biorxiv.org· Sun, G., Hudelmaier, T., Gilligan, J. C., Gonzalez, G. A., Yin, P., Wan, F., Ma, Z., Durrant, M. G., Ricci-Tam, C., Pawluk, A., Puschnik, A. S., Konermann, S., Hsu, P. D. ·· 23 hours agoPickScore68
Systematic mapping of the prokaryotic noncoding sequence space with a genomic language model
In brief
Researchers used a genomic language model fine-tuned on prokaryotic intergenic sequences to organize 376 million intergenic regions from 1.3 terabase pairs of genomes and metagenomes into 5.14 million clusters.
Why it matters
The preprint demonstrates a pipeline from DNA sequence representations to noncoding RNA discovery, with large-scale clustering and token entropy-based internal architecture identification that can inform prokaryotic genome mining methods.
Source: biorxiv.org · biorxiv.org