{"id":"https://openalex.org/W4409643576","doi":"https://doi.org/10.1186/s13321-025-01000-9","title":"Prediction of the water solubility by a graph convolutional-based neural network on a highly curated dataset","display_name":"Prediction of the water solubility by a graph convolutional-based neural network on a highly curated dataset","publication_year":2025,"publication_date":"2025-04-21","ids":{"openalex":"https://openalex.org/W4409643576","doi":"https://doi.org/10.1186/s13321-025-01000-9","pmid":"https://pubmed.ncbi.nlm.nih.gov/40259418"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01000-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01000-9","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01000-9","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/s13321-025-01000-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001763010","display_name":"Nadin Ulrich","orcid":"https://orcid.org/0000-0002-1267-0429"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nadin Ulrich","raw_affiliation_strings":["Department of Exposure Science, Helmholtz Centre for Environmental Research-UFZ, Permoserstrasse 15, 04318, Leipzig, Germany. nadin.ulrich@ufz.de","PAULY, Theresienstrasse 50, 04129, Leipzig, Germany. nadin.ulrich@ufz.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Exposure Science, Helmholtz Centre for Environmental Research-UFZ, Permoserstrasse 15, 04318, Leipzig, Germany. nadin.ulrich@ufz.de","institution_ids":[]},{"raw_affiliation_string":"PAULY, Theresienstrasse 50, 04129, Leipzig, Germany. nadin.ulrich@ufz.de","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048527532","display_name":"Karsten Voigt","orcid":"https://orcid.org/0000-0003-4265-2034"},"institutions":[{"id":"https://openalex.org/I4210151088","display_name":"European Alliance Against Depression","ror":"https://ror.org/04w19j463","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210151088"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Karsten Voigt","raw_affiliation_strings":["PAULY, Theresienstrasse 50, 04129, Leipzig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PAULY, Theresienstrasse 50, 04129, Leipzig, Germany","institution_ids":["https://openalex.org/I4210151088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117236448","display_name":"Anton Kudria","orcid":null},"institutions":[{"id":"https://openalex.org/I137479271","display_name":"Helmholtz Centre for Environmental Research","ror":"https://ror.org/000h6jb29","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I137479271"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anton Kudria","raw_affiliation_strings":["Department of Exposure Science, Helmholtz Centre for Environmental Research-UFZ, Permoserstrasse 15, 04318, Leipzig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Exposure Science, Helmholtz Centre for Environmental Research-UFZ, Permoserstrasse 15, 04318, Leipzig, Germany","institution_ids":["https://openalex.org/I137479271"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006451889","display_name":"Alexander B\u00f6hme","orcid":"https://orcid.org/0000-0003-1874-051X"},"institutions":[{"id":"https://openalex.org/I137479271","display_name":"Helmholtz Centre for Environmental Research","ror":"https://ror.org/000h6jb29","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I137479271"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander B\u00f6hme","raw_affiliation_strings":["Department of Exposure Science, Helmholtz Centre for Environmental Research-UFZ, Permoserstrasse 15, 04318, Leipzig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Exposure Science, Helmholtz Centre for Environmental Research-UFZ, Permoserstrasse 15, 04318, Leipzig, Germany","institution_ids":["https://openalex.org/I137479271"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034391215","display_name":"Ralf\u2010Uwe Ebert","orcid":null},"institutions":[{"id":"https://openalex.org/I137479271","display_name":"Helmholtz Centre for Environmental Research","ror":"https://ror.org/000h6jb29","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I137479271"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf-Uwe Ebert","raw_affiliation_strings":["Department of Exposure Science, Helmholtz Centre for Environmental Research-UFZ, Permoserstrasse 15, 04318, Leipzig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Exposure Science, Helmholtz Centre for Environmental Research-UFZ, Permoserstrasse 15, 04318, Leipzig, Germany","institution_ids":["https://openalex.org/I137479271"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001763010"],"corresponding_institution_ids":[],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":6.5474,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96542499,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"17","issue":"1","first_page":"55","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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":0.98089998960495,"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/solubility","display_name":"Solubility","score":0.6937056183815002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6167706251144409},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5676395893096924},{"id":"https://openalex.org/keywords/boiling-point","display_name":"Boiling point","score":0.5530821681022644},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4995083808898926},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49529829621315},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.49339500069618225},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.47541719675064087},{"id":"https://openalex.org/keywords/partition-coefficient","display_name":"Partition coefficient","score":0.4652717113494873},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4651741683483124},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4596386253833771},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43399763107299805},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4108465313911438},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2938944697380066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27873221039772034},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2576764225959778},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15601548552513123},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.11662155389785767},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.10346737504005432},{"id":"https://openalex.org/keywords/organic-chemistry","display_name":"Organic