{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T02:50:54Z","timestamp":1774579854090,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,23]]},"DOI":"10.1145\/3733723.3733736","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T08:49:08Z","timestamp":1750409348000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["DTIO: Data Stack for AI-driven Workflows"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4023-3485","authenticated-orcid":false,"given":"Keith Alex","family":"Bateman","sequence":"first","affiliation":[{"name":"Illinois Institute of Technology, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9719-9567","authenticated-orcid":false,"given":"Neeraj","family":"Rajesh","sequence":"additional","affiliation":[{"name":"Illinois Institute of Technology, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1694-6541","authenticated-orcid":false,"given":"Jaime","family":"Cernuda","sequence":"additional","affiliation":[{"name":"Illinois Institute of Technology, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7487-1947","authenticated-orcid":false,"given":"Luke","family":"Logan","sequence":"additional","affiliation":[{"name":"Illinois Institute of Technology, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0661-7509","authenticated-orcid":false,"given":"Bogdan","family":"Nicolae","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7890-3934","authenticated-orcid":false,"given":"Franck","family":"Cappello","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1093-0792","authenticated-orcid":false,"given":"Xian-He","family":"Sun","sequence":"additional","affiliation":[{"name":"Illinois Institute of Technology, Chicago, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3943-663X","authenticated-orcid":false,"given":"Anthony","family":"Kougkas","sequence":"additional","affiliation":[{"name":"Illinois Institute of Technology, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,22]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Gustaf Ahdritz Nazim Bouatta Christina Floristean Sachin Kadyan Qinghui Xia William Gerecke Timothy\u00a0J O\u2019Donnell Daniel Berenberg Ian Fisk Niccol\u00f2 Zanichelli et\u00a0al. 2024. OpenFold: Retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization. Nature Methods (2024) 1\u201311.","DOI":"10.1038\/s41592-024-02272-z"},{"key":"e_1_3_3_1_3_2","unstructured":"Oren Ben-Kiki Clark Evans and Brian Ingerson. 2009. Yaml ain\u2019t markup language (yaml\u2122) version 1.1. Working Draft 2008 5 11 (2009)."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Suren Byna M\u00a0Scot Breitenfeld Bin Dong Quincey Koziol Elena Pourmal Dana Robinson Jerome Soumagne Houjun Tang Venkatram Vishwanath and Richard Warren. 2020. ExaHDF5: Delivering efficient parallel I\/O on exascale computing systems. Journal of Computer Science and Technology 35 (2020) 145\u2013160.","DOI":"10.1007\/s11390-020-9822-9"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Hugo Caro Sulyvan Dollin Anne Biton Bryan Brancotte Dimitri Desvillechabrol Yoann Dufresne Blaise Li Etienne Kornobis Fr\u00e9d\u00e9ric Lemoine Nicolas Maillet et\u00a0al. 2023. BioConvert: a comprehensive format converter for life sciences. NAR Genomics and Bioinformatics 5 3 (2023) lqad074.","DOI":"10.1093\/nargab\/lqad074"},{"key":"e_1_3_3_1_6_2","unstructured":"Gnosis\u00a0Research Center. 2024. Hardware Overview | Gnosis Research Center. https:\/\/grc.iit.edu\/resources\/hardware-overview"},{"key":"e_1_3_3_1_7_2","unstructured":"Avi Chawla. 2025. I\/O Optimization in Data Projects - by Avi Chawla. https:\/\/blog.dailydoseofds.com\/p\/io-optimization-in-data-projects"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Mathew\u00a0J Cherukara Tao Zhou Youssef Nashed Pablo Enfedaque Alex Hexemer Ross\u00a0J Harder and Martin\u00a0V Holt. 2020. AI-enabled high-resolution scanning coherent diffraction imaging. Applied Physics Letters 117 4 (2020).","DOI":"10.1063\/5.0013065"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/IMCOM51814.2021.9377366"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Hariharan Devarajan Gerd Heber and Kathryn Mohror. 2024. H5Intent: Autotuning HDF5 with User Intent. IEEE Transactions on Parallel and Distributed Systems (2024).","DOI":"10.1109\/TPDS.2024.3492704"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00035"},{"key":"e_1_3_3_1_12_2","unstructured":"Argonne Leadership\u00a0Computing Facility. 2025. Machine Overview - ALCF User Guides. https:\/\/docs.alcf.anl.gov\/polaris\/machine-overview\/"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006363"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00023"},{"key":"e_1_3_3_1_15_2","unstructured":"NITRD Group et\u00a0al. 2019. The Convergence of High Performance Computing Big Data and Machine Learning."},{"key":"e_1_3_3_1_16_2","unstructured":"OpenFabrics Interfaces\u00a0Working Group. 2024. ofiwg\/libfabric: Open Fabric Interfaces. https:\/\/github.com\/ofiwg\/libfabric"},{"key":"e_1_3_3_1_17_2","unstructured":"The\u00a0HDF Group. 