{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T19:37:47Z","timestamp":1725910667433},"publisher-location":"Cham","reference-count":51,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319598246"},{"type":"electronic","value":"9783319598260"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-59826-0_5","type":"book-chapter","created":{"date-parts":[[2017,9,18]],"date-time":"2017-09-18T07:16:01Z","timestamp":1505718961000},"page":"117-128","source":"Crossref","is-referenced-by-count":0,"title":["Cloud Storage-Management Techniques for NGS Data"],"prefix":"10.1007","author":[{"given":"Evangelos","family":"Theodoridis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,9,19]]},"reference":[{"key":"5_CR1","unstructured":"1000 genomes project (2013). http:\/\/www.1000genomes.org\/"},{"key":"5_CR2","unstructured":"Amazon S3 multipart upload. http:\/\/aws.amazon.com\/blogs\/aws\/amazon-s3-multipart-upload\/"},{"key":"5_CR3","unstructured":"Apache Hadoop. http:\/\/hadoop.apache.org\/"},{"key":"5_CR4","unstructured":"Apache Hive. https:\/\/hive.apache.org\/"},{"key":"5_CR5","unstructured":"Apache Flink. http:\/\/flink.incubator.apache.org"},{"key":"5_CR6","unstructured":"Apache Pig. http:\/\/pig.apache.org\/"},{"key":"5_CR7","unstructured":"Apache Samza. http:\/\/samza.incubator.apache.org\/"},{"key":"5_CR8","unstructured":"Apache Spark. https:\/\/spark.apache.org\/"},{"key":"5_CR9","unstructured":"Apache Tez. http:\/\/tez.apache.org\/"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Bongcam-Rudloff, E., et al.: The next NGS challenge conference: data processing and integration. EMBnet. J. 19(A), p-3 (2013)","DOI":"10.14806\/ej.19.A.686"},{"key":"5_CR11","unstructured":"Bowtie. http:\/\/bowtie-bio.sourceforge.net\/index.shtml"},{"key":"5_CR12","unstructured":"Burrows-Wheeler Aligner. http:\/\/bio-bwa.sourceforge.net\/"},{"key":"5_CR13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2164-13-491","volume":"13","author":"Y.J. Chang","year":"2012","unstructured":"Chang, Y.J., Chen, C.C., Chen, C.L., Ho, J.M.: A de novo next generation genomic sequence assembler based on string graph and MapReduce cloud computing framework. BMC Genomics 13, 1\u201317 (2012)","journal-title":"BMC Genomics"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Chen, C.C., Chang, Y.J., Chung, W.C., Lee, D.T., Ho, J.M.: CloudRS: an error correction algorithm of high-throughput sequencing data based on scalable framework. In: BigData Conference, pp. 717\u2013722. IEEE (2013)","DOI":"10.1109\/BigData.2013.6691642"},{"issue":"6","key":"5_CR15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0098146","volume":"9","author":"W.-C. Chung","year":"2014","unstructured":"Chung, W.-C., et al.: CloudDOE: a user-friendly tool for deploying Hadoop clouds and analyzing high-throughput sequencing data with MapReduce. PLoS One 9(6), e98146 (2014). doi:10.1371\/journal.pone.0098146","journal-title":"PLoS One"},{"key":"5_CR16","unstructured":"CloudGENE A graphical MapReduce platform for cloud computing. http:\/\/cloudgene.uibk.ac.at\/index.html"},{"key":"5_CR17","unstructured":"COST Action BM1006: next generation sequencing data analysis network. http:\/\/www.seqahead.eu\/"},{"key":"5_CR18","unstructured":"Crossbow. http:\/\/bowtie-bio.sourceforge.net\/crossbow\/index.shtml"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Daugelaite, J., O\u2019 Driscoll, A., Sleator, R.D.: An overview of multiple sequence alignments and cloud computing in bioinformatics. ISRN Biomath. 2013, 14 pp. (2013). doi:10.1155\/2013\/615630. Article ID 615630","DOI":"10.1155\/2013\/615630"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Genome 10K Community of Scientists: Genome 10K: a proposal to obtain whole-genome sequence for 10,000 vertebrate species. J. Hered. 100, 659\u2013674 (2009)","DOI":"10.1093\/jhered\/esp086"},{"issue":"Suppl. 