{"id":"https://openalex.org/W2027447543","doi":"https://doi.org/10.1504/ijbra.2008.017165","title":"The generalised k-Truncated Suffix Tree for time-and space-efficient searches in multiple DNA or protein sequences","display_name":"The generalised k-Truncated Suffix Tree for time-and space-efficient searches in multiple DNA or protein sequences","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2027447543","doi":"https://doi.org/10.1504/ijbra.2008.017165","mag":"2027447543","pmid":"https://pubmed.ncbi.nlm.nih.gov/18283030"},"language":"en","primary_location":{"id":"doi:10.1504/ijbra.2008.017165","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijbra.2008.017165","pdf_url":null,"source":{"id":"https://openalex.org/S207086575","display_name":"International Journal of Bioinformatics Research and Applications","issn_l":"1744-5485","issn":["1744-5485","1744-5493"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310317825","host_organization_name":"Inderscience Publishers","host_organization_lineage":["https://openalex.org/P4310317825"],"host_organization_lineage_names":["Inderscience Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Bioinformatics Research and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080725960","display_name":"Marcel H. Schulz","orcid":"https://orcid.org/0000-0002-1252-3656"},"institutions":[{"id":"https://openalex.org/I7877124","display_name":"Charit\u00e9 - Universit\u00e4tsmedizin Berlin","ror":"https://ror.org/001w7jn25","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I7877124"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marcel H. Schulz","raw_affiliation_strings":["Institute fur Medizinische Genetik, Charite Universitatsmedizin Berlin, Augustenburger Platz 1, 13353 Berlin, Germany.marcel.schulz@molgen.mpg.de","Institute fur Medizinische Genetik, Charite Universitatsmedizin Berlin, Augustenburger Platz 1, 13353 Berlin, Germany","International Max Planck Research School for Computational Biology and Scientific Computing, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute fur Medizinische Genetik, Charite Universitatsmedizin Berlin, Augustenburger Platz 1, 13353 Berlin, Germany.marcel.schulz@molgen.mpg.de","institution_ids":["https://openalex.org/I7877124"]},{"raw_affiliation_string":"Institute fur Medizinische Genetik, Charite Universitatsmedizin Berlin, Augustenburger Platz 1, 13353 Berlin, Germany","institution_ids":["https://openalex.org/I7877124"]},{"raw_affiliation_string":"International Max Planck Research School for Computational Biology and Scientific Computing, Berlin, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108107330","display_name":"Sebastian Bauer","orcid":null},"institutions":[{"id":"https://openalex.org/I7877124","display_name":"Charit\u00e9 - Universit\u00e4tsmedizin Berlin","ror":"https://ror.org/001w7jn25","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I7877124"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Bauer","raw_affiliation_strings":["Institute fur Medizinische Genetik, Charite Universitatsmedizin Berlin, Augustenburger Platz 1, 13353 Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute fur Medizinische Genetik, Charite Universitatsmedizin Berlin, Augustenburger Platz 1, 13353 Berlin, Germany","institution_ids":["https://openalex.org/I7877124"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033225381","display_name":"Peter N. Robinson","orcid":"https://orcid.org/0000-0002-0736-9199"},"institutions":[{"id":"https://openalex.org/I7877124","display_name":"Charit\u00e9 - Universit\u00e4tsmedizin Berlin","ror":"https://ror.org/001w7jn25","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I7877124"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter N. Robinson","raw_affiliation_strings":["Institute fur Medizinische Genetik, Charite Universitatsmedizin Berlin, Augustenburger Platz 1, 13353 Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute fur Medizinische Genetik, Charite Universitatsmedizin Berlin, Augustenburger Platz 1, 13353 Berlin, Germany","institution_ids":["https://openalex.org/I7877124"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7877124"],"apc_list":null,"apc_paid":null,"fwci":4.6699,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.94366029,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"4","issue":"1","first_page":"81","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9965000152587891,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9854999780654907,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.940758228302002},{"id":"https://openalex.org/keywords/generalized-suffix-tree","display_name":"Generalized suffix tree","score":0.9345313310623169},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.8704944849014282},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.818189263343811},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5479353666305542},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5472301244735718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5431782603263855},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.5385322570800781},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5126856565475464},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.4698913097381592},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36572831869125366},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3490470051765442},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.33329445123672485},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3301942050457001}],"concepts":[{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.940758228302002},{"id":"https://openalex.org/C118146561","wikidata":"https://www.wikidata.org/wiki/Q5532514","display_name":"Generalized