We are very happy to have been able to show people what we do at the SynBio Lab in Biomedicina BCN! Thank you for coming to see us at the #openPRBB

📸 #FotoDeLaSetmana: L'#openPRBB va acollir més de 1.500 persones que es van apropar al #PRBB per descobrir la seva ciència de la mà dels seus protagonistes. 🔗 ellipse.prbb.org/ca/openprbb-20…

Yesterday the SynBio lab got together to celebrate the lab's christmas dinner! it's great to be able to enjoy the group on a special occasion. Happy Holidays to all!!😚☃️🎁🎄

El taller de la Lorena i la Maria sobre bacteris marins i corrosió dels vaixells va ser tot un èxit! ⛵️🦠 Mireu quins bacteris marins tan originals que van inventar els petits investigadors que van passar per la #FestaDeLaCiència! 😍

🎉Exciting news! Our very own Noelia Ferruz has begun work on ATHENA, a new AI model designed to create custom proteins. From carbon capture to environmental cleanup, the project can provide completely new ways of tackling long elusive problems. The project is backed by a €1.5M

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Chemistry with one half to David Baker “for computational protein design” and the other half jointly to Demis Hassabis and John M. Jumper “for protein structure prediction.”

Do you have a wizard in your lab? Nominate your scientific mentor by filling out a form on our website for a chance to win prizes—earn an extra entry by resharing this post with the hashtag #LabWiz and tag Promega! Explore our resources and join the fun. bit.ly/4i4nsbF

#LabWiz Promega Corporation

Guiding Generative Protein Language Models with Reinforcement Learning 1. The paper introduces DPO_pLM, a reinforcement learning (RL) framework for optimizing protein sequences using pre-trained protein language models (pLMs), enabling the discovery of sequences with desired

Check out our latest work to improve AI-based protein design 🧪

Protein language models excel at generating natural-like proteins but struggle to sample from rare, high-value regions, like highly active enzymes. We introduce DPO_pLM, an RL framework to iteratively optimize protein properties! See Filippo’s thread and arxiv.org/abs/2412.12979

Check out our latest work, presented at GEMBio Workshop at ICLR 2026 2025! Really excited to see all recent contributions to the field of AI protein design and experimental feedback 🧬🧪🚀

Katie Partington at #VariantEffect25

It’s never been easier to align your protein language model (pLM)! We’ve released a major update to our ProtRL repo: ✅ GRPO via Hugging Face Trainer ✅ New support for weighted DPO Built for flexible, scalable RL with HF trainer base! Check here: github.com/AI4PDLab/ProtRL