Jonathan Frazer

The second session (Thr 09/10, morning) was dedicated to the Genomic Basis & History of Disease.

Loops of DNA Equipped Ancient Life To Become Complex | Quanta Magazine New work shows that physical folding of the genome to control genes located far away may have been an early evolutionary development.

I adored writing this piece. It brings together several of the things preoccupying me right now, like chromatin organization and gene regulation. There's so much more to be said on that. Also, these marine critters look gorgeous.
www.quantamagazine.org/loops-of-dna...

The most beautiful data is on the horizon!

This is truly an incredible breakthrough IMO. Really exemplifies what you get when deep domain expertise (popgen/evolution/disease genetics in this case) fuses with cleverly crafted ML. What u get r sleek, well thought out architectures that absolutely destroy the behemoths. Wow!! 1/

Most of the #EurIPS workshops now have their websites online 🙌

A lot of them have active call for participation and/or papers, so if you see something relevant to your field of research please consider submitting!

Links for most workshops are available at: eurips.cc/workshops/

We are excited to share GPN-Star, a cost-effective, biologically grounded genomic language modeling framework that achieves state-of-the-art performance across a wide range of variant effect prediction tasks relevant to human genetics.
www.biorxiv.org/content/10.1...
(1/n)

Excited for a major milestone in our efforts to map enhancers and interpret variants in the human genome:

The E2G Portal! e2g.stanford.edu

This collates our predictions of enhancer-gene regulatory interactions across >1,600 cell types and tissues.

Uses cases 👇

1/

NeurIPS 2025 financial assistance and volunteer applications are now open for both San Diego and Mexico City! The deadline for both applications is 1 Oct AoE. See neurips.cc/Conferences/... for more details.

Many of the most complex and useful functions in biology emerge at the scale of whole genomes.

Today, we share our preprint “Generative design of novel bacteriophages with genome language models”, where we validate the first, functional AI-generated genomes 🧵

Exciting to see our protein binder design pipeline BindCraft published in its final form in @Nature ! This has been an amazing collaborative effort with Lennart, Christian, @sokrypton.org, Bruno and many other amazing lab members and collaborators.

www.nature.com/articles/s41...

News PhD and MSc positions in Phylogenetic, Computational, and/or Evolutionary Paleobiology [Posted September 2025. Deadline is January 15, 2026. See below for information about the lab, student opportu…

I'm hoping to take 1 MSc & 1 PhD student next year in the areas of Phylogenetic, Computational, and/or Evolutionary Paleobiology. Please reach out if you are interested in joining the @oupaleobiology.bsky.social, especially if interested in working on fossil echinoderms. Link for more info below. 🧪

De-novo promoters emerge more readily from random DNA than from genomic DNA Promoters are DNA sequences that help to initiate transcription. Point mutations can create de-novo promoters, which can consequently transcribe inactive genes or create novel transcripts. We know lit...

Excited / nervous to share the “magnum opus” of my postdoc in Andreas Wagner’s lab!

"De-novo promoters emerge more readily from random DNA than from genomic DNA"

This project is the accumulation of 4 years of work, and lays the foundation for my future group. In short, we… (1/4)

@jengreitz.bsky.social l & my lab want to co-hire a computational biologist/biostatistician with project management expertise to help map the regulatory code of the human genome and discover genetic mechanisms of disease.

Details below
careersearch.stanford.edu/jobs/computa...

Plz RT

Assessing variant effect predictors and disease mechanisms in intrinsically disordered proteins Author summary Some parts of proteins, known as intrinsically disordered regions, do not fold into fixed shapes. Instead, they stay flexible and play key roles in controlling how cells work, often by ...

New paper out today in PLOS Comp Biol:
journals.plos.org/ploscompbiol...

Intrinsically disordered regions make variant prediction deceptively easy for benign changes but very hard for pathogenic ones. Our work shows why current tools struggle here, and why disorder-aware approaches are needed.

Biallelic variants in the non-coding RNA gene RNU4-2 cause a recessive neurodevelopmental syndrome with distinct white matter changes Genetic variants in RNU4-2, which encodes U4, a key non-coding small nuclear RNA (snRNA) component of the major spliceosome, were recently shown to cause a prevalent neurodevelopmental disorder (NDD) ...

