{"id":"https://openalex.org/W2777416523","doi":"https://doi.org/10.1021/acs.jcim.7b00616","title":"Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition","display_name":"Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition","publication_year":2017,"publication_date":"2017-12-22","ids":{"openalex":"https://openalex.org/W2777416523","doi":"https://doi.org/10.1021/acs.jcim.7b00616","mag":"2777416523","pmid":"https://pubmed.ncbi.nlm.nih.gov/29268609"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.7b00616","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.7b00616","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":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Mol2vec_Unsupervised_Machine_Learning_Approach_with_Chemical_Intuition/5773974","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058097371","display_name":"Sabrina Jaeger-Honz","orcid":"https://orcid.org/0000-0003-1144-7468"},"institutions":[{"id":"https://openalex.org/I4210157022","display_name":"BioMed X Institute","ror":"https://ror.org/05drfac92","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210157022"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sabrina Jaeger","raw_affiliation_strings":["BioMed X Innovation Center, Im Neuenheimer Feld 515, 69120 Heidelberg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1144-7468","affiliations":[{"raw_affiliation_string":"BioMed X Innovation Center, Im Neuenheimer Feld 515, 69120 Heidelberg, Germany","institution_ids":["https://openalex.org/I4210157022"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051191427","display_name":"Simone Fulle","orcid":"https://orcid.org/0000-0002-7646-5889"},"institutions":[{"id":"https://openalex.org/I4210157022","display_name":"BioMed X Institute","ror":"https://ror.org/05drfac92","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210157022"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Simone Fulle","raw_affiliation_strings":["BioMed X Innovation Center, Im Neuenheimer Feld 515, 69120 Heidelberg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7646-5889","affiliations":[{"raw_affiliation_string":"BioMed X Innovation Center, Im Neuenheimer Feld 515, 69120 Heidelberg, Germany","institution_ids":["https://openalex.org/I4210157022"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067176307","display_name":"Samo Turk","orcid":"https://orcid.org/0000-0003-2044-7670"},"institutions":[{"id":"https://openalex.org/I4210157022","display_name":"BioMed X Institute","ror":"https://ror.org/05drfac92","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210157022"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Samo Turk","raw_affiliation_strings":["BioMed X Innovation Center, Im Neuenheimer Feld 515, 69120 Heidelberg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2044-7670","affiliations":[{"raw_affiliation_string":"BioMed X Innovation Center, Im Neuenheimer Feld 515, 69120 Heidelberg, Germany","institution_ids":["https://openalex.org/I4210157022"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051191427","https://openalex.org/A5067176307"],"corresponding_institution_ids":["https://openalex.org/I4210157022"],"apc_list":null,"apc_paid":null,"fwci":27.0401,"has_fulltext":false,"cited_by_count":746,"citation_normalized_percentile":{"value":0.99785114,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"58","issue":"1","first_page":"27","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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":1.0,"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":0.9922999739646912,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9902999997138977,"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/word2vec","display_name":"Word2vec","score":0.8375380039215088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.69298255443573},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6780095100402832},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.6202602386474609},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5670120120048523},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4655269980430603},{"id":"https://openalex.org/keywords/vector-space","display_name":"Vector space","score":0.4531342387199402},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.44550788402557373},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4331347942352295},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4018283188343048},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39634469151496887},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16291946172714233},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.14017066359519958},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.0987524688243866},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09658581018447876}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.8375380039215088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.69298255443573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6780095100402832},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.6202602386474609},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5670120120048523},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4655269980430603},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.4531342387199402},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.44550788402557373},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4331347942352295},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4018283188343048},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39634469151496887},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