{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:43:27Z","timestamp":1742989407227,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031349591"},{"type":"electronic","value":"9783031349607"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-34960-7_6","type":"book-chapter","created":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T15:04:08Z","timestamp":1687964648000},"page":"72-85","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing Variant Calling for\u00a0Human Genome Analysis: A Comprehensive Pipeline Approach"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6601-7513","authenticated-orcid":false,"given":"Miguel","family":"Pinheiro","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6331-6091","authenticated-orcid":false,"given":"Jorge Miguel","family":"Silva","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6672-6176","authenticated-orcid":false,"given":"Jos\u00e9 Luis","family":"Oliveira","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,6,29]]},"reference":[{"unstructured":"US DOE Joint Genome Institute: Hawkins Trevor 4 Branscomb Elbert 4 Predki Paul 4 Richardson Paul 4 Wenning Sarah 4 Slezak Tom 4 Doggett Norman 4 Cheng Jan-Fang 4 Olsen Anne 4 Lucas Susan 4 Elkin Christopher 4 Uberbacher Edward 4 Frazier Marvin 4, RIKEN Genomic Sciences Center: Sakaki Yoshiyuki 9 Fujiyama Asao 9 Hattori Masahira 9 Yada Tetsushi 9 Toyoda Atsushi 9 Itoh Takehiko 9 Kawagoe Chiharu 9 Watanabe Hidemi 9 Totoki Yasushi 9 Taylor Todd 9, Genoscope, CNRS UMR-8030: Weissenbach Jean 10 Heilig Roland 10 Saurin William 10 Artiguenave Francois 10 Brottier Philippe 10 Bruls Thomas 10 Pelletier Eric 10 Robert Catherine 10 Wincker Patrick 10, Institute of Molecular Biotechnology: Rosenthal Andr\u00e9 12 Platzer Matthias 12 Nyakatura Gerald 12 Taudien Stefan 12 Rump Andreas 12 Department of Genome Analysis, GTC Sequencing Center: Smith Douglas R. 11 Doucette-Stamm Lynn 11 Rubenfield Marc 11 Weinstock Keith 11 Lee Hong Mei 11 Dubois JoAnn 11, Beijing Genomics Institute\/Human Genome Center: Yang Huanming 13 Yu Jun 13 Wang Jian 13 Huang Guyang 14 Gu Jun 15, et al. Initial sequencing and analysis of the human genome. nature, 409(6822):860\u2013921, 2001","key":"6_CR1"},{"issue":"2","key":"6_CR2","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1038\/nrg3642","volume":"15","author":"D Sims","year":"2014","unstructured":"Sims, D., Sudbery, I., Ilott, N.E., Heger, A., Ponting, C.P.: Sequencing depth and coverage: key considerations in genomic analyses. Nat. Rev. Genet. 15(2), 121\u2013132 (2014)","journal-title":"Nat. Rev. Genet."},{"issue":"5","key":"6_CR3","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1038\/nrg2573","volume":"10","author":"J Kaye","year":"2009","unstructured":"Kaye, J., Heeney, C., Hawkins, N., De Vries, J., Boddington, P.: Data sharing in genomics-re-shaping scientific practice. Nat. Rev. Genet. 10(5), 331\u2013335 (2009)","journal-title":"Nat. Rev. Genet."},{"doi-asserted-by":"crossref","unstructured":"Papageorgiou, L., Eleni, P., Raftopoulou, S., Mantaiou, M., Megalooikonomou, V., Vlachakis, D.: Genomic big data hitting the storage bottleneck. EMBnet J. 24 (2018)","key":"6_CR4","DOI":"10.14806\/ej.24.0.910"},{"issue":"5","key":"6_CR5","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1203\/PDR.0b013e3181d6245e","volume":"67","author":"V Maojo","year":"2010","unstructured":"Maojo, V., Martin-Sanchez, F., Kulikowski, C., Rodriguez-Paton, A., Fritts, M.: Nanoinformatics and DNA-based computing: catalyzing nanomedicine. Pediatr. Res. 67(5), 481\u2013489 (2010)","journal-title":"Pediatr. Res."},{"unstructured":"European Genomic Data Infrastructure (GDI). https:\/\/gdi.onemilliongenomes.eu. Accessed 24 Feb 2023","key":"6_CR6"},{"unstructured":"Beyond 1 Million Genomes. https:\/\/b1mg-project.eu. Accessed 24 Feb 2023","key":"6_CR7"},{"issue":"15","key":"6_CR8","doi-asserted-by":"publisher","first-page":"2156","DOI":"10.1093\/bioinformatics\/btr330","volume":"27","author":"P Danecek","year":"2011","unstructured":"Danecek, P., et al.: The variant call format and VCFtools. Bioinformatics 27(15), 2156\u20132158 (2011)","journal-title":"Bioinformatics"},{"doi-asserted-by":"crossref","unstructured":"Martin, M., et al.: WhatsHAP: fast and accurate read-based phasing. BioRxiv, 085050 (2016)","key":"6_CR9","DOI":"10.1101\/085050"},{"issue":"8","key":"6_CR10","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1038\/nbt.3300","volume":"33","author":"B Alipanahi","year":"2015","unstructured":"Alipanahi, B., Delong, A., Weirauch, M.T., Frey, B.J.: Predicting the sequence specificities of DNA- and RNA- binding proteins by deep learning. Nat. Biotechnol. 