-based platforms now support binding mode exploration, lead optimization, and structure-based VS of covalent ligands. Alongside traditional approaches, new artificial intelligence (AI) and machine learning (ML) tools are assisting in prioritizing candidate molecules. This review introduces the fundamental principles and mechanisms of covalent inhibition, then provides a comprehensive overview of computational tools including covalent docking, warhead placement algorithms, and pharmacophore modeling, supporting early-stage drug discovery and chemical biology. Case studies highlight practical applications. We also cover curated databases of covalent binders and experimental 3D protein-ligand complexes, plus tools for assessing nucleophilic residue reactivity, all essential for robust covalent modeling. Finally, we briefly address risks associated with covalent chemistry. While progress is notable, further advances are needed. Nonetheless, today's covalent docking and AI-driven tools already make a meaningful impact by enabling rational design, generating new ideas, refining hypotheses, and expanding the boundaries of druggability.

MOTIVATION: Cytochrome P450 (CYP) is a superfamily of enzymes responsible for the metabolism of drugs, xenobiotics and endogenous compounds. CYP2D6 metabolizes about 30% of drugs and predicting potential CYP2D6 inhibition is important in early-stage drug discovery. RESULTS: We developed an original in silico approach for the prediction of CYP2D6 inhibition combining the knowledge of the protein structure and its dynamic behavior in response to the binding of various ligands and machine learning modeling. This approach includes structural information for CYP2D6 based on the available crystal structures and molecular dynamic simulations (MD) that we performed to take into account conformational changes of the binding site. We performed modeling using three learning algorithms--support vector machine, RandomForest and NaiveBayesian--and we constructed combined models based on topological information of known CYP2D6 inhibitors and predicted binding energies computed by docking on both X-ray and MD protein conformations. In addition, we identified three MD-derived structures that are capable all together to better discriminate inhibitors and non-inhibitors compared with individual CYP2D6 conformations, thus ensuring complementary ligand profiles. Inhibition models based on classical molecular descriptors and predicted binding energies were able to predict CYP2D6 inhibition with an accuracy of 78% on the training set and 75% on the external validation set.