16291946172714233},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.14017066359519958},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0987524688243866},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09658581018447876},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"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":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","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":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.7b00616","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.7b00616","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:29268609","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29268609","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},{"id":"pmh:oai:figshare.com:article/5773974","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Mol2vec_Unsupervised_Machine_Learning_Approach_with_Chemical_Intuition/5773974","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/5773974","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Mol2vec_Unsupervised_Machine_Learning_Approach_with_Chemical_Intuition/5773974","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W1501531009","https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1975875968","https://openalex.org/W1988037271","https://openalex.org/W2017252311","https://openalex.org/W2024213882","https://openalex.org/W2027482274","https://openalex.org/W2039749139","https://openalex.org/W2046589863","https://openalex.org/W2066273100","https://openalex.org/W2066532920","https://openalex.org/W2076498053","https://openalex.org/W2095705004","https://openalex.org/W2096541451","https://openalex.org/W2101234009","https://openalex.org/W2110990863","https://openalex.org/W2119512897","https://openalex.org/W2129434099","https://openalex.org/W2189911347","https://openalex.org/W2225513621","https://openalex.org/W2247359815","https://openalex.org/W2271840356","https://openalex.org/W2290847742","https://openalex.org/W2295598076","https://openalex.org/W2405035126","https://openalex.org/W2472085920","https://openalex.org/W2556014018","https://openalex.org/W2556131117","https://openalex.org/W2560674852","https://openalex.org/W2591077138","https://openalex.org/W2594183968","https://openalex.org/W2610148085","https://openalex.org/W2620416363","https://openalex.org/W2685808923","https://openalex.org/W2735246657","https://openalex.org/W2735869434","https://openalex.org/W2950577311","https://openalex.org/W2964113829","https://openalex.org/W3100157108","https://openalex.org/W3102476541","https://openalex.org/W4210702584"],"related_works":["https://openalex.org/W2734744645","https://openalex.org/W2187500075","https://openalex.org/W2153189372","https://openalex.org/W2348964713","https://openalex.org/W2366673626","https://openalex.org/W2160451891","https://openalex.org/W2384093694","https://openalex.org/W2096566459","https://openalex.org/W4231949702","https://openalex.org/W2777416523"],"abstract_inverted_index":{"Inspired":[0],"by":[1,65,94],"natural":[2],"language":[3],"processing":[4],"techniques,":[5],"we":[6],"here":[7],"introduce":[8],"Mol2vec,":[9],"which":[10,172],"is":[11,118,187],"an":[12,96],"unsupervised":[13,97],"machine":[14,80,98],"learning":[15,81,99],"approach":[16,100,185],"to":[17,83],"learn":[18],"vector":[19,40,44,90,123],"representations":[20,45,132],"of":[21,30,46,69,105,109,128],"molecular":[22,47],"substructures.":[23,57],"Like":[24],"the":[25,39,67,70,174],"Word2vec":[26,176],"models,":[27],"where":[28],"vectors":[29,64,68],"closely":[31],"related":[32,56],"words":[33],"are":[34,92,142],"in":[35,38,51,182],"close":[36],"proximity":[37],"space,":[41],"Mol2vec":[42,116,165],"learns":[43],"substructures":[48,72],"that":[49,107,186],"point":[50],"similar":[52],"directions":[53],"for":[54,74,157,196],"chemically":[55],"Compounds":[58],"can":[59,166,191],"finally":[60],"be":[61,76,167,193],"encoded":[62],"as":[63,134,160],"summing":[66],"individual":[71],"and,":[73],"instance,":[75],"fed":[77],"into":[78],"supervised":[79],"approaches":[82],"predict":[84],"compound":[85,130,146,163],"properties.":[86],"The":[87,114,139],"underlying":[88],"substructure":[89],"embeddings":[91],"obtained":[93,156],"training":[95],"on":[101,144,178],"a":[102,161,183],"so-called":[103],"corpus":[104],"compounds":[106],"consists":[108],"all":[110],"available":[111],"chemical":[112],"matter.":[113],"resulting":[115,181],"model":[117],"pretrained":[119],"once,":[120],"yields":[121],"dense":[122],"representations,":[124],"and":[125,136,148,152,189],"overcomes":[126],"drawbacks":[127],"common":[129],"feature":[131],"such":[133],"sparseness":[135],"bit":[137],"collisions.":[138],"prediction":[140],"capabilities":[141],"demonstrated":[143],"several":[145],"property":[147],"bioactivity":[149],"data":[150],"sets":[151],"compared":[153],"with":[154,170,198],"results":[155],"Morgan":[158],"fingerprints":[159],"reference":[162],"representation.":[164],"easily":[168,194],"combined":[169],"ProtVec,":[171],"employs":[173],"same":[175],"concept":[177],"protein":[179],"sequences,":[180],"proteochemometric":[184],"alignment-independent":[188],"thus":[190],"also":[192],"used":[195],"proteins":[197],"low":[199],"sequence":[200],"similarities.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":49},{"year":2025,"cited_by_count":124},{"year":2024,"cited_by_count":143},{"year":2023,"cited_by_count":116},{"year":2022,"cited_by_count":110},{"year":2021,"cited_by_count":91},{"year":2020,"cited_by_count":71},{"year":2019,"cited_by_count":31},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2018-01-05T00:00:00"}