ProCyon: A multimodal foundation model for protein phenotypes

Understanding the roles of human proteins remains a major challenge, with approximately 20% of human proteins lacking known functions and more than 40% missing context-specific functional insights. Even well-annotated proteins are often poorly characterized in diverse biological contexts, disease states, and perturbations. We present P ro C yon , a foundation model for modeling, generating, and predicting protein phenotypes across five interrelated knowledge domains: molecular functions, therapeutic mechanisms, disease associations, functional protein domains, and molecular interactions. To support this, we created P ro C yon -INSTRUCT, a dataset of 33 million protein phenotype instructions, representing a comprehensive resource for multiscale protein phenotypes. By co-training a large language model with multimodal molecular encoders, P ro C yon integrates phenotypic and protein data. A novel architecture and instruction tuning strategy allow P ro C yon to process arbitrarily interleaved protein-and-phenotype inputs, achieve zero-shot task transfer, and generate free- form text phenotypes interleaved with retrieved protein sequence, structure, and drug modalities in a single unified model. P ro C yon achieves strong performance against single-modality models, multimodal models such as ESM3, as well as text-only LLMs on dozens of benchmarking tasks such as contextual protein retrieval and question answering. We extensively evaluate P ro C yon for biological applications, including identifying protein domains that bind small molecule drugs, predicting peptide binding with enzymes, and assessing the functional impact of Alzheimer’s disease mutations. P ro C yon enables conditional retrieval of proteins linked to small molecules through complementary mechanisms of action. It generates candidate phenotypes for under-characterized proteins recently implicated in Parkinson’s disease, facilitating hypothesis generation for poorly understood proteins and biological processes. P ro C yon paves the way toward an effective, general solution for functional