Debora Marks

New paper “Proteome-wide model for human disease genetics” is now live at Nature Genetics: rdcu.be/eRu7K
popEVE (pop.evemodel.org) finds the needles in the haystacks of human genetic variation:

Try it! Give feedback -and be kind, it's beta ...

My new paper "Deep Learning is Not So Mysterious or Different": arxiv.org/abs/2503.02113. Generalization behaviours in deep learning can be intuitively understood through a notion of soft inductive biases, and formally characterized with countable hypothesis bounds! 1/12

RNA, RNA, RNA -> RNAGym!
read all about it! biorxiv.org/content/10.110…
Been a long time goal of @deboramarks.bsky.social We tried a million years ago,
sciencedirect.com/science/articl���
Now total refresh led by Rohit Arora and Murphy Angelo and Pascal Notin for pulling together!!

Which RNAs are functional? Been a long time goal of @deboramarks.bsky.social to start an RNA sequence —> function and structure mapping.

Huge thx to team for pushing on this when - led by Rohit Arora and Murphy Angelo for seeing this thru and Pascal Notin for pulling together!!!

End-to-end differentiable homology search for protein fitness prediction.

@yaringal.bsky.social @deboramarks.bsky.social @pascalnotin.bsky.social

arxiv.org/abs/2506.089...

This, by Michael Lynch.

I'd include AI techbros as well.

www.pnas.org/doi/10.1073/...

Fermat's Library | Home Fermat’s Library is a platform for illuminating academic papers. A new scientific paper annotated every week.

Weekly: Great papers across the centuries and subjects! Relaxing!
fermatslibrary.com/journal_club

Machine Learning in Computational Biology Youtube channel for the Machine Learning in Computational Biology conference.

Just under a week until the #MLCB2025 paper/abstract deadline on June 1st! In-person registration is full but you can join the wait list forms.gle/gnj6AAV7oWj6... or watch online at youtube.com/@mlcbconf. Sept 10-11 at @nygenome.org. Full deets at mlcb.org! Please RP.

From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language Models Generative models trained on natural sequences are increasingly used to predict the effects of genetic variation, enabling progress in therapeutic design, disease risk prediction, and synthetic biolog...

New preprint in collaboration with @paulinanunezv.bsky.social supervised by @jonnyfrazer.bsky.social and Mafalda Dias – we propose a simple approach to improving zero-shot variant effect prediction in pre-existing protein and genome language models: 🧶 1/n

www.biorxiv.org/content/10.1...

Want to improve your protein or genomic language model’s performance at zero-shot variant effect prediction? We propose a simple adjustment to likelihood-based predicton

Proteome-wide model for human disease genetics Identifying variants driving disease accelerates both genetic diagnosis and therapeutic development, but missense variants still present a bottleneck as their effects are less straightforward than tru...

Agree for now maybe .. but, maybe, we will get to the point we don’t need family to discover strong variant effects?
Some suggestion this might be true .. see www.medrxiv.org/content/10.1... “Proteome-wide model for human disease genetics”

Important new paper from the Dias-Frazer lab @CRG in Barcelona - needed to be shown. Next-stop non coding variation :)

From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language Models https://www.biorxiv.org/content/10.1101/2025.05.20.655154v1

Is a photo subversive? NSF staff overcome obstacles to 75th anniversary portrait Management tried to quash outpouring of support for beleaguered agency

Is a photo subversive? NSF staff overcome obstacles to 75th anniversary portrait | Science | AAAS www.science.org/content/arti...

Interested in working with us in trying to solve human genetics? Great talk at #VariantEffect25. by @roseorenbuch-art.bsky.social - now the rest of the genome and complex diseases! Contact us by DM or deboramarks@gmail.com if interested.

And now, the final talk of #VariantEffect25. @roseorenbuch-art.bsky.social from Harvard Medical School presents work from our long-standing collaboration, and one that’s very close to my heart: Proteome-wide model for human disease genetics