Gherman Novakovsky (слава Україні! 🇺🇦)
@NovakovskyG
PhD, Illumina AI lab; interested in Deep Learning and genome regulation; also drawing, martial arts, guitar, and death metal! (he/him)
Excited to share my first contribution here at Illumina! We developed PromoterAI, a deep neural network that accurately identifies non-coding promoter variants that disrupt gene expression.🧵 (1/)
Excited to introduce LiftOn – an open-source tool for accurate liftover of genome annotations (GFF) across assemblies. 🚀 👉 Code &community: github.com/Kuanhao-Chao/L… It’s been incredibly rewarding building this for the genomics community. Thank you to all collaborators/friends!
Genome annotation is falling behind how fast genomes can be assembled—but Johns Hopkins researchers @KuanHaoChao, @StevenSalzberg1, @elapertea, @alaina_shumate, @celinehohzm, & @alan_mayonnaise (+ @JakobHeinz9) have created a tool that can change that: cs.jhu.edu/news/solving-t…
We observed the same across six promoter variant effect benchmarks. Evo2 did worse than basic CNNs and had ~0.5 auROC on some tasks.
*Easter egg alert* NOT in the published paper. We also benchmarked Evo 2 and while it did better than other gLMs (consistent that scale can improve gLMs), it still falls short of a basic CNN trained using one-hot sequences and far short of supervised SOTA x.com/pkoo562/status…
Congratulations Gherman! 🖥️🧬🥳 A tour-de-force of AI/ML on predicting promoter variant effects in humans. 🔗: science.org/doi/10.1126/sc… #MachineLearning #Bioinformatics #Genomics
Excited to share my first contribution here at Illumina! We developed PromoterAI, a deep neural network that accurately identifies non-coding promoter variants that disrupt gene expression.🧵 (1/)
Today, we unveiled PromoterAI, a groundbreaking algorithm that, for the first time at scale, accurately deciphers pathogenic regulatory genetic variants in the noncoding regions of the human genome. In a study published today in @ScienceMagazine, researchers report a 6% increase…