What if we could universally recombine, insert, delete, or invert any two pieces of DNA? In back-to-back nature papers, we report the discovery of bridge RNAs and 3 atomic structures of the first natural RNA-guided recombinase - a new mechanism for programmable genome design

So proud to see our work on machine learning + enzyme design just published! doi.org/10.1016/j.cels… Fun collaboration between X, The Moonshot Factory Google DeepMind & Triplebar that we hope can be a template for integrating ML and high throughput screening in protein engineering

Great collaboration with Pontus Gourdon's lab! Through coulmn-masking of the MSA, we were able to use AlphaFold3 to model different end-states of a membrane transporter in complex with its cargo.

We are recruiting a colleague to our division at Chalmers in Data-Driven Life Science (broadly defined), a competitive starting package is offered and you get to be part of a support, yet young and ambitious research environment.

A Perspective by Stephanie Wankowicz and James Fraser discusses ways macromolecules use conformational entropy to control binding, catalysis, and allostery nature.com/articles/s4158…

Protein modeling may be swiftly pivoting from one-shot prediction to steerable, context-aware generation. Example: FKSFold uses Feynman-Kac control to inject ipTM rewards into AlphaFold3’s diffusion and rescues 3 of 8 tough molecular-glue ternaries.

The follow-up work by Enrico Trizio and Peilin Kang is out on Nature Computational Science!🧨 A semi-automatic method to extensively sample "everywhere and everything" (metastable and transition states) "all at once" (in a single simulation) 🔥 📑: nature.com/articles/s4358… Short🧵 IIT

📢Ritorna la Walk of Life di Torino! La ricerca corre, corri anche tu: 🏃‍♀️🏃‍♂️il 25 maggio ti aspettiamo alla III edizione della Walk of Life di Torino, un’occasione di incontro per dare una speranza concreta a chi affronta una malattia genetica rara. bit.ly/4j5MW7U

New Online! Molecular machineries shaping the mitochondrial inner membrane bit.ly/4jW82XD

A huge milestone for personalised #mRNA therapeutics for inherited disease! A baby with an ultra-rare mitochondrial disease was treated at UPenn with an mRNA-encoded gene-corrector. The mRNA was made to treat a single individual in just 7 months! nejm.org/doi/full/10.10…

Our several-years-old fix to ProteinMPNN's tendency to make weird antibody CDR seqs is finally out. We run an antibody LM in parallel & added its logits to ProteinMPNN's, fixing most issues we encountered. It also increased % of HER2-binding trastuzumab designs >10-fold

Un 38enne recupera la vista grazie a una terapia genica: primo caso al mondo a Napoli #terapiagenica #29luglio #napoli #tigem #telethon tgcom24.mediaset.it/salute/terapia…

Priyadarshan Kinatukara The MSA is essentially the experimental data used as input to AlphaFold. AF didn't solve the protein folding problem, it solved the graph extraction (from MSA) and 3D embedding problem. Knowing the MSA, lets one analyze if low confidence prediction is simply due to lack of data.

Today we share a technical report demonstrating how our drug design engine achieves a step-change in accuracy for predicting biomolecular structures, more than doubling the performance of AlphaFold 3 on key benchmarks and unlocking rational drug design even for examples it has

Quick Bilayer Builder: doi.org/10.1016/j.jmb.…

PhD positions in my lab (AI for Science), but with special preference for people who complement our current activities or are enthusiastic about contributing to our on going work. Looking for technically strong, independent and proactive candidates. chalmers.se/en/about-chalm…

Metadiffusion: Inference-Time Meta-Energy Biasing of Biomolecular Diffusion Models 1. The authors introduce metadiffusion, a method that adds an inference-time meta-energy biasing layer on top of pretrained biomolecular diffusion models like Boltz-2, enabling diverse