{"id":"https://openalex.org/W2114907886","doi":"https://doi.org/10.1186/1471-2105-10-s1-s16","title":"Crystallizing short-read assemblies around seeds","display_name":"Crystallizing short-read assemblies around seeds","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2114907886","doi":"https://doi.org/10.1186/1471-2105-10-s1-s16","mag":"2114907886","pmid":"https://pubmed.ncbi.nlm.nih.gov/19208115"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-10-s1-s16","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-s1-s16","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-S1-S16","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-S1-S16","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035514887","display_name":"Mohammad Sajjad Hossain","orcid":"https://orcid.org/0000-0003-3054-4925"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Sajjad Hossain","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stony Brook, NY 11794-4400 USA. sajjad@cs.sunysb.edu","Department of Computer Science, Stony Brook University, Stony Brook, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, NY 11794-4400 USA. sajjad@cs.sunysb.edu","institution_ids":["https://openalex.org/I59553526"]},{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038466345","display_name":"Navid Hamed Azimi","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Navid Azimi","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stony Brook, NY, 11794-4400, USA","Department of Computer Science, Stony Brook University, Stony Brook, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, NY, 11794-4400, USA","institution_ids":["https://openalex.org/I59553526"]},{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060741187","display_name":"Steven Skiena","orcid":"https://orcid.org/0000-0003-0397-7514"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Skiena","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stony Brook, NY, 11794-4400, USA","Department of Computer Science, Stony Brook University, Stony Brook, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, NY, 11794-4400, USA","institution_ids":["https://openalex.org/I59553526"]},{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, USA","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":2.7701,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.90841069,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"10","issue":"S1","first_page":"S16","last_page":"S16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.6863999962806702,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.6863999962806702,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.07779999822378159,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.035999998450279236,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/contig","display_name":"Contig","score":0.8114502429962158},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.7368336915969849},{"id":"https://openalex.org/keywords/sanger-sequencing","display_name":"Sanger sequencing","score":0.6362733840942383},{"id":"https://openalex.org/keywords/hybrid-genome-assembly","display_name":"Hybrid genome assembly","score":0.6273239850997925},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6099017858505249},{"id":"https://openalex.org/keywords/nanopore-sequencing","display_name":"Nanopore sequencing","score":0.5267928242683411},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4971061050891876},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4839404225349426},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4221239984035492},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.338287353515625},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.1753556728363037},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.14690297842025757},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.0992307960987091},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.0938330888748169}],"concepts":[{"id":"https://openalex.org/C59582021","wikidata":"https://www.wikidata.org/wiki/Q1128751","display_name":"Contig","level":4,"score":0.8114502429962158},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.7368336915969849},{"id":"https://openalex.org/C76818968","wikidata":"https://www.wikidata.org/wiki/Q181940","display_name":"Sanger sequencing","level":4,"score":0.6362733840942383},{"id":"https://openalex.org/C113425843","wikidata":"https://www.wikidata.org/wiki/Q5953213","display_name":"Hybrid genome assembly","level":5,"score":0.6273239850997925},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6099017858505249},{"id":"https://openalex.org/C126513998","wikidata":"https://www.wikidata.org/wiki/Q8973627","display_name":"Nanopore sequencing","level":4,"score":0.5267928242683411},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4971061050891876},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4839404225349426},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4221239984035492},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.338287353515625},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.1753556728363037},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.14690297842025757},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0992307960987091},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0938330888748169},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-10-s1-s16","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-s1-s16","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-S1-S16","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:19208115","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19208115","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:8014b17bbbac4a52a97f316b931b6a2f","is_oa":true,"landing_page_url":"https://doaj.org/article/8014b17bbbac4a52a97f316b931b6a2f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 