Pharmacophore-Guided Generative Design of Novel Drug-Like Molecules

TL;DR

The paper tackles the challenge of accelerating early-stage drug discovery without overreliance on computationally expensive docking. It introduces a pharmacophore-guided de novo design framework implemented in a reinforcement-learning setup (FREED++) that jointly optimizes pharmacophore similarity to reference compounds and structural novelty using dual representations (CATS and MACCS). In a case study on estrogen receptor modulators, generated molecules exhibit strong pharmacophoric alignment to actives while maintaining substantial scaffold diversity and acceptable drug-like properties, with improved QED and synthetic accessibility over baselines. The approach demonstrates potential for producing patentable, biologically relevant compounds and outlines future directions to broaden pharmacophore representations and validate results experimentally.

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.

Figures (3)

• Figure 1: Schematic representation of proposed pipeline.
• Figure 2: Distributions of key properties evaluated in experiments.
• Figure 3: Best generated molecules and their pharmacophore analogue.