Pharmacophore-Guided Generative Design of Novel Drug-Like Molecules

Ekaterina Podplutova, Anastasia Vepreva, Olga A. Konovalova, Vladimir Vinogradov, Dmitrii O. Shkil, Andrei Dmitrenko

Keywords: Generative drug design, pharmacophore modeling, de novo molecular generation, scaffold diversity, patentability assessment, synthetic accessibility, drug-likeness

TL;DR: Generative framework for de novo molecule design using pharmacophore similarity and structural diversity, integrating similarity metrics with reinforcement learning to balance drug-likeness, accessibility, docking, and novelty.

Abstract: The integration of artificial intelligence (AI) in early-stage drug discovery offers unprecedented opportunities for exploring chemical space and accelerating hit-to-lead optimization. However, docking optimization in generative approaches is computationally expensive and may lead to inaccurate results. Here, we present a novel generative framework that balances pharmacophore similarity to reference compounds with structural diversity from active molecules. The framework allows users to provide custom reference sets, including FDA-approved drugs or clinical candidates, and guides the \textit{de novo} generation of potential therapeutics. We demonstrate its applicability through a case study targeting estrogen receptor modulators and antagonists for breast cancer. The generated compounds maintain high pharmacophoric fidelity to known active molecules while introducing substantial structural novelty, suggesting strong potential for functional innovation and patentability. Comprehensive evaluation of the generated molecules against common drug-like properties confirms the robustness and pharmaceutical relevance of the approach.

Submission Track: Benchmarking in AI for Materials Design - Short Paper

Submission Category: AI-Guided Design

Institution Location: Saint-Petersburg

AI4Mat RLSF: Yes

Submission Number: 146