Excited to share that UniversalEPI is officially published in @narjournal.bsky.social! 🚀 Check out the final paper and use the model here: 📄 Paper: academic.oup.com/nar/article/... 💻 Code: github.com/BoevaLab/Uni... (1/3) 🧵

Boeva Lab is #hiring postdocs and senior scientists in AI/ML for Cancer Biology! Check the offer and apply at: jobs.ethz.ch/job/view/JOP...

We are pleased to announce our latest public hub, UniversalEPI ENCODE for hg38. It shows Hi-C interaction predictions based on ENCODE ATAC-seq data, generated by UniversalEPI: bit.ly/UniversalEPI_... Thanks to the Boeva Lab at ETH Zurich for creating this hub.

🚨 New preprint out! We studied deep learning models for high-resolution DNA accessibility prediction from DNA sequence! Key takeaway: ConvNeXt V2 blocks consistently boost accuracy. 📖 Preprint: biorxiv.org/content/10.1... 🔗Code: github.com/BoevaLab/ASAP 📦 pip install atac-asap

Evaluation of deep learning approaches for high-resolution chromatin accessibility prediction from genomic sequence [new] Deep learning for 4bp ATAC-seq prediction. ConvNeXt-based models (ConvNextDCNNs) robust for variant effects.

🚀 New preprint from our lab, Ekaterina Krymova, and @fabiantheis.bsky.social: UniversalEPI, an attention-based method to predict enhancer-promoter interactions from DNA sequence and ATAC-seq🌟 Read the full preprint: www.biorxiv.org/content/10.1... by @aayushgrover.bsky.social, L. Zhang & I.L. Ibarra

UniversalEPI: Harnessing Attention Mechanisms to Decode Chromatin Interactions in Rare and Unexplored Cell Types https://www.biorxiv.org/content/10.1101/2024.11.22.624813v1