Reposted by Jonathan FrazerAndres Bendesky @bendeskylab.com · 04/10/202610 days left to apply for an Assistant Professorship in Evolutionary Biology at Columbia. 01729
Reposted by Jonathan FrazerBen de Bivort @debivort.bsky.social · 22/09/2026Hello friends, the Harvard Life Science departments have banded together to hire a new colleague working at the intersection of Life Sciences and AI. Could be primarily an experimentalist, or could be primarily a compute/theorist. academicpositions.harvard.edu/postings/16773academicpositions.harvard.eduTenure-Track Professor in Life Science and AIThe Life Sciences Departments in Harvard Faculty of Arts and Sciences seek to recruit a tenure-track professor whose research is at the interface of AI and life sciences, from methodological developme... 34154
Reposted by Jonathan FrazerMartin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 24/09/2026AlphaFold Database is expanding into pandemic preparedness. Together with NVIDIA, DeepMind, EBI et al. we exhaustively predicted ~1.7 million homo- & heterodimers across 2,812 viral proteomes, resulting in 8,028 high-confidence predictions. 📄 research.nvidia.com/labs/dbr/ass... 🌐 alphafold.ebi.ac.uk 28838
Reposted by Jonathan FrazerEzequiel Galpern @eag91.bsky.social · 25/09/2026🧬 What do deep-learning models for proteins actually learn? Our new review looks at how model predictions relate to fitness, folding stability and function. With @cwjpugh.bsky.social, Mafalda Dias & @jonnyfrazer.bsky.social 🔗 chemrxiv.org/doi/full/10....chemrxiv.orgFrom sequences and structures to fitness, folding and function: challenges in the age of AI | ChemRxivDeep-learning models have transformed our ability to predict the phenotypic effects of sequence perturbations. Protein language models (pLMs) score the evolutionary propensity of any amino-acid substi... 177
Reposted by Jonathan FrazerCentre de Regulació Genòmica (CRG) @crg.eu · 15/09/2026We are at a critical moment for the future of European science. As @eu-life.bsky.social founder, and together with 100s of institutes and universities across the continent, we call for an ambitious funding pot for FP10. See Luis Serrano's comments in El Mundo. www.mundoamerica.com/entertainmen...mundoamerica.comEuropean science calls for ambitious investment in research: "Current decisions determine Europe's future. We are falling behind China and the USA""To remain global leaders, a competitive economic power, and a sovereign actor, Europe needs strong science and innovation." Seven scientific organizations, representing... 066
Reposted by Jonathan FrazerAndres Bendesky @bendeskylab.com · 11/09/2026We have a tenure-track faculty position in Evolutionary Biology in Columbia's E3B Department. Application deadline is October 15. Come be our colleague. Please RT! apply.interfolio.com/193016apply.interfolio.com Apply - Interfolio {{$ctrl.$state.data.pageTitle}} - Apply - Interfolio 082105
Jonathan Frazer @jonnyfrazer.bsky.social · 10/09/2026Congratulations! Beautiful work. I know Mafalda and @m1quelag.bsky.social found it a pleasure to review. 031
Reposted by Jonathan FrazerNik Baya @nbaya.bsky.social · 19/08/2026Introducing the BRaVa results browser v1! 🎉 1.2M+ individuals across 10 global biobanks 44 heritable, disease-relevant traits (and counting) 419M gene- & variant-level association tests ➡️ nikbaya.github.io/brava_browser/ 1176
Reposted by Jonathan FrazerArc Institute @arcinstitute.org · 20/08/2026The 2026 Virtual Cell Challenge has begun! Submissions and the leaderboard are now open. This year's task: multi-context generalization and zero-shot prediction. Models will need to predict perturbation responses in cellular contexts with no training data. arcinstitute.org/news/virtual...arcinstitute.orgThe 2026 Virtual Cell Challenge: predicting perturbation responses in cell contexts a model has never seen | Arc InstituteRegistration for the 2026 Virtual Cell Challenge is open at virtualcellchallenge.org. This year the task is zero-shot: we are not releasing a training set, and the evaluation dataset is far more expan... 1145