2","key":"5_CR21","doi-asserted-by":"crossref","first-page":"I1","DOI":"10.1186\/1752-0509-8-S2-I1","volume":"8","author":"D. Gomez-Cabrero","year":"2014","unstructured":"Gomez-Cabrero, D., Abugessaisa, I., Maier, D., Teschendorff, A., Merkenschlager, M., Gisel, A., Ballestar, E., Bongcam-Rudloff, E., Conesa A., Tegn\u00e9r, J.: Data integration in the era of omics: current and future challenges. BMC Syst. Biol. 8(Suppl. 2), I1 (2014)","journal-title":"BMC Syst. Biol."},{"key":"5_CR22","unstructured":"Google BigQuery. https:\/\/developers.google.com\/bigquery\/"},{"key":"5_CR23","unstructured":"Google BigQuery. https:\/\/cloud.google.com\/developers\/articles\/getting-started-with-google-bigquery"},{"key":"5_CR24","unstructured":"Hadoop Yarn. http:\/\/hadoop.apache.org\/docs\/current\/hadoop-yarn\/hadoop-yarn-site\/YARN.html"},{"key":"5_CR25","unstructured":"Human genome project information (2013). http:\/\/web.ornl.gov\/sci\/techresources\/HumanGenome\/"},{"key":"5_CR26","unstructured":"Illumina. https:\/\/www.illumina.com\/"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Lin, Y.-C., Yu, C.-S., Lin, Y.-J.: Enabling large-scale biomedical analysis in the cloud. BioMed. Res. Int. 2013, 6 pp. (2013). doi:10.1155\/2013\/185679. Article ID 185679","DOI":"10.1155\/2013\/185679"},{"key":"5_CR28","doi-asserted-by":"crossref","first-page":"330","DOI":"10.14778\/1920841.1920886","volume":"3","author":"S. Melnik","year":"2010","unstructured":"Melnik, S., Gubarev, A., Long, J.J., Romer, G., Shivakumar, S., Tolton, M., Vassilakis, T.: Dremel: interactive analysis of web-scale datasets. Proc. VLDB Endow. 3, 330\u2013339 (2010)","journal-title":"Proc. VLDB Endow."},{"key":"5_CR29","volume-title":"Mapreduce Design Patterns: Building Effective Algorithms and Analytics for Hadoop and Other Systems","author":"D. Miner","year":"2012","unstructured":"Miner, D., Shook, A.: Mapreduce Design Patterns: Building Effective Algorithms and Analytics for Hadoop and Other Systems, 1st edn. O\u2019Reilly Media, Inc., Sebastopol (2012)","edition":"1"},{"issue":"6","key":"5_CR30","doi-asserted-by":"crossref","first-page":"876","DOI":"10.1093\/bioinformatics\/bts054","volume":"28","author":"M. Niemenmaa","year":"2012","unstructured":"Niemenmaa, M., et al.: Hadoop-BAM: directly manipulating next generation sequencing data in the cloud. Bioinformatics 28(6), 876\u2013877 (2012)","journal-title":"Bioinformatics"},{"issue":"23","key":"5_CR31","doi-asserted-by":"crossref","first-page":"3014","DOI":"10.1093\/bioinformatics\/btt528","volume":"29","author":"H. Nordberg","year":"2013","unstructured":"Nordberg, H., Bhatia, K., Wang, K., Wang, Z.: BioPig: a Hadoop-based analytic toolkit for large-scale sequence data. Bioinformatics 29(23), 3014\u20133019 (2013)","journal-title":"Bioinformatics"},{"issue":"5","key":"5_CR32","first-page":"774","volume":"46","author":"A. O\u2019Driscoll","year":"2013","unstructured":"O\u2019Driscoll, A., Daugelaite, J., Sleator, R.D.: Big data\u2019, Hadoop and cloud computing in genomics. J. Biomed. Inform. 46(5), 774\u2013781 (2013)","journal-title":"Hadoop and cloud computing in genomics. J. Biomed. Inform."},{"issue":"8","key":"5_CR33","volume":"8","author":"R.V. Pandey","year":"2013","unstructured":"Pandey, R.V., Schl\u00f6tterer, C.: DistMap: a toolkit for distributed short read mapping on a Hadoop cluster. PLoS One 8(8), e72614 (2013)","journal-title":"PLoS One"},{"key":"5_CR34","volume-title":"Pig Design Patterns","author":"P. Pasupuleti","year":"2014","unstructured":"Pasupuleti, P.: Pig Design Patterns. Packt Publishing, Birmingham (2014)"},{"key":"5_CR35","unstructured":"Picard Tools. http:\/\/picard.sourceforge.net\/"},{"key":"5_CR36","unstructured":"Pig Latin. http:\/\/pig.apache.org\/docs\/r0.13.0\/basic.html"},{"issue":"15","key":"5_CR37","doi-asserted-by":"publisher","first-page":"2159","DOI":"10.1093\/bioinformatics\/btr325","volume":"27","author":"L. Pireddu","year":"2011","unstructured":"Pireddu, L., Leo, S., Zanetti, G.: