DOE OSTI · code-174434
genomeocean: a pretrained microbial genome foundational model (genomeoceanLLM) v1.0
Abstract
We present Genomeocean, a foundational genome language model that represents the microbial genome sequences from complex environmental samples. By training on a large, diverse metagenomic dataset, Genomeocean learns species-specific sequence composition and can generate long, realistic open reading frames (ORFs). Our model employs a Byte-pair-encoding (BPE) tokenization strategy, allowing it to efficiently process large genomic datasets and generate long sequences up to 50kb. We demonstrate that fine-tuning Genomeocean can generate novel gene clusters encoding biosynthetic pathways, showcasing its ability to model both fundamental and complex biological processes. Our work establishes Genomeocean as a powerful tool for understanding microbial genome biology and paves the way for its application in a range of fields, from synthetic biology to microbiome research.
Keep this discovery
Explore connections, maps & timelines
Wang, Zhong [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)], Egan, Rob [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)], Liu, Fengchen [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)], Kautsar, Satria [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)], Goldhaber-Gordon, Shira [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)], Wu, Weimin [Northwestern University], Zhou, Zhihan [Northwestern University], Ho, Harrison [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); Univ. of California, Merced, CA (United States)], Shi, Lizhen [Northwestern University], Liu, Han [Northwestern University]. 2025-01-21. genomeocean: a pretrained microbial genome foundational model (genomeoceanLLM) v1.0. https://doi.org/10.11578/dc.20260202.1
Cite the original work for its findings. Save a collection to share your selection of sources.