Volodymyr Kuleshov

PlantCAD2 is a DNA foundation model pre-trained on 65 angiosperm genomes, showing improved performance in evolutionary conservation and chromatin accessible region prediction compared to existing models.

NTv3 is a foundation model that predicts genome function, annotates genes, and designs DNA sequences across species, outperforming existing models in multiple tasks.

The paper introduces PlantCaduceus, a DNA language model for plants, showing high transferability across species and improved performance in mutation prediction and variant identification.

GATTACA bins metagenomic contigs into species-specific clusters using compact k-mer indexing and MinHash, achieving accuracy comparable to existing methods but with significant speed improvements.