Reposted by Jonathan FrazerBIST-Barcelona Institute of Science and Technology @bist.eu · 16/06/2026🦠 How did our cells originate? A study by @gabaldonlab.bsky.social at @irbbarcelona.org & @bsc-cns.bsky.social suggests cellular complexity emerged gradually over millions of years, rather than from a single evolutionary event. 📝 Published in @nature.com #BISTCommunity 👉 bist.eu/a-study-by-i... 0106
Reposted by Jonathan FrazerAtlas of Variant Effects Alliance @varianteffect.bsky.social · 10/08/2026@eag91.bsky.social was recently the 100th speaker of our Variant Effects Seminar Series. The work he presented has just been published as a preprint. Learn more: tinyurl.com/mrxf5zxv @solersanchisx.bsky.social, @cwjpugh.bsky.social, @federicobilleci.bsky.social, @jonnyfrazer.bsky.sociallnkd.inBlending physics-based models improves protein folding stability prediction | Ezequiel Galpern posted on the topic | LinkedIn🎉 New preprint: “Blending physics-based and inverse folding models to disentangle variant effects on stability and function” ➡️ Read it on https://lnkd.in/dCDw-3nb Together with Xavier Soler Sanchis... 073
Reposted by Jonathan FrazerBen Lehner @benlehner.bsky.social · 09/08/2026Conservation and divergence in the allosteric architectures of five human protein kinases. Excited to share our new preprint by @carlafolgado.bsky.social @tonibeltran.bsky.social @sangerinstitute.bsky.social @crg.eu @ibv-csic.bsky.social www.biorxiv.org/content/10.6...biorxiv.orgConservation and divergence in the allosteric architectures of five human protein kinasesProtein kinases are central to biological regulation, dysregulated in many diseases, and the targets of a hundred clinically-approved drugs. Structural conservation of kinase active sites makes the de... 02010
Reposted by Jonathan FrazerEzequiel Galpern @eag91.bsky.social · 08/08/2026🚨 Paid MSc research opportunity at CRG Barcelona! With Mafalda Dias and @jonnyfrazer.bsky.social, we’re hosting a 4-month MSc project: 🧬 “Folding versus function: disentangling the molecular mechanisms of missense variants in gene-trait associations” More info 👇 www.crg.eu/en/content/t... 035
Reposted by Jonathan FrazerEli Weinstein @eliweinstein.bsky.social · 07/08/2026Very excited about our new results, showing variational synthesis + large scale screens + co-designed training -> robust scaling laws for sequence-activity models. 041
Jonathan Frazer @jonnyfrazer.bsky.social · 06/08/2026Also, applications are open for masters projects at the CRG, including one in our group to work with @eag91.bsky.social www.crg.eu/en/content/t...crg.euCentre for Genomic Regulation Website 011
Jonathan Frazer @jonnyfrazer.bsky.social · 05/08/2026Blend to disentangle! New preprint led by our talented postdoc @eag91.bsky.social 163
Reposted by Jonathan FrazerMiquel Anglada-Girotto @m1quelag.bsky.social · 28/07/20261/ We’ve been working on making it easier to fine-tune AlphaGenome on new RNA-seq samples, with a focus on one of my favourite regulatory layers: splicing! Blog post: genomicsxai.github.io/blogs/2026-0...genomicsxai.github.ioBeyond coverage tracks: fine-tuning AlphaGenome's splicing heads from scratchSummary DeepMind has released AlphaGenome’s code and model weights, and the community has since developed alphagenome_ft and alphagenome-pytorch to enable seamless fine-tuning in both JAX and PyTorch.... 1164
Reposted by Jonathan FrazerPeter Koo @pkoo562.bsky.social · 23/05/2025Excited 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) 2195
