{"id":"https://openalex.org/W3016179152","doi":"https://doi.org/10.1109/icassp40776.2020.9053425","title":"Augmenting Molecular Images with Vector Representations as a Featurization Technique for Drug Classification","display_name":"Augmenting Molecular Images with Vector Representations as a Featurization Technique for Drug Classification","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016179152","doi":"https://doi.org/10.1109/icassp40776.2020.9053425","mag":"3016179152"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.03646","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047690521","display_name":"Daniel de Marchi","orcid":"https://orcid.org/0000-0002-9222-8840"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel de Marchi","raw_affiliation_strings":["Dept. of Statistics and Operations Research, University of North Carolina at Chapel Hill"],"affiliations":[{"raw_affiliation_string":"Dept. of Statistics and Operations Research, University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067048881","display_name":"Amarjit Budhiraja","orcid":"https://orcid.org/0000-0002-7912-5433"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amarjit Budhiraja","raw_affiliation_strings":["Dept. of Statistics and Operations Research, University of North Carolina at Chapel Hill"],"affiliations":[{"raw_affiliation_string":"Dept. of Statistics and Operations Research, University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047690521"],"corresponding_institution_ids":["https://openalex.org/I114027177"],"apc_list":null,"apc_paid":null,"fwci":0.1443,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50522869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"956","last_page":"960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9991999864578247,"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":0.9991999864578247,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9878000020980835,"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"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9776999950408936,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.9228533506393433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6731499433517456},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6141404509544373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5581870675086975},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5438753366470337},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5049343705177307},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5029675364494324},{"id":"https://openalex.org/keywords/expressive-power","display_name":"Expressive power","score":0.4407931864261627},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4116995334625244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3461993336677551},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3027074337005615},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1482865810394287},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.14138194918632507}],"concepts":[{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.9228533506393433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6731499433517456},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6141404509544373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5581870675086975},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5438753366470337},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5049343705177307},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5029675364494324},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.4407931864261627},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4116995334625244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3461993336677551},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3027074337005615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1482865810394287},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.14138194918632507},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.03646","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.03646","pdf_url":"https://arxiv.org/pdf/2008.03646","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.03646","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.03646","pdf_url":"https://arxiv.org/pdf/2008.03646","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1988037271","https://openalex.org/W2200017991","https://openalex.org/W2274287116","https://openalex.org/W2290847742","https://openalex.org/W2472085920","https://openalex.org/W2594183968","https://openalex.org/W2610148085","https://openalex.org/W2685808923","https://openalex.org/W2767891136","https://openalex.org/W2886791556","https://openalex.org/W2900489253","https://openalex.org/W2945551948","https://openalex.org/W2963454409","https://openalex.org/W2963676163","https://openalex.org/W2964122860","https://openalex.org/W2964350391","https://openalex.org/W3100157108","https://openalex.org/W4289292158","https://openalex.org/W6733974131","https://openalex.org/W6756302984"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W3098238745"],"abstract_inverted_index":{"One":[0],"of":[1,18,41,101],"the":[2,16,21,39,91,96,109,120,128],"key":[3],"steps":[4],"in":[5,53],"building":[6],"deep":[7],"learning":[8],"systems":[9],"for":[10,20],"drug":[11],"classification":[12],"and":[13,33,73,84],"generation":[14],"is":[15],"choice":[17],"featurization":[19,24],"molecules.":[22],"Previous":[23],"methods":[25],"have":[26],"included":[27],"molecular":[28,42,59],"images,":[29],"binary":[30,46],"strings,":[31],"graphs,":[32],"SMILES":[34],"strings.":[35],"This":[36],"paper":[37],"proposes":[38],"creation":[40],"images":[43],"\"captioned\"":[44],"with":[45],"vectors":[47],"that":[48],"encode":[49,68,77],"information":[50],"not":[51],"contained":[52],"or":[54],"easily":[55],"understood":[56],"from":[57],"a":[58,81,116],"image":[60],"alone.":[61],"Specifically,":[62],"we":[63],"use":[64],"Morgan":[65],"fingerprints,":[66],"which":[67,76,99],"higher":[69],"level":[70],"structural":[71],"information,":[72],"MACCS":[74],"keys,":[75],"yes/no":[78],"questions":[79],"about":[80],"molecule's":[82],"properties":[83],"structure.":[85],"We":[86],"tested":[87],"our":[88],"method":[89],"on":[90,119],"HIV":[92,110,121],"dataset":[93],"published":[94],"by":[95,105],"Pande":[97],"lab,":[98],"consists":[100],"41,127":[102],"molecules":[103],"labeled":[104],"if":[106],"they":[107],"inhibit":[108],"virus.":[111],"Our":[112],"final":[113],"model":[114,129],"achieved":[115],"state-of-the-art":[117],"AUC-ROC":[118],"dataset,":[122],"outperforming":[123],"all":[124],"other":[125,135],"methods.":[126],"Moreover,":[127],"converged":[130],"significantly":[131],"faster":[132],"than":[133,142],"most":[134],"methods,":[136],"requiring":[137],"dramatically":[138],"less":[139],"computational":[140],"power":[141],"unaugmented":[143],"images.":[144]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}