{"doi":"10.1107/s2059798323010586","title":"Deep residual networks for crystallography trained on synthetic data","abstract":"The use of artificial intelligence to process diffraction images is challenged by the need to assemble large and precisely designed training data sets. To address this, a codebase called Resonet was developed for synthesizing diffraction data and training residual neural networks on these data. Here, two per-pattern capabilities of Resonet are demonstrated: (i) interpretation of crystal resolution and (ii) identification of overlapping lattices. Resonet was tested across a compilation of diffraction images from synchrotron experiments and X-ray free-electron laser experiments. Crucially, these models readily execute on graphics processing units and can thus significantly outperform conventional algorithms. While Resonet is currently utilized to provide real-time feedback for macromolecular crystallography users at the Stanford Synchrotron Radiation Lightsource, its simple Python-based interface makes it easy to embed in other processing frameworks. This work highlights the utility of physics-based simulation for training deep neural networks and lays the groundwork for the development of additional models to enhance diffraction collection and analysis.","journal":"Acta Crystallographica Section D Structural Biology","year":2024,"id":459087,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":4,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.8871,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":240884,"name":"James M. Holton","orcid":"0000-0002-0596-0137","position":1,"is_corresponding":false},{"id":1077648,"name":"Artem Y. Lyubimov","orcid":"0000-0002-2089-1870","position":2,"is_corresponding":false},{"id":1286333,"name":"Sabine Hollatz","orcid":null,"position":3,"is_corresponding":false},{"id":272544,"name":"Irimpan I. Mathews","orcid":"0000-0001-6254-3519","position":4,"is_corresponding":false},{"id":1286334,"name":"Aleksander Cichosz","orcid":null,"position":5,"is_corresponding":false},{"id":1286335,"name":"Vardan Martirosyan","orcid":null,"position":6,"is_corresponding":false},{"id":1286336,"name":"Teo Zeng","orcid":null,"position":7,"is_corresponding":false},{"id":1286337,"name":"Ryan Stofer","orcid":null,"position":8,"is_corresponding":false},{"id":1285888,"name":"Ruobin Liu","orcid":"0000-0003-1628-5226","position":9,"is_corresponding":false},{"id":1286338,"name":"Jinhu Song","orcid":null,"position":10,"is_corresponding":false},{"id":1286339,"name":"S.E. McPhillips","orcid":null,"position":11,"is_corresponding":false},{"id":1286340,"name":"Mike Soltis","orcid":null,"position":12,"is_corresponding":false},{"id":249658,"name":"Aina E. Cohen","orcid":"0000-0003-2414-9427","position":13,"is_corresponding":false},{"id":240883,"name":"Derek Mendez","orcid":"0000-0002-2269-0060","position":0,"is_corresponding":true}],"reference_count":62,"raw_metadata":null,"created_at":"2026-07-19T02:03:55.280882Z","pmid":"38164955","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}