Discovery of microbial intergenic features with genomic language modeling and multimodal search
- 1Massachusetts Institute of Technology
Abstract
Systematic characterization of microbial noncoding regions is limited by two distinct challenges: discovery of conserved sequence features without predefined motifs and functional interpretation of newly identified elements. We address these challenges by training a sparse autoencoder on genomic language model (gLM2) representations to identify intergenic sequence features without prior annotation, and by implementing multimodal search to generate functional hypotheses from conserved associations with neighboring proteins, RNA families, and genomic organization. This framework uncovered divergent, previously uncharacterized noncoding elements, including candidate regulatory DNA sequences and structured RNAs not captured by existing annotation models. gLM2-derived intergenic features can be explored through SeqHub's multimodal search, freely available for academic use at seqhub.org.
Related
- Comparative evaluation of metabolomic, microbial, and integrated features for distinguishing a rat model of heatstroke death from cervical-dislocation controls and estimating postmortem interval across organs
- A Context-Aware 14-3-3 Binding Predictor Enabled by Data Augmentation, Multi-Scale Biological Features, and Protein Language Model Embeddings
- Simultaneous multi-task assessment of five neurological language disorders via cross-corpus multimodal learning
- MEMOIR-VLM—a multimodal vision-language model for Alzheimer's disease classification and question answering
- MGM2 as a Multimodal Foundation Model for Microbial Community States and Responses
BibTeX
@misc{zulaybar2026discovery,
title = {{Discovery of microbial intergenic features with genomic language modeling and multimodal search}},
author = {N. Zulaybar and M. Tranzillo and R. Silverstein and Y. Hwang and A. Cornman},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.15.751765},
url = {https://www.biorxiv.org/content/10.64898/2026.09.15.751765v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Discovery of microbial intergenic features with genomic language modeling and multimodal search
AU - N. Zulaybar
AU - M. Tranzillo
AU - R. Silverstein
AU - Y. Hwang
AU - A. Cornman
PY - 2026
DA - 2026/09/15
PB - bioRxiv
DO - 10.64898/2026.09.15.751765
UR - https://www.biorxiv.org/content/10.64898/2026.09.15.751765v1
AB - Systematic characterization of microbial noncoding regions is limited by two distinct challenges: discovery of conserved sequence features without predefined motifs and functional interpretation of newly identified elements. We address these challenges by training a sparse autoencoder on genomic language model (gLM2) representations to identify intergenic sequence features without prior annotation, and by implementing multimodal search to generate functional hypotheses from conserved associations with neighboring proteins, RNA families, and genomic organization. This framework uncovered divergent, previously uncharacterized noncoding elements, including candidate regulatory DNA sequences and structured RNAs not captured by existing annotation models. gLM2-derived intergenic features can be explored through SeqHub's multimodal search, freely available for academic use at seqhub.org.
ER -