{"id":"https://openalex.org/W4319597566","doi":"https://doi.org/10.1186/s13321-023-00686-z","title":"Efficient virtual high-content screening using a distance-aware transformer model","display_name":"Efficient virtual high-content screening using a distance-aware transformer model","publication_year":2023,"publication_date":"2023-02-08","ids":{"openalex":"https://openalex.org/W4319597566","doi":"https://doi.org/10.1186/s13321-023-00686-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/36755346"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-023-00686-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00686-z","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00686-z","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/s13321-023-00686-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071556399","display_name":"Manuel Sellner","orcid":"https://orcid.org/0000-0003-3961-0175"},"institutions":[{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Manuel S. Sellner","raw_affiliation_strings":["Department of Pharmaceutical Sciences, University of Basel, Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pharmaceutical Sciences, University of Basel, Basel, Switzerland","institution_ids":["https://openalex.org/I1850255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101138262","display_name":"Amr H. Mahmoud","orcid":null},"institutions":[{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Amr H. Mahmoud","raw_affiliation_strings":["Department of Pharmaceutical Sciences, University of Basel, Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pharmaceutical Sciences, University of Basel, Basel, Switzerland","institution_ids":["https://openalex.org/I1850255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041891399","display_name":"Markus A. Lill","orcid":"https://orcid.org/0000-0003-3023-5188"},"institutions":[{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Markus A. Lill","raw_affiliation_strings":["Department of Pharmaceutical Sciences, University of Basel, Basel, Switzerland. markus.lill@unibas.ch","Department of Pharmaceutical Sciences, University of Basel, Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pharmaceutical Sciences, University of Basel, Basel, Switzerland. markus.lill@unibas.ch","institution_ids":[]},{"raw_affiliation_string":"Department of Pharmaceutical Sciences, University of Basel, Basel, Switzerland","institution_ids":["https://openalex.org/I1850255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071556399"],"corresponding_institution_ids":["https://openalex.org/I1850255"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":1.7462,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86474863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"15","issue":"1","first_page":"18","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9990000128746033,"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":0.9990000128746033,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/virtual-screening","display_name":"Virtual screening","score":0.7917221784591675},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7341370582580566},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.7304803133010864},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.6882789731025696},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6698445677757263},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6654115915298462},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5565893054008484},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.4404718577861786},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37387603521347046},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3523510694503784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3058888912200928},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.24826571345329285},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.102862149477005}],"concepts":[{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.7917221784591675},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7341370582580566},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.7304803133010864},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.6882789731025696},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6698445677757263},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6654115915298462},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5565893054008484},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.4404718577861786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37387603521347046},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3523510694503784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3058888912200928},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.24826571345329285},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.102862149477005},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-023-00686-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00686-z","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00686-z","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:36755346","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36755346","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:9906956","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9906956","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9906956/pdf/13321_2023_Article_686.