SEAL: a distributed short read mapping and duplicate removal tool. Bioinformatics 27(15), 2159\u20132160 (2011). doi:10.1093\/bioinformatics\/btr325. http:\/\/biodoop-seal.sourceforge.net\/","journal-title":"Bioinformatics"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Regierer, B., et al.: ICT needs and challenges for big data in the life sciences. A workshop report-SeqAhead\/ISBE Workshop in Pula, Sardinia, 6 June 2013. EMBnet. J. 19(1), pp-31 (2013)","DOI":"10.14806\/ej.19.1.699"},{"key":"5_CR39","unstructured":"Roche\/454 http:\/\/www.454.com\/"},{"key":"5_CR40","unstructured":"SAMtools http:\/\/www.htslib.org\/"},{"key":"5_CR41","doi-asserted-by":"crossref","first-page":"1363","DOI":"10.1093\/bioinformatics\/btp236","volume":"25","author":"M.C. Schatz","year":"2009","unstructured":"Schatz, M.C.: CloudBurst: highly sensitive read mapping with MapReduce. Bioinformatics 25, 1363\u20131369 (2009)","journal-title":"Bioinformatics"},{"issue":"1","key":"5_CR42","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1093\/bioinformatics\/btt601","volume":"30","author":"A. Schumacher","year":"2014","unstructured":"Schumacher, A., et al.: SeqPig: simple and scalable scripting for large sequencing data sets in Hadoop. Bioinformatics 30(1), 119\u2013120 (2014)","journal-title":"Bioinformatics"},{"key":"5_CR43","unstructured":"SeqWare https:\/\/seqware.github.io\/"},{"key":"5_CR44","unstructured":"SoapsSNP http:\/\/bowtie-bio.sourceforge.net\/index.shtml"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Thusoo, A., Sarma, J.S., Jain, N., Shao, Z., Chakka, P., Anthony, S., Liu, H., Wyckoff, P., Murthy, R.: 2009. Hive: a warehousing solution over a map-reduce framework. Proc. VLDB Endow. 2(2), 1626\u20131629 (2009)","DOI":"10.14778\/1687553.1687609"},{"key":"5_CR46","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btp120","author":"C. Trapnell","year":"2009","unstructured":"Trapnell, C., Pachter, L., Salzberg, S.L.: TopHat: discovering splice junctions with RNA-Seq. Bioinformatics (2009). doi:10.1093\/bioinformatics\/btp120","journal-title":"Bioinformatics"},{"key":"5_CR47","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4302-1943-9","volume-title":"Pro Hadoop","author":"J. Venner","year":"2009","unstructured":"Venner, J.: Pro Hadoop, 1st edn. Apress, Berkely, CA (2009)","edition":"1"},{"key":"5_CR48","volume-title":"Hadoop: The Definitive Guide","author":"T. White","year":"2009","unstructured":"White, T.: Hadoop: The Definitive Guide, 1st edn. O\u2019Reilly Media, Inc., Sebastopol (2009)","edition":"1"},{"key":"5_CR49","doi-asserted-by":"crossref","unstructured":"Wiewi\u00f3rka, M.S., et al.: SparkSeq: fast, scalable, cloud-ready tool for the interactive genomic data analysis with nucleotide precision. Bioinformatics (2014) doi:10.1093\/bioinformatics\/btu343. First published online: May 19 (2014)","DOI":"10.1093\/bioinformatics\/btu343"},{"key":"5_CR50","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1093\/bioinformatics\/btq057","volume":"26","author":"T.D. Wu","year":"2010","unstructured":"Wu, T.D., Nacu, S.: Fast and SNP-tolerant detection of complex variants and splicing in short reads. Bioinformatics 26, 873\u2013881 (2010)","journal-title":"Bioinformatics"},{"key":"5_CR51","unstructured":"Zaharia, M., et al.: Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation (NSDI\u201912) (2012)"}],"container-title":["Algorithms for Next-Generation Sequencing Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-59826-0_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,3]],"date-time":"2019-10-03T12:00:53Z","timestamp":1570104053000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-59826-0_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319598246","9783319598260"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-59826-0_5","relation":{},"subject":[],"published":{"date-parts":[[2017]]}}}