This dataset contains 8,192 bp Sorghum bicolor v3 sequence windows for the
Evolutionary_constraint split from
kuleshov-group/cross-species-single-nucleotide-annotation.
Columns:
sequence: 8,192 bp DNA sequence window.
label: original binary conservation label.
The source coordinates match:
/workdir/jz963/genomes/Sorghum_bicolor_v3.1.1/assembly/Sbicolor_454_v3.0.1.fa
Window definition:
chrom:pos-4095 through chrom:pos+4096, so the original… See the full description on the dataset page:
https://huggingface.co/datasets/JingjingZhai/full_conservation_within_andropogoneae.