Carbon-A open gene-finding model and 566M-candidate database released for 22,617 species
Overview
Thomas Wolf announced the release of Carbon-A, an open model that finds genes directly in DNA without needing a close relative as a reference, along with a database of 566.34 million candidate genes across 22,617 species, from fungi to mammals.
A later report from Leandro von Werra adds that the candidates are about 16 times the gene annotations in the RefSeq dataset, and that wet-lab RNA experiments in cats, Syrian hamsters, chickens, and Arabidopsis supported 239 candidates missing from RefSeq. Both reports say the model only marks gene locations; the authors state it does not design DNA or predict what a gene does.
Written by AI from the articles below · updated Oct 8, 9:02 PM ET
Check the sources:
Article timeline
Follow the coverage from different perspectives. Times are ET.
- Leandro von WerraPickCarbon-A open model and database predict 566 million gene candidates across 22,617 species
AICarbon-A is an open model that predicts gene locations directly from DNA, and it has been used to annotate genomes from over 22,000 species. The release includes a database of 566 million gene candidates, about 16 times the gene annotations in the RefSeq dataset. Wet-lab RNA experiments supported 239 candidates missing from RefSeq across cats, Syrian hamsters, chickens, and Arabidopsis.
- Thomas WolfCarbon-A open model finds 566 million candidate genes across 22,617 species
AIThe team released Carbon-A, an open model that finds genes directly in DNA, along with a database of 566.34 million candidate genes across 22,617 species. The model reads genomes without needing a close relative, and wet-lab validation in cats, chickens, and arabidopsis is cited, with 239 genes found missing from reference annotations of common species. The authors say the model marks gene locations but does not design DNA or predict gene function.
Heat trend
Not enough continuous observations to show a trend yet.