New 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...

Very proud of this paper, now officially out at PRX LIFE journals.aps.org/prxlife/abst.... Here @mrazo.bsky.social shows that geometry-aware autoencoder architecture can discover low dimensional phenotypic spaces traversed by evolution. 1/2

Beyond Mendel: a new genetics agenda Most traits aren’t “one gene–one trait”. A Genetics perspective calls for new experimental paradigms to capture polygenic effects in real environmental context—backed by large-scale automated phenotyping and new infrastructure. www.evolbio.mpg.de/3866699/news...

Job alert: open position for a Professor or Associate Professor of Computational Genomics in Health and Disease at University College London. Based in the Department of Genetics, Evolution and Environment of UCL, and UGI, and funded by the UCL Health Strategy. www.ucl.ac.uk/work-at-ucl/... 🧪

Have you ever wondered 🤔... Does phenotypic variance respond to environmental perturbation? Does it have a genetic basis? Are mean and variance regulating loci exposed to different selection pressures? These and more questions are explored in our new preprint 🔥 www.biorxiv.org/content/10.6...

A huge thank you to Iva and Cynthia @seaprof.bsky.social and the all Riginos lab for inviting me to make a modest contribution to this study. My first coral paper 🌊🪸 🎉 A dream come true 😊. I really encourage you to read it #MustRead Two major take-home messages for hybridization genomics 👇

Can we simulate realistic evolutionary trajectories and “replay the tape of life”? In this work, we propose a flexible, generalizable deep learning framework for modeling how the entire protein sequence evolves over time while capturing complex interactions across sites. 1/n doi.org/10.64898/202...

Hello again! After defending my PhD in population genomics at University of Bern and taking a multi-year hiatus from the digital world, I’m back to reconnect with the scientific community. Here is a quick "comeback thread" on what I've been up to: 🧵1/6