Protein-STORY: Semantic Text-Oriented Representation Yields biologically meaningful Protein embeddings

ACL ARR 2026 January Submission7674 Authors

Keywords: Bio-NLP, Bioinformatics, Semantic Alignment, Knowledge-Enhanced Embeddings, Proteins, Representation Learning, Retrieval

Abstract: Unsupervised representation learning using masked language modeling on the language of life has transformed protein research, enabling the analysis of a protein universe that is expanding at an exponential pace. However, most current models rely solely on sequence data, overlooking decades of expert-curated biological knowledge stored in natural language. While recent multimodal and knowledge-graph-based approaches attempt to bridge this gap, they often rely on shallow functional labels that lack the contextual depth of full textual narratives. We present Protein-STORY, a general pipeline that synthesizes protein embeddings from diverse, multi-source text descriptions. At the core of our approach is a novel network architecture designed for the semantic compression of multi document embeddings, which integrates high-fidelity functional and structural insights into a unified representation. Our experiments demonstrate that Protein-STORY produces biologically meaningful embeddings ($r\approx0.75$) that outperform existing models on diverse downstream tasks (+2 pts F1 in function prediction). Furthermore, by projecting the story of a protein into a natural language semantic space, our model enables effective zero-shot text-prompted protein search.

Paper Type: Short

Research Area: Clinical and Biomedical Applications

Research Area Keywords: bioinformatics, biomedical knowledge extraction and discovery

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 7674