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:6fabb041a6114f35993cf52d1dba1e0e","is_oa":true,"landing_page_url":"https://doaj.org/article/6fabb041a6114f35993cf52d1dba1e0e","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 1-10 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-023-00686-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00686-z","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00686-z","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/15","display_name":"Life in Land","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319597566.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1757990252","https://openalex.org/W1983478747","https://openalex.org/W2092493635","https://openalex.org/W2096733369","https://openalex.org/W2103311408","https://openalex.org/W2174991771","https://openalex.org/W2529996553","https://openalex.org/W2884441791","https://openalex.org/W2886791556","https://openalex.org/W2887997457","https://openalex.org/W2896457183","https://openalex.org/W2901476322","https://openalex.org/W2951048875","https://openalex.org/W2973114758","https://openalex.org/W2995422623","https://openalex.org/W3005680577","https://openalex.org/W3009999522","https://openalex.org/W3022874757","https://openalex.org/W3027690603","https://openalex.org/W3032299950","https://openalex.org/W3034303554","https://openalex.org/W3034781633","https://openalex.org/W3035302862","https://openalex.org/W3057682811","https://openalex.org/W3098269892","https://openalex.org/W3098306883","https://openalex.org/W3105590657","https://openalex.org/W3114632476","https://openalex.org/W3162665866","https://openalex.org/W3195831412","https://openalex.org/W3203898572","https://openalex.org/W4214624153"],"related_works":["https://openalex.org/W3037485788","https://openalex.org/W2074812962","https://openalex.org/W1992095612","https://openalex.org/W3171568022","https://openalex.org/W2008024114","https://openalex.org/W4311620446","https://openalex.org/W3095261004","https://openalex.org/W2099101879","https://openalex.org/W4319597566","https://openalex.org/W4245476402"],"abstract_inverted_index":{"Molecular":[0],"similarity":[1,20,91,109,123,137,150,251],"search":[2,26,180,221],"is":[3,39],"an":[4],"often-used":[5],"method":[6,119,211,244],"in":[7,11,32,69,79,98,223],"drug":[8],"discovery,":[9],"especially":[10],"virtual":[12,224],"screening":[13,133,225],"studies.":[14],"While":[15,115],"simple":[16],"one-":[17],"or":[18],"two-dimensional":[19],"metrics":[21],"can":[22],"be":[23,246],"applied":[24],"to":[25,55,66,94,104,157,166,176,195,245],"databases":[27],"containing":[28,169],"billions":[29],"of":[30,36,77,107,144,185,205,216,236,242,248],"molecules":[31,78,93],"a":[33,52,61,145,167,201],"reasonable":[34],"amount":[35],"time,":[37],"this":[38,48,243],"not":[40],"the":[41,74,80,90,102,108,118,127,142,154,164,178,219,233,237,240,249],"case":[42],"for":[43,149],"complex":[44],"three-dimensional":[45],"methods.":[46],"In":[47],"work,":[49],"we":[50,116],"trained":[51,113,199],"transformer":[53],"model":[54,103,165,174,192,238],"autoencode":[56],"tokenized":[57],"SMILES":[58],"strings":[59],"using":[60,121],"custom":[62],"loss":[63,147],"function":[64,148],"developed":[65],"conserve":[67],"similarities":[68],"latent":[70,82,99],"space.":[71],"This":[72],"allows":[73,101],"direct":[75],"sampling":[76],"generated":[81],"space":[83,100,181,222],"based":[84],"on":[85,200],"their":[86,95,230],"Euclidian":[87,96],"distance.":[88],"Reducing":[89],"between":[92],"distance":[97,234],"perform":[105],"independent":[106,247],"metric":[110],"it":[111],"was":[112,193],"on.":[114],"test":[117],"here":[120],"2D":[122],"as":[124],"proof-of-concept":[125],"study,":[126],"algorithm":[128],"will":[129],"enable":[130],"also":[131,188],"high-content":[132],"with":[134],"time-consuming":[135],"3D":[136],"metrics.":[138],"We":[139,187],"show":[140,189],"that":[141,190],"presence":[143],"specific":[146],"conservation":[151],"greatly":[152],"improved":[153],"model's":[155],"ability":[156],"predict":[158],"highly":[159,228],"similar":[160],"molecules.":[161],"When":[162],"applying":[163],"database":[168],"1.5":[170],"billion":[171],"molecules,":[172],"our":[173,191],"managed":[175],"reduce":[177],"relevant":[179,220],"by":[182],"5":[183],"orders":[184],"magnitude.":[186],"able":[194],"generalize":[196],"adequately":[197],"when":[198],"relatively":[202],"small":[203],"dataset":[204],"representative":[206],"structures.":[207],"The":[208],"herein":[209],"presented":[210],"thereby":[212],"provides":[213],"new":[214],"means":[215],"substantially":[217],"reducing":[218],"approaches,":[226],"thus":[227],"increasing":[229],"throughput.":[231],"Additionally,":[232],"awareness":[235],"causes":[239],"efficiency":[241],"underlying":[250],"metric.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}