a lot of important benchmarks shown here
@lxsasse.bsky.social @saramostafavi.bsky.social

New (and hotly anticipated - at least by me) preprint from my group describing a better way to partition training data for genomic-trained models to solve the long-neglected problem of homology-based data leakage. Thread from first author @muntakimrafi.bsky.social 👇

0/ Essential reading for anyone training or using sequence-function models trained on genomic sequences! 🚨 In our new preprint, we explore the ways homology within genomes can cause leakage when training sequence-based models and ways to prevent it

Had a lot of fun at the CSHL Biological Data Science conference.

Thanks to the scholarship from the "James P. Taylor Foundation for open science" for making it possible.

#cshl

I am attending the Biological Data Science Meeting at CSHL. Will be giving a talk this Friday morning on the results from the Random Promoter DREAM Challenge. Will also be presenting a poster on a recent work where we address and solve the homology-based leakage in genome trained models.

Thrilled to share our research at the recent @KipoiZoo seminar! 🧬 We showed how chromosomal splitting of genome can cause train-test leakage through sequence homology and proposed a scalable solution to tackle it. Preprint coming soon!

youtu.be/0_08qB0wLoM?...

1/If you're training ML models on DNA sequences, u need to take a look at our new paper in @NatureBiotech! It contains analysis done by over 300 researchers, tells the story of how we built state-of-the-art for short regulatory DNA and developed a framework to keep improving