{"id":"https://openalex.org/W2010099233","doi":"https://doi.org/10.1021/ci200324e","title":"NAOMI: On the Almost Trivial Task of Reading Molecules from Different File formats","display_name":"NAOMI: On the Almost Trivial Task of Reading Molecules from Different File formats","publication_year":2011,"publication_date":"2011-11-08","ids":{"openalex":"https://openalex.org/W2010099233","doi":"https://doi.org/10.1021/ci200324e","mag":"2010099233","pmid":"https://pubmed.ncbi.nlm.nih.gov/22067015"},"language":"en","primary_location":{"id":"doi:10.1021/ci200324e","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci200324e","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","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/A5075399884","display_name":"Sascha Urbaczek","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sascha Urbaczek","raw_affiliation_strings":["Center for Bioinformatics (ZBH), Bundesstrasse 43, 20146 Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Bioinformatics (ZBH), Bundesstrasse 43, 20146 Hamburg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084039570","display_name":"Adrian Kolodzik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adrian Kolodzik","raw_affiliation_strings":["Center for Bioinformatics (ZBH), Bundesstrasse 43, 20146 Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Bioinformatics (ZBH), Bundesstrasse 43, 20146 Hamburg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108424666","display_name":"J. Fischer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Robert Fischer","raw_affiliation_strings":["Center for Bioinformatics (ZBH), Bundesstrasse 43, 20146 Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Bioinformatics (ZBH), Bundesstrasse 43, 20146 Hamburg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051614433","display_name":"Tobias Lippert","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tobias Lippert","raw_affiliation_strings":["Center for Bioinformatics (ZBH), Bundesstrasse 43, 20146 Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Bioinformatics (ZBH), Bundesstrasse 43, 20146 Hamburg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038236946","display_name":"Stefan Heuser","orcid":"https://orcid.org/0009-0004-1314-887X"},"institutions":[{"id":"https://openalex.org/I106618798","display_name":"Beiersdorf (Germany)","ror":"https://ror.org/04aqg9s78","country_code":"DE","type":"company","lineage":["https://openalex.org/I106618798"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Heuser","raw_affiliation_strings":["Research Active Ingredients, Beiersdorf AG, Troplowitzstrasse 15, 22529 Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Active Ingredients, Beiersdorf AG, Troplowitzstrasse 15, 22529 Hamburg, Germany","institution_ids":["https://openalex.org/I106618798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082901628","display_name":"Inken Groth","orcid":null},"institutions":[{"id":"https://openalex.org/I106618798","display_name":"Beiersdorf (Germany)","ror":"https://ror.org/04aqg9s78","country_code":"DE","type":"company","lineage":["https://openalex.org/I106618798"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Inken Groth","raw_affiliation_strings":["Research Active Ingredients, Beiersdorf AG, Troplowitzstrasse 15, 22529 Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Active Ingredients, Beiersdorf AG, Troplowitzstrasse 15, 22529 Hamburg, Germany","institution_ids":["https://openalex.org/I106618798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059481994","display_name":"Tanja Schulz\u2010Gasch","orcid":null},"institutions":[{"id":"https://openalex.org/I118019719","display_name":"Roche (Switzerland)","ror":"https://ror.org/00by1q217","country_code":"CH","type":"company","lineage":["https://openalex.org/I118019719"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tanja Schulz-Gasch","raw_affiliation_strings":["Pharmaceutical Division, F. Hoffmann-La Roche Ltd., CH-4070 Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pharmaceutical Division, F. Hoffmann-La Roche Ltd., CH-4070 Basel, Switzerland","institution_ids":["https://openalex.org/I118019719"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083205378","display_name":"Matthias Rarey","orcid":"https://orcid.org/0000-0002-9553-6531"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Matthias Rarey","raw_affiliation_strings":["Center for Bioinformatics (ZBH), Bundesstrasse 43, 20146 Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Bioinformatics (ZBH), Bundesstrasse 43, 20146 Hamburg, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5083205378"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8928,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.95409116,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"51","issue":"12","first_page":"3199","last_page":"3207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9868999719619751,"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/cheminformatics","display_name":"Cheminformatics","score":0.9430131912231445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7946879863739014},{"id":"https://openalex.org/keywords/file-format","display_name":"File