{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,4]],"date-time":"2024-07-04T17:39:48Z","timestamp":1720114788045},"reference-count":63,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2017,4,1]],"date-time":"2017-04-01T00:00:00Z","timestamp":1491004800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2017,4]]},"DOI":"10.1016\/j.ins.2016.08.085","type":"journal-article","created":{"date-parts":[[2016,9,6]],"date-time":"2016-09-06T08:55:06Z","timestamp":1473152106000},"page":"90-109","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":7,"special_numbering":"C","title":["Indexing Next-Generation Sequencing data"],"prefix":"10.1016","volume":"384","author":[{"given":"Vahid","family":"Jalili","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-8306-6739","authenticated-orcid":false,"given":"Matteo","family":"Matteucci","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-2574-1174","authenticated-orcid":false,"given":"Marco","family":"Masseroli","sequence":"additional","affiliation":[]},{"given":"Stefano","family":"Ceri","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"7319","key":"10.1016\/j.ins.2016.08.085_bib0001","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.1038\/nature09534","article-title":"A map of human genome variation from population-scale sequencing","volume":"467","author":"1000_Genomes_Project_Consortium","year":"2010","journal-title":"Nature"},{"key":"10.1016\/j.ins.2016.08.085_bib0002","series-title":"EDBT\/ICDT workshops","first-page":"3","article-title":"Bounds for overlapping interval join on MapReduce","author":"Afrati","year":"2015"},{"issue":"11","key":"10.1016\/j.ins.2016.08.085_bib0003","doi-asserted-by":"crossref","first-page":"1386","DOI":"10.1093\/bioinformatics\/btl647","article-title":"Nested Containment List (NCList): a new algorithm for accelerating interval query of genome alignment and interval databases","volume":"23","author":"Alekseyenko","year":"2007","journal-title":"Bioinformatics"},{"issue":"17","key":"10.1016\/j.ins.2016.08.085_bib0004","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","article-title":"Gapped BLAST and PSI-BLAST: a new generation of protein database search programs","volume":"25","author":"Altschul","year":"1997","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/j.ins.2016.08.085_bib0005","series-title":"Technical Report","article-title":"Solutions to Klee\u2019s rectangle problems","author":"Bentley","year":"1977"},{"issue":"5","key":"10.1016\/j.ins.2016.08.085_bib0006","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1016\/0020-0190(79)90117-0","article-title":"Decomposable searching problems","volume":"8","author":"Bentley","year":"1979","journal-title":"Inf. Process. Lett."},{"issue":"Suppl. 1","key":"10.1016\/j.ins.2016.08.085_bib0007","doi-asserted-by":"crossref","first-page":"D556","DOI":"10.1093\/nar\/gkj133","article-title":"Ensembl 2006","volume":"34","author":"Birney","year":"2006","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/j.ins.2016.08.085_bib0008","series-title":"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, 66","first-page":"1","article-title":"SciHadoop: array-based query processing in Hadoop","author":"Buck","year":"2011"},{"issue":"8","key":"10.1016\/j.ins.2016.08.085_bib0009","doi-asserted-by":"crossref","first-page":"1621","DOI":"10.1038\/ismej.2012.8","article-title":"Ultra-high-throughput microbial community analysis on the illumina HiSeq and MiSeq platforms","volume":"6","author":"Caporaso","year":"2012","journal-title":"ISME J."},{"issue":"9","key":"10.1016\/j.ins.2016.08.085_bib0010","doi-asserted-by":"crossref","first-page":"1313","DOI":"10.1093\/bioinformatics\/btr123","article-title":"GeCo++: a C++ library for genomic features computation and annotation in the presence of variants","volume":"27","author":"Cereda","year":"2011","journal-title":"Bioinformatics"},{"key":"10.1016\/j.ins.2016.08.085_bib0011","series-title":"EDBT","first-page":"463","article-title":"Processing interval joins on Map-Reduce","author":"Chawda","year":"2014"},{"issue":"13","key":"10.1016\/j.ins.2016.08.085_bib0012","doi-asserted-by":"crossref","first-page":"2182","DOI":"10.1111\/j.1742-4658.2011.08128.x","article-title":"Structure and function of active chromatin and DNase I hypersensitive sites","volume":"278","author":"Cockerill","year":"2011","journal-title":"FEBS J."