{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T11:40:01Z","timestamp":1755862801903,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2201583"],"award-info":[{"award-number":["2201583"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,22]]},"DOI":"10.1145\/3698587.3701354","type":"proceedings-article","created":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T10:05:08Z","timestamp":1734343508000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Impact of the Networking Infrastructure on the Performance of Variant Calling on Human Genomes in Commodity Clusters"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9268-4364","authenticated-orcid":false,"given":"Manas Jyoti","family":"Das","sequence":"first","affiliation":[{"name":"Southern Illinois Univ. Edwardsville, USA and University of Missouri"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1859-0438","authenticated-orcid":false,"given":"Praveen","family":"Rao","sequence":"additional","affiliation":[{"name":"University of Missouri, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3465-4056","authenticated-orcid":false,"given":"Lisong","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Nebraska-Lincoln, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,12,16]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btv506"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"J. M. Abuin J. C. Pichel T. F. Pena and J. Amigo. 2016. SparkBWA: Speeding up the Alignment of High-Throughput DNA Sequencing Data. PLoS ONE 11 5 (2016).","DOI":"10.1371\/journal.pone.0155461"},{"key":"e_1_3_2_1_3_1","volume-title":"Heterogeneous Hardware\/Software Acceleration of the BWA-MEM DNA Alignment Algorithm. In 2015 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD). 240--246","author":"Ahmed Nauman","year":"2015","unstructured":"Nauman Ahmed, Vlad-Mihai Sima, Ernst Houtgast, Koen Bertels, and Zaid Al-Ars. 2015. Heterogeneous Hardware\/Software Acceleration of the BWA-MEM DNA Alignment Algorithm. In 2015 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD). 240--246."},{"key":"e_1_3_2_1_4_1","volume-title":"A Global Reference for Human Genetic Variation. Nature 526, 7571","author":"Auton Adam","year":"2015","unstructured":"Adam Auton and et.al. 2015. A Global Reference for Human Genetic Variation. Nature 526, 7571 (2015), 68--74."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.05.016"},{"key":"e_1_3_2_1_6_1","volume-title":"Proc. of the 8th USENIX Conference on Hot Topics in Cloud Computing","author":"Chen Yu-Ting","year":"2016","unstructured":"Yu-Ting Chen, Jason Cong, Zhenman Fang, Jie Lei, and Peng Wei. 2016. When Apache Spark Meets FPGAs: A Case Study for Next-Generation DNA Sequencing Acceleration. In Proc. of the 8th USENIX Conference on Hot Topics in Cloud Computing (Denver, CO). 64--70."},{"key":"e_1_3_2_1_7_1","unstructured":"J. Cong Jie Lei Sen Li Myron Peto P. Spellman Peng Wei and Peipei Zhou. 2015. CS-BWAMEM: A Fast and Scalable Read Aligner at the Cloud Scale for Whole Genome Sequencing. In High Throughput Sequencing Algorithms and Applications (HITSEQ)."},{"key":"e_1_3_2_1_8_1","volume-title":"Cloud-based Biomedical Data Storage and Analysis for Genomic Research: Landscape Analysis of Data Governance in Emerging NIH-Supported Platforms. Human Genetics and Genomics Advances 4, 3","author":"Dahlquist Jacklyn M","year":"2023","unstructured":"Jacklyn M Dahlquist, Sarah C Nelson, and Stephanie M Fullerton. 2023. Cloud-based Biomedical Data Storage and Analysis for Genomic Research: Landscape Analysis of Data Governance in Emerging NIH-Supported Platforms. Human Genetics and Genomics Advances 4, 3 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615268"},{"key":"e_1_3_2_1_10_1","volume-title":"Proc. of 6th OSDI Conference. 137--150","author":"Dean Jeffrey","year":"2004","unstructured":"Jeffrey Dean and Sanjay Ghemawat. 2004. MapReduce: Simplified Data Processing on Large Clusters. In Proc. of 6th OSDI Conference. 137--150."