IDPForge presents deep learning method for intrinsically disordered proteins
IDPForge is a new machine‑learning approach that uses a transformer protein‑language diffusion model to generate all‑atom ensembles of intrinsically disordered proteins (IDPs) and disordered regions (IDRs). Unlike AlphaFold and RoseTTAFold, which struggle with IDPs, IDPForge does not need sequence‑specific training, back‑transformations from coarse‑grained models, or ensemble reweighting. The…
Key points
- IDPForge uses a transformer diffusion model to generate IDP ensembles
- No sequence‑specific training or back‑transformations required
- Ensembles match NMR and SAXS experimental data
The authors note that IDPForge is available as an open‑source resource, enabling integrative structural studies of proteins that contain disordered segments. Funding comes from the National Institutes of Health (grant 5R01GM12762706), NIH 1R35GM163971, the Canada Research Chairs Program, and the U.C. Berkeley Chemical Biology Training Program (NIH T32 GM152983). No competing interests were declared.
By extending AI protein modeling to disordered regions, IDPForge could improve drug target identification and accelerate biomedical research that relies on accurate protein ensembles.
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- OpenAI CEO Sam Altman says math onslaught won't stop despite researcher frustration · 2 src
- AI startups aim to automate formal software verification with $365M funding · 2 src
- Researchers find instruction exposure unlocks rhetorical patterns in LLMs · 1 src
- New guide introduces LLMs for scientists and professionals · 1 src
- Researchers introduce Seq@K to test language models with sequential feedback · 6 src
Comments
via GitHub Discussions