},{"key":"10.1016\/j.ins.2016.08.085_bib0013","series-title":"Proceedings of Fourth IEEE Symposium on Bioinformatics and Bioengineering, BIBE 2004.","first-page":"587","article-title":"Indexing genomic databases","author":"Cooper","year":"2004"},{"key":"10.1016\/j.ins.2016.08.085_bib0014","series-title":"Section 14.3: Interval Trees","first-page":"348","author":"Cormen","year":"2009"},{"issue":"12","key":"10.1016\/j.ins.2016.08.085_bib0015","doi-asserted-by":"crossref","first-page":"1230","DOI":"10.14778\/2536274.2536283","article-title":"A demonstration of spatialhadoop: an efficient MapReduce framework for spatial data","volume":"6","author":"Eldawy","year":"2013","journal-title":"Proc. VLDB Endowment"},{"key":"10.1016\/j.ins.2016.08.085_bib0016","series-title":"Proceedings of the 16th International Conference on Very Large Data Bases","first-page":"1","article-title":"The time index: an access structure for temporal data","author":"Elmasri","year":"1990"},{"issue":"7414","key":"10.1016\/j.ins.2016.08.085_bib0017","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/nature11247","article-title":"An integrated encyclopedia of DNA elements in the human genome","volume":"489","author":"ENCODE_Project_Consortium","year":"2012","journal-title":"Nature"},{"issue":"3","key":"10.1016\/j.ins.2016.08.085_bib0018","first-page":"327","article-title":"A new data structure for cumulative frequency tables","volume":"24","author":"Fenwick","year":"1994","journal-title":"Software"},{"key":"10.1016\/j.ins.2016.08.085_bib0019","series-title":"Statistical Methods for Research Workers","author":"Fisher","year":"1925"},{"key":"10.1016\/j.ins.2016.08.085_bib0020","unstructured":"GA4GH_Data_Working_Group, GA4GH API, 2015. URL http:\/\/ga4gh.org\/#\/documentation"},{"key":"10.1016\/j.ins.2016.08.085_bib0021","series-title":"Proceedings of 20th International Conference on Data Engineering, 2004.","first-page":"29","article-title":"Bulk operations for space-partitioning trees","author":"Ghanem","year":"2004"},{"issue":"4","key":"10.1016\/j.ins.2016.08.085_bib0022","doi-asserted-by":"crossref","first-page":"732","DOI":"10.1101\/gr.603103","article-title":"GALA, a database for genomic sequence alignments and annotations","volume":"13","author":"Giardine","year":"2003","journal-title":"Genome Res."},{"issue":"2","key":"10.1016\/j.ins.2016.08.085_bib0023","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/0169-023X(95)00034-P","article-title":"Indexing temporal data using existing B+-trees","volume":"18","author":"Goh","year":"1996","journal-title":"Data Knowl. Eng."},{"key":"10.1016\/j.ins.2016.08.085_bib0024","series-title":"CIDR","first-page":"5","article-title":"Sorting and indexing with partitioned B-trees.","volume":"3","author":"Graefe","year":"2003"},{"key":"10.1016\/j.ins.2016.08.085_bib0025","series-title":"ACM SIGMOD International Conference on Management of Data","first-page":"47","article-title":"R-trees: a dynamic index structure for spatial searching","volume":"vol. 14","author":"Guttman","year":"1984"},{"key":"10.1016\/j.ins.2016.08.085_bib0026","series-title":"6th International Conference on Pervasive Computing and Applications (ICPCA), 2011","first-page":"363","article-title":"Survey on NoSQL database","author":"Han","year":"2011"},{"issue":"17","key":"10.1016\/j.ins.2016.08.085_bib0027","doi-asserted-by":"crossref","first-page":"2761","DOI":"10.1093\/bioinformatics\/btv293","article-title":"Using combined evidence from replicates to evaluate ChIP-seq peaks","volume":"31","author":"Jalili","year":"2015","journal-title":"Bioinformatics"},{"key":"10.1016\/j.ins.2016.08.085_bib0028","first-page":"1","article-title":"MuSERA: multiple sample enriched region assessment","author":"Jalili","year":"2016","journal-title":"Briefings Bioinf."},{"key":"10.1016\/j.ins.2016.08.085_bib0029","series-title":"31st IEEE International Conference on Data Engineering (ICDE), 2015.","first-page":"471","article-title":"Bi-temporal timeline index: a data structure for processing queries on bi-temporal data","author":"Kaufmann","year":"2015"},{"issue":"6","key":"10.1016\/j.ins.2016.08.085_bib0030","doi-asserted-by":"crossref","first-page":"996","DOI":"10.1101\/gr.229102. Article published online before print in May 2002","article-title":"The human genome browser at UCSC","volume":"12","author":"Kent","year":"2002","journal-title":"Genome Res."},{"issue":"7","key":"10.1016\/j.ins.2016.08.085_bib0031","doi-asserted-by":"crossref","first-page":"e0133198","DOI":"10.1371\/journal.pone.0133198","article-title":"Indexing arbitrary-length k-mers in sequencing reads","volume":"10","author":"Kowalski","year":"2015","journal-title":"PloS One"},{"issue":"9","key":"10.1016\/j.ins.2016.08.085_bib0032","doi-asserted-by":"crossref","first-page":"1813","DOI":"10.1101\/gr.136184.111","article-title":"ChIP-seq guidelines and practices of the ENCODE and modENCODE consortia","volume":"22","author":"Landt","year":"2012","journal-title":"Genome Res."