suffix tree","level":4,"score":0.9345313310623169},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.8704944849014282},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.818189263343811},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5479353666305542},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5472301244735718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5431782603263855},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.5385322570800781},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5126856565475464},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.4698913097381592},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36572831869125366},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3490470051765442},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.33329445123672485},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3301942050457001},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid 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":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1504/ijbra.2008.017165","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijbra.2008.017165","pdf_url":null,"source":{"id":"https://openalex.org/S207086575","display_name":"International Journal of Bioinformatics Research and Applications","issn_l":"1744-5485","issn":["1744-5485","1744-5493"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310317825","host_organization_name":"Inderscience Publishers","host_organization_lineage":["https://openalex.org/P4310317825"],"host_organization_lineage_names":["Inderscience Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Bioinformatics Research and Applications","raw_type":"journal-article"},{"id":"pmid:18283030","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18283030","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":"International journal of bioinformatics research and applications","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.184.4400","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.184.4400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dx.doi.org/10.1504/IJBRA.2008.017165","raw_type":"text"},{"id":"pmh:oai:edoc.mpg.de:404862","is_oa":false,"landing_page_url":"http://edoc.mpg.de/404862","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Bioinformatics Research and Applications : Ijbra, v.4, 81-95 (2008)","raw_type":"Article"},{"id":"pmh:oai:pure.mpg.de:item_1584660","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0010-80B3-8","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Bioinformatics Research and Applications : Ijbra","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W117230746","https://openalex.org/W1495956867","https://openalex.org/W1504417041","https://openalex.org/W1969173824","https://openalex.org/W1975136411","https://openalex.org/W1986324942","https://openalex.org/W1990061958","https://openalex.org/W2020816856","https://openalex.org/W2029135821","https://openalex.org/W2030962049","https://openalex.org/W2059513841","https://openalex.org/W2109062349","https://openalex.org/W2121252285","https://openalex.org/W2130564474","https://openalex.org/W2131492087","https://openalex.org/W2134283755","https://openalex.org/W2153527568","https://openalex.org/W2159707167"],"related_works":["https://openalex.org/W2003608043","https://openalex.org/W2405892617","https://openalex.org/W153119118","https://openalex.org/W2583658747","https://openalex.org/W2158874082","https://openalex.org/W1575722140","https://openalex.org/W4293529780","https://openalex.org/W1498395615","https://openalex.org/W2073921136","https://openalex.org/W1965532872"],"abstract_inverted_index":{"Efficient":[0],"searching":[1],"for":[2,27,49,91,112,114],"specific":[3],"subsequences":[4],"in":[5,33,84,106,117],"a":[6,28,50,81],"set":[7],"of":[8,15,30,39,42,52,70,94,96],"longer":[9],"sequences":[10,116,121],"is":[11],"an":[12,57,68],"important":[13],"component":[14],"many":[16],"bioinformatics":[17],"algorithms.":[18,126],"Generalised":[19],"suffix":[20,23,73],"trees":[21],"and":[22,45,109],"arrays":[24],"allow":[25],"searches":[26,90,113],"pattern":[29],"length":[31,41,95],"n":[32,37],"time":[34,86,108],"proportional":[35],"to":[36,98,123],"independent":[38],"the":[40,43,60],"sequences,":[44],"are":[46],"thus":[47],"attractive":[48],"variety":[51],"applications.":[53],"Here,":[54],"we":[55],"present":[56],"algorithm":[58,79],"termed":[59],"generalised":[61],"k-Truncated":[62],"Suffix":[63],"Tree":[64],"(kTST),":[65],"that":[66,87],"represents":[67],"adaption":[69],"Ukkonen's":[71],"linear-time":[72],"tree":[74,83],"construction":[75],"algorithm.":[76],"The":[77,101],"kTST":[78,102],"creates":[80],"k-deep":[82],"linear":[85],"allows":[88],"rapid":[89],"short":[92,115],"patterns":[93],"up":[97],"k":[99],"characters.":[100],"can":[103],"offer":[104],"advantages":[105],"computational":[107],"memory":[110],"usage":[111],"DNA":[118],"or":[119],"protein":[120],"compared":[122],"other":[124],"suffix-based":[125]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