33(8), 831\u2013838 (2015)","journal-title":"Nat. Biotechnol."},{"issue":"1","key":"6_CR11","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1038\/s41588-018-0295-5","volume":"51","author":"J Zou","year":"2019","unstructured":"Zou, J., Huss, M., Abid, A., Mohammadi, P., Torkamani, A., Telenti, A.: A primer on deep learning in genomics. Nat. Genet. 51(1), 12\u201318 (2019)","journal-title":"Nat. Genet."},{"unstructured":"Johannes, K.: DNA-SEQ-GATK-variant-calling (2021). https:\/\/github.com\/snakemake-workflows\/dna-seq-gatk-variant-calling","key":"6_CR12"},{"doi-asserted-by":"crossref","unstructured":"Van der Auwera, G.A., et al.: From fastQ data to high-confidence variant calls: the genome analysis toolkit best practices pipeline. Curr. Protoc. Bioinform. 43(1), 11\u201310 (2013)","key":"6_CR13","DOI":"10.1002\/0471250953.bi1110s43"},{"issue":"3","key":"6_CR14","first-page":"1","volume":"5","author":"J O\u2019Rawe","year":"2013","unstructured":"O\u2019Rawe, J., et al.: Low concordance of multiple variant-calling pipelines: practical implications for exome and genome sequencing. Genome Med. 5(3), 1\u201318 (2013)","journal-title":"Genome Med."},{"issue":"9","key":"6_CR15","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1101\/gr.107524.110","volume":"20","author":"A McKenna","year":"2010","unstructured":"McKenna, A., et al.: The genome analysis toolkit: a mapreduce framework for analyzing next-generation DNA sequencing data. Genome Res. 20(9), 1297\u20131303 (2010)","journal-title":"Genome Res."},{"issue":"10","key":"6_CR16","doi-asserted-by":"publisher","first-page":"983","DOI":"10.1038\/nbt.4235","volume":"36","author":"R Poplin","year":"2018","unstructured":"Poplin, R., et al.: A universal SNP and small-indel variant caller using deep neural networks. Nat. Biotech. 36(10), 983\u2013987 (2018)","journal-title":"Nat. Biotech."},{"issue":"5","key":"6_CR17","doi-asserted-by":"publisher","first-page":"100129","DOI":"10.1016\/j.xgen.2022.100129","volume":"2","author":"ND Olson","year":"2022","unstructured":"Olson, N.D., et al.: PrecisionFDA truth challenge v2: calling variants from short and long reads in difficult-to-map regions. Cell Genomics 2(5), 100129 (2022)","journal-title":"Cell Genomics"},{"issue":"16","key":"6_CR18","doi-asserted-by":"publisher","first-page":"2078","DOI":"10.1093\/bioinformatics\/btp352","volume":"25","author":"H Li","year":"2009","unstructured":"Li, H., et al.: The sequence alignment\/map format and samtools. Bioinformatics 25(16), 2078\u20132079 (2009)","journal-title":"Bioinformatics"},{"unstructured":"Garrison, E., Marth, G.: Haplotype-based variant detection from short-read sequencing. arXiv preprint (2012). arXiv:1207.3907","key":"6_CR19"},{"issue":"17","key":"6_CR20","doi-asserted-by":"publisher","first-page":"2283","DOI":"10.1093\/bioinformatics\/btp373","volume":"25","author":"DC Koboldt","year":"2009","unstructured":"Koboldt, D.C., et al.: VarScan: variant detection in massively parallel sequencing of individual and pooled samples. Bioinformatics 25(17), 2283\u20132285 (2009)","journal-title":"Bioinformatics"},{"issue":"11","key":"6_CR21","doi-asserted-by":"publisher","first-page":"1525","DOI":"10.1093\/bioinformatics\/bts167","volume":"28","author":"SP Sadedin","year":"2012","unstructured":"Sadedin, S.P., Pope, B., Oshlack, A.: Bpipe: a tool for running and managing bioinformatics pipelines. Bioinformatics 28(11), 1525\u20131526 (2012)","journal-title":"Bioinformatics"},{"unstructured":"Seven Bridges. Publications and case studies (2021)","key":"6_CR22"},{"issue":"5","key":"6_CR23","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1101\/gr.213611.116","volume":"27","author":"VA Schneider","year":"2017","unstructured":"Schneider, V.A., et al.: Evaluation of GRCh38 and de novo haploid genome assemblies demonstrates the enduring quality of the reference assembly. Genome Res. 27(5), 849\u2013864 (2017)","journal-title":"Genome Res."},{"issue":"7","key":"6_CR24","doi-asserted-by":"publisher","first-page":"e1001091","DOI":"10.1371\/journal.pbio.1001091","volume":"9","author":"DM Church","year":"2011","unstructured":"Church, D.M., et al.: Modernizing reference genome assemblies. PLoS Biol. 9(7), e1001091 (2011)","journal-title":"PLoS Biol."