{"id":"https://openalex.org/W2155270700","doi":"https://doi.org/10.1093/bib/bbp044","title":"Knowledge-based data analysis comes of age","display_name":"Knowledge-based data analysis comes of age","publication_year":2009,"publication_date":"2009-10-23","ids":{"openalex":"https://openalex.org/W2155270700","doi":"https://doi.org/10.1093/bib/bbp044","mag":"2155270700","pmid":"https://pubmed.ncbi.nlm.nih.gov/19854753"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbp044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbp044","pdf_url":"https://academic.oup.com/bib/article-pdf/11/1/30/482756/bbp044.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bib/article-pdf/11/1/30/482756/bbp044.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014591184","display_name":"Michael F. Ochs","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M. F. Ochs","raw_affiliation_strings":["Division of Oncology Biostatistics and Bioinformatics, 550 North Broadway, Suite 1103, Johns Hopkins University, Baltimore, MD 21205, USA. mfo@jhu.edu","Associate Professor of Oncology, Division of Oncology Biostatistics and Bioinformatics, 550 North Broadway, Suite 1103, Johns Hopkins University, Baltimore, MD 21205, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Oncology Biostatistics and Bioinformatics, 550 North Broadway, Suite 1103, Johns Hopkins University, Baltimore, MD 21205, USA. mfo@jhu.edu","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]},{"raw_affiliation_string":"Associate Professor of Oncology, Division of Oncology Biostatistics and Bioinformatics, 550 North Broadway, Suite 1103, Johns Hopkins University, Baltimore, MD 21205, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014591184"],"corresponding_institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":{"value":4011,"currency":"USD","value_usd":4011},"fwci":1.3849,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.80560787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"11","issue":"1","first_page":"30","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9991000294685364,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9991000294685364,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9988999962806702,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9936000108718872,"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/overfitting","display_name":"Overfitting","score":0.7953566908836365},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.739363968372345},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6478145122528076},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.5993951559066772},{"id":"https://openalex.org/keywords/statistical-inference","display_name":"Statistical inference","score":0.5361362099647522},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5031420588493347},{"id":"https://openalex.org/keywords/systems-biology","display_name":"Systems biology","score":0.4456402659416199},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4428699016571045},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4343108832836151},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.4146050810813904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40225154161453247},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.391250342130661},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3893379271030426},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.26247191429138184},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.19848501682281494},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.17469805479049683},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16723832488059998},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1381383240222931}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7953566908836365},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.739363968372345},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6478145122528076},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.5993951559066772},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.5361362099647522},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5031420588493347},{"id":"https://openalex.org/C152662350","wikidata":"https://www.wikidata.org/wiki/Q815297","display_name":"Systems biology","level":2,"score":0.4456402659416199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4428699016571045},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4343108832836151},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.4146050810813904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40225154161453247},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.391250342130661},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3893379271030426},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.26247191429138184},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.19848501682281494},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.17469805479049683},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16723832488059998},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1381383240222931},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040641","descriptor_name":"Quantitative Trait Loci","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040641","descriptor_name":"Quantitative Trait Loci","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040641","descriptor_name":"Quantitative Trait Loci","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040641","descriptor_name":"Quantitative Trait Loci","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D049490","descriptor_name":"Systems Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049490","descriptor_name":"Systems Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049490","descriptor_name":"Systems Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049490","descriptor_name":"Systems Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055106","descriptor_name":"Genome-Wide Association Study","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055106","descriptor_name":"Genome-Wide Association Study","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055106","descriptor_name":"Genome-Wide Association Study","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055106","descriptor_name":"Genome-Wide Association Study","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbp044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbp044","pdf_url":"https://academic.oup.com/bib/article-pdf/11/1/30/482756/bbp044.