{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T15:22:04Z","timestamp":1758122524632,"version":"3.37.3"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2017,10,7]],"date-time":"2017-10-07T00:00:00Z","timestamp":1507334400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"crossref","award":["2016YFB1000403","2016YFB1000403"],"award-info":[{"award-number":["2016YFB1000403","2016YFB1000403"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"crossref","award":["2016YFB1000403","2016YFB1000403"],"award-info":[{"award-number":["2016YFB1000403","2016YFB1000403"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Office of Science of the U.S. Department of Energy","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1007\/s10766-017-0524-z","type":"journal-article","created":{"date-parts":[[2017,10,7]],"date-time":"2017-10-07T06:52:50Z","timestamp":1507359170000},"page":"762-775","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Combining Hadoop with MPI to Solve Metagenomics Problems that are both Data- and Compute-intensive"],"prefix":"10.1007","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7666-0150","authenticated-orcid":false,"given":"Han","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhichao","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiandong","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenting","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengxian","family":"Chi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,10,7]]},"reference":[{"issue":"8","key":"524_CR1","doi-asserted-by":"crossref","first-page":"901","DOI":"10.14778\/3090163.3090168","volume":"10","author":"M Anderson","year":"2017","unstructured":"Anderson, M., Smith, S., Sundaram, N., Capot\u0103, M., Zhao, Z., Dulloor, S., Satish, N., Willke, T.L.: Bridging the gap between hpc and big data frameworks. Proc. VLDB Endow. 10(8), 901\u2013912 (2017)","journal-title":"Proc. VLDB Endow."},{"issue":"1","key":"524_CR2","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/99.660313","volume":"5","author":"L Dagum","year":"1998","unstructured":"Dagum, L., Menon, R.: Openmp: an industry standard api for shared-memory programming. IEEE Comput. Sci. Eng. 5(1), 46\u201355 (1998)","journal-title":"IEEE Comput. Sci. Eng."},{"issue":"1","key":"524_CR3","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean, J., Ghemawat, S.: Mapreduce: simplified data processing on large clusters. Commun. ACM 51(1), 107\u2013113 (2008)","journal-title":"Commun. ACM"},{"key":"524_CR4","doi-asserted-by":"crossref","unstructured":"Fox, G.C., Qiu, J., Kamburugamuve, S., Jha, S., Luckow, A.: Hpc-abds high performance computing enhanced apache big data stack. In: 2015 15th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), pp. 1057\u20131066. IEEE (2015)","DOI":"10.1109\/CCGrid.2015.122"},{"key":"524_CR5","unstructured":"Gittens, A., Devarakonda, A., Racah, E., Ringenburg, M., Gerhardt, L., Kottalam, J., Liu, J., Maschhoff, K., Canon, S., Chhugani, J., et\u00a0al.: Matrix factorization at scale: a comparison of scientific data analytics in spark and c+ mpi using three case studies (2016). arXiv preprint arXiv:1607.01335"},{"issue":"6","key":"524_CR6","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/0167-8191(96)00024-5","volume":"22","author":"W Gropp","year":"1996","unstructured":"Gropp, W., Lusk, E., Doss, N., Skjellum, A.: A high-performance, portable implementation of the mpi message passing interface standard. Parallel Comput. 22(6), 789\u2013828 (1996)","journal-title":"Parallel Comput."},{"issue":"2","key":"524_CR7","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1089\/cmb.2014.0251","volume":"22","author":"X Guo","year":"2015","unstructured":"Guo, X., Yu, N., Ding, X., Wang, J., Pan, Y.: Dime: a novel framework for de novo metagenomic sequence assembly. J. Comput. Biol. 22(2), 159\u2013177 (2015)","journal-title":"J. Comput. Biol."},{"key":"524_CR8","first-page":"97","volume":"4","author":"D Heger","year":"2013","unstructured":"Heger, D.: Hadoop performance tuning-a pragmatic & iterative approach. CMG J. 4, 97\u2013113 (2013)","journal-title":"CMG J."},{"issue":"6016","key":"524_CR9","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1126\/science.1200387","volume":"331","author":"M Hess","year":"2011","unstructured":"Hess, M., Sczyrba, A., Egan, R., Kim, T.W., Chokhawala, H., Schroth, G., Luo, S., Clark, D.S., Chen, F., Zhang, T., et al.: Metagenomic discovery of biomass-degrading genes and genomes from cow rumen. Science 331(6016), 463\u2013467 (2011)","journal-title":"Science"},{"key":"524_CR10","doi-asserted-by":"crossref","unstructured":"Joshi, S.B.: Apache hadoop performance-tuning methodologies and best practices. In: Proceedings of the 3rd ACM\/SPEC International Conference on Performance Engineering, pp. 241\u2013242. ACM (2012)","DOI":"10.1145\/2188286.2188323"},{"key":"524_CR11","doi-asserted-by":"crossref","unstructured":"Kiveris, R., Lattanzi, S., Mirrokni, V., Rastogi, V., Vassilvitskii, S.: Connected components in mapreduce and beyond. In: Proceedings of the ACM Symposium on Cloud Computing, pp. 