{"id":"https://openalex.org/W3172178673","doi":"https://doi.org/10.1186/s12859-021-04252-y","title":"Predicting biological pathways of chemical compounds with a profile-inspired approach","display_name":"Predicting biological pathways of chemical compounds with a profile-inspired approach","publication_year":2021,"publication_date":"2021-06-12","ids":{"openalex":"https://openalex.org/W3172178673","doi":"https://doi.org/10.1186/s12859-021-04252-y","mag":"3172178673","pmid":"https://pubmed.ncbi.nlm.nih.gov/34118870"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-021-04252-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04252-y","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04252-y","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/track/pdf/10.1186/s12859-021-04252-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044337901","display_name":"Javier L\u00f3pez-Ib\u00e1\u00f1ez","orcid":"https://orcid.org/0000-0003-1623-5245"},"institutions":[{"id":"https://openalex.org/I4210104776","display_name":"Centro Nacional de Biotecnolog\u00eda","ror":"https://ror.org/015w4v032","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210104776"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Lopez-Iba\u00f1ez","raw_affiliation_strings":["Computational Systems Biology Group, National Center for Biotecnology (CNB-CSIC), Darwin 3, 28049, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Systems Biology Group, National Center for Biotecnology (CNB-CSIC), Darwin 3, 28049, Madrid, Spain","institution_ids":["https://openalex.org/I4210104776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062274087","display_name":"Florencio Pazos","orcid":"https://orcid.org/0000-0002-2646-6226"},"institutions":[{"id":"https://openalex.org/I4210104776","display_name":"Centro Nacional de Biotecnolog\u00eda","ror":"https://ror.org/015w4v032","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210104776"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Florencio Pazos","raw_affiliation_strings":["Computational Systems Biology Group, National Center for Biotecnology (CNB-CSIC), Darwin 3, 28049, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Systems Biology Group, National Center for Biotecnology (CNB-CSIC), Darwin 3, 28049, Madrid, Spain","institution_ids":["https://openalex.org/I4210104776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030602787","display_name":"M\u00f3nica Chagoyen","orcid":"https://orcid.org/0000-0001-6911-1591"},"institutions":[{"id":"https://openalex.org/I4210104776","display_name":"Centro Nacional de Biotecnolog\u00eda","ror":"https://ror.org/015w4v032","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210104776"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Monica Chagoyen","raw_affiliation_strings":["Computational Systems Biology Group, National Center for Biotecnology (CNB-CSIC), Darwin 3, 28049, Madrid, Spain. monica.chagoyen@cnb.csic.es","Computational Systems Biology Group, National Center for Biotecnology (CNB-CSIC), Darwin 3, 28049, Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0001-6911-1591","affiliations":[{"raw_affiliation_string":"Computational Systems Biology Group, National Center for Biotecnology (CNB-CSIC), Darwin 3, 28049, Madrid, Spain. monica.chagoyen@cnb.csic.es","institution_ids":["https://openalex.org/I4210104776"]},{"raw_affiliation_string":"Computational Systems Biology Group, National Center for Biotecnology (CNB-CSIC), Darwin 3, 28049, Madrid, Spain","institution_ids":["https://openalex.org/I4210104776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030602787"],"corresponding_institution_ids":["https://openalex.org/I4210104776"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1990,"currency":"EUR","value_usd":2146},"fwci":0.8956,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.72698575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"22","issue":"1","first_page":"320","last_page":"320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.4641999900341034,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.4641999900341034,"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":0.25540000200271606,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.1387999951839447,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.614614725112915},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.5949684381484985},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43483978509902954},{"id":"https://openalex.org/keywords/biological-pathway","display_name":"Biological pathway","score":0.4317624568939209},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3556230068206787},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3521149754524231},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32573625445365906},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.175226092338562},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.0903911292552948},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.08627992868423462}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.614614725112915},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5949684381484985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43483978509902954},{"id":"https://openalex.org/C9927688","wikidata":"https://www.wikidata.org/wiki/Q4915012","display_name":"Biological