format","score":0.7284248471260071},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.714674711227417},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6567392945289612},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5705316066741943},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47741687297821045},{"id":"https://openalex.org/keywords/chemical-database","display_name":"Chemical database","score":0.44864752888679504},{"id":"https://openalex.org/keywords/data-file","display_name":"Data file","score":0.44516441226005554},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.44381770491600037},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.4286532998085022},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3887122869491577},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3865578770637512},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.23499950766563416},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.19524160027503967}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.9430131912231445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946879863739014},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.7284248471260071},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.714674711227417},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6567392945289612},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5705316066741943},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47741687297821045},{"id":"https://openalex.org/C203394866","wikidata":"https://www.wikidata.org/wiki/Q2881060","display_name":"Chemical database","level":2,"score":0.44864752888679504},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.44516441226005554},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.44381770491600037},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.4286532998085022},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3887122869491577},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3865578770637512},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.23499950766563416},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.19524160027503967},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","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":"D048088","descriptor_name":"Informatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D048088","descriptor_name":"Informatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D048088","descriptor_name":"Informatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci200324e","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci200324e","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:22067015","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22067015","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":"Journal of chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1636454816","https://openalex.org/W1975147762","https://openalex.org/W1999118725","https://openalex.org/W2010861052","https://openalex.org/W2038702914","https://openalex.org/W2045873232","https://openalex.org/W2049961577","https://openalex.org/W2096360825","https://openalex.org/W2127760066","https://openalex.org/W2148797284"],"related_works":["https://openalex.org/W2317928565","https://openalex.org/W4281772408","https://openalex.org/W2140972311","https://openalex.org/W2902857455","https://openalex.org/W164221359","https://openalex.org/W4212982662","https://openalex.org/W4224246462","https://openalex.org/W4207004502","https://openalex.org/W4207063555","https://openalex.org/W2780675302"],"abstract_inverted_index":{"In":[0],"most":[1],"cheminformatics":[2,161],"workflows,":[3],"chemical":[4,52,87,104,118],"information":[5],"is":[6,25,40,65,139],"stored":[7],"in":[8,131],"files":[9],"which":[10,54,92,120,151],"provide":[11],"the":[12,22,62,86,102,125,132],"necessary":[13],"data":[14,64,69,149],"for":[15,96,124,159],"subsequent":[16],"calculations.":[17],"The":[18],"correct":[19],"interpretation":[20],"of":[21,35,99,128,134],"file":[23,46,88,105,144],"formats":[24,106],"an":[26,42,50],"important":[27],"prerequisite":[28],"to":[29,56,76],"obtain":[30],"meaningful":[31],"results.":[32],"Consistent":[33],"reading":[34],"molecules":[36,100,129],"from":[37,101],"files,":[38],"however,":[39],"not":[41],"easy":[43],"task.":[44],"Each":[45],"format":[47,89],"implicitly":[48],"represents":[49],"underlying":[51],"model,":[53],"has":[55,121],"be":[57,77],"taken":[58],"into":[59],"consideration":[60],"when":[61],"input":[63],"processed.":[66],"Additionally,":[67],"many":[68],"sources":[70],"contain":[71],"invalid":[72],"molecules.":[73],"These":[74,111],"have":[75],"identified":[78],"and":[79,109],"either":[80],"corrected":[81],"or":[82],"discarded.":[83],"We":[84],"present":[85],"converter":[90],"NAOMI,":[91],"provides":[93],"efficient":[94],"procedures":[95,112],"reliable":[97],"handling":[98],"common":[103],"SDF,":[107],"MOL2,":[108],"SMILES.":[110],"are":[113],"based":[114],"on":[115],"a":[116,156],"consistent":[117],"model":[119],"been":[122],"designed":[123],"appropriate":[126],"representation":[127],"relevant":[130],"context":[133],"drug":[135],"discovery.":[136],"NAOMI's":[137],"functionality":[138],"tested":[140],"by":[141],"round":[142],"robin":[143],"IO":[145],"exercises":[146],"with":[147],"public":[148],"sets,":[150],"we":[152],"believe":[153],"should":[154],"become":[155],"standard":[157],"test":[158],"every":[160],"tool.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}