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:19854753","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19854753","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":"Briefings in bioinformatics","raw_type":null},{"id":"pmh:oai:europepmc.org:2697173","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3700349","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bib/bbp044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbp044","pdf_url":"https://academic.oup.com/bib/article-pdf/11/1/30/482756/bbp044.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8582673968","display_name":null,"funder_award_id":"P30 CA006973","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"}],"funders":[{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2155270700.pdf","grobid_xml":"https://content.openalex.org/works/W2155270700.grobid-xml"},"referenced_works_count":74,"referenced_works":["https://openalex.org/W1516237374","https://openalex.org/W1521396122","https://openalex.org/W1614353361","https://openalex.org/W1768527575","https://openalex.org/W1902027874","https://openalex.org/W1963600204","https://openalex.org/W1964542367","https://openalex.org/W1964964549","https://openalex.org/W1970156673","https://openalex.org/W1970263201","https://openalex.org/W1976843725","https://openalex.org/W2000054602","https://openalex.org/W2007771322","https://openalex.org/W2017594520","https://openalex.org/W2022359874","https://openalex.org/W2025183726","https://openalex.org/W2029426756","https://openalex.org/W2036099373","https://openalex.org/W2038538527","https://openalex.org/W2040827479","https://openalex.org/W2041467022","https://openalex.org/W2050171305","https://openalex.org/W2053609837","https://openalex.org/W2055043387","https://openalex.org/W2058060770","https://openalex.org/W2064690543","https://openalex.org/W2070678426","https://openalex.org/W2072572998","https://openalex.org/W2077542647","https://openalex.org/W2083320231","https://openalex.org/W2090184738","https://openalex.org/W2092423825","https://openalex.org/W2093889847","https://openalex.org/W2095718954","https://openalex.org/W2098039318","https://openalex.org/W2103431543","https://openalex.org/W2108022229","https://openalex.org/W2108274758","https://openalex.org/W2111510713","https://openalex.org/W2116383839","https://openalex.org/W2118737745","https://openalex.org/W2121604817","https://openalex.org/W2121940247","https://openalex.org/W2122815743","https://openalex.org/W2122863289","https://openalex.org/W2123775239","https://openalex.org/W2126602684","https://openalex.org/W2128058093","https://openalex.org/W2129332325","https://openalex.org/W2130494035","https://openalex.org/W2131660156","https://openalex.org/W2135030836","https://openalex.org/W2136787567","https://openalex.org/W2140937045","https://openalex.org/W2146264532","https://openalex.org/W2147426864","https://openalex.org/W2150077252","https://openalex.org/W2150671144","https://openalex.org/W2150926065","https://openalex.org/W2153507021","https://openalex.org/W2153508883","https://openalex.org/W2154947819","https://openalex.org/W2155680682","https://openalex.org/W2164727176","https://openalex.org/W2168715739","https://openalex.org/W2170470863","https://openalex.org/W2316677206","https://openalex.org/W2411921399","https://openalex.org/W2555756618","https://openalex.org/W2611370172","https://openalex.org/W3083113686","https://openalex.org/W4230900352","https://openalex.org/W4236236547","https://openalex.org/W4247420482"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W3009056573","https://openalex.org/W2036180122","https://openalex.org/W2202323525","https://openalex.org/W344920071","https://openalex.org/W2915863966","https://openalex.org/W78967844","https://openalex.org/W4389305771","https://openalex.org/W3202802607"],"abstract_inverted_index":{"The":[0],"emergence":[1,119,144],"of":[2,79,84,120,131,145],"high-throughput":[3],"technologies":[4],"for":[5,12,19],"measuring":[6],"biological":[7,31,150,156],"systems":[8],"has":[9],"introduced":[10],"problems":[11],"data":[13,133],"interpretation":[14],"that":[15,122,154],"must":[16,68],"be":[17,27],"addressed":[18],"proper":[20],"inference.":[21],"First,":[22],"analysis":[23,66,146],"techniques":[24,49,102,121],"need":[25],"to":[26,29,111,126,137],"matched":[28],"the":[30,38,54,63,70,82,92,113,118,127,129,142],"system,":[32],"reflecting":[33],"in":[34,73],"their":[35],"mathematical":[36,48,124],"structure":[37,125],"underlying":[39],"behavior":[40],"being":[41],"studied.":[42],"When":[43],"this":[44],"is":[45],"not":[46,60],"done,":[47],"will":[50],"generate":[51],"answers,":[52],"but":[53],"values":[55],"and":[56,105,134,141],"reliability":[57],"estimates":[58],"may":[59],"accurately":[61],"reflect":[62],"biology.":[64],"Second,":[65],"approaches":[67,147],"address":[69],"vast":[71],"excess":[72],"variables":[74],"measured":[75],"(e.g.":[76,86],"transcript":[77],"levels":[78],"genes)":[80],"over":[81],"number":[83],"samples":[85],"tumors,":[87],"time":[88],"points),":[89],"known":[90],"as":[91],"'large-p,":[93],"small-n'":[94],"problem.":[95],"In":[96],"large-p,":[97],"small-n":[98],"paradigms,":[99],"standard":[100],"statistical":[101,139],"generally":[103],"fail,":[104],"computational":[106],"learning":[107],"algorithms":[108],"are":[109],"prone":[110],"overfit":[112],"data.":[114],"Here":[115],"we":[116],"review":[117],"match":[123],"biology,":[128],"use":[130],"integrated":[132],"prior":[135],"knowledge":[136],"guide":[138],"analysis,":[140],"recent":[143],"utilizing":[148],"simple":[149],"models.":[151],"We":[152],"show":[153],"novel":[155],"insights":[157],"have":[158],"been":[159],"gained":[160],"using":[161],"these":[162],"techniques.":[163]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
