Also: ESM, ESMFold
AI models trained on millions of protein sequences, the way chatbots are trained on text.
Only what the cited papers report.
Search Google Patents for this topic: all patents · recent applications (2022+)
Patent searches are generated from the topic's key terms; a patent is a legal claim, not proof that something works. See the Patents page.
Readiness: lab lab studies · prototype demonstrated objects · commercial products or buildings in real use · review summaries of other studies.
Export this topic's references: BibTeX · RIS (Zotero, EndNote, Mendeley)
Rives and colleagues trained a language model on 86 billion amino acids from 250 million proteins; its learned representations encoded structure and enabled state-of-the-art prediction of mutation effects.
As reported in: Rives, Meier, Sercu et al. (2021). Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proceedings of the National Academy of Sciences. doi:10.1073/pnas.2016239118
Lin and colleagues scaled protein language models to 15 billion parameters, predicting atomic-level structure up to 60× faster, and predicted over 617 million metagenomic protein structures.
As reported in: Lin, Akin, Rao et al. (2023). Evolutionary-scale prediction of atomic-level protein structure with a language model. Science. doi:10.1126/science.ade2574