Reposted by Jonathan FrazerHannah Dickmänken @hannahdckmnkn.bsky.social · 29/01/2026Paper alert! 💻 How many cells do you need to train reliable deep learning models in regulatory genomics? We asked how data quality, sequencing depth, and dataset size affect training of sequence-to-function models from scATAC-seq. Out now www.nature.com/articles/s41... (details below)nature.comEvaluating single-cell ATAC-seq atlasing technologies using sequence-to-function modeling - Nature CommunicationsGenerating high-quality training data for machine learning is costly. Here, authors include sequence-to-function modeling in benchmarking of custom and commercial droplet-based scATAC platforms, and r... 23417
Reposted by Jonathan FrazerLars Velten @larsplus.bsky.social · 16/07/2026@juruehle.bsky.social's PhD work is now out in Genome Biology 📚🧬 : Lentiviral single-cell MPRA of synthetic enhancers reveals motif affinity-based encoding of cell state specificity link.springer.com/article/10.1186/s13059-026-04186-9 Julia achieved three cool things with this work...🧵link.springer.comLentiviral single-cell MPRA of synthetic enhancers reveals motif affinity-based encoding of cell state specificity - Genome BiologyBackground Cell state-specific gene expression programs emerge from the interplay between cis-regulatory elements (CREs), such as enhancers, and transcription factors (TFs). Massively parallel reporte... 1186
Reposted by Jonathan FrazerElzo de Wit lab @ NKI @dewitlab.bsky.social · 06/07/2026(1/10) The majority of human genetic variation is located in non-coding regions. The great challenge of the post-genomic era is to assign function to these variants. We reasoned that combining haplotyping with allele-specific multiomics can help pinpoint the functional ones: rdcu.be/fgr5W. A thread:rdcu.beMapping functional non-coding variation in individual human genomes through haplotyping, multiomics, and deep learningNature Communications - How non-coding mutations in DNA contribute to phenotypes is a largely unresolved question. Here the authors integrate personal genomics and machine learning to identify... 15324
Reposted by Jonathan FrazerCentre de Regulació Genòmica (CRG) @crg.eu · 15/06/2026Mafalda Dias es finalista del premio Vanguardia de la Ciencia. Su línea de investigación está ayudando agilizar el diagnóstico de enfermedades raras, ofreciendo una evidencia adicional para médicos que ya tienen sospechas sobre ciertos genes implicados según los síntomas. ¡Vota ahora!lavanguardia.com“Diagnosticamos enfermedades raras analizando millones de años de evolución”Vota a las finalistas del premio Vanguardia de la Ciencia 075
Jonathan Frazer @jonnyfrazer.bsky.social · 01/06/2026Mafalda has been shortlisted for the 2026 Premio Vanguardia de la Ciencia, one of the more visible science prizes in Spain. Her interview: www.lavanguardia.com/vanguardia-d... ...and we would be very grateful if you could vote here: www.lavanguardia.com/vanguardia-d...lavanguardia.comLa IA mejora el estudio de las enfermedades rarasVota a las finalistas del premio Vanguardia de la Ciencia 051
Reposted by Jonathan FrazerAndrew Gordon Wilson @andrewgwils.bsky.social · 27/05/2026How much does a language model forget when finetuned on new tasks? We show both model size and optimization matter and forgetting can be nearly eliminated with self-generated replay! arxiv.org/abs/2605.26097 w/Martin Marek, Dongkyu Cho, Shikai Qiu, Rumi Chunara, and Pavel Izmailov. 1/8 1498
Reposted by Jonathan FrazerALLOX @alloxbio.bsky.social · 27/05/2026AI drug discovery has a data problem. We're fixing it. At ALLOX, we've spent the last few years building something that didn't exist before: a platform that systematically maps functional hotspots at scale, measuring the effects of mutations on protein-protein interactions across the proteome. 143
Reposted by Jonathan FrazerKipoi @kipoizoo.bsky.social · 28/04/2026Join us for our next Kipoi Seminar with Noor Youssef, Harvard Medical School @harvardmed.bsky.social @deboramarks.bsky.social 👉 Predicting Viral Evolution to Accelerate Vaccine and Therapeutic Design 🧬 Wed May 6, 5:30pm CET 🍃http://kipoi.org/seminar 🦋 @kipoizoo.bsky.social 021