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btv179"},{"key":"e_1_3_2_1_12_1","volume-title":"The Design and Operation of CloudLab. In 2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Duplyakin Dmitry","year":"2019","unstructured":"Dmitry Duplyakin, Robert Ricci, Aleksander Maricq, Gary Wong, Jonathon Duerig, Eric Eide, Leigh Stoller, Mike Hibler, David Johnson, Kirk Webb, Aditya Akella, Kuangching Wang, Glenn Ricart, Larry Landweber, Chip Elliott, Michael Zink, Emmanuel Cecchet, Snigdhaswin Kar, and Prabodh Mishra. 2019. The Design and Operation of CloudLab. In 2019 USENIX Annual Technical Conference (USENIX ATC 19) (Renton, WA). 1--14."},{"key":"e_1_3_2_1_13_1","volume-title":"DNAscope: High Accuracy Small Variant Calling Using Machine Learning. bioRxiv:2022.05.20.492556","author":"Freed Donald","year":"2022","unstructured":"Donald Freed, Renke Pan, Haodong Chen, Zhipan Li, Jinnan Hu, and Rafael Aldana. 2022. DNAscope: High Accuracy Small Variant Calling Using Machine Learning. bioRxiv:2022.05.20.492556 (2022)."},{"key":"e_1_3_2_1_14_1","unstructured":"GA4GH. 2021. The Variant Call Format (VCF) Version 4.2 Specification. https:\/\/samtools.github.io\/hts-specs\/VCFv4.2.pdf."},{"key":"e_1_3_2_1_15_1","unstructured":"Erik Garrison and Gabor Marth. 2012. Haplotype-Based Variant Detection From Short-Read Sequencing. arXiv:1207.3907"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.4227"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrg.2016.49"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1400097.1400105"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/4472.4478"},{"key":"e_1_3_2_1_20_1","unstructured":"Broad Institute. 2023. GATK4. https:\/\/gatk.broadinstitute.org."},{"key":"e_1_3_2_1_21_1","volume-title":"D1 (11","author":"Katz Kenneth","year":"2021","unstructured":"Kenneth Katz, Oleg Shutov, Richard Lapoint, Michael Kimelman, J Rodney Brister, and Christopher O'Sullivan. 2021. The Sequence Read Archive: A Decade More of Explosive Growth. Nucleic Acids Research 50, D1 (11 2021), D387-D390."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13073-020-00791-w"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrg.2017.113"},{"key":"e_1_3_2_1_24_1","volume-title":"Aligning Sequence Reads, Clone Sequences and Assembly Contigs With BWA-MEM. arXiv e-prints","author":"Heng Li.","year":"2013","unstructured":"Heng Li. 2013. Aligning Sequence Reads, Clone Sequences and Assembly Contigs With BWA-MEM. arXiv e-prints (2013), arXiv:1303.3997. arXiv:1303.3997"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btp352"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Wen-Wei Liao Mobin Asri Jana Ebler Daniel Doerr Marina Haukness Glenn Hickey Shuangjia Lu Julian K Lucas Jean Monlong Haley J Abel et al. 2023. A Draft Human Pangenome Reference. Nature 617 7960 (2023) 312--324.","DOI":"10.1530\/ey.20.12.1"},{"key":"e_1_3_2_1_27_1","volume-title":"Proc. of the 13th USENIX Conference on Operating Systems Design and Implementation","author":"Moritz Philipp","year":"2018","unstructured":"Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I. Jordan, and Ion Stoica. 2018. Ray: A Distributed Framework for Emerging AI Applications. In Proc. of the 13th USENIX Conference on Operating Systems Design and Implementation (Carlsbad, CA, USA). 561--577."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-016-0917-0"},{"key":"e_1_3_2_1_29_1","unstructured":"NCBI. 2013. Genome Reference Consortium Human Build 38. https:\/\/www.ncbi.nlm.nih.gov\/assembly\/."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1186\/1756-0500-4-171"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bts054"},{"key":"e_1_3_2_1_32_1","unstructured":"Frank A. Nothaft. 2017. Scalable Systems and Algorithms for Genomic Variant Analysis. Ph.D. Dissertation. UC Berkeley ProQuest."},{"volume-title":"Proc. of the 2015 ACM SIGMOD Conference","author":"Nothaft Frank Austin","key":"e_1_3_2_1_33_1","unstructured":"Frank Austin Nothaft, Matt Massie, Timothy Danford, Zhao Zhang, Uri Laserson, Carl Yeksigian, Jey Kottalam, Arun Ahuja, Jeff Hammerbacher, Michael D. Linderman, Michael J. Franklin, Anthony D. Joseph, and David A. Patterson. 