{"id":"https://openalex.org/W4226159083","doi":"https://doi.org/10.1088/2632-2153/ac3ffb","title":"Chemformer: a pre-trained transformer for computational chemistry","display_name":"Chemformer: a pre-trained transformer for computational chemistry","publication_year":2021,"publication_date":"2021-12-07","ids":{"openalex":"https://openalex.org/W4226159083","doi":"https://doi.org/10.1088/2632-2153/ac3ffb"},"language":"en","primary_location":{"id":"doi:10.1088/2632-2153/ac3ffb","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ac3ffb","pdf_url":"https://iopscience.iop.org/article/10.1088/2632-2153/ac3ffb/pdf","source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://iopscience.iop.org/article/10.1088/2632-2153/ac3ffb/pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013570692","display_name":"Ross Irwin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143795","display_name":"AstraZeneca (Sweden)","ror":"https://ror.org/04wwrrg31","country_code":"SE","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210143795"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ross Irwin","raw_affiliation_strings":["Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077444955","display_name":"Spyridon Dimitriadis","orcid":null},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]},{"id":"https://openalex.org/I4210143795","display_name":"AstraZeneca (Sweden)","ror":"https://ror.org/04wwrrg31","country_code":"SE","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210143795"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Spyridon Dimitriadis","raw_affiliation_strings":["Department of Computer and Information Science, Link\u00f6ping University, Link\u00f6ping, Sweden","Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, Link\u00f6ping University, Link\u00f6ping, Sweden","institution_ids":["https://openalex.org/I102134673"]},{"raw_affiliation_string":"Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089237271","display_name":"Jiazhen He","orcid":"https://orcid.org/0000-0001-5848-8318"},"institutions":[{"id":"https://openalex.org/I4210143795","display_name":"AstraZeneca (Sweden)","ror":"https://ror.org/04wwrrg31","country_code":"SE","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210143795"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jiazhen He","raw_affiliation_strings":["Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046421751","display_name":"Esben Jannik Bjerrum","orcid":"https://orcid.org/0000-0003-1614-7376"},"institutions":[{"id":"https://openalex.org/I4210143795","display_name":"AstraZeneca (Sweden)","ror":"https://ror.org/04wwrrg31","country_code":"SE","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210143795"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Esben Jannik Bjerrum","raw_affiliation_strings":["Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-1614-7376","affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046421751"],"corresponding_institution_ids":["https://openalex.org/I4210143795"],"apc_list":{"value":1600,"currency":"GBP","value_usd":1962},"apc_paid":{"value":1600,"currency":"GBP","value_usd":1962},"fwci":21.1634,"has_fulltext":false,"cited_by_count":270,"citation_normalized_percentile":{"value":0.99664547,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"3","issue":"1","first_page":"015022","last_page":"015022"},"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":0.9995999932289124,"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":0.9936000108718872,"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/cheminformatics","display_name":"Cheminformatics","score":0.834010660648346},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.764359712600708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.753429114818573},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.716396152973175},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6405051946640015},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.587688684463501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.510973334312439},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3217654824256897},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14699241518974304},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.13335126638412476},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0848066508769989}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.834010660648346},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.764359712600708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753429114818573},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.716396152973175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6405051946640015},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.587688684463501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.510973334312439},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3217654824256897},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14699241518974304},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.13335126638412476},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0848066508769989},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1088/2632-2153/ac3ffb","