{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Gasparotto P"],"funding":["Swiss Data Science Center"],"pagination":["931-944"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11299607"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["57(Pt 4)"],"pubmed_abstract":["Serial crystallography (SX) involves combining observations from a very large number of diffraction patterns coming from crystals in random orientations. To compile a complete data set, these patterns must be indexed (<i>i.e.</i> their orientation determined), integrated and merged. Introduced here is <i>TORO</i> (<i>Torch</i>-powered robust optimization) <i>Indexer</i>, a robust and adaptable indexing algorithm developed using the <i>PyTorch</i> framework. <i>TORO</i> is capable of operating on graphics processing units (GPUs), central processing units (CPUs) and other hardware accelerators supported by <i>PyTorch</i>, ensuring compatibility with a wide variety of computational setups. In tests, <i>TORO</i> outpaces existing solutions, indexing thousands of frames per second when running "],"journal":["Journal of applied crystallography"],"pubmed_title":["<i>TORO Indexer</i>: a <i>PyTorch</i>-based indexing algorithm for kilohertz serial crystallography."],"pmcid":["PMC11299607"],"funding_grant_id":["C19-03 (RED-ML project)"],"pubmed_authors":["Assmann G","Bejar B","Stadler HC","Ashton AW","Leonarski F","Barba L","Gasparotto P","Mendonca H","Janousch M"],"additional_accession":[]},"is_claimable":false,"name":"<i>TORO Indexer</i>: a <i>PyTorch</i>-based indexing algorithm for kilohertz serial crystallography.","description":"Serial crystallography (SX) involves combining observations from a very large number of diffraction patterns coming from crystals in random orientations. To compile a complete data set, these patterns must be indexed (<i>i.e.</i> their orientation determined), integrated and merged. Introduced here is <i>TORO</i> (<i>Torch</i>-powered robust optimization) <i>Indexer</i>, a robust and adaptable indexing algorithm developed using the <i>PyTorch</i> framework. <i>TORO</i> is capable of operating on graphics processing units (GPUs), central processing units (CPUs) and other hardware accelerators supported by <i>PyTorch</i>, ensuring compatibility with a wide variety of computational setups. In tests, <i>TORO</i> outpaces existing solutions, indexing thousands of frames per second when running ","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Aug","modification":"2025-04-26T05:26:21.212Z","creation":"2025-04-06T11:33:04.242Z"},"accession":"S-EPMC11299607","cross_references":{"pubmed":["39108821"],"doi":["10.1107/S1600576724003182"]}}