},{"key":"10.1016\/j.ins.2016.08.085_bib0033","series-title":"Proceedings of the IEEE","first-page":"1","article-title":"A parallel algorithm for N-way interval set intersection","author":"Layer","year":"2015"},{"issue":"1","key":"10.1016\/j.ins.2016.08.085_bib0034","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/bioinformatics\/bts652","article-title":"Binary interval search: a scalable algorithm for counting interval intersections","volume":"29","author":"Layer","year":"2013","journal-title":"Bioinformatics"},{"issue":"5","key":"10.1016\/j.ins.2016.08.085_bib0035","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1093\/bioinformatics\/btq671","article-title":"Tabix: fast retrieval of sequence features from generic TAB-delimited files","volume":"27","author":"Li","year":"2011","journal-title":"Bioinformatics"},{"issue":"16","key":"10.1016\/j.ins.2016.08.085_bib0036","doi-asserted-by":"crossref","first-page":"2078","DOI":"10.1093\/bioinformatics\/btp352","article-title":"The sequence alignment\/map format and SAMtools","volume":"25","author":"Li","year":"2009","journal-title":"Bioinformatics"},{"issue":"12","key":"10.1016\/j.ins.2016.08.085_bib0037","doi-asserted-by":"crossref","first-page":"1881","DOI":"10.1093\/bioinformatics\/btv048","article-title":"GenoMetric Query Language: a novel approach to large-scale genomic data management","volume":"31","author":"Masseroli","year":"2015","journal-title":"Bioinformatics"},{"key":"10.1016\/j.ins.2016.08.085_bib0038","series-title":"Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","first-page":"392","article-title":"A parallel plane sweep algorithm for multi-core systems","author":"McKenney","year":"2009"},{"issue":"1","key":"10.1016\/j.ins.2016.08.085_bib0039","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/s10844-014-0353-0","article-title":"An efficient and flexible scanning of databases of protein secondary structures with the segment index and multithreaded alignment","volume":"46","author":"Mrozek","year":"2016","journal-title":"J. Intell. Inf. Syst."},{"issue":"14","key":"10.1016\/j.ins.2016.08.085_bib0040","doi-asserted-by":"crossref","first-page":"1919","DOI":"10.1093\/bioinformatics\/bts277","article-title":"BEDOPS: high-performance genomic feature operations","volume":"28","author":"Neph","year":"2012","journal-title":"Bioinformatics"},{"issue":"1","key":"10.1016\/j.ins.2016.08.085_bib0041","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1109\/TCBB.2012.170","article-title":"Genomic region operation kit for flexible processing of deep sequencing data","volume":"10","author":"Ovaska","year":"2013","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinf."},{"issue":"10","key":"10.1016\/j.ins.2016.08.085_bib0042","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1038\/nrg2641","article-title":"ChIP\u2013seq: advantages and challenges of a maturing technology","volume":"10","author":"Park","year":"2009","journal-title":"Nat. Rev. Genet."},{"issue":"6","key":"10.1016\/j.ins.2016.08.085_bib0043","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1093\/bioinformatics\/btq033","article-title":"BEDTools: a flexible suite of utilities for comparing genomic features","volume":"26","author":"Quinlan","year":"2010","journal-title":"Bioinformatics"},{"issue":"7","key":"10.1016\/j.ins.2016.08.085_bib0044","doi-asserted-by":"crossref","first-page":"R67","DOI":"10.1186\/gb-2011-12-7-r67","article-title":"ZINBA integrates local covariates with DNA-seq data to identify broad and narrow regions of enrichment, even within amplified genomic regions","volume":"12","author":"Rashid","year":"2011","journal-title":"Genome Biol."},{"issue":"11","key":"10.1016\/j.ins.2016.08.085_bib0045","doi-asserted-by":"crossref","first-page":"e26715","DOI":"10.1371\/journal.pone.0026715","article-title":"Segtor: rapid annotation of genomic coordinates and single nucleotide variations using segment trees","volume":"6","author":"Renaud","year":"2011","journal-title":"PloS One"},{"issue":"8","key":"10.1016\/j.ins.2016.08.085_bib0046","doi-asserted-by":"crossref","first-page":"1457","DOI":"10.1089\/cmb.2006.13.1457","article-title":"Fjoin: simple and efficient computation of feature overlaps","volume":"13","author":"Richardson","year":"2006","journal-title":"J. Comput. Biol."},{"issue":"7539","key":"10.1016\/j.ins.2016.08.085_bib0047","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1038\/518314a","article-title":"Epigenomics: roadmap for regulation","volume":"518","author":"Romanoski","year":"2015","journal-title":"Nature"},{"issue":"8","key":"10.1016\/j.ins.2016.08.085_bib0048","first-page":"16","article-title":"Next-generation sequencing transforms today\u2019s biology","volume":"200","author":"Schuster","year":"2007","journal-title":"Nature"},{"issue":"1","key":"10.1016\/j.ins.2016.08.085_bib0049","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1038\/nmeth1156","article-title":"Next-generation sequencing transforms today\u2019s biology","volume":"5","author":"Schuster","year":"2008","journal-title":"Nature Meth."