GCMDiff: a condition-guided diffusion framework for pharmacophore-fragment drug discovery and target-specific molecular design

Drug discovery remains a costly and time-consuming process, motivating the development of artificial intelligence approaches to accelerate molecular design. Many generative models, including generative pre-trained transformers (GPT), rely on one-dimensional SMILES representations that lack explicit structural topology and are constrained by rigid syntax rules. Moreover, most existing models perform unconditional molecule generation, while the few conditional diffusion approaches often rely on abstract parameters rather than pharmacologically interpretable constraints. Consequently, current methods have limited ability to enforce explicit drug-like and pharmacophore requirements during molecular generation. Here, we propose GCMDiff, a multi-condition guided diffusion framework for molecular graph generation that supports controllable and interpretable molecular design. Unlike SMILES-based models, GCMDiff employs an atom-pair and bond-centric molecular graph representation that directly captures explicit chemical topologies. Crucially, we introduce an interpretable pharmacological condition embedding that integrates multi-modal constraints, including atom number, Lipinski’s Rule of Five constraints, and structural moieties derived from Checkmol, PubChem, and Rings in Drugs descriptors. These explicit features guide the diffusion process toward promising chemical spaces satisfying user-defined prerequisites. Benchmark experiments demonstrate that GCMDiff generates chemically valid and structurally diverse molecules, achieving 99.6% novelty and 100% uniqueness while maintaining atom and bond distributions consistent with drug-like chemical space. As a practical application, GCMDiff was applied to epidermal growth factor receptor (EGFR) inhibitor design, where generated candidates reproduced key binding interactions, including the conserved hydrogen bond between a quinazoline scaffold and residue Met793. These results demonstrate that GCMDiff provides a flexible and interpretable framework for pharmacophore-fragment-conditioned molecular generation, enabling controllable exploration of drug-like chemical space and facilitating early-stage rational drug discovery. Scientific contribution GCMDiff advances molecular design by employing a graph-based diffusion framework that bypasses SMILES-related syntax limitations. Its core innovation is a multi-modal condition encoder integrating drug-like properties and pharmacophores, enabling interpretable, pharmacophore-fragment-conditioned molecular generation. The model achieves 99.6% novelty and 100% uniqueness while demonstrating practical utility through the design of novel EGFR inhibitors that replicate essential Met793 binding interactions. This framework effectively bridges generative AI with rational, constraint-driven lead optimization.