{"id":"https://openalex.org/W4402555999","doi":"https://doi.org/10.1021/acs.jcim.4c00863","title":"MolPipeline: A Python Package for Processing Molecules with RDKit in Scikit-learn","display_name":"MolPipeline: A Python Package for Processing Molecules with RDKit in Scikit-learn","publication_year":2024,"publication_date":"2024-09-17","ids":{"openalex":"https://openalex.org/W4402555999","doi":"https://doi.org/10.1021/acs.jcim.4c00863","pmid":"https://pubmed.ncbi.nlm.nih.gov/39288001"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.4c00863","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00863","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/A5055412887","display_name":"Jochen Sieg","orcid":"https://orcid.org/0000-0001-5343-7255"},"institutions":[{"id":"https://openalex.org/I4210107087","display_name":"BASF (Germany)","ror":"https://ror.org/01q8f6705","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210107087"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jochen Sieg","raw_affiliation_strings":["BASF SE, Ludwigshafen, 67056, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5343-7255","affiliations":[{"raw_affiliation_string":"BASF SE, Ludwigshafen, 67056, Germany","institution_ids":["https://openalex.org/I4210107087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035707383","display_name":"Christian Feldmann","orcid":"https://orcid.org/0000-0002-3803-851X"},"institutions":[{"id":"https://openalex.org/I4210107087","display_name":"BASF (Germany)","ror":"https://ror.org/01q8f6705","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210107087"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian W. Feldmann","raw_affiliation_strings":["BASF SE, Ludwigshafen, 67056, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3803-851X","affiliations":[{"raw_affiliation_string":"BASF SE, Ludwigshafen, 67056, Germany","institution_ids":["https://openalex.org/I4210107087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018827857","display_name":"Jennifer Hemmerich","orcid":"https://orcid.org/0000-0003-0372-8956"},"institutions":[{"id":"https://openalex.org/I4210107087","display_name":"BASF (Germany)","ror":"https://ror.org/01q8f6705","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210107087"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jennifer Hemmerich","raw_affiliation_strings":["BASF SE, Ludwigshafen, 67056, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0372-8956","affiliations":[{"raw_affiliation_string":"BASF SE, Ludwigshafen, 67056, Germany","institution_ids":["https://openalex.org/I4210107087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043723616","display_name":"Conrad Stork","orcid":"https://orcid.org/0000-0002-5499-742X"},"institutions":[{"id":"https://openalex.org/I4210107087","display_name":"BASF (Germany)","ror":"https://ror.org/01q8f6705","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210107087"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Conrad Stork","raw_affiliation_strings":["BASF SE, Ludwigshafen, 67056, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5499-742X","affiliations":[{"raw_affiliation_string":"BASF SE, Ludwigshafen, 67056, Germany","institution_ids":["https://openalex.org/I4210107087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056295166","display_name":"Frederik Sandfort","orcid":"https://orcid.org/0009-0009-6941-7860"},"institutions":[{"id":"https://openalex.org/I4210107087","display_name":"BASF (Germany)","ror":"https://ror.org/01q8f6705","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210107087"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frederik Sandfort","raw_affiliation_strings":["BASF SE, Ludwigshafen, 67056, Germany"],"raw_orcid":"https://orcid.org/0009-0009-6941-7860","affiliations":[{"raw_affiliation_string":"BASF SE, Ludwigshafen, 67056, Germany","institution_ids":["https://openalex.org/I4210107087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063130047","display_name":"Philipp Eiden","orcid":"https://orcid.org/0009-0004-8699-8410"},"institutions":[{"id":"https://openalex.org/I4210107087","display_name":"BASF (Germany)","ror":"https://ror.org/01q8f6705","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210107087"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Eiden","raw_affiliation_strings":["BASF SE, Ludwigshafen, 67056, Germany"],"raw_orcid":"https://orcid.org/0009-0004-8699-8410","affiliations":[{"raw_affiliation_string":"BASF SE, Ludwigshafen, 67056, Germany","institution_ids":["https://openalex.org/I4210107087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070920579","display_name":"Miriam