I am absolutely delighted to share our work describing a new *recessive* condition caused by variants in #RNU4-2. Yes, that #RNU4-2!

tinyurl.com/3j9r56s8
@rociorius.bsky.social @yuyangchen.bsky.social @gregfindlay.bsky.social @dgmacarthur.bsky.social @cassimons.bsky.social @nickywhiffin.bsky.social

A generative deep learning approach to de novo antibiotic design A generative AI platform is developed for de novo antibiotic design, yielding lead compounds with selective antibacterial activity, distinct mechanisms of action, and in vivo efficacy against multidru...

🧪 A generative AI framework designed new antibiotics by exploring uncharted chemical space.

The approach yielded two lead compounds effective against multidrug-resistant N.gonorrhoeae and S.aureus in mouse models of infection. 🧬💻 #MLSky

Probing the Dark Energy in the Functional Protein Universe We show how to localize and quantify the functional evolutionary constraints on natural proteins. The method compares the perturbations caused by local sequence variants to the energetics of the prote...

❗New Preprint w/ C Bueno (‪@cabb99.bsky.social‬), IE Sánchez (@nachoquique.bsky.social‬), PG Wolynes & DU Ferreiro (@diegulise.bsky.social‬)

We define the Protein Dark Energy and use it to localize and quantify the functional evolutionary constraints on natural proteins

arxiv.org/abs/2508.08109

A common takeaway from "the bitter lesson" is we don't need to put effort into encoding inductive biases, we just need compute. Nothing could be further from the truth! Better inductive biases mean better scaling exponents, which means exponential improvements with computation.

This is not just HHMI. All Chan Zuckerberg Initiative funding calls are CLOSED. The Gates Foundation has no Grand Challenges funding opportunities. I've never seen anything like this. Private foundations have just decided to stop supporting biomedical research.

Three major trends in comparative transcriptomics

🧬🧬🧬 New review from the lab:

Evolution of comparative transcriptomics: biological scales, phylogenetic spans, and modeling frameworks

authors.elsevier.com/sd/article/S...

By @mattezambon.bsky.social & @fedemantica.bsky.social, together with @jonnyfrazer.bsky.social & Mafalda Dias.

The 2026 Probabilistic Modeling in Genomics (ProbGen) meeting will be held at UC Berkeley, March 25-28, 2026. We have an amazing list of keynote speakers and session chairs:
probgen2026.github.io

Please help spread the news.

Borzoi-informed fine mapping improves causal variant prioritization in complex trait GWAS Genome-wide association studies (GWAS) have identified thousands of trait-associated loci. Prioritizing causal variants within these loci is critical for characterizing trait biology. Statistical fine...

I'm excited to share work on a research direction my team has been advancing: connecting machine learning derived genetic variant embeddings to downstream tasks in human genetics. This work was led by the amazing Divyanshi Srivastava! www.biorxiv.org/content/10.1...

*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

Excited to be presenting my paper "Deep Learning is Not So Mysterious or Different" tomorrow at ICML, 11 am - 1:30 pm, East Exhibition Hall A-B, E-500. I made a little video overview as part of the ICML process (viewable from Chrome): recorder-v3.slideslive.com#/share?share...

EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅

EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu

eurips.cc

A Collectivist, Economic Perspective on AI Information technology is in the midst of a revolution in which omnipresent data collection and machine learning are impacting the human world as never before. The word "intelligence" is being used as...

What if AI isn’t about building solo geniuses, but designing social systems?
Michael Jordan advocates blending ML, economics, and uncertainty management to prioritize social welfare over mere prediction.
A must-read rethink.
arxiv.org/abs/2507.062...

Check out our latest work on the evolution of animal genome regulation out today in @nature.com. Nicely summarized below by @ianakim.bsky.social.
www.nature.com/articles/s41...

This is a major output from our ERC-StG project Evocellmap @erc.europa.eu at @crg.eu

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/

New preprint - collab with the groups of @mehurles.bsky.social and @dr-appie.bsky.social. We imputed missing fluid intelligence test scores into ~170k @ukbiobank.bsky.social indivs & showed how this reduces bias and increases power for rare+common variant analyses. www.medrxiv.org/content/10.1...

🚨 New paper 🚨 RNA modeling just got its own Gym! 🏋️ Introducing RNAGym, large-scale benchmarks for RNA fitness and structure prediction.
🧵 1/9