{"id":"https://openalex.org/W4220887735","doi":"https://doi.org/10.1186/s13321-022-00601-y","title":"Explaining and avoiding failure modes in goal-directed generation of small molecules","display_name":"Explaining and avoiding failure modes in goal-directed generation of small molecules","publication_year":2022,"publication_date":"2022-04-01","ids":{"openalex":"https://openalex.org/W4220887735","doi":"https://doi.org/10.1186/s13321-022-00601-y","pmid":"https://pubmed.ncbi.nlm.nih.gov/35365218"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-022-00601-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00601-y","pdf_url":null,"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://doi.org/10.1186/s13321-022-00601-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069491447","display_name":"Maxime Langevin","orcid":"https://orcid.org/0000-0002-5498-4661"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I3018075036","display_name":"Sanofi (France)","ror":"https://ror.org/02n6c9837","country_code":"FR","type":"company","lineage":["https://openalex.org/I3018075036"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Maxime Langevin","raw_affiliation_strings":["Molecular Design Sciences - Integrated Drug Discovery, Sanofi R&D, 94400, Vitry-sur-Seine, France","PASTEUR, D\u00e9partement de chimie, \u00c9cole Normale Sup\u00e9rieure, PSL University, Sorbonne Universit\u00e9, CNRS, 75005, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular Design Sciences - Integrated Drug Discovery, Sanofi R&D, 94400, Vitry-sur-Seine, France","institution_ids":["https://openalex.org/I3018075036"]},{"raw_affiliation_string":"PASTEUR, D\u00e9partement de chimie, \u00c9cole Normale Sup\u00e9rieure, PSL University, Sorbonne Universit\u00e9, CNRS, 75005, Paris, France","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I39804081","https://openalex.org/I2746051580","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060343355","display_name":"Rodolphe Vuilleumier","orcid":"https://orcid.org/0000-0001-5386-699X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Rodolphe Vuilleumier","raw_affiliation_strings":["PASTEUR, D\u00e9partement de chimie, \u00c9cole Normale Sup\u00e9rieure, PSL University, Sorbonne Universit\u00e9, CNRS, 75005, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PASTEUR, D\u00e9partement de chimie, \u00c9cole Normale Sup\u00e9rieure, PSL University, Sorbonne Universit\u00e9, CNRS, 75005, Paris, France","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I39804081","https://openalex.org/I2746051580","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046201147","display_name":"Marc Bianciotto","orcid":"https://orcid.org/0000-0002-4345-995X"},"institutions":[{"id":"https://openalex.org/I3018075036","display_name":"Sanofi (France)","ror":"https://ror.org/02n6c9837","country_code":"FR","type":"company","lineage":["https://openalex.org/I3018075036"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marc Bianciotto","raw_affiliation_strings":["Molecular Design Sciences - Integrated Drug Discovery, Sanofi R&D, 94400, Vitry-sur-Seine, France. marc.bianciotto@sanofi.com","Molecular Design Sciences - Integrated Drug Discovery, Sanofi R&D, 94400, Vitry-sur-Seine, France"],"raw_orcid":"https://orcid.org/0000-0002-4345-995X","affiliations":[{"raw_affiliation_string":"Molecular Design Sciences - Integrated Drug Discovery, Sanofi R&D, 94400, Vitry-sur-Seine, France. marc.bianciotto@sanofi.com","institution_ids":["https://openalex.org/I3018075036"]},{"raw_affiliation_string":"Molecular Design Sciences - Integrated Drug Discovery, Sanofi R&D, 94400, Vitry-sur-Seine, France","institution_ids":["https://openalex.org/I3018075036"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069491447"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I3018075036","https://openalex.org/I39804081"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":5.0282,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.95870605,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"14","issue":"1","first_page":"20","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9843999743461609,"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":0.9829999804496765,"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":0.6397457122802734},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.3349573016166687},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.158500075340271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6397457122802734},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3349573016166687},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.158500075340271}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13321-022-00601-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00601-y","pdf_url":null,"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:35365218","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35365218","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:HAL:hal-03921241v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03921241","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, 2022, 14 (1), pp.20. ⟨10.1186/s13321-022-00601-y⟩","raw_type":"Journal articles"},{"id":"pmh:oai:doaj.org/article:dfdfc3492b0846e8a4ea19633e34131f","is_oa":true,"landing_page_url":"https://doaj.org/article/dfdfc3492b0846e8a4ea19633e34131f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 14, Iss 1, Pp 1-13 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8973583","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8973583","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/s13321-022-00601-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00601-y","pdf_url":null,"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":[],"awards":[{"id":"https://openalex.org/G4344721933","display_name":null,"funder_award_id":"2019/0821","funder_id":"https://openalex.org/F4320321663","funder_display_name":"Association Nationale de la Recherche et de la Technologie"}],"funders":[{"id":"https://openalex.org/F4320321663","display_name":"Association Nationale de la Recherche et de la Technologie","ror":"https://ror.org/00ht2ab73"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1932198206","https://openalex.org/W1975875968","https://openalex.org/W1977242738","https://openalex.org/W1988037271","https://openalex.org/W2128245586","https://openalex.org/W2132022337","https://openalex.org/W2578240541","https://openalex.org/W2594183968","https://openalex.org/W2610148085","https://openalex.org/W2773987374","https://openalex.org/W2796306022","https://openalex.org/W2899070097","https://openalex.org/W2900694120","https://openalex.org/W2901476322","https://openalex.org/W2902415322","https://openalex.org/W2911964244","https://openalex.org/W2914542247","https://openalex.org/W2953128081","https://openalex.org/W2956961449","https://openalex.org/W3014154196","https://openalex.org/W3015475346","https://openalex.org/W3015572666","https://openalex.org/W3094553402","https://openalex.org/W3100751385","https://openalex.org/W3100839802","https://openalex.org/W3116202926","https://openalex.org/W3133989558","https://openalex.org/W3152642460"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Despite":[0],"growing":[1],"interest":[2],"and":[3,66,88,106,117],"success":[4],"in":[5],"automated":[6],"in-silico":[7],"molecular":[8],"design,":[9],"questions":[10],"remain":[11],"regarding":[12],"the":[13,48,62,67,85,90,115,118],"ability":[14],"of":[15,23],"goal-directed":[16,34,91],"generation":[17,35,92],"algorithms":[18],"to":[19,47,55,82,113],"perform":[20],"unbiased":[21],"exploration":[22],"novel":[24],"chemical":[25],"spaces.":[26],"A":[27],"specific":[28],"phenomenon":[29],"has":[30],"recently":[31],"been":[32],"highlighted:":[33],"guided":[36],"with":[37,43,84,97],"machine":[38],"learning":[39],"models":[40,87],"produce":[41],"molecules":[42,107],"high":[44,110],"scores":[45,53,111],"according":[46,54,112],"optimization":[49,116],"model,":[50],"but":[51],"low":[52],"control":[56,119],"models,":[57,100],"even":[58],"when":[59],"trained":[60],"on":[61],"same":[63,68],"data":[64],"distribution":[65],"target.":[69],"In":[70],"this":[71,76,101],"work,":[72],"we":[73],"show":[74,95],"that":[75,96],"worrisome":[77],"behavior":[78],"is":[79],"actually":[80],"due":[81],"issues":[83],"predictive":[86,99],"not":[89],"algorithms.":[93],"We":[94],"appropriate":[98],"issue":[102],"can":[103],"be":[104],"resolved,":[105],"generated":[108],"have":[109],"both":[114],"models.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}