{"id":"https://openalex.org/W4377139006","doi":"https://doi.org/10.1186/s13321-023-00716-w","title":"Combatting over-specialization bias in growing chemical databases","display_name":"Combatting over-specialization bias in growing chemical databases","publication_year":2023,"publication_date":"2023-05-19","ids":{"openalex":"https://openalex.org/W4377139006","doi":"https://doi.org/10.1186/s13321-023-00716-w","pmid":"https://pubmed.ncbi.nlm.nih.gov/37208694"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-023-00716-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00716-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00716-w","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"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":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00716-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055291408","display_name":"Katharina Dost","orcid":"https://orcid.org/0000-0002-1514-0685"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Katharina Dost","raw_affiliation_strings":["School of Computer Science, University of Auckland, 38 Princes Street, 1010, Auckland, New Zealand. katharina.dost@auckland.ac.nz","enviPath UG & Co. KG, In den Graswiesen 13, 55437, Ockenheim, Germany. katharina.dost@auckland.ac.nz","School of Computer Science, University of Auckland, 38 Princes Street, 1010, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Auckland, 38 Princes Street, 1010, Auckland, New Zealand. katharina.dost@auckland.ac.nz","institution_ids":[]},{"raw_affiliation_string":"enviPath UG & Co. KG, In den Graswiesen 13, 55437, Ockenheim, Germany. katharina.dost@auckland.ac.nz","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science, University of Auckland, 38 Princes Street, 1010, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074703352","display_name":"Zac Pullar-Strecker","orcid":"https://orcid.org/0000-0002-8819-6129"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Zac Pullar-Strecker","raw_affiliation_strings":["School of Computer Science, University of Auckland, 38 Princes Street, 1010, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Auckland, 38 Princes Street, 1010, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083529271","display_name":"Liam Brydon","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Liam Brydon","raw_affiliation_strings":["School of Computer Science, University of Auckland, 38 Princes Street, 1010, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Auckland, 38 Princes Street, 1010, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053302519","display_name":"Kunyang Zhang","orcid":"https://orcid.org/0009-0008-4588-9487"},"institutions":[{"id":"https://openalex.org/I63664421","display_name":"Swiss Federal Institute of Aquatic Science and Technology","ror":"https://ror.org/00pc48d59","country_code":"CH","type":"facility","lineage":["https://openalex.org/I2799323385","https://openalex.org/I63664421"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Kunyang Zhang","raw_affiliation_strings":["Eawag-Swiss Federal Institute of Aquatic Science and Technology, \u00dcberlandstrasse 133, 8600, D\u00fcbendorf, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eawag-Swiss Federal Institute of Aquatic Science and Technology, \u00dcberlandstrasse 133, 8600, D\u00fcbendorf, Switzerland","institution_ids":["https://openalex.org/I63664421"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032396408","display_name":"Jasmin Hafner","orcid":"https://orcid.org/0000-0002-1474-5869"},"institutions":[{"id":"https://openalex.org/I63664421","display_name":"Swiss Federal Institute of Aquatic Science and Technology","ror":"https://ror.org/00pc48d59","country_code":"CH","type":"facility","lineage":["https://openalex.org/I2799323385","https://openalex.org/I63664421"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jasmin Hafner","raw_affiliation_strings":["Eawag-Swiss Federal Institute of Aquatic Science and Technology, \u00dcberlandstrasse 133, 8600, D\u00fcbendorf, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eawag-Swiss Federal Institute of Aquatic Science and Technology, \u00dcberlandstrasse 133, 8600, D\u00fcbendorf, Switzerland","institution_ids":["https://openalex.org/I63664421"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028387093","display_name":"Patricia Riddle","orcid":"https://orcid.org/0000-0001-8616-0053"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Patricia J. Riddle","raw_affiliation_strings":["School of Computer Science, University of Auckland, 38 Princes Street, 1010, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Auckland, 38 Princes Street, 1010, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079908211","display_name":"J\u00f6rg Wicker","orcid":"https://orcid.org/0000-0003-0533-3368"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"J\u00f6rg S. Wicker","raw_affiliation_strings":["School of Computer Science, University of Auckland, 38 Princes Street, 1010, Auckland, New Zealand","enviPath UG & Co. KG, In den Graswiesen 13, 55437, Ockenheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Auckland, 38 Princes Street, 1010, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"enviPath UG & Co. KG, In den Graswiesen 13, 