Site4Drug: Predicting Drug-Binding Target Sites with an AI Agent
For drug discovery researchers, this addresses the bottleneck of selecting targetable protein sites, especially for membrane proteins, by providing a modality-aware and constraint-based approach.
Site4Drug is an AI agent that predicts drug-binding target sites on proteins, particularly membrane proteins, by integrating constraints like accessibility, topology, and post-translational modifications. It outputs ranked targetable regions with evidence summaries and can recommend binding modalities, aiming to reduce failure in site selection.
Selecting where to intervene on a protein (i.e., choosing a targetable site) is often a more ambiguous and failure-prone bottleneck than selecting what binds, especially for membrane proteins where accessibility, topology, and post-translational modifications (PTMs) constrain actionable regions. We present Site4Drug, a modality-aware site-finding agent that outputs a ranked list of targetable regions with explicit constraints, evidence summaries, risk flags, and a traceable decision log. Rather than requiring users to specify the drug modality upfront, Site4Drug can recommend a binding modality (e.g., antibody/peptide-like vs small-molecule) from the same evidence used for site discovery, including topology, hydropathy, PTM propensity, disulfides, domain context, and sequence. Importantly, this evidence is applied consistently across modalities, including small-molecule pocket discovery, to avoid selecting chemically plausible but biologically occluded sites.