Loading
The tools that design entirely new proteins to bind a chosen target, now used for cancer binders and antibodies.
RFdiffusion and ProteinMPNN from the Baker Lab are the core tools of de novo protein design. RFdiffusion (Nature 2023) uses denoising diffusion to generate protein backbones conditioned on a target, ProteinMPNN then designs an amino acid sequence to fold into that backbone, RFdiffusion2 (2025) extends the approach to enzyme design, and RFantibody extends it to antibodies. Together they are the basis of Xaira Therapeutics and many binder programmes, including designed binders against cancer targets. The strength is validated de novo binders that have been made and shown to bind in the lab. Developability and immunogenicity of designed proteins remain empirical questions answered only by experiment, so each design still has to be made and tested. For a newcomer: these tools invent new proteins shaped to grab a chosen target, and several have already worked in the lab.
Denoising diffusion over protein backbones conditioned on a target.
Query for this technology: (TITLE:"RFdiffusion / RFdiffusion2 and ProteinMPNN" OR ABSTRACT:"RFdiffusion / RFdiffusion2 and ProteinMPNN" OR TITLE:"Baker Lab" OR ABSTRACT:"Baker Lab") AND (cancer OR tumor OR tumour OR oncology OR carcinoma OR lymphoma OR leukemia OR leukaemia OR myeloma OR sarcoma OR melanoma OR glioma). Results are unfiltered search hits about RFdiffusion / RFdiffusion2 and ProteinMPNN (Baker Lab), not a curated reading list.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI-driven drug & target discovery and the tags foundation-model, protein-design.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI-driven drug & target discovery and the tags foundation-model, protein-design.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI-driven drug & target discovery and the tag foundation-model.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI-driven drug & target discovery and the tag foundation-model.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI-driven drug & target discovery and the tag foundation-model.
Shares Institute for Protein Design (University of Washington) and the tag protein-design.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow and the tag foundation-model.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow and the tag foundation-model.
Open-source projects that implement or serve this technology, from OnCo's own catalogue: licence and last activity as the repository reported them on the day of the fetch. Listing is not endorsement; check the licence before reuse and the validation before clinical use.
The Baker lab's diffusion model for designing new proteins and binders, with released weights.