Tool Updates
AtomWorks & RosettaFold3 (in Foundry) now open-source on GitHub
We’re excited to share that two major repositories are live on the RosettaCommons GitHub: AtomWorks and Foundry. AtomWorks is a broadly applicable data framework for manipulating structural data and developing biomolecular foundation models across a wide range of biological tasks. AtomWorks has already been used to train structure prediction, generative protein design, and fixed-backbone sequence…
Read MoreRFdiffusion2 is Now Available On GitHub
The long awaited inference code for RFdiffusion2 is now public! Developed by the Baker Lab, RFDiffusion2 builds on the capabilities of RFdiffusion AA to model more complex enzyme structures than was previously possible with the original RFdiffusion method. What’s New? In the first RFdiffusion release, enzyme design was restricted: the geometry of the active site…
Read Morehu.MAP3.0: atlas of human protein complexes by integration of >25,000 proteomic experiments
What the paper is about The paper introduces hu.MAP3.0, a giant “atlas” (map) of how human proteins come together into complexes. Proteins rarely act alone. Most of the work inside cells, such as making energy, repairing DNA, or responding to signals, occurs when proteins assemble into complexes, much like machines built from many parts. The…
Read MoreDirectContacts2: A network of direct physical protein interactions derived from high-throughput mass spectrometry experiments
What this paper is about Every function in our body relies on proteins working together in groups called protein complexes. However, not every protein in a complex directly interacts with every other protein; some proteins only connect indirectly through other proteins. Knowing which proteins physically touch each other is like having the wiring diagram of…
Read MoreComplete computational design of high-efficiency Kemp elimination enzymes
This paper presents a fully computational approach to designing enzymes that efficiently catalyze a model chemical reaction, demonstrating performance comparable to natural enzymes without experimental optimization. It highlights a practical step forward in enzyme design for broader applications in science and industry. What is this paper about? The researchers developed a fully computational method, eliminating…
Read MoreNew Docker Images on Rosetta Commons DockerHub
We are excited to announce that Rosetta Commons supported Docker images for RFdiffusion, ProteinMPNN, and LigandMPNN are now available on DockerHub! We hope that these images will make it easier to Try them out, share your feedback, and help us keep improving open science tools! Is there another tool from our community you would like…
Read More