2024. HDFGroup\/hdf5: Official HDF5(R) Library Repository. https:\/\/github.com\/HDFGroup\/hdf5"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Helgi\u00a0I Ing\u00f3lfsson. 2023. MuMMI a machine learning-driven modeling infrastructure for coupling different simulation scales; showcased for RAS-RAF activation. Biophysical Journal 122 3 (2023) 463a.","DOI":"10.1016\/j.bpj.2022.11.2486"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307681.3325405"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205322"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Albert Krewinkel and Robert Winkler. 2017. Formatting Open Science: agilely creating multiple document formats for academic manuscripts with Pandoc Scholar. PeerJ computer science 3 (2017) e112.","DOI":"10.7717\/peerj-cs.112"},{"key":"e_1_3_3_1_22_2","unstructured":"Argonne\u00a0National Laboratory. 2024. mochi-hpc\/mochi-margo: Argobots bindings for the Mercury RPC library. https:\/\/github.com\/mochi-hpc\/mochi-margo"},{"key":"e_1_3_3_1_23_2","unstructured":"Argonne\u00a0National Laboratory. 2024. mochi-hpc\/mochi-thallium: Thallium is a C++14 library wrapping Margo Mercury and Argobots and providing an object-oriented way to use these libraries.https:\/\/github.com\/mochi-hpc\/mochi-thallium"},{"key":"e_1_3_3_1_24_2","unstructured":"Argonne\u00a0National Laboratory. 2024. USCiLab\/cereal: A C++11 library for serialization. https:\/\/github.com\/USCiLab\/cereal"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Josh Moore Daniela Basurto-Lozada S\u00e9bastien Besson John Bogovic Jord\u00e3o Bragantini Eva\u00a0M Brown Jean-Marie Burel Xavier Casas\u00a0Moreno Gustavo de Medeiros Erin\u00a0E Diel et\u00a0al. 2023. OME-Zarr: a cloud-optimized bioimaging file format with international community support. Histochemistry and Cell Biology 160 3 (2023) 223\u2013251.","DOI":"10.1007\/s00418-023-02209-1"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00018"},{"key":"e_1_3_3_1_27_2","unstructured":"Mahantesh\u00a0K Pattanshetti. 2020. Design of High-Performance Computing System for Big Data Analytics. JOURNAL OF ALGEBRAIC STATISTICS 11 1 (2020) 115\u2013121."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Robert\u00a0B Ross George Amvrosiadis Philip Carns Charles\u00a0D Cranor Matthieu Dorier Kevin Harms Greg Ganger Garth Gibson Samuel\u00a0K Gutierrez Robert Latham et\u00a0al. 2020. Mochi: Composing data services for high-performance computing environments. Journal of Computer Science and Technology 35 (2020) 121\u2013144.","DOI":"10.1007\/s11390-020-9802-0"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Sangmin Seo Abdelhalim Amer Pavan Balaji Cyril Bordage George Bosilca Alex Brooks Philip Carns Adri\u00e1n Castell\u00f3 Damien Genet Thomas Herault et\u00a0al. 2017. Argobots: A lightweight low-level threading and tasking framework. IEEE Transactions on Parallel and Distributed Systems 29 3 (2017) 512\u2013526.","DOI":"10.1109\/TPDS.2017.2766062"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2013.6702617"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Markus Stabrin Fabian Schoenfeld Thorsten Wagner Sabrina Pospich Christos Gatsogiannis and Stefan Raunser. 2020. TranSPHIRE: automated and feedback-optimized on-the-fly processing for cryo-EM. Nature communications 11 1 (2020) 5716.","DOI":"10.1038\/s41467-020-19513-2"},{"key":"e_1_3_3_1_32_2","unstructured":"NumPy team. 2024. NumPy -. https:\/\/numpy.org\/"},{"key":"e_1_3_3_1_33_2","unstructured":"How to\u00a0Optimize Data I\/O by Choosing the Right File Format\u00a0with Pandas. 2025. Shittu Olumide. https:\/\/www.statology.org\/how-to-optimize-data-io-by-choosing-the-right-file-format-with-pandas\/"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Maxim Zvyagin Alexander Brace Kyle Hippe Yuntian Deng Bin Zhang Cindy\u00a0Orozco Bohorquez Austin Clyde Bharat Kale Danilo Perez-Rivera Heng Ma et\u00a0al. 2023. GenSLMs: Genome-scale language models reveal SARS-CoV-2 evolutionary dynamics. The International Journal of High Performance Computing Applications 37 6 (2023) 683\u2013705.","DOI":"10.1177\/10943420231201154"}],"event":{"name":"SSDBM 2025: 37th International Conference on Scalable Scientific Data Management","location":"Columbus USA","acronym":"SSDBM 2025"},"container-title":["Proceedings of the 37th International Conference on Scalable Scientific Data Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3733723.3733736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T11:37:11Z","timestamp":1750419431000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3733723.3733736"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":33,"alternative-id":["10.1145\/3733723.3733736","10.1145\/3733723"],"URL":"https:\/\/doi.org\/10.1145\/3733723.3733736","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]},"assertion":[{"value":"2025-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}