},{"issue":"10","key":"10.1016\/j.ins.2016.08.085_bib0050","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1038\/nbt1486","article-title":"Next-generation DNA sequencing","volume":"26","author":"Shendure","year":"2008","journal-title":"Nature Biotechnol."},{"key":"10.1016\/j.ins.2016.08.085_bib0051","series-title":"ACM SIGMOD Record","first-page":"236","article-title":"A taxonomy of time databases","volume":"vol. 14","author":"Snodgrass","year":"1985"},{"key":"10.1016\/j.ins.2016.08.085_bib0052","unstructured":"R. Sriharsha, Magellan, 2015. URL http:\/\/spark-packages.org\/package\/harsha2010\/magellan"},{"issue":"4","key":"10.1016\/j.ins.2016.08.085_bib0053","doi-asserted-by":"crossref","first-page":"679","DOI":"10.2298\/CSIS101020035S","article-title":"Advanced indexing technique for temporal data","volume":"7","author":"Stantic","year":"2010","journal-title":"Comput. Sci. Inf. Syst."},{"issue":"10","key":"10.1016\/j.ins.2016.08.085_bib0054","doi-asserted-by":"crossref","first-page":"1599","DOI":"10.1101\/gr.403602","article-title":"The generic genome browser: a building block for a model organism system database","volume":"12","author":"Stein","year":"2002","journal-title":"Genome Res."},{"key":"10.1016\/j.ins.2016.08.085_bib0055","series-title":"Proceedings of the 21st ACM international conference on Information and Knowledge Management","first-page":"2139","article-title":"Clost: a hadoop-based storage system for big spatio-temporal data analytics","author":"Tan","year":"2012"},{"key":"10.1016\/j.ins.2016.08.085_bib0056","series-title":"10th RoEduNet International Conference (RoEduNet), 2011","first-page":"1","article-title":"A comparison between several NoSQL databases with comments and notes","author":"Tudorica","year":"2011"},{"issue":"120","key":"10.1016\/j.ins.2016.08.085_bib0057","first-page":"11","article-title":"Design patterns: elements of reusable object-oriented software","volume":"49","author":"Vlissides","year":"1995","journal-title":"Reading: Addison-Wesley"},{"issue":"10","key":"10.1016\/j.ins.2016.08.085_bib0058","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/ng.2764","article-title":"The Cancer Genome Atlas pan-cancer analysis project","volume":"45","author":"Weinstein","year":"2013","journal-title":"Nat. Genet."},{"issue":"1","key":"10.1016\/j.ins.2016.08.085_bib0059","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13015-016-0069-5","article-title":"Bitpacking techniques for indexing genomes: I. Hash tables","volume":"11","author":"Wu","year":"2016","journal-title":"Algorithms Mol. Biol."},{"key":"10.1016\/j.ins.2016.08.085_bib0060","series-title":"Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems","first-page":"70","article-title":"Geospark: A cluster computing framework for processing large-scale spatial data","author":"Yu","year":"2015"},{"key":"10.1016\/j.ins.2016.08.085_bib0061","series-title":"Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation","first-page":"15","article-title":"Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing","author":"Zaharia","year":"2012"},{"issue":"9","key":"10.1016\/j.ins.2016.08.085_bib0062","doi-asserted-by":"crossref","first-page":"R137","DOI":"10.1186\/gb-2008-9-9-r137","article-title":"Model-based analysis of ChIP-seq (MACS)","volume":"9","author":"Zhang","year":"2008","journal-title":"Genome Biol."},{"issue":"7","key":"10.1016\/j.ins.2016.08.085_bib0063","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1093\/bioinformatics\/btt070","article-title":"Efficient comparison of sets of intervals with nc-lists","volume":"29","author":"Zytnicki","year":"2013","journal-title":"Bioinformatics"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025516306685?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025516306685?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2018,9,8]],"date-time":"2018-09-08T15:52:37Z","timestamp":1536421957000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025516306685"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4]]},"references-count":63,"alternative-id":["S0020025516306685"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2016.08.085","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2017,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Indexing Next-Generation Sequencing data","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2016.08.085","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2017 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}]}}