biostudies-literatureTerwilliger TCPhenix Industrial ConsortiumNational Institutes of Health, National Institute of General Medical SciencesLawrence Berkeley National LaboratoryWellcome TrustNIGMS NIH HHS234-244https://www.ebi.ac.uk/biostudies/studies/S-EPMC9986801biostudies-literatureUnknown79(Pt 3)Experimental structure determination can be accelerated with artificial intelligence (AI)-based structure-prediction methods such as AlphaFold. Here, an automatic procedure requiring only sequence information and crystallographic data is presented that uses AlphaFold predictions to produce an electron-density map and a structural model. Iterating through cycles of structure prediction is a key element of this procedure: a predicted model rebuilt in one cycle is used as a template for prediction in the next cycle. This procedure was applied to X-ray data for 215 structures released by the Protein Data Bank in a recent six-month period. In 87% of cases our procedure yielded a model with at least 50% of C^α atoms matching those in the deposited models within 2 Å. Predictions from thActa crystallographica. Section D, Structural biologyAccelerating crystal structure determination with iterative AlphaFold prediction.PMC9986801DE-AC02-05CH11231GM063210P01 GM063210R35 GM131883209407/Z/17/ZPoon BKTerwilliger TCRichardson JSAdams PDCroll TIOeffner RDWilliams CJAfonine PVMcCoy AJLiebschner DRead RJfalseAccelerating crystal structure determination with iterative AlphaFold prediction.Experimental structure determination can be accelerated with artificial intelligence (AI)-based structure-prediction methods such as AlphaFold. Here, an automatic procedure requiring only sequence information and crystallographic data is presented that uses AlphaFold predictions to produce an electron-density map and a structural model. Iterating through cycles of structure prediction is a key element of this procedure: a predicted model rebuilt in one cycle is used as a template for prediction in the next cycle. This procedure was applied to X-ray data for 215 structures released by the Protein Data Bank in a recent six-month period. In 87% of cases our procedure yielded a model with at least 50% of C^α atoms matching those in the deposited models within 2 Å. Predictions from th2023-01-01T00:00:00Z2023 Mar2026-05-29T05:30:23.147Z2025-02-18T23:44:33.824ZS-EPMC99868013687643310.1107/S205979832300102X