{"id":"https://openalex.org/W4388855368","doi":"https://doi.org/10.1186/s13321-023-00781-1","title":"On the difficulty of validating molecular generative models realistically: a case study on public and proprietary data","display_name":"On the difficulty of validating molecular generative models realistically: a case study on public and proprietary data","publication_year":2023,"publication_date":"2023-11-21","ids":{"openalex":"https://openalex.org/W4388855368","doi":"https://doi.org/10.1186/s13321-023-00781-1","pmid":"https://pubmed.ncbi.nlm.nih.gov/37990215"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-023-00781-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00781-1","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00781-1","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/s13321-023-00781-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045140841","display_name":"Koichi Handa","orcid":"https://orcid.org/0000-0003-2748-9742"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I90469020","display_name":"Teijin (Japan)","ror":"https://ror.org/038kxkq33","country_code":"JP","type":"company","lineage":["https://openalex.org/I90469020"]}],"countries":["GB","JP"],"is_corresponding":true,"raw_author_name":"Koichi Handa","raw_affiliation_strings":["Centre for Molecular Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK. ko.handa@teijin.co.jp","Toxicology & DMPK Research Department, Teijin Institute for Bio-Medical Research, Teijin Pharma Limited, 4-3-2 Asahigaoka, Hino-Shi, Tokyo, 191-8512, Japan. ko.handa@teijin.co.jp","Centre for Molecular Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Molecular Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK. ko.handa@teijin.co.jp","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Toxicology & DMPK Research Department, Teijin Institute for Bio-Medical Research, Teijin Pharma Limited, 4-3-2 Asahigaoka, Hino-Shi, Tokyo, 191-8512, Japan. ko.handa@teijin.co.jp","institution_ids":["https://openalex.org/I90469020"]},{"raw_affiliation_string":"Centre for Molecular Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064256420","display_name":"Morgan Thomas","orcid":"https://orcid.org/0000-0002-1610-3499"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Morgan C. Thomas","raw_affiliation_strings":["Centre for Molecular Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Molecular Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027609089","display_name":"Michiharu Kageyama","orcid":"https://orcid.org/0000-0001-7449-593X"},"institutions":[{"id":"https://openalex.org/I90469020","display_name":"Teijin (Japan)","ror":"https://ror.org/038kxkq33","country_code":"JP","type":"company","lineage":["https://openalex.org/I90469020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Michiharu Kageyama","raw_affiliation_strings":["Toxicology & DMPK Research Department, Teijin Institute for Bio-Medical Research, Teijin Pharma Limited, 4-3-2 Asahigaoka, Hino-Shi, Tokyo, 191-8512, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toxicology & DMPK Research Department, Teijin Institute for Bio-Medical Research, Teijin Pharma Limited, 4-3-2 Asahigaoka, Hino-Shi, Tokyo, 191-8512, Japan","institution_ids":["https://openalex.org/I90469020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109282158","display_name":"Takeshi Iijima","orcid":"https://orcid.org/0009-0000-0305-9401"},"institutions":[{"id":"https://openalex.org/I90469020","display_name":"Teijin (Japan)","ror":"https://ror.org/038kxkq33","country_code":"JP","type":"company","lineage":["https://openalex.org/I90469020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Iijima","raw_affiliation_strings":["Toxicology & DMPK Research Department, Teijin Institute for Bio-Medical Research, Teijin Pharma Limited, 4-3-2 Asahigaoka, Hino-Shi, Tokyo, 191-8512, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toxicology & DMPK Research Department, Teijin Institute for Bio-Medical Research, Teijin Pharma Limited, 4-3-2 Asahigaoka, Hino-Shi, Tokyo, 191-8512, Japan","institution_ids":["https://openalex.org/I90469020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026643759","display_name":"Andreas Bender","orcid":"https://orcid.org/0000-0002-6683-7546"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andreas Bender","raw_affiliation_strings":["Centre for Molecular Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK. ab454@cam.ac.uk","Centre for Molecular Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Molecular Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK. ab454@cam.ac.uk","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Centre for