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ac3ffb","pdf_url":"https://iopscience.iop.org/article/10.1088/2632-2153/ac3ffb/pdf","source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1088/2632-2153/ac3ffb","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ac3ffb","pdf_url":"https://iopscience.iop.org/article/10.1088/2632-2153/ac3ffb/pdf","source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4226159083.pdf"},"referenced_works_count":75,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1757990252","https://openalex.org/W1975147762","https://openalex.org/W2064675550","https://openalex.org/W2101234009","https://openalex.org/W2157331557","https://openalex.org/W2325811289","https://openalex.org/W2551217916","https://openalex.org/W2594183968","https://openalex.org/W2604296437","https://openalex.org/W2624871570","https://openalex.org/W2753921001","https://openalex.org/W2886791556","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2900090807","https://openalex.org/W2945260553","https://openalex.org/W2947423323","https://openalex.org/W2963587345","https://openalex.org/W2966357564","https://openalex.org/W2994678679","https://openalex.org/W2998367408","https://openalex.org/W3007488165","https://openalex.org/W3025593963","https://openalex.org/W3027819927","https://openalex.org/W3030970797","https://openalex.org/W3030978062","https://openalex.org/W3032781902","https://openalex.org/W3034999214","https://openalex.org/W3035172872","https://openalex.org/W3038856956","https://openalex.org/W3088265803","https://openalex.org/W3088999551","https://openalex.org/W3091477290","https://openalex.org/W3093934881","https://openalex.org/W3094771832","https://openalex.org/W3100358278","https://openalex.org/W3103092523","https://openalex.org/W3109892317","https://openalex.org/W3114291043","https://openalex.org/W3117879109","https://openalex.org/W3119022334","https://openalex.org/W3154464317","https://openalex.org/W3157265962","https://openalex.org/W3160706794","https://openalex.org/W3171707284","https://openalex.org/W3181403764","https://openalex.org/W4237622019","https://openalex.org/W4254658870","https://openalex.org/W4288089799","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6675354045","https://openalex.org/W6683258052","https://openalex.org/W6736161267","https://openalex.org/W6739365718","https://openalex.org/W6739901393","https://openalex.org/W6744596635","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6762122294","https://openalex.org/W6766867396","https://openalex.org/W6766978945","https://openalex.org/W6769311223","https://openalex.org/W6769627184","https://openalex.org/W6774009640","https://openalex.org/W6779235351","https://openalex.org/W6780104034","https://openalex.org/W6780226713","https://openalex.org/W6784313401","https://openalex.org/W6784526300","https://openalex.org/W6786619936","https://openalex.org/W6796905988","https://openalex.org/W6803196593"],"related_works":["https://openalex.org/W1573015311","https://openalex.org/W1570419641","https://openalex.org/W4386509167","https://openalex.org/W2889938001","https://openalex.org/W4293771607","https://openalex.org/W3165034028","https://openalex.org/W2296499206","https://openalex.org/W3210319767","https://openalex.org/W132037564","https://openalex.org/W4246770172"],"abstract_inverted_index":{"Abstract":[0],"Transformer":[1],"models":[2],"coupled":[3],"with":[4],"a":[5,17,33,104],"simplified":[6],"molecular":[7,105],"line":[8],"entry":[9],"system":[10],"(SMILES)":[11],"have":[12],"recently":[13],"proven":[14],"to":[15,41,58],"be":[16,38,55,124],"powerful":[18],"combination":[19],"for":[20,32,94,103],"solving":[21],"challenges":[22],"in":[23],"cheminformatics.":[24],"These":[25],"models,":[26],"however,":[27],"are":[28],"often":[29],"developed":[30],"specifically":[31],"single":[34],"application":[35],"and":[36,61,74,85,108,121],"can":[37,54,71,112],"very":[39],"resource-intensive":[40],"train.":[42],"In":[43],"this":[44],"work":[45],"we":[46,66,90],"present":[47],"the":[48],"Chemformer":[49,111],"model\u2014a":[50],"Transformer-based":[51],"model":[52],"which":[53],"quickly":[56],"applied":[57],"both":[59],"sequence-to-sequence":[60],"discriminative":[62,116],"cheminformatics":[63],"tasks.":[64,81],"Additionally,":[65],"show":[67,109],"that":[68,110],"self-supervised":[69],"pre-training":[70],"improve":[72,99],"performance":[73],"significantly":[75],"speed":[76],"up":[77],"convergence":[78],"on":[79,100,114],"downstream":[80],"On":[82],"direct":[83],"synthesis":[84],"retrosynthesis":[86],"prediction":[87],"benchmark":[88],"datasets":[89,120],"publish":[91],"state-of-the-art":[92],"results":[93],"top-1":[95],"accuracy.":[96],"We":[97],"also":[98],"existing":[101],"approaches":[102],"optimisation":[106],"task":[107],"optimise":[113],"multiple":[115],"tasks":[117],"simultaneously.":[118],"Models,":[119],"code":[122],"will":[123],"made":[125],"available":[126],"after":[127],"publication.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":35},{"year":2025,"cited_by_count":104},{"year":2024,"cited_by_count":69},{"year":2023,"cited_by_count":52},{"year":2022,"cited_by_count":10}],"updated_date":"2026-06-27T08:28:00.272161","created_date":"2025-10-10T00:00:00"}