New online! Decoding the regulatory genome with large-scale deep learning

Beware of LLM blindspots. #AI4Science

Yijie Kang (CSHL, Stony Brook) from @pkoo562.bsky.social Lab presented "Decoding the sequence basis of Pol II elongation with deep learning"

Exciting symposium on AI and Biology at EMBO | EMBL in Heidelberg on 10-13 March 2026! Excellent lineup of invited speakers across various scales of biology! Deadline for abstract submission is coming up — Dec 2. 🔗 www.embl.org/about/info/c... #EESAIBio @EMBLEvents

Which mutations rewire function of regulatory DNA? Excited to share SEAM: Systematic Explanation of Attribtuion-based Mechanisms. SEAM is an explainable AI method that dissects cis-regulatory mechanisms learned by seq2fun genomic deep learning models. Led by @EESetiz 1/N 🧵👇

Congratulations to John Clarke, Michel Devoret and John Martinis on receiving the 2025 Nobel Prize in Physics! www.nobelprize.org/prizes/physi... I have fond memories of my time in the Clarke lab, where I did my Honors Thesis on ultra low-field MRI w/ SQUIDs as an undergrad at UC Berkeley!

Check out a Research Highlights on our work at @naturemethods by Lin Tang! www.nature.com/articles/s41...

Richard Bonneau giving the last keynote on navigating the complexity of drug discovery and their lab-in-the-loop for molecule design! #MLCB

2025 MLCB day 2 is starting now! Streaming live now! m.youtube.com/watch?v=PxlXNb…

Some technical delays but we are all set! First talk by Alexis Battle! @alexisbattle.bsky.social

2025 Machine Learning in Computational Biology (#MLCB) meeting starts TODAY (9/10) at 9:30a (EST) at the NY Genome Center in NYC! We have a great lineup of keynotes, contributed talks, and posters today and tomorrow Schedule: mlcb.org/schedule Join for free via livestream: m.youtube.com/@mlcbconf

*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

Our work on "Evaluating the representational power of pre-trained DNA language models for regulatory genomics" led by @AmberZqt with help from @NiraliSomia & @stevenyuyy is finally published in Genome Biology! Check it out! genomebiology.biomedcentral.com/articles/10....

One thing that really bothers me with the new "virtual cell" terminology is that it is currently largely focused on a very narrow definition of models that can predict effects of trans perturbations (gene dosage, drugs etc) on gene expression. 1/

Excited to launch our AlphaGenome API goo.gle/3ZPUeFX along with the preprint goo.gle/45AkUyc describing and evaluating our latest DNA sequence model powering the API. Looking forward to seeing how scientists use it! @googledeepmind

This a really exciting leap forward for genomic sequence to activity gene regulation models. It is a genuine improvement over pretty much all SOTA models spanning a wide range of regulatory, transcriptional and post-transcriptional processes. 1/

Congrats @avsecz.bsky.social! Looking forward to exploring what it has learned! 🧬

@pkoo562.bsky.social Peter Koo at #AIxBio

With contributions from fantastic colleagues @martinsteinegger.bsky.social , @mikeinouye.bsky.social, @jlistgarten.bsky.social , @ideasbyjin.bsky.social, @michael-heinzinger.bsky.social, and many more, the first CSHL volume on ML for Protein Science and Engineering is out: lnkd.in/dQdgGPpp

The #MLCB deadline has been extended to June 3 (AOE)! Still time to submit your cutting-edge work on machine learning in biology. Don’t miss out! 👉 www.mlcb.org #ComputationalBiology #ML4Bio

Building virtual cells is a great goal in the age of AI, but it requires far more than training transformers with scRNAseq. *Scaling* as the primary strategy with hopes of emergent properties is lazy. Will the plan to fuse representations across mediocre (unimodal) foundation models work?!

Awesome paper. Simple post-hoc trick (averaging over homologs) with elegant evolution theory dramatically improves zero shot coding variant effect prediction in pLMs & actually delivers better results from the larger models (inverting the trend with raw likelihoods). 1/

Excited to share an update to D3 (DNA Discrete Diffusion) — an application of score-entropy discrete diffusion model for regulatory genomics! 🧬 Paper: biorxiv.org/content/10.110… (See thread below 👇) (1/n)

My sympathy and support for all the international students and postdocs at Harvard. I can only imagine how scary this must feel. Stay strong. And if there's anything I can do to help those in compbio, please reach out. All of us need to rally to help them out. 1/

The premier conference on Machine Learning for Computational Biology is Sep 9-10 at the NY Genome Center in NYC! Submission deadline is June 1 for 2-page abstracts and 8-page papers (eligible for proceedings track). Registration is now open! (Link below) Please retweet!