55437, Ockenheim, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5055291408"],"corresponding_institution_ids":["https://openalex.org/I154130895"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":0.7773,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74906629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"15","issue":"1","first_page":"53","last_page":"53"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.6883000135421753,"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":0.6883000135421753,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.24609999358654022,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13180","display_name":"Chemistry and Chemical Engineering","score":0.02370000071823597,"subfield":{"id":"https://openalex.org/subfields/2304","display_name":"Environmental Chemistry"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7284258008003235},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.6820240616798401},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5940709114074707},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5860747694969177},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5824098587036133},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5742970705032349},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.479995459318161},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44505488872528076},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.4257446527481079},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4209012985229492},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4206163287162781},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41139790415763855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3848879933357239},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.14473429322242737},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.12434419989585876},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09945175051689148}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7284258008003235},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.6820240616798401},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5940709114074707},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5860747694969177},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5824098587036133},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5742970705032349},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.479995459318161},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44505488872528076},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.4257446527481079},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4209012985229492},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4206163287162781},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41139790415763855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3848879933357239},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.14473429322242737},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.12434419989585876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09945175051689148},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13321-023-00716-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00716-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00716-w","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"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":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:37208694","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37208694","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 cheminformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10197453","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10197453","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10197453/pdf/13321_2023_Article_716.pdf","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":"J Cheminform","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:ea1fac4c3e694c90bc74732f0bf436e3","is_oa":true,"landing_page_url":"https://doaj.org/article/ea1fac4c3e694c90bc74732f0bf436e3","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 15, Iss 1, Pp 1-17 (2023)","raw_type":"article"},{"id":"pmh:oai:dora:eawag_31031","is_oa":false,"landing_page_url":"https://www.dora.lib4ri.ch/eawag/islandora/object/eawag%3A31031","pdf_url":null,"source":{"id":"https://openalex.org/S4306400127","display_name":"DORA Eawag (Swiss Federal Institute of Aquatic Science and Technology (Eawag))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63664421","host_organization_name":"Swiss Federal Institute of Aquatic Science and Technology","host_organization_lineage":["https://openalex.org/I63664421"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1186/s13321-023-00716-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00716-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00716-w","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"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":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320801","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4377139006.pdf"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W123476658","https://openalex.org/W1607624180","https://openalex.org/W1853837125","https://openalex.org/W1966026565","https://openalex.org/W1978769691","https://openalex.org/W1991238353","https://openalex.org/W1999954155","https://openalex.org/W2017254234","https://openalex.org/W2031173376","https://openalex.org/W2032536435","https://openalex.org/W2034553680","https://openalex.org/W2082982490","https://openalex.org/W2090299879","https://openalex.org/W2104665533","https