Jonathan Frazer @jonnyfrazer.bsky.social · 10/04/2026Very nice paper from Regeneron www.nature.com/articles/s41...nature.comPopulation-scale repeat expansions elucidate disease risk and brain atrophy - NatureDecreased brain volumes and increased NfL levels can be observed earlier than disease diagnosis in short-tandem-repeat-associated neurological diseases. 030
Reposted by Jonathan FrazerIRB Barcelona @irbbarcelona.org · 08/04/2026🧬 What if reading a tumor's mutations could tell us exactly how to fight it? Dr. @nlbigas.bsky.social is doing exactly that — decoding the genomic fingerprints of #cancer to guide personalized treatments. This is #CancerResearch, reimagined. youtube.comBiomedical genomics - Dr. Núria López-BigasDr. Núria López-Bigas, Group Leader, Biomedical Genomics Laboratory, IRB Barcelona. 062
Reposted by Jonathan FrazerDebora Marks @deboramarks.bsky.social · 23/03/2026Meet evedesign: open-source AI, accessible protein design ✅Combine models for multiobjective optimization ✅Integrate experimental data ✅ Run on your own infrastructure 📄Paper: www.biorxiv.org/content/10.6... 💻Code: github.com/evedesignbio 🌐Webserver: evedesign.bio Collaborate: hello@evedesign.biodeboramarkslab.substack.comevedesign: accessible biosequence design with a unified frameworkUnified protein design for computational researchers and experimentalists 0276
Reposted by Jonathan FrazerClaus Wilke @clauswilke.com · 11/03/2026New paper showing that much of the apparent success of protein language models in predicting mutational effects is a mirage: These models mostly memorize sites. 1/ www.biorxiv.org/content/10.6...biorxiv.org 617972
Reposted by Jonathan FrazerJulia Rühle @juruehle.bsky.social · 04/03/2026The main project of my PhD 🧬🔬 is out: we developed single-cell lentiMPRA, a lentivirus-based method to measure enhancer activity and transcriptomes at single-cell resolution. We then applied sc-lentiMPRA to fully synthetic enhancers 🧩... 🔗 doi.org/10.64898/202...doi.org 34613
Reposted by Jonathan FrazerAlejo Rodriguez-Fraticelli @alejofraticelli.bsky.social · 26/02/2026🚨 NEW @FraticelliLab PREPRINT JUST WENT LIVE biorxiv.org/content/10.6... Here, we describe PLSTCs, Soluplus-based expansion cultures of primary mouse *Acute Myeloid Leukemia* Stem Cells. And then we use LARRY barcoding to identify drivers of leukemogenicity and drug resistance! 1298
Reposted by Jonathan FrazerFabian Theis @fabiantheis.bsky.social · 24/02/2026Join us at Cell Symposia: Single-Cell Biology in the Era of AI (Dec 2–4, 2026, Munich) 🇩🇪 From multi-omics to AI-driven models of cellular dynamics — an exciting lineup across experimental & computational biology. Hope to see you there! 🔗 www.cell-symposia.com/single-cell-...cell-symposia.comHome – Cell Symposia: Decoding Cellular Complexity: Single Cell Biology in the Era of AICell Symposia: Decoding Cellular Complexity: Single Cell Biology in the Era of AI 01510
Reposted by Jonathan FrazerFabian Theis @fabiantheis.bsky.social · 23/02/2026🚀 From modality-specific to compositional foundation models for cell biology Happy to share our new Perspective in Cell Systems. We describe an emerging shift toward compositional multimodal architectures 🧩 authors.elsevier.com/c/1mdzg8YyDf... 1113
Reposted by Jonathan FrazerLars Velten @larsplus.bsky.social · 17/02/2026Early bird registration is closing Feb 28! We will have an AMAZING party! 023
Reposted by Jonathan FrazerPhillip Isola @phillipisola.bsky.social · 11/02/2026Our grad-level "Deep Learning" course (MIT's 6.7960) is now freely available online through OpenCourseWare: ocw.mit.edu/courses/6-79... Lecture videos, psets, and readings are all provided. Had a lot of fun teaching this with @sarameghanbeery.bsky.social and @jeremybernste.in! 312438
Jonathan Frazer @jonnyfrazer.bsky.social · 09/02/2026Post 3 of attempting to share more ML/Bio papers on Bluesky: Accelerating Scientific Research with Gemini: Case Studies and Common Techniques arxiv.org/abs/2602.03837arxiv.orgAccelerating Scientific Research with Gemini: Case Studies and Common TechniquesRecent advances in large language models (LLMs) have opened new avenues for accelerating scientific research. While models are increasingly capable of assisting with routine tasks, their ability to co... 030