Mathea","orcid":"https://orcid.org/0000-0002-3214-1487"},"institutions":[{"id":"https://openalex.org/I4210107087","display_name":"BASF (Germany)","ror":"https://ror.org/01q8f6705","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210107087"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Miriam Mathea","raw_affiliation_strings":["BASF SE, Ludwigshafen, 67056, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3214-1487","affiliations":[{"raw_affiliation_string":"BASF SE, Ludwigshafen, 67056, Germany","institution_ids":["https://openalex.org/I4210107087"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5070920579"],"corresponding_institution_ids":["https://openalex.org/I4210107087"],"apc_list":null,"apc_paid":null,"fwci":13.315,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.9917389,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"64","issue":"24","first_page":"9027","last_page":"9033"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9975000023841858,"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":0.9975000023841858,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.989300012588501,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9707000255584717,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7985996007919312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5127385854721069},{"id":"https://openalex.org/keywords/r-package","display_name":"R package","score":0.46831685304641724},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.27123379707336426}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7985996007919312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5127385854721069},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.46831685304641724},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27123379707336426}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","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}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.4c00863","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00863","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:39288001","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39288001","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2128245586","https://openalex.org/W2406943157","https://openalex.org/W2525356667","https://openalex.org/W2784226073","https://openalex.org/W2966284335","https://openalex.org/W2966357564","https://openalex.org/W3116202926","https://openalex.org/W4293257826","https://openalex.org/W4385210687","https://openalex.org/W4387617009","https://openalex.org/W6912710183","https://openalex.org/W6930159245","https://openalex.org/W6931371219"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W1699080303","https://openalex.org/W4297799326","https://openalex.org/W3116064965","https://openalex.org/W4401016539","https://openalex.org/W4400651710"],"abstract_inverted_index":{"The":[0],"open-source":[1],"package":[2,69],"scikit-learn":[3],"provides":[4,100],"various":[5],"machine":[6,28],"learning":[7,29],"algorithms":[8],"and":[9,50,120],"data":[10,23,80],"processing":[11],"tools,":[12],"including":[13],"the":[14,27,33,101],"Pipeline":[15],"class,":[16],"which":[17,36],"allows":[18],"users":[19],"to":[20,26,40,64,70,78,104,128],"prepend":[21],"custom":[22],"transformation":[24],"steps":[25],"model.":[30],"We":[31,62],"introduce":[32],"MolPipeline":[34,99],"package,":[35],"extends":[37],"this":[38],"concept":[39],"cheminformatics":[41,110],"by":[42],"wrapping":[43],"standard":[44],"RDKit":[45],"functionality,":[46],"such":[47,116],"as":[48,117],"reading":[49],"writing":[51],"SMILES":[52],"strings":[53],"or":[54],"calculating":[55],"molecular":[56,121],"descriptors":[57],"from":[58],"a":[59],"molecule":[60],"object.":[61],"aimed":[63],"build":[65],"an":[66],"easy-to-use":[67],"Python":[68],"create":[71],"completely":[72],"automated":[73],"end-to-end":[74],"pipelines":[75],"that":[76],"scale":[77],"large":[79],"sets.":[81],"Particular":[82],"emphasis":[83],"was":[84],"put":[85],"on":[86],"handling":[87],"erroneous":[88],"instances,":[89],"where":[90],"resolution":[91],"would":[92],"require":[93],"manual":[94],"intervention":[95],"in":[96],"default":[97],"pipelines.":[98],"building":[102,125],"blocks":[103],"enable":[105],"seamless":[106],"integration":[107],"of":[108],"common":[109],"tasks":[111],"within":[112],"scikit-learn's":[113],"pipeline":[114,124],"framework,":[115],"scaffold":[118],"splits":[119],"standardization,":[122],"making":[123],"easily":[126],"adaptable":[127],"diverse":[129],"project":[130],"requirements.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}
