#AACRai25 cochairs Valentina Boeva and Benjamin Haibe-Kains adjourned the AACR Conference on AI and Machine Learning. We thank all of the chairs—including @marzyehghassemi.bsky.social and @bowang87.bsky.social—for developing an outstanding program. @valboeva.bsky.social @bhaibeka.bsky.social

🔥A very cool piece from Alexander Theus and team is finally on arXiv: arxiv.org/abs/2506.22712 Ever wondered if you can linearly interpolate between transformers and still get a working model? Now you know how. A breakthrough! 🚀

🚨 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

Our new call for VIB.AI group leaders is online! Junior and senior positions available to develop innovative ML methods in biology. With professorship at CS or Medical Faculty. Deadline 14th June. DM for more info.

The Americans are doing to Kseniia what the Russians did to Brittney Griner for having 0.7 grams of cannabis oil. Except no one is coming to negotiate her freedom and Harvard is sitting on their hands. I am so ashamed. Please share this story. www.nytimes.com/2025/04/11/s...

🥳🔥Our study is out in Genome Biology! Conventional filtering out high-mtRNA cells depletes key malignant populations in cancer single-cell studies. Read it here 👉 genomebiology.biomedcentral.com/articles/10.... Thanks to the dream team: Josephine Yates and Agneizska Kraft!

Interested in cutting-edge ML and AI in cancer research? Join us at the AACR Special Conference on Artificial Intelligence and Machine Learning in Montreal, July 10–12, 2025: 🔗 www.aacr.org/meeting/aacr... ⏳ Submit your abstract by April 16, 2025 at 1 p.m. ET!

🎤 It is a pleasure to welcome Itay Tirosh from the Weizmann Institute at [BC]². Itay will present in the session 'Bioinformatics for cancer research'. 🔹Session chaired by @valboeva.bsky.social and @carmonation.bsky.social 👉Interested? Submit your abstract before 27 Feb: tinyurl.com/49w6wthj

I have big news: @ellis.eu has launched its 2nd major research center, @ellisfinland.bsky.social! I have agreed to start as founding director & the first call for PI positions is open. This is a major opportunity for outstanding researchers, join us! ellisinstitute.fi/PI-recruit

Looking forward to meeting the Lausanne AI Center people and giving a talk on predicting enhancer-promoter interactions using our deep ensemble model this Wednesday! memento.epfl.ch/event/ai-cen...

Looking forward to presenting our recent (and yet unpublished) work at UNIL/CHUV next Thursday! If you're in Lausanne and would like to meet, ping me—I’ll be around from Tuesday to Friday!

🌟If you are at #NeurIPS2024, stop by our poster on the first single-cell #cancer foundation model. Amazing work by @flobarkmann.bsky.social and Alex Theus 👇

📅Are you attending #NeurIPS2024 and curious about the latest in self-supervised learning (SSL) for biology? - Stop by our poster on applying SSL on single-cell data: SSL workshop on Saturday! Work by amazing team of @oovcharenko.bsky.social, P. Toma, Imant D., J. Vogt and @flobarkmann.bsky.social

A mathematical model clarifies the ABC Score formula used in enhancer-gene prediction https://www.biorxiv.org/content/10.1101/2024.11.29.626072v1

Not checking nuclear markers like MALAT1 or intronic reads in your scRNA-seq data?🚨 We show their power to flag low-quality cells—even in top public datasets. It’s time to prioritize better QC for cleaner, more reliable genomics research! Read more: bmcgenomics.biomedcentral.com/articles/10.... 1/8

🚀 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

Should now we start doing it for whole human tumors?!

Hiring! I'm looking for a postdoc in machine learning of spatial single-cell data. Exciting project to develop methods for modelling cellular circuits in disease and regeneration of heart, liver and bone marrow using Xenium data from our lab. tinyurl.com/ymkvk7vn

Before I go to bed let me post an amazing paper by Filipe Pereira’s group (Ervin Ascic et al) for your enjoyment. I think this is a likely fundamental breakthrough in cancer immunotherapy: personalized, yet generic and probably pan-cancer. www.science.org/doi/10.1126/...