1\u201313. ACM (2014)","DOI":"10.1145\/2670979.2670997"},{"key":"524_CR12","doi-asserted-by":"crossref","unstructured":"Li, M., Zeng, L., Meng, S., Tan, J., Zhang, L., Butt, A.R., Fuller, N.: Mronline: Mapreduce online performance tuning. In: Proceedings of the 23rd International Symposium on High-Performance Parallel and Distributed Computing, pp. 165\u2013176. ACM (2014)","DOI":"10.1145\/2600212.2600229"},{"key":"524_CR13","doi-asserted-by":"crossref","unstructured":"Lu, X., Liang, F., Wang, B., Zha, L., Xu, Z.: Datampi: extending mpi to hadoop-like big data computing. In: 2014 IEEE 28th International Symposium on Parallel and Distributed Processing, pp. 829\u2013838. IEEE (2014)","DOI":"10.1109\/IPDPS.2014.90"},{"issue":"1","key":"524_CR14","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/nrg2626","volume":"11","author":"ML Metzker","year":"2010","unstructured":"Metzker, M.L.: Sequencing technologies\u2014the next generation. Nat. Rev. Genet. 11(1), 31\u201346 (2010)","journal-title":"Nat. Rev. Genet."},{"key":"524_CR15","doi-asserted-by":"crossref","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)","DOI":"10.1093\/bioinformatics\/btt528"},{"key":"524_CR16","unstructured":"Nvidia, C.: Compute Unified Device Architecture Programming Guide (2007). http:\/\/developer.download.nvidia.com\/compute\/cuda\/1.0\/NVIDIA_CUDA_Programming_Guide_1.0.pdf"},{"key":"524_CR17","doi-asserted-by":"crossref","unstructured":"Olston, C., Reed, B., Srivastava, U., Kumar, R., Tomkins, A.: Pig latin: a not-so-foreign language for data processing. In: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, pp. 1099\u20131110. ACM (2008)","DOI":"10.1145\/1376616.1376726"},{"key":"524_CR18","first-page":"18","volume":"1","author":"J Qiu","year":"2014","unstructured":"Qiu, J., Jha, S., Luckow, A., Fox, G.C.: Towards hpc-abds: an initial high-performance big data stack. Build. Robust Big Data Ecosyst. ISO\/IEC JTC 1, 18\u201321 (2014)","journal-title":"Build. Robust Big Data Ecosyst. ISO\/IEC JTC"},{"key":"524_CR19","doi-asserted-by":"crossref","unstructured":"Rasheed, Z., Rangwala, H.: A map-reduce framework for clustering metagenomes. In: Parallel and Distributed Processing Symposium Workshops and Ph.D. Forum (IPDPSW), 2013 IEEE 27th International, pp. 549\u2013558. IEEE (2013)","DOI":"10.1109\/IPDPSW.2013.100"},{"key":"524_CR20","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.procs.2015.07.286","volume":"53","author":"JL Reyes-Ortiz","year":"2015","unstructured":"Reyes-Ortiz, J.L., Oneto, L., Anguita, D.: Big data analytics in the cloud: spark on hadoop vs mpi\/openmp on beowulf. Proc. Comput. Sci. 53, 121\u2013130 (2015)","journal-title":"Proc. Comput. Sci."},{"key":"524_CR21","doi-asserted-by":"crossref","unstructured":"Schmidt, B., Hildebrandt, A.: Next-generation sequencing: big data meets high performance computing. Drug Discovery Today 4(4), 712\u2013717 (2017)","DOI":"10.1016\/j.drudis.2017.01.014"},{"key":"524_CR22","doi-asserted-by":"crossref","unstructured":"Shi, L., Wang, Z., Yu, W., Meng, X.: Performance evaluation and tuning of biopig for genomic analysis. In: Proceedings of the 2015 International Workshop on Data-Intensive Scalable Computing Systems, p.\u00a09. ACM (2015)","DOI":"10.1145\/2831244.2831252"},{"issue":"2","key":"524_CR23","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1145\/321879.321884","volume":"22","author":"RE Tarjan","year":"1975","unstructured":"Tarjan, R.E.: Efficiency of a good but not linear set union algorithm. J. ACM (JACM) 22(2), 215\u2013225 (1975)","journal-title":"J. ACM (JACM)"},{"key":"524_CR24","doi-asserted-by":"crossref","unstructured":"Vavilapalli, V.K., Murthy, A.C., Douglas, C., Agarwal, S., Konar, M., Evans, R., Graves, T., Lowe, J., Shah, H., Seth, S., et\u00a0al.: Apache hadoop yarn: yet another resource negotiator. In: Proceedings of the 4th Annual Symposium on Cloud Computing, p.\u00a05. ACM (2013)","DOI":"10.1145\/2523616.2523633"},{"key":"524_CR25","unstructured":"Website: Apache hadoop. https:\/\/hadoop.apache.org"},{"key":"524_CR26","unstructured":"Website: Apache pig. http:\/\/pig.apache.org"},{"key":"524_CR27","unstructured":"Website: Apache tez. https:\/\/tez.aprche.org"},{"issue":"10\u201310","key":"524_CR28","first-page":"95","volume":"10","author":"M Zaharia","year":"2010","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: cluster computing with working sets. HotCloud 10(10\u201310), 95 (2010)","journal-title":"HotCloud"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-017-0524-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-017-0524-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-017-0524-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,18]],"date-time":"2020-05-18T09:16:58Z","timestamp":1589793418000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-017-0524-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,7]]},"references-count":28,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,8]]}},"alternative-id":["524"],"URL":"https:\/\/doi.org\/10.1007\/s10766-017-0524-z","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2017,10,7]]}}}