Conference proceeding
Translating the Language of Life
Companion Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, pp 1-1
11 Oct 2025
Abstract
Proteins are fundamental to life, yet uncovering their structure and function has long required intensive experiments. Recent work, such as ESM [?], shows that language models can learn molecular biology as a language. We present Prometheus, a protein language model (PLM) that translates raw sequences into natural language by combining pretrained encoders (ESM-2, ESM-Cambrian) with a large language model backbone. To enable training, we introduce ProtQA, a large-scale question answering dataset from UniProt spanning functional, structural, and biomedical aspects. Prometheus demonstrates the promise of multimodal LLMs to make protein knowledge accessible and interactive, bridging biological sequences and human understanding.
Metrics
5 Record Views
Details
- Title
- Translating the Language of Life
- Creators
- Chaz Allegra - Rowan UniversityRobi Polikar - Rowan UniversityGail Rosen - Drexel University
- Publication Details
- Companion Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, pp 1-1
- Conference
- BCB Companion '25: Companion Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics
- Series
- ACM Conferences
- Publisher
- ACM; NEW YORK
- Number of pages
- 1
- Grant note
- US National Science Foundation: 1936782, 1936791
This work is supported by the US National Science Foundation under Grants #1936782 and #1936791.
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:001661442600024
- Scopus ID
- 2-s2.0-105025461894
- Other Identifier
- 991022138657904721