Jonathan Frazer (@jonnygfrazer) 's Twitter Profile
Jonathan Frazer

@jonnygfrazer

Probabilistic machine learning for diagnosis and preemptive care. #EvolutionaryMedicine. PI at the @CRGenomica.

ID: 924715145938587648

linkhttps://www.crg.eu/ca/programmes-groups/dias-frazer-lab calendar_today29-10-2017 19:10:45

892 Tweet

1,1K Followers

2,2K Following

Antoine Wehenkel (@wehenkelantoine) 's Twitter Profile Photo

Alert non-LLM internship position in Zurich Health AI 🍏🚨🧑‍💻 If you 1) have a strong background in deep probabilistic modeling, SBI, hybrid learning or causality 2) are curious about exciting health applications, you should apply! jobs.apple.com/en-il/details/…

Will Ratcliff (@wc_ratcliff) 's Twitter Profile Photo

New preprint up! We sequenced hundreds of samples from across one of Earth's oldest living organisms - the Pando aspen clone - to understand how mutations accumulate and spread in long-lived clonal organisms. Our results were…surprising. 1/30

New preprint up! We sequenced hundreds of samples from across one of Earth's oldest living organisms - the Pando aspen clone - to understand how mutations accumulate and spread in long-lived clonal organisms. Our results were…surprising. 1/30
James Sharpe (@_jamessharpe) 's Twitter Profile Photo

I like this take on interdisciplinarity - it rings true to me. Be brave - don´t be afraid to venture out into topics that you don't necessarily master, but at the same time keep a balance: true expertise and scholarship in your key fields is also important.

Atlas of Variant Effects Alliance (@varianteffects) 's Twitter Profile Photo

📢Join us for the first Variant Effects Seminar Series OPEN MIC session on Dec 3, 9-10am PT (5-6pm GMT+1). w/special guests Benedetta Bolognesi Jonathan Frazer Don't miss this exciting discussion! #OpenMic #VariantOfUncertainSignificance #VariantPrediction 🎙️ℹ️varianteffect.org/seminar-series

📢Join us for the first Variant Effects Seminar Series OPEN MIC session on Dec 3, 9-10am PT (5-6pm GMT+1). w/special guests <a href="/Bennibolo/">Benedetta Bolognesi</a> <a href="/Jonnygfrazer/">Jonathan Frazer</a> Don't miss this exciting discussion! #OpenMic
#VariantOfUncertainSignificance #VariantPrediction 🎙️ℹ️varianteffect.org/seminar-series
Jonathan Frazer (@jonnygfrazer) 's Twitter Profile Photo

Models of variant effects have come a long way in the last few years. When it comes to diagnosis and preventative care, how can we make safe and yet efficient use of them? Here are some of our (Mafalda Dias Rose Orenbuch Debora Marks) thoughts authors.elsevier.com/c/1k7J9_4GsX0xy

Noor Youssef (@nooryoussef03) 's Twitter Profile Photo

🚨 New in Immunity ! EVE-Vax, an AI model that anticipates future viral evolution and designs antigens to proactively test vaccines + therapeutics—before variants even emerge. We envision this work will help make future-proofed vaccines and therapeutics. 👇 (1/7)

Tomas Marques-Bonet (@tmarquesbonet) 's Twitter Profile Photo

Postdoc opportunity! The Comparative Genomics lab (Institute of Evolutionary Biology (IBE), UPF Barcelona) is seeking a postdoc with experience to work on environmental DNA and mammalian monitoring together with Esther Lizano ! CVs -> [email protected] #postdoc #genomics #eDNA #conservation #Barcelona

Postdoc opportunity! The Comparative Genomics lab (<a href="/IBE_Barcelona/">Institute of Evolutionary Biology (IBE)</a>, <a href="/UPFBarcelona/">UPF Barcelona</a>) is seeking a postdoc with experience to work on environmental DNA and mammalian monitoring together with <a href="/estherlizano/">Esther Lizano</a> !
CVs -&gt; cvtmblab@gmail.com #postdoc #genomics #eDNA #conservation #Barcelona
Biology+AI Daily (@biologyaidaily) 's Twitter Profile Photo

From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language Models 1.This study introduces Likelihood-Fitness Bridging (LFB), a method that improves variant effect prediction in protein and genome language models (pLMs and gLMs) by averaging

From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language Models

1.This study introduces Likelihood-Fitness Bridging (LFB), a method that improves variant effect prediction in protein and genome language models (pLMs and gLMs) by averaging
Ruben Weitzman (@ruben_weitzman) 's Twitter Profile Photo

🚨ICML Paper Alert🚨 What if finding the right protein homologs wasn't a slow search, but a learned part of the model itself? We introduce 𝐏𝐫𝐨𝐭𝐫𝐢𝐞𝐯𝐞𝐫, an end-to-end framework that learns to retrieve the most useful homologs for self-supervised reconstruction! (1/12)

🚨ICML Paper Alert🚨
What if finding the right protein homologs wasn't a slow search, but a learned part of the model itself?
We introduce 𝐏𝐫𝐨𝐭𝐫𝐢𝐞𝐯𝐞𝐫, an end-to-end framework that learns to retrieve the most useful homologs for self-supervised reconstruction! (1/12)
Jose Miguel Hernández-Lobato (@jmhernandez233) 's Twitter Profile Photo

Looking for Postdoc/Research Assistant to work on deep generative models, with a focus on the domain of molecules. Application deadline 3 July 2025. More info: jobs.cam.ac.uk/job/51666/

Aviv Spinner (@avivspinner) 's Twitter Profile Photo

What would our data landscapes look like if we could biochemically characterize 100s, 1000s, 10^n evolutionary sequences? Papers like this make strides towards that moonshot dream!! Such neat work from Margaux Pinney, Ph.D. lab! science.org/doi/10.1126/sc…

Alan Amin (@alannawzadamin) 's Twitter Profile Photo

There are many domain-specific noise processes for discrete diffusion, but masking dominates! Why? We show masking exploits a key property of discrete diffusion, which we use to unlock the potential of those structured processes and beat masking! Nate Gruver Andrew Gordon Wilson 1/7

There are many domain-specific noise processes for discrete diffusion, but masking dominates! Why? We show masking exploits a key property of discrete diffusion, which we use to unlock the potential of those structured processes and beat masking! <a href="/gruver_nate/">Nate Gruver</a> <a href="/andrewgwils/">Andrew Gordon Wilson</a> 1/7