2015. Rethinking Data-Intensive Science Using Scalable Analytics Systems. In Proc. of the 2015 ACM SIGMOD Conference (Victoria, Australia). 631--646."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMsr1809937"},{"volume-title":"Mapping and Sequencing the Human Genome","author":"National Research Council Committee on Mapping and Sequencing the Human Genome. 1988.","key":"e_1_3_2_1_35_1","unstructured":"National Research Council Committee on Mapping and Sequencing the Human Genome. 1988. Mapping and Sequencing the Human Genome. National Academies Press."},{"key":"e_1_3_2_1_36_1","volume-title":"Making Sense of Performance in Data Analytics Frameworks. In 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI 15)","author":"Ousterhout Kay","year":"2015","unstructured":"Kay Ousterhout, Ryan Rasti, Sylvia Ratnasamy, Scott Shenker, and Byung-Gon Chun. 2015. Making Sense of Performance in Data Analytics Frameworks. In 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI 15). 293--307."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-023-05292-2"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btr325"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.4235"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD62652.2024.00044"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482047"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-013"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btp236"},{"key":"e_1_3_2_1_44_1","volume-title":"Somatic small-variant calling methods in Illumina DRAGEN Secondary Analysis. bioRxiv","author":"Scheffler Konrad","year":"2023","unstructured":"Konrad Scheffler, Severine Catreux, Taylor O'Connell, Heejoon Jo, Varun Jain, Theo Heyns, Jeffrey Yuan, Lisa Murray, James Han, and Rami Mehio. 2023. Somatic small-variant calling methods in Illumina DRAGEN Secondary Analysis. bioRxiv 2023.03.23.534011 (2023)."},{"key":"e_1_3_2_1_45_1","unstructured":"Sentieon. 2023. https:\/\/www.nature.com\/articles\/d44224-023-00020-w."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.1002195"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1038\/s10038-020-00862-1"},{"key":"e_1_3_2_1_48_1","volume-title":"Hadoop: The Definitive Guide","author":"White Tom","year":"2009","unstructured":"Tom White. 2009. Hadoop: The Definitive Guide (1st ed.). O'Reilly Media, Inc.","edition":"1"},{"key":"e_1_3_2_1_49_1","unstructured":"Wikipedia. 2000. FASTQ Format. https:\/\/en.wikipedia.org\/wiki\/FASTQ_format."},{"key":"e_1_3_2_1_50_1","volume-title":"Proc. of 2nd USENIX Conference on Hot Topics in Cloud Computing. 1--7.","author":"Zaharia Matei","year":"2010","unstructured":"Matei Zaharia, Mosharaf Chowdhury, Michael J. Franklin, Scott Shenker, and Ion Stoica. 2010. Spark: Cluster Computing with Working Sets. In Proc. of 2nd USENIX Conference on Hot Topics in Cloud Computing. 1--7."},{"key":"e_1_3_2_1_51_1","volume-title":"PipeMEM: A Framework to Speed Up BWA-MEM in Spark with Low Overhead. Genes 10, 11","author":"Zhang Lingqi","year":"2019","unstructured":"Lingqi Zhang, Cheng Liu, and Shoubin Dong. 2019. PipeMEM: A Framework to Speed Up BWA-MEM in Spark with Low Overhead. Genes 10, 11 (2019)."}],"event":{"name":"BCB '24: 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","sponsor":["SIGBio ACM Special Interest Group on Bioinformatics"],"location":"Shenzhen China","acronym":"BCB '24"},"container-title":["Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698587.3701354","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3698587.3701354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T11:26:05Z","timestamp":1755861965000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698587.3701354"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"references-count":51,"alternative-id":["10.1145\/3698587.3701354","10.1145\/3698587"],"URL":"https:\/\/doi.org\/10.1145\/3698587.3701354","relation":{},"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"2024-12-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}