Polypharmacological Target-Aware Molecule Generation

Designing compounds capable of modulating multiple target proteins simultaneously (i.e., polypharmacology) is critical for treating complex diseases like cancer and neurodegenerative disorders. However, AI-driven multi-target drug design remains severely hindered by the scarcity of multi-target 3D structural data and the inefficiency of traditional "generate-then-filter" pipelines. There is a pressing need for scalable methods that can satisfy diverse binding constraints across multiple proteins without relying on scarce structural priors.

To overcome these bottlenecks, we reformulate multi-target drug design as a sequence-based generation task and introduce PolyTamGen, an end-to-end autoregressive framework. We first curate a large-scale ligand-centric bioactivity dataset from ChEMBL and BindingDB, comprising 1.6 million unique ligands and 4.9 million bioactivity entries. PolyTamGen encodes target protein sets using ESM3, compresses these high-dimensional features into compact tokens via an attention module, and feeds them into a sequence-based compound generator to produce the final multi-target ligands. We further apply Direct Preference Optimization (DPO) to improve docking-based affinity proxies and drug-likeness. Extensive experiments on dual- and triple-target benchmarks demonstrate that PolyTamGen improves joint success rates over representative baselines while maintaining high chemical validity and diversity.

The code is available at https://github.com/bjzgcai/PolyTamGen. The processed data, model checkpoints, and benchmark results are available at Zenodo: https://doi.org/10.5281/zenodo.20594128.

Supplementary data are available at Bioinformatics online.