10, Iss Suppl 1, p S16 (2009)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2648751","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2648751","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-10-s1-s16","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-s1-s16","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-S1-S16","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/12","display_name":"Responsible consumption and production"}],"awards":[{"id":"https://openalex.org/G2260358573","display_name":"ITR:  Gene Design for Vaccines and Therapeutic Phages","funder_award_id":"0325123","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6402637011","display_name":"Sequence Assembly for High-Throughput Technologies","funder_award_id":"0444815","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2114907886.pdf","grobid_xml":"https://content.openalex.org/works/W2114907886.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W647308575","https://openalex.org/W1498892184","https://openalex.org/W1584540095","https://openalex.org/W1658221551","https://openalex.org/W1974646727","https://openalex.org/W1982494531","https://openalex.org/W1984236772","https://openalex.org/W2023911006","https://openalex.org/W2026186077","https://openalex.org/W2043714862","https://openalex.org/W2050163545","https://openalex.org/W2054880642","https://openalex.org/W2056737635","https://openalex.org/W2079286282","https://openalex.org/W2083215220","https://openalex.org/W2107282968","https://openalex.org/W2119923823","https://openalex.org/W2121016876","https://openalex.org/W2127651281","https://openalex.org/W2138270253","https://openalex.org/W2142749416","https://openalex.org/W2151017710","https://openalex.org/W2155845142","https://openalex.org/W2160969485","https://openalex.org/W2161668137","https://openalex.org/W2162010421","https://openalex.org/W2163415691","https://openalex.org/W2171475724","https://openalex.org/W6643873256"],"related_works":["https://openalex.org/W3009176350","https://openalex.org/W1519765314","https://openalex.org/W2127651281","https://openalex.org/W3090794301","https://openalex.org/W3167837387","https://openalex.org/W2949198880","https://openalex.org/W2952788979","https://openalex.org/W2763726643","https://openalex.org/W2899138449","https://openalex.org/W3005683565"],"abstract_inverted_index":{"BACKGROUND:":[0],"New":[1],"short-read":[2,42,114,145],"sequencing":[3,53],"technologies":[4],"produce":[5,110],"enormous":[6],"volumes":[7],"of":[8,33,97,99,128,141,178],"25-30":[9],"base":[10],"paired-end":[11,165],"reads.":[12,166],"The":[13],"resulting":[14],"reads":[15,88,152],"have":[16],"vastly":[17],"different":[18,27,180],"characteristics":[19],"than":[20,29,118,204],"produced":[21],"by":[22,80,207],"Sanger":[23],"sequencing,":[24],"and":[25,156],"require":[26],"approaches":[28],"the":[30,49,64,75,144],"previous":[31],"generation":[32],"sequence":[34,68],"assemblers.":[35,209],"In":[36],"this":[37,199],"paper,":[38],"we":[39,60,137],"present":[40],"a":[41,90,125],"de":[43,66],"novo":[44,67],"assembler":[45,84],"particularly":[46],"targeted":[47],"at":[48],"new":[50],"ABI":[51],"SOLiD":[52,77,185],"technology.":[54],"RESULTS:":[55],"This":[56],"paper":[57],"presents":[58],"what":[59],"believe":[61,138],"to":[62,109,139,143,153],"be":[63,122,140],"first":[65],"assembly":[69,146],"results":[70,197],"on":[71,192,198],"real":[72,193],"data":[73,200],"from":[74,162],"emerging":[76],"platform,":[78],"introduced":[79],"Applied":[81],"Biosystems.":[82],"Our":[83],"SHORTY":[85,132],"augments":[86],"short-paired":[87],"using":[89,113,149,183],"trivially":[91],"small":[92],"number":[93],"(5":[94],"-":[95,102],"10)":[96],"seeds":[98,106],"length":[100],"300":[101],"500":[103],"bp.":[104],"These":[105],"enable":[107],"us":[108],"significant":[111],"assemblies":[112,171],"coverage":[115],"no":[116],"more":[117],"100x,":[119],"which":[120,136],"can":[121],"obtained":[123],"in":[124],"single":[126,150],"run":[127],"these":[129],"high-capacity":[130],"sequencers.":[131],"exploits":[133],"two":[134],"ideas":[135],"interest":[142],"community:":[147],"(1)":[148],"seed":[151],"crystallize":[154],"assemblies,":[155],"(2)":[157],"estimating":[158],"intercontig":[159],"distances":[160],"accurately":[161],"multiple":[163],"spanning":[164],"CONCLUSION:":[167],"We":[168],"demonstrate":[169],"effective":[170],"(N50":[172],"contig":[173],"sizes":[174],"approximately":[175],"40":[176],"kb)":[177],"three":[179],"bacterial":[181],"species":[182],"simulated":[184],"data.":[186],"Sequencing":[187],"artifacts":[188],"limit":[189],"our":[190,196],"performance":[191],"data,":[194],"however":[195],"are":[201],"substantially":[202],"better":[203],"those":[205],"achieved":[206],"competing":[208]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