://openalex.org/W2112483442","https://openalex.org/W2123649031","https://openalex.org/W2131623463","https://openalex.org/W2147781375","https://openalex.org/W2159887157","https://openalex.org/W2171955717","https://openalex.org/W2174759676","https://openalex.org/W2189911347","https://openalex.org/W2255883267","https://openalex.org/W2276859037","https://openalex.org/W2287058098","https://openalex.org/W2293450022","https://openalex.org/W2332266441","https://openalex.org/W2468778456","https://openalex.org/W2559145072","https://openalex.org/W2591456708","https://openalex.org/W2591883888","https://openalex.org/W2777416523","https://openalex.org/W2785813126","https://openalex.org/W2795265078","https://openalex.org/W2893425640","https://openalex.org/W2901476322","https://openalex.org/W2912328818","https://openalex.org/W2918239264","https://openalex.org/W2925830236","https://openalex.org/W2972597827","https://openalex.org/W3017317785","https://openalex.org/W3039572662","https://openalex.org/W3096437212","https://openalex.org/W3097145107","https://openalex.org/W3097920362","https://openalex.org/W3102400420","https://openalex.org/W3106761016","https://openalex.org/W3112587790","https://openalex.org/W3121097143","https://openalex.org/W3126904456","https://openalex.org/W3127347132","https://openalex.org/W3136198265","https://openalex.org/W3140809986","https://openalex.org/W4206107836","https://openalex.org/W4206723194","https://openalex.org/W4210373151","https://openalex.org/W4210840458","https://openalex.org/W4248330450","https://openalex.org/W4285278690"],"related_works":["https://openalex.org/W2902857455","https://openalex.org/W4212982662","https://openalex.org/W2161782568","https://openalex.org/W4254684673","https://openalex.org/W4226062292","https://openalex.org/W4281772408","https://openalex.org/W2023175890","https://openalex.org/W1501776718","https://openalex.org/W623607250","https://openalex.org/W4245429118"],"abstract_inverted_index":{"BACKGROUND:":[0],"Predicting":[1],"in":[2,101,142,148,170,181,280,300],"advance":[3],"the":[4,12,20,23,48,83,91,102,110,130,140,143,149,161,167,182,190,214,224,243,254,267,298],"behavior":[5],"of":[6,15,50,78,94,109,139,178,200,211,216,269],"new":[7,16],"chemical":[8],"compounds":[9,65,141],"can":[10,34,59,227,277],"support":[11,278],"design":[13],"process":[14,283],"products":[17],"by":[18],"directing":[19],"research":[21,205],"toward":[22],"most":[24],"promising":[25],"candidates":[26],"and":[27,45,85,104,154,175,194,291],"ruling":[28],"out":[29],"others.":[30],"Such":[31],"predictive":[32,80],"models":[33,56,81,97],"be":[35,229],"data-driven":[36],"using":[37],"Machine":[38],"Learning":[39],"or":[40],"based":[41],"on":[42,47,98,213],"researchers'":[43],"experience":[44],"depend":[46],"collection":[49],"past":[51],"results.":[52,237],"In":[53,114],"either":[54],"case:":[55],"(or":[57],"researchers)":[58],"only":[60,221,251,286],"make":[61],"reliable":[62],"assumptions":[63],"about":[64],"that":[66,126,151,158,223,233,241,275],"are":[67],"similar":[68],"to":[69,128,188,202,284,296],"what":[70],"they":[71],"have":[72],"seen":[73],"before.":[74],"Therefore,":[75],"consequent":[76],"usage":[77],"these":[79],"shapes":[82],"dataset":[84,100,131,168,299],"causes":[86],"a":[87,124,136,197,203,262,301],"continuous":[88,255],"specialization":[89,132,201,256],"shrinking":[90],"applicability":[92],"domain":[93],"all":[95],"trained":[96],"this":[99,115],"future,":[103],"increasingly":[105],"harming":[106],"model-based":[107],"exploration":[108],"space.":[111],"PROPOSED":[112],"SOLUTION:":[113],"paper,":[116],"we":[117,145,164,239,273],"propose":[118],"CANCELS":[119,184,234,276],"(CounterActiNg":[120],"Compound":[121],"spEciaLization":[122],"biaS),":[123],"technique":[125],"helps":[127],"break":[129],"spiral.":[133],"Aiming":[134],"for":[135],"smooth":[137],"distribution":[138],"dataset,":[144],"identify":[146],"areas":[147],"space":[150,193],"fall":[152],"short":[153],"suggest":[155],"additional":[156],"experiments":[157,212],"help":[159],"bridge":[160],"gap.":[162],"Thereby,":[163],"generally":[165],"improve":[166],"quality":[169],"an":[171],"entirely":[172],"unsupervised":[173],"manner":[174],"create":[176],"awareness":[177],"potential":[179,292],"flaws":[180],"data.":[183],"does":[185],"not":[186,220,285],"aim":[187],"cover":[189],"entire":[191],"compound":[192],"hence":[195],"retains":[196],"desirable":[198],"degree":[199],"specified":[204],"domain.":[206],"RESULTS:":[207],"An":[208],"extensive":[209],"set":[210],"use-case":[215],"biodegradation":[217],"pathway":[218],"prediction":[219],"reveals":[222],"bias":[225,245],"spiral":[226],"indeed":[228],"observed":[230,244],"but":[231,258,294],"also":[232,259,295],"produces":[235],"meaningful":[236],"Additionally,":[238],"demonstrate":[240],"mitigating":[242],"is":[246,306],"crucial":[247],"as":[248],"it":[249],"cannot":[250],"intervene":[252],"with":[253],"process,":[257],"significantly":[260],"improves":[261],"predictor's":[263],"performance":[264],"while":[265],"reducing":[266],"number":[268],"required":[270],"experiments.":[271],"Overall,":[272],"believe":[274],"researchers":[279],"their":[281,289],"experimentation":[282],"better":[287],"understand":[288],"data":[290],"flaws,":[293],"grow":[297],"sustainable":[302],"way.":[303],"All":[304],"code":[305],"available":[307],"under":[308],"github.com/KatDost/Cancels":[309],".":[310]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}