{"id":"https://openalex.org/W2171826528","doi":"https://doi.org/10.1109/csb.2003.1227304","title":"Fast and sensitive probe selection for DNA chips using jumps in matching statistics","display_name":"Fast and sensitive probe selection for DNA chips using jumps in matching statistics","publication_year":2004,"publication_date":"2004-03-23","ids":{"openalex":"https://openalex.org/W2171826528","doi":"https://doi.org/10.1109/csb.2003.1227304","mag":"2171826528","pmid":"https://pubmed.ncbi.nlm.nih.gov/16452779"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2003.1227304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-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/A5059606670","display_name":"Sven Rahmann","orcid":"https://orcid.org/0000-0002-8536-6065"},"institutions":[{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]},{"id":"https://openalex.org/I4210142260","display_name":"Max Planck Institute for Molecular Genetics","ror":"https://ror.org/03ate3e03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210142260"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"S. Rahmann","raw_affiliation_strings":["Department of Computational Molecular Biology, Max-Planck Institute of Molecular Genetics, Berlin, Germany","Department of Mathematics and Computer Science, Freie Universit\u00e4t Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computational Molecular Biology, Max-Planck Institute of Molecular Genetics, Berlin, Germany","institution_ids":["https://openalex.org/I4210142260"]},{"raw_affiliation_string":"Department of Mathematics and Computer Science, Freie Universit\u00e4t Berlin, Germany","institution_ids":["https://openalex.org/I75951250"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5059606670"],"corresponding_institution_ids":["https://openalex.org/I4210142260","https://openalex.org/I75951250"],"apc_list":null,"apc_paid":null,"fwci":8.3183,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.97482506,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2452","issue":null,"first_page":"57","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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":0.9994999766349792,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9993000030517578,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9925000071525574,"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/substring","display_name":"Substring","score":0.713740348815918},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.608418881893158},{"id":"https://openalex.org/keywords/bernoullis-principle","display_name":"Bernoulli's principle","score":0.5885618925094604},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5732694864273071},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5258241891860962},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5215582847595215},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.512479305267334},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.47371405363082886},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45249316096305847},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.42938217520713806},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3706844449043274},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.3442417085170746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29383212327957153},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.28905507922172546},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12785089015960693},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.09451237320899963}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.713740348815918},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.608418881893158},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.5885618925094604},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5732694864273071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5258241891860962},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5215582847595215},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.512479305267334},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.47371405363082886},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45249316096305847},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.42938217520713806},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3706844449043274},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.3442417085170746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29383212327957153},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28905507922172546},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12785089015960693},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.09451237320899963},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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":"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":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004867","descriptor_name":"Equipment Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004867","descriptor_name":"Equipment Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004867","descriptor_name":"Equipment Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015342","descriptor_name":"DNA Probes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015342","descriptor_name":"DNA Probes","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015342","descriptor_name":"DNA Probes","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D019544","descriptor_name":"Equipment Failure Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019544","descriptor_name":"Equipment Failure Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019544","descriptor_name":"Equipment Failure Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000295","qualifier_name":"instrumentation","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000295","qualifier_name":"instrumentation","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000295","qualifier_name":"instrumentation","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1109/csb.2003.1227304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-article"},{"id":"pmid:16452779","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16452779","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":"Proceedings. IEEE Computer Society Bioinformatics Conference","raw_type":null},{"id":"pmh:oai:edoc.mpg.de:176130","is_oa":false,"landing_page_url":"http://edoc.mpg.de/176130","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":"PROCEEDINGS OF THE 2nd IEEE COMPUTER SOCIETY BIOINFORMATICS CONFERENCE (CSB '03), IEEE, 57-64 (2003)","raw_type":"Conference-Paper"},{"id":"pmh:oai:pure.mpg.de:item_1586258","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0010-8B30-9","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":"PROCEEDINGS OF THE 2nd IEEE COMPUTER SOCIETY BIOINFORMATICS CONFERENCE (CSB '03)","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W938539187","https://openalex.org/W1543263356","https://openalex.org/W1600463518","https://openalex.org/W1990061958","https://openalex.org/W2055417893","https://openalex.org/W2096990720","https://openalex.org/W2118086882","https://openalex.org/W2118782342","https://openalex.org/W2135995702","https://openalex.org/W2142599475","https://openalex.org/W2164938926","https://openalex.org/W2250706290","https://openalex.org/W2533248932","https://openalex.org/W2610179052","https://openalex.org/W4230300507"],"related_works":["https://openalex.org/W2051304374","https://openalex.org/W4286787697","https://openalex.org/W2902482624","https://openalex.org/W4230921427","https://openalex.org/W2902555313","https://openalex.org/W2376315482","https://openalex.org/W4249054680","https://openalex.org/W3112977702","https://openalex.org/W2218650848","https://openalex.org/W2366227422"],"abstract_inverted_index":{"The":[0,60,120],"design":[1],"of":[2,29,34,51,57,69,85,105,109,131,141,147],"large":[3,23],"scale":[4,24],"DNA":[5],"microarrays":[6],"is":[7,63],"a":[8,27,91,97,128,159],"challenging":[9],"problem.":[10],"So":[11],"far,":[12],"probe":[13,35,154],"selection":[14,155,173],"algorithms":[15],"must":[16],"trade":[17],"the":[18,32,49,67,83,103,106,110,134,139,145,148,172],"ability":[19],"to":[20,101,124,143,161],"cope":[21],"with":[22,127],"problems":[25],"for":[26,87,153],"loss":[28],"accuracy":[30,146],"in":[31,44,71,90,118],"estimation":[33],"quality.":[36],"We":[37,65,81],"present":[38,96],"an":[39,162],"approach":[40,152],"based":[41],"on":[42],"jumps":[43,70,86,142],"matching":[45,72],"statistics":[46,73],"that":[47,113],"combines":[48],"best":[50],"both":[52],"worlds.":[53],"This":[54],"article":[55],"consists":[56],"two":[58,75,114],"parts.":[59],"first":[61],"part":[62],"theoretical.":[64],"introduce":[66],"notion":[68],"between":[74],"strings":[76,89,116],"and":[77,95],"derive":[78],"their":[79],"properties.":[80],"estimate":[82],"frequency":[84],"random":[88,115],"non-uniform":[92],"Bernoulli":[93],"model":[94],"new":[98],"heuristic":[99],"argument":[100],"find":[102],"center":[104],"length":[107],"distribution":[108],"longest":[111,149],"substring":[112],"have":[117],"common.":[119],"results":[121],"are":[122],"generalized":[123],"near-perfect":[125],"matches":[126],"small":[129],"number":[130],"mismatches.":[132],"In":[133],"second":[135],"part,":[136],"we":[137],"use":[138],"concept":[140],"improve":[144],"common":[150],"factor":[151],"by":[156],"moving":[157],"from":[158],"string-based":[160],"energy-based":[163],"specificity":[164],"measure,":[165],"while":[166],"only":[167],"slightly":[168],"more":[169],"than":[170],"doubling":[171],"time.":[174]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}