chemistry","score":0.10134527087211609}],"concepts":[{"id":"https://openalex.org/C155574463","wikidata":"https://www.wikidata.org/wiki/Q170731","display_name":"Solubility","level":2,"score":0.6937056183815002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6167706251144409},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5676395893096924},{"id":"https://openalex.org/C188596812","wikidata":"https://www.wikidata.org/wiki/Q1003183","display_name":"Boiling point","level":2,"score":0.5530821681022644},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4995083808898926},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49529829621315},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.49339500069618225},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.47541719675064087},{"id":"https://openalex.org/C192552737","wikidata":"https://www.wikidata.org/wiki/Q898797","display_name":"Partition coefficient","level":2,"score":0.4652717113494873},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4651741683483124},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4596386253833771},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43399763107299805},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4108465313911438},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2938944697380066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27873221039772034},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2576764225959778},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15601548552513123},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11662155389785767},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.10346737504005432},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.10134527087211609},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-025-01000-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01000-9","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01000-9","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:40259418","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40259418","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:doaj.org/article:688088389e5842b4a9e34f69e10d592d","is_oa":true,"landing_page_url":"https://doaj.org/article/688088389e5842b4a9e34f69e10d592d","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 17, Iss 1, Pp 1-13 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12012962","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12012962","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":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-025-01000-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01000-9","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01000-9","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":"Clean water and sanitation","id":"https://metadata.un.org/sdg/6","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409643576.pdf","grobid_xml":"https://content.openalex.org/works/W4409643576.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W109496764","https://openalex.org/W1993965618","https://openalex.org/W1998123416","https://openalex.org/W2002285059","https://openalex.org/W2009307057","https://openalex.org/W2010304681","https://openalex.org/W2013894207","https://openalex.org/W2029558057","https://openalex.org/W2061477847","https://openalex.org/W2061481072","https://openalex.org/W2069506489","https://openalex.org/W2071504476","https://openalex.org/W2073150707","https://openalex.org/W2076498053","https://openalex.org/W2094836090","https://openalex.org/W2115758667","https://openalex.org/W2147781375","https://openalex.org/W2485283686","https://openalex.org/W2559145072","https://openalex.org/W2594183968","https://openalex.org/W2735246657","https://openalex.org/W2901003004","https://openalex.org/W2918678708","https://openalex.org/W2937726486","https://openalex.org/W2958712449","https://openalex.org/W2958810150","https://openalex.org/W2963640965","https://openalex.org/W2963935931","https://openalex.org/W2966797369","https://openalex.org/W3018495986","https://openalex.org/W3032963903","https://openalex.org/W3113282615","https://openalex.org/W3134146005","https://openalex.org/W3167275903","https://openalex.org/W4392918434"],"related_works":["https://openalex.org/W16228418","https://openalex.org/W2005727843","https://openalex.org/W2106731674","https://openalex.org/W4387327236","https://openalex.org/W2183488467","https://openalex.org/W1990237101","https://openalex.org/W4309907966","https://openalex.org/W2028462208","https://openalex.org/W4387896287","https://openalex.org/W2187490799"],"abstract_inverted_index":{"of":[0,5,20,61,100],"0.896,":[1],"and":[2,35],"an":[3,89],"rmse":[4],"0.657":[6],"on":[7,31,46,88],"our":[8,37,95],"independently":[9],"selected":[10],"test":[11,91],"set,":[12,92],"which":[13],"is":[14],"close":[15],"to":[16,22,39,56,98],"the":[17,29,32,58,84,101],"experimental":[18,85],"error":[19],"0.5":[21],"0.6":[23],"log":[24],"units.":[25],"We":[26],"further":[27],"provide":[28],"information":[30],"application":[33,66],"domain":[34],"compare":[36,94],"performance":[38],"other":[40],"existing":[41],"prediction":[42,96,103],"tools.Scientific":[43],"contribution":[44],"Based":[45,87],"a":[47,53,64,75],"highly":[48],"curated":[49],"dataset,":[50],"we":[51,79,93],"developed":[52],"neural":[54],"network":[55],"predict":[57],"water":[59],"solubility":[60],"chemicals":[62],"for":[63],"broad":[65],"domain.":[67],"Data":[68],"curation":[69],"was":[70],"done":[71],"by":[72],"us":[73],"in":[74,83],"step-wise":[76],"procedure,":[77],"where":[78],"identified":[80],"various":[81],"errors":[82],"data.":[86],"independent":[90],"results":[97],"those":[99],"available":[102],"models.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}