Free in-person registration is open for #MLCB2025! Sept 10-11 at @nygenome.org and online at youtube.com/@mlcbconf. Paper/abstract deadline is June 1, more deets including our fantastic invited speaker lineup at mlcb.org! Please RP.

As #NeurIPS2025 submission deadline approaches, I’m expecting lots of posts of papers that be like…

At @iclr_conf and interested in AI x Bio? Come see new work by the Koo Lab! 1. Oral presentation at @gembioworkshop by Evan Seitz (@EESeitz) on Decoding the mechanistic impact of genetic variation on regulatory sequences with deep learning! openreview.net/forum?id=Ptj...

How can we predict spatial transcriptomics from histology images to enable simple, affordable, and reliable analysis of spatially resolved gene expression in routine clinical use? 🤔 Introducing DeepSpot – a deep learning model designed to tackle this! 🧵👇 www.medrxiv.org/content/10.1...

Evaluations are easy when you don't test ML models under distributional shifts... (we desperately need collaboration with wet-lab biologist to generate data under varying levels of covariate shift to better evaluate generalization capabilities of genomics AI models!)

Proud of Jakub Kaczmarzyk, 3rd grad student (MD/PhD) to join my lab, who is defending today! Jakub has been instrumental in shaping my lab’s culture and he’s done great science along the way — developing tools to explain histopathology foundation models. Thanks for everything!

Can we learn protein biology from a language model? In new work led by @liambai.bsky.social and me, we explore how sparse autoencoders can help us understand biology—going from mechanistic interpretability to mechanistic biology.

MLCB is an excellent conference and a great opportunity to meet other people in the field. Highly recommend attending!

Excited for this meeting!

[SAVE THE DATE] MLCB 2025 is happening Sept 10-11 at the NY Genome Center in NYC! Attend the premier conference at the intersection of ML & Bio, share your research and make lasting connections! Submission deadline: June 1 More details: mlcb.github.io Help spread the word—please RT! #MLCB2025

Tumors need a lot of nutrients to grow. By engineering and implanting fat cells to outcompete cancers for nutrients we can suppress them. Novel cancer therapy called Adipose Manipulation Transplantation (AMT). AMAZING work led by and dedicated to Hai Nguyen. www.nature.com/articles/s41...

Massively parallel reporter assays (MPRAs) testing >680,000 sequences combined with machine learning to improve regulatory element & variant effect prediction. Amazing work by @vagar.bsky.social, Fumitaka Inoue, @jshendure.bsky.social and many others as part of ENCODE. www.nature.com/articles/s41...

@anusri.bsky.social first author & developer of ChromBPNet is looking for opportunities in industry in ML for bio/genomics. She is an excellent rigorous scientist (as u can see from the paper). Very strongly recommend her. Plz reach out to her if u have openings. Plz forward.

Deep learning with data beyond the genome: Our paper on active machine learning to model regulatory DNA is out today in Cell Systems. With functional assays and DNA synthesis you can generate any training examples, not just genomic sequences. 🧵 kwnsfk27.r.eu-west-1.awstrack.me/L0/https:%2F...

You probably already know, but: @pkoo562.bsky.social is awesome. DM him.

Our ChromBPNet preprint out! www.biorxiv.org/content/10.1... Huge congrats to Anusri! This was quite a slog (for both of us) but we r very proud of this one! It is a long read but worth it IMHO. Methods r in the supp. materials. Bluetorial coming soon below 1/

Great positions! Go work with Peter, he is excellent!

I'm hiring: 1. Research associate (wet-lab w/ phd) to generate mpra perturbation data 2. ML postdoc to build multimodal generative AI for DNA (eg diffusion and LLMs) 3. Bioinformatician (any level) to process and harmonize functional genomics data to train foundation models DM me if interested!

In a big life update, I successfully defended my PhD thesis - massive thanks to my PI Nathan and assessors @steinaerts.bsky.social @proftomellis.bsky.social . Thrilled to share that I will be joining @pkoo562.bsky.social at CSHL in the new year for a post-doc improving genomic deep learning models!

Congrats (again)! Looking forward to working with you!

🚨 We’re hiring! 🚨 The Simons Center for Quantitative Biology at Cold Spring Harbor Laboratory is looking for a Research Technician to join our team. If you’re passionate about genomics, AI, and experimental science, we want to hear from you. Help us spread the word! jobrxiv.org/job/cold-spr...

Excited to be presenting Orthrus with Ruain Shi and Keren Isaev @karini925.bsky.social today! We will be presenting our spotlight at the workshop on AI for new drug modalities #NeurIPS2024 Come chat about a new approach to mRNA representation learning!

Also want to point to this other recent preprint that also shows that optimized ab-initio CNN models beat DNALMs even on the (relatively pointless) surrogate tasks used in the DNALM papers. CNNs also beat several other foundation models in other domains. arxiv.org/abs/2411.02796 #bioMLeval