},{"issue":"7536","key":"6_CR25","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1038\/nature13907","volume":"517","author":"MJ Chaisson","year":"2015","unstructured":"Chaisson, M.J., et al.: Resolving the complexity of the human genome using single-molecule sequencing. Nature 517(7536), 608\u2013611 (2015)","journal-title":"Nature"},{"issue":"6","key":"6_CR26","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1038\/s41592-018-0001-7","volume":"15","author":"FJ Sedlazeck","year":"2018","unstructured":"Sedlazeck, F.J., et al.: Accurate detection of complex structural variations using single-molecule sequencing. Nat. Methods 15(6), 461\u2013468 (2018)","journal-title":"Nat. Methods"},{"issue":"1","key":"6_CR27","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1101\/gr.210500.116","volume":"27","author":"MA Eberle","year":"2017","unstructured":"Eberle, M.A., et al.: A reference data set of 5.4 million phased human variants validated by genetic inheritance from sequencing a three-generation 17-member pedigree. Genome Res. 27(1), 157\u2013164 (2017)","journal-title":"Genome Res."},{"issue":"5","key":"6_CR28","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1038\/ng.806","volume":"43","author":"MA DePristo","year":"2011","unstructured":"DePristo, M.A., et al.: A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat. Genet. 43(5), 491\u2013498 (2011)","journal-title":"Nat. Genet."},{"issue":"15","key":"6_CR29","doi-asserted-by":"publisher","first-page":"2114","DOI":"10.1093\/bioinformatics\/btu170","volume":"30","author":"AM Bolger","year":"2014","unstructured":"Bolger, A.M., Lohse, M., Usadel, B.: Trimmomatic: a flexible trimmer for illumina sequence data. Bioinformatics 30(15), 2114\u20132120 (2014)","journal-title":"Bioinformatics"},{"unstructured":"Andrews, S., et al.: FastQC: a quality control tool for high throughput sequence data (2010)","key":"6_CR30"},{"unstructured":"Broad Institute. Picard Toolkit. http:\/\/broadinstitute.github.io\/picard\/. Accessed 24 Feb 2023","key":"6_CR31"},{"issue":"19","key":"6_CR32","doi-asserted-by":"publisher","first-page":"3047","DOI":"10.1093\/bioinformatics\/btw354","volume":"32","author":"P Ewels","year":"2016","unstructured":"Ewels, P., Magnusson, M., Lundin, S., K\u00e4ller, M.: MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics 32(19), 3047\u20133048 (2016)","journal-title":"Bioinformatics"},{"unstructured":"Miller, R.R., Zhang, L., Chen, L.: Next-generation sequencing bioinformatics pipelines. Clin. Lab. News: A Publication of AACC, 46(3), 12\u201315 (2020)","key":"6_CR33"},{"issue":"5","key":"6_CR34","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41587-019-0054-x","volume":"37","author":"P Krusche","year":"2019","unstructured":"Krusche, P., et al.: Best practices for benchmarking germline small-variant calls in human genomes. Nat. Biotechnol. 37(5), 555\u2013560 (2019)","journal-title":"Nat. Biotechnol."},{"issue":"1","key":"6_CR35","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1186\/s12864-022-08365-3","volume":"23","author":"YA Barbitoff","year":"2022","unstructured":"Barbitoff, Y.A., Abasov, R., Tvorogova, V.E., Glotov, A.S., Predeus, A.V.: Systematic benchmark of state-of-the-art variant calling pipelines identifies major factors affecting accuracy of coding sequence variant discovery. BMC Genomics 23(1), 155 (2022)","journal-title":"BMC Genomics"},{"issue":"1","key":"6_CR36","doi-asserted-by":"publisher","first-page":"1809","DOI":"10.1038\/s41598-022-05833-4","volume":"12","author":"Y-L Lin","year":"2022","unstructured":"Lin, Y.-L., et al.: Comparison of GATK and DeepVariant by trio sequencing. Sci. Rep. 12(1), 1809 (2022)","journal-title":"Sci. Rep."}],"container-title":["Lecture Notes in Computer Science","Bioinformatics and Biomedical Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-34960-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T15:04:53Z","timestamp":1687964693000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-34960-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031349591","9783031349607"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-34960-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"29 June 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The repository for the replication of the results described in this paper are available at .","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Reproducibility"}},{"value":"IWBBIO","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Work-Conference on Bioinformatics and Biomedical Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Meloneras, Gran Canaria","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwbbio2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iwbbio.ugr.es\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"203","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"79","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"39% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}