RESEARCH · RESEARCH · #720
SpecOpt: contact-diff agentic method to optimize binding specificity of existing small molecules (arXiv:2609.21165v1)
This arXiv preprint defines 'specificity optimization' (SpecOpt): making constrained structural changes to existing drugs to increase binding preference for an intended target over measured off-targets while keeping drug-like properties. The authors provide a ChEMBL-derived benchmark and an agentic pipeline that docks compounds to targets and off-targets, encodes residue-aware atom–protein contact differences, asks a large language model to propose modifications, and filters candidates by similarity, ADMET, and docking selectivity; on 915 compounds the mean target–off-target binding gap shifted from −0.72 to +0.47 kcal/mol and 84.8% of compounds improved while mean Tanimoto similarity remained 0.72; ablations show residue-specific contact identities are critical.
KEY POINTS
- This arXiv preprint defines 'specificity optimization' (SpecOpt): making constrained structural changes to existing drugs to increase binding preference for an intended target over measured off-targets while keeping drug-like properties.
- The authors provide a ChEMBL-derived benchmark and an agentic pipeline that docks compounds to targets and off-targets, encodes residue-aware atom–protein contact differences, asks a large language model to propose modifications, and filters candidates by similarity, ADMET, and docking selectivity; on 915 compounds the mean target–off-target binding gap shifted from −0.72 to +0.47 kcal/mol and 84.8% of compounds improved while mean Tanimoto similarity remained 0.72; ablations show residue-specific contact identities are critical.
- Defines a practical task and shows that residue-aware differential contact signals plus LLM-guided edits can substantially improve target selectivity of existing compounds, relevant to safer AI-guided drug optimization.
WHY IT MATTERS
Defines a practical task and shows that residue-aware differential contact signals plus LLM-guided edits can substantially improve target selectivity of existing compounds, relevant to safer AI-guided drug optimization.