pathway","level":4,"score":0.4317624568939209},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3556230068206787},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3521149754524231},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32573625445365906},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.175226092338562},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0903911292552948},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.08627992868423462}],"mesh":[{"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":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/s12859-021-04252-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04252-y","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04252-y","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:34118870","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34118870","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:digital.csic.es:10261/243602","is_oa":true,"landing_page_url":"http://hdl.handle.net/10261/243602","pdf_url":null,"source":{"id":"https://openalex.org/S4306400616","display_name":"DIGITAL.CSIC (Spanish National Research Council (CSIC))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I134820265","host_organization_name":"Consejo Superior de Investigaciones Cient\u00edficas","host_organization_lineage":["https://openalex.org/I134820265"],"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":"","raw_type":"art\u00edculo"},{"id":"pmh:oai:doaj.org/article:0302ac36c47b445c87093abad707ed05","is_oa":true,"landing_page_url":"https://doaj.org/article/0302ac36c47b445c87093abad707ed05","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 22, Iss 1, Pp 1-14 (2021)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8199418","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8199418","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/s12859-021-04252-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04252-y","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04252-y","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":[],"awards":[{"id":"https://openalex.org/G151939327","display_name":null,"funder_award_id":"BIO2010-22109","funder_id":"https://openalex.org/F4320338080","funder_display_name":"European Social Fund"},{"id":"https://openalex.org/G5853512768","display_name":null,"funder_award_id":"BIO2010-22109","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G7306655403","display_name":null,"funder_award_id":"BIO2015-72091-EXP","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320326262","display_name":"Ministerio de Asuntos Econ\u00f3micos y Transformaci\u00f3n Digital, Gobierno de Espa\u00f1a","ror":"https://ror.org/03sv46s19"},{"id":"https://openalex.org/F4320338080","display_name":"European Social Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3172178673.pdf","grobid_xml":"https://content.openalex.org/works/W3172178673.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1574109141","https://openalex.org/W1822017433","https://openalex.org/W1935434993","https://openalex.org/W1969051510","https://openalex.org/W1972763168","https://openalex.org/W1979537657","https://openalex.org/W1981885395","https://openalex.org/W1982390234","https://openalex.org/W1989277387","https://openalex.org/W1990810992","https://openalex.org/W2004467618","https://openalex.org/W2035753075","https://openalex.org/W2047583216","https://openalex.org/W2057000344","https://openalex.org/W2058336694","https://openalex.org/W2070789802","https://openalex.org/W2099812585","https://openalex.org/W2102122585","https://openalex.org/W2112692578","https://openalex.org/W2138512826","https://openalex.org/W2162011385","https://openalex.org/W2174759676","https://openalex.org/W2301231318","https://openalex.org/W2559588208","https://openalex.org/W2997158276","https://openalex.org/W3214380909","https://openalex.org/W4233698560","https://openalex.org/W4245668478"],"related_works":["https://openalex.org/W2415545834","https://openalex.org/W2069695727","https://openalex.org/W2150084125","https://openalex.org/W2118505788","https://openalex.org/W2151866902","https://openalex.org/W2066632517","https://openalex.org/W2157193718","https://openalex.org/W1986892844","https://openalex.org/W2046406569","https://openalex.org/W4399552602"],"abstract_inverted_index":{"BACKGROUND:":[0],"Assignment":[1],"of":[2,20,40,57,80,95,109,147],"chemical":[3,18,71,97,111],"compounds":[4],"to":[5,12,48,52,70,104],"biological":[6,87,107],"pathways":[7],"is":[8,134,153],"a":[9,41,74,78,91,110,148,156],"crucial":[10],"step":[11],"understand":[13],"the":[14,17,34,85,106,121],"relationship":[15],"between":[16],"repertory":[19],"an":[21],"organism":[22],"and":[23,37,44,124],"its":[24],"biology.":[25],"Protein":[26],"sequence":[27],"profiles":[28],"are":[29],"very":[30],"successful":[31],"in":[32,84,140],"capturing":[33],"main":[35],"structural":[36],"functional":[38],"features":[39],"protein":[42],"family,":[43],"can":[45,139],"be":[46],"used":[47],"assign":[49],"new":[50],"members":[51],"it":[53],"based":[54,89],"on":[55,90,120],"matching":[56],"their":[58,96],"sequences":[59],"against":[60],"these":[61],"profiles.":[62],"In":[63],"this":[64,68,102],"work,":[65],"we":[66],"extend":[67],"idea":[69],"compounds,":[72],"constructing":[73],"profile-inspired":[75],"model":[76],"for":[77],"set":[79],"related":[81],"metabolites":[82],"(those":[83],"same":[86],"pathway),":[88],"fragment-based":[92],"vectorial":[93],"representation":[94,103],"structures.":[98],"RESULTS:":[99],"We":[100],"use":[101],"predict":[105],"pathway":[108],"compound":[112],"with":[113,136],"good":[114],"overall":[115],"accuracy":[116],"(AUC":[117],"0.74-0.90":[118],"depending":[119],"database":[122],"tested),":[123],"analyzed":[125],"some":[126],"factors":[127],"that":[128],"affect":[129],"performance.":[130],"The":[131,151],"approach,":[132],"which":[133],"compared":[135],"equivalent":[137],"methods,":[138],"addition":[141],"detect":[142],"those":[143],"molecular":[144],"fragments":[145],"characteristic":[146],"pathway.":[149],"CONCLUSIONS:":[150],"method":[152],"available":[154],"as":[155],"graphical":[157],"interactive":[158],"web":[159],"server":[160],"http://csbg.cnb.csic.es/iFragMent":[161],".":[162]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