Reposted by Jonathan FrazerJonas Hübotter @jonhue.bsky.social · 29/01/2026Training LLMs with verifiable rewards uses 1bit signal per generated response. This hides why the model failed. Today, we introduce a simple algorithm that enables the model to learn from any rich feedback! And then turns it into dense supervision. (1/n) 1103
Jonathan Frazer @jonnyfrazer.bsky.social · 06/02/2026Post 2 of sharing interesting ML/bio papers that don’t seem to be getting much attention on Bluesky. Three papers on self-distillation, all from the same week! arxiv.org/abs/2601.18734 arxiv.org/abs/2601.19897 arxiv.org/abs/2601.20802arxiv.orgSelf-Distilled Reasoner: On-Policy Self-Distillation for Large Language ModelsKnowledge distillation improves large language model (LLM) reasoning by compressing the knowledge of a teacher LLM to train smaller LLMs. On-policy distillation advances this approach by having the st... 020
Reposted by Jonathan FrazerAndrew Saxe @saxelab.bsky.social · 03/02/2026Why don’t neural networks learn all at once, but instead progress from simple to complex solutions? And what does “simple” even mean across different neural network architectures? Sharing our new paper @iclr_conf led by Yedi Zhang with Peter Latham arxiv.org/abs/2512.20607 716042
Jonathan Frazer @jonnyfrazer.bsky.social · 03/02/2026Bluesky doesn’t really shine yet as a place to discover papers, especially at the intersection of biology and ML. To help a little, I’m going to start sharing papers I find interesting. To kick things off, here’s one from @petar-v.bsky.social and colleagues at DeepMind arxiv.org/abs/2601.22950arxiv.orgPerplexity Cannot Always Tell Right from WrongPerplexity -- a function measuring a model's overall level of "surprise" when encountering a particular output -- has gained significant traction in recent years, both as a loss function and as a simp... 36510
Reposted by Jonathan FrazerEzequiel Galpern @eag91.bsky.social · 22/01/2026"Probing the Dark Energy in the Functional Protein Universe" is now published in @pnas.org 🎉 www.pnas.org/doi/10.1073/...pnas.orgPNASProceedings of the National Academy of Sciences (PNAS), a peer reviewed journal of the National Academy of Sciences (NAS) - an authoritative source of high-impact, original research that broadly spans... 064
Reposted by Jonathan FrazerKevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 16/01/2026For no reason, I remembered today that I too once got to take a picture holding Nobel Prize that I didn't earn 21219
Reposted by Jonathan FrazerStein Aerts @steinaerts.bsky.social · 15/01/2026TF-MINDI is out! A new method to learn cis-regulatory codes through rich embeddings of TF binding sites. TF-MINDI decomposes motif neighbourhoods, and works downstream of any sequence-to-function deep learning model. We deeply study the enhancer code in human neural development, check out the thread 16038
Reposted by Jonathan FrazerSarah Gurev @sarahgurev.bsky.social · 13/01/2026We’ve updated the EVEREST benchmark to include real-world viral evolution! www.biorxiv.org/content/10.1... Co-led by Noor Youssef and me, along with co-authors Navami Jain, Aarushi Mehrotra, Sarrah Leung, Abigail Jackson, @deboramarks.bsky.social, and with @cepi.net @futurehousesf.bsky.social! 152
Reposted by Jonathan FrazerManuel Irimia @mirimiam.bsky.social · 23/12/2025🚨🚨🚨 We're looking for a research tech to work on alt splicing, pancreatic islets and diabetes. The goal is to set a high-throughput platform to investigate the role of alternative exons in beta cell biology! Interested in joining our lab at @melisupf.bsky.social? 👇 www.upf.edu/documents/d/...upf.edu 065
Jonathan Frazer @jonnyfrazer.bsky.social · 03/12/2025My guess is main conference (bridge) workshops (panda) 100