Molecular Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5045140841"],"corresponding_institution_ids":["https://openalex.org/I241749","https://openalex.org/I90469020"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":3.2983,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.93569143,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"15","issue":"1","first_page":"112","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9934999942779541,"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":0.9018999934196472,"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/computer-science","display_name":"Computer science","score":0.6727467179298401},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6334824562072754},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5963979959487915},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4696079194545746},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.4650733470916748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46354812383651733},{"id":"https://openalex.org/keywords/converse","display_name":"Converse","score":0.46173322200775146},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4608113467693329},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4346996247768402},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35948142409324646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14799970388412476},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09039980173110962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6727467179298401},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6334824562072754},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5963979959487915},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4696079194545746},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.4650733470916748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46354812383651733},{"id":"https://openalex.org/C2776809875","wikidata":"https://www.wikidata.org/wiki/Q1375963","display_name":"Converse","level":2,"score":0.46173322200775146},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4608113467693329},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4346996247768402},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35948142409324646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14799970388412476},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09039980173110962},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-023-00781-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00781-1","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00781-1","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:37990215","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37990215","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:10664602","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10664602","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10664602/pdf/13321_2023_Article_781.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:a1962702708c4ae49fdd8709d48991b3","is_oa":true,"landing_page_url":"https://doaj.org/article/a1962702708c4ae49fdd8709d48991b3","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"}],"best_oa_location":{"id":"doi:10.1186/s13321-023-00781-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00781-1","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00781-1","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":[{"id":"https://metadata.un.org/sdg/17","score":0.4699999988079071,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326474","display_name":"Teijin Pharma","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4388855368.pdf"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1562424368","https://openalex.org/W1592238003","https://openalex.org/W1971849220","https://openalex.org/W1974502630","https://openalex.org/W1988037271","https://openalex.org/W1994637284","https://openalex.org/W2019678805","https://openalex.org/W2043000057","https://openalex.org/W2064675550","https://openalex.org/W2096525273","https://openalex.org/W2112912103","https://openalex.org/W2130629641","https://openalex.org/W2267520918","https://openalex.org/W2290847742","https://openalex.org/W2327079070","https://openalex.org/W2529996553","https://openalex.org/W2558999090","https://openalex.org/W2578240541","https://openalex.org/W2593632281","https://openalex.org/W2610148085","https://openalex.org/W2773987374","https://openalex.org/W2800873928","https://openalex.org/W2805002767","https://openalex.org/W2887447356","https://openalex.org/W2900694120","https://openalex.org/W2901951655","https://openalex.org/W2911964244","https://openalex.org/W2937307539","https://openalex.org/W2949986955","https://openalex.org/W2953128081","https://openalex.org/W3007300673","https://openalex.org/W3008071995","https://openalex.org/W3094686696","https