PhenoMoler: Phenotype-Guided Molecular Optimization via Chemistry Large Language Model
This work addresses the need for phenotype-aware drug design in computational chemistry, offering a novel approach for researchers and pharmaceutical developers, though it builds incrementally on existing methods by integrating expression profiles with language models.
The authors tackled the problem of molecular generative models neglecting system-level phenotypic effects by developing PhenoMoler, a framework that integrates a chemistry large language model with expression profiles to guide molecular design based on drug-induced transcriptional responses, resulting in generated compounds that are chemically valid, novel, diverse, and exhibit comparable or enhanced drug-likeness, optimized properties, and superior binding affinity to cancer targets compared to FDA-approved drugs.
Current molecular generative models primarily focus on improving drug-target binding affinity and specificity, often neglecting the system-level phenotypic effects elicited by compounds. Transcriptional profiles, as molecule-level readouts of drug-induced phenotypic shifts, offer a powerful opportunity to guide molecular design in a phenotype-aware manner. We present PhenoMoler, a phenotype-guided molecular generation framework that integrates a chemistry large language model with expression profiles to enable biologically informed drug design. By conditioning the generation on drug-induced differential expression signatures, PhenoMoler explicitly links transcriptional responses to chemical structure. By selectively masking and reconstructing specific substructures-scaffolds, side chains, or linkers-PhenoMoler supports fine-grained, controllable molecular optimization. Extensive experiments demonstrate that PhenoMoler generates chemically valid, novel, and diverse molecules aligned with desired phenotypic profiles. Compared to FDA-approved drugs, the generated compounds exhibit comparable or enhanced drug-likeness (QED), optimized physicochemical properties, and superior binding affinity to key cancer targets. These findings highlight PhenoMoler's potential for phenotype-guided and structure-controllable molecular optimization.