BacLM Collection Genomic Language Model (350M) trained on bacterial protein and intergenic (DNA) sequences. • 2 items • Updated May 2 • 1
BacBench Collection A multi-scale benchmark suite for bacterial genomics. • 10 items • Updated May 8 • 4
Bacformer Collection Modeling whole-bacterial genomes as a sequence of contextual proteins. • 9 items • Updated Jun 5 • 4
BacCorpus Collection A dataset of diverse bacterial genomes across habitats. Includes deduplicated genomes, proteins and intergenic sequences. • 3 items • Updated 17 days ago • 1