://openalex.org/W3098269892","https://openalex.org/W3100157108","https://openalex.org/W3100358278","https://openalex.org/W3100751385","https://openalex.org/W3103098434","https://openalex.org/W3116865743","https://openalex.org/W3125539506","https://openalex.org/W3133989558","https://openalex.org/W3165571652","https://openalex.org/W3170120958","https://openalex.org/W3187501257","https://openalex.org/W3209416355","https://openalex.org/W3210833421","https://openalex.org/W3212543990","https://openalex.org/W4220802400","https://openalex.org/W4240082606","https://openalex.org/W4247001379","https://openalex.org/W4291288469","https://openalex.org/W4293257826","https://openalex.org/W4300861533","https://openalex.org/W4304203195","https://openalex.org/W4308683713","https://openalex.org/W4381053688","https://openalex.org/W4385688843","https://openalex.org/W6600808470","https://openalex.org/W6604896550"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W2280377497","https://openalex.org/W3174044702","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4283803360","https://openalex.org/W4317695495","https://openalex.org/W4387506531"],"abstract_inverted_index":{"While":[0],"a":[1,82,108,138,262,298],"multitude":[2],"of":[3,38,107,158,172,290,294],"deep":[4],"generative":[5,83,142,238,295],"models":[6,296],"have":[7,302],"recently":[8],"emerged":[9],"there":[10],"exists":[11],"no":[12],"best":[13],"practice":[14],"for":[15,218],"their":[16,313],"practically":[17],"relevant":[18],"validation.":[19],"On":[20],"the":[21,44,56,69,78,104,118,146,173,187,221,237,251,274,292],"one":[22],"hand,":[23],"novel":[24],"de":[25,93,266],"novo-generated":[26],"molecules":[27],"cannot":[28],"be":[29],"refuted":[30],"by":[31,55,76],"retrospective":[32,66],"validation":[33,39,48,67],"(so":[34],"that":[35,102,156,236],"this":[36,61,96],"type":[37],"is":[40,49],"biased);":[41],"but":[42],"on":[43,86,151,273],"other":[45],"hand":[46],"prospective":[47],"expensive":[50],"and":[51,129,134,148,170,177,192,203,258,308],"then":[52],"often":[53],"biased":[54],"human":[57,73],"selection":[58],"process.":[59,264],"In":[60],"case":[62],"study,":[63,276],"we":[64,98,154],"frame":[65],"as":[68,137,261],"ability":[70],"to":[71,123,281,312],"mimic":[72],"drug":[74,247,259],"design,":[75],"answering":[77],"following":[79,111],"question:":[80],"Can":[81],"model":[84,239],"trained":[85],"early-stage":[87,152],"project":[88,132],"compounds":[89,92,160,205,213,244],"generate":[90],"middle/late-stage":[91,159,204,243],"novo?":[94],"To":[95],"end,":[97],"used":[99,135],"experimental":[100],"data":[101],"contains":[103],"elapsed":[105],"time":[106,119],"synthetic":[109,127],"expansion":[110],"hit":[112],"identification":[113],"from":[114,245],"five":[115],"public":[116,165,207],"(where":[117,186],"series":[120],"was":[121,161,209,223],"pre-processed":[122],"better":[124],"reflect":[125],"realistic":[126],"expansions)":[128],"six":[130],"in-house":[131,184,219],"datasets,":[133],"REINVENT":[136,150],"widely":[139],"adopted":[140],"RNN-based":[141],"model.":[143],"After":[144],"splitting":[145],"dataset":[147],"training":[149],"compounds,":[153],"found":[155],"rediscovery":[157,227],"much":[162],"higher":[163,210],"in":[164,183,206,297],"projects":[166,185,208,220],"(at":[167],"1.60%,":[168],"0.64%,":[169],"0.21%":[171],"top":[174],"100,":[175],"500,":[176],"5000":[178],"scored":[179],"generated":[180],"compounds)":[181],"than":[182,214],"values":[188],"were":[189],"0.00%,":[190],"0.03%,":[191],"0.04%,":[193],"respectively).":[194],"Similarly,":[195],"average":[196],"single":[197],"nearest":[198],"neighbour":[199],"similarity":[200],"between":[201,211,254],"early-":[202],"active":[212],"inactive":[215],"compounds;":[216],"however,":[217],"converse":[222],"true,":[224],"which":[225,301,309],"makes":[226],"(if":[228],"so":[229],"desired)":[230],"more":[231],"difficult.":[232],"We":[233],"hence":[234,287],"show":[235],"recovers":[240],"very":[241],"few":[242],"real-world":[246,263,299],"discovery":[248,260],"projects,":[249],"highlighting":[250],"fundamental":[252],"difference":[253],"purely":[255],"algorithmic":[256],"design":[257,269],"Evaluating":[265],"novo":[267],"compound":[268],"approaches":[270],"appears,":[271],"based":[272],"current":[275],"difficult":[277],"or":[278],"even":[279],"impossible":[280],"do":[282],"retrospectively.Scientific":[283],"Contribution":[284],"This":[285],"contribution":[286],"illustrates":[288],"aspects":[289],"evaluating":[291],"performance":[293],"setting":[300],"not":[303],"been":[304],"extensively":[305],"described":[306],"previously":[307],"hopefully":[310],"contribute":[311],"further":[314],"future":[315],"development.":[316]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}