Blog post
Debating the balance between model openness and biosecurity guardrails
Key Takeaways The scientific community is currently debating how to balance open research with biosecurity protections when it comes to biological AI tools. Biological AI tools are primarily designed for drug discovery, treating illnesses, and other broader societal benefits. Advancements in AI, such as chatbots, could provide opportunities for even inexperienced bad actors to misuse…
Read MoreBiohub releases open source models that utilize evolution to design disease target binders
Key Takeaways Biohub has released open source ESM protein language models that use evolutionary data to streamline drug discovery and map functional protein spaces. ESMFold2 successfully generated lab-validated, high-affinity protein binders against five disease targets in cancer and immunology. The models were used to generate the ESM Atlas, which maps 6.8 billion sequences and 1.1…
Read MoreOpenBind releases initial structure and affinity dataset for structure-based machine learning
Key Takeaways OpenBind is generating dense, high-quality protein-ligand datasets that link structural data with binding measurements at a large scale. This release provides a realistic, structurally novel testbed linking high-resolution crystallographic data directly with biophysical binding affinity. The initial release targets the Enterovirus A71 (EV-A71) 2A protease (modeled via a closely related Coxsackievirus A16 surrogate…
Read MoreSummer 2026 Workshop Registrations Now Open
Two exciting week-long workshops this summer are now accepting applications. On July 20 – 24, 2026, the ML & Rosetta Intro Bootcamp will be held at John Hopkins University in Baltimore, Maryland. The bootcamp will be a blend of lectures and hands-on projects to introduce and then practice key concepts and skills with machine learning…
Read MoreSpeed Up PyRosetta Development with Autocompletion and Type Checking
By Harrison Truscott PyRosetta, the Python interface to the Rosetta binary, now comes packaged with type stub files (.pyi). These files describe the module’s classes, methods, and variables, as well as function signatures, types of function parameters and return values, and descriptive docstrings. Type stub files can be used by the Integrated Development Environment (IDE)…
Read MoreA Zero-Shot Approach to de novo Metalloenzyme Design
Key Takeaways: dEVA (design by EVolutionary Algorithm) is a framework that achieves the zero-shot design of a highly efficient metalloenzyme without any reliance on natural templates. Design objectives were tailored to the specific chemistry of metalloenzymes, in particular catalytic zinc sites, and from only three experimentally-tested designs found desB, the most efficient de novo designed…
Read MoreImmunogen Design Workshop Hosted by the Meiler Lab Cultivated Collaborations
On April 13 – 15, 2026, fifteen participants from as far away as South Korea gathered at Vanderbilt University to learn about the Rosetta software suite. Attendees were a blend of industry, university, and non-profit affiliates at career levels from graduate students to principal investigators. The “Computationally Guided Immunogen Design with Rosetta and ML Tools”…
Read MoreDeep Learning’s Impact on de novo Protein Design
Key Takeaways: With advancements in AI, the field of protein engineering has shifted from template-based approaches to de novo designs with approaches including seed-based design, deep generative models, and binder hallucination. Design towards specific protein functions is the current frontier factoring in parameters including neosurfaces, conditional binding with biological stimuli, and dynamic modeling, linking deep…
Read MoreNext Generation Generative Model Unlocks de novo Designs at Scale
Key Takeaways: NVIDIA’s new Proteina-Complexa model combines generative AI with inference-time search algorithms to operate 30-60x faster than RFdiffusion when designing custom proteins that target specific diseases. In a test to find binders for 127 different targets from over 1 million protein designs, the model successfully found binders for 68% of the targets. The model…
Read MoreML Protein Design Bootcamp Now Available on YouTube
Hosted in November 2025 by the University of California Davis, this course provides a practical, beginner-friendly overview of modern AI/ML tools for protein structure prediction and design, including AlphaFold, ESMFold, ProteinMPNN, and RFdiffusion, along with the workflows that connect them. This is a relatively novice-level course. The curriculum is focused on understanding and using existing…
Read More