{"id":"https://openalex.org/W2003483025","doi":"https://doi.org/10.1021/ci200235e","title":"Anatomy of High-Performance 2D Similarity Calculations","display_name":"Anatomy of High-Performance 2D Similarity Calculations","publication_year":2011,"publication_date":"2011-09-07","ids":{"openalex":"https://openalex.org/W2003483025","doi":"https://doi.org/10.1021/ci200235e","mag":"2003483025","pmid":"https://pubmed.ncbi.nlm.nih.gov/21854053"},"language":"en","primary_location":{"id":"doi:10.1021/ci200235e","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci200235e","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4839782","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050897400","display_name":"Imran S. Haque","orcid":"https://orcid.org/0000-0001-7782-2852"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Imran S. Haque","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, California 94305, United States","Department of Computer Science, Stanford University, Stanford, California 94305 (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, California 94305, United States","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, California 94305 (United States)","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032418986","display_name":"Vijay S. Pande","orcid":"https://orcid.org/0000-0003-2774-1178"},"institutions":[{"id":"https://openalex.org/I61970326","display_name":"Vertex Pharmaceuticals (United States)","ror":"https://ror.org/00anb1726","country_code":"US","type":"company","lineage":["https://openalex.org/I61970326"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay S. Pande","raw_affiliation_strings":["Vertex Pharmaceuticals Incorporated, 130 Waverley Street, Cambridge, Massachusetts 02139, United States","\u2020 Department of Computer Science and \u2021 Department of Chemistry, Stanford University, Stanford, California 94305, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vertex Pharmaceuticals Incorporated, 130 Waverley Street, Cambridge, Massachusetts 02139, United States","institution_ids":["https://openalex.org/I61970326"]},{"raw_affiliation_string":"\u2020 Department of Computer Science and \u2021 Department of Chemistry, Stanford University, Stanford, California 94305, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077218712","display_name":"W. Patrick Walters","orcid":"https://orcid.org/0000-0003-2860-7958"},"institutions":[{"id":"https://openalex.org/I61970326","display_name":"Vertex Pharmaceuticals (United States)","ror":"https://ror.org/00anb1726","country_code":"US","type":"company","lineage":["https://openalex.org/I61970326"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"W. Patrick Walters","raw_affiliation_strings":["Vertex Pharmaceuticals Incorporated, 130 Waverley Street, Cambridge, Massachusetts 02139, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vertex Pharmaceuticals Incorporated, 130 Waverley Street, Cambridge, Massachusetts 02139, United States","institution_ids":["https://openalex.org/I61970326"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077218712"],"corresponding_institution_ids":["https://openalex.org/I61970326"],"apc_list":null,"apc_paid":null,"fwci":4.1711,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.94405974,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"51","issue":"9","first_page":"2345","last_page":"2351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9847999811172485,"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/bottleneck","display_name":"Bottleneck","score":0.7884129881858826},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7778090238571167},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6921260356903076},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5399290323257446},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5375608205795288},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.510798454284668},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5017862319946289},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4878833293914795},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.43999382853507996},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4251171052455902},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3819707930088043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3399093747138977},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3013022243976593},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12542331218719482},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.09961467981338501}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7884129881858826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778090238571167},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6921260356903076},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5399290323257446},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5375608205795288},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.510798454284668},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5017862319946289},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4878833293914795},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.43999382853507996},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4251171052455902},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3819707930088043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3399093747138977},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3013022243976593},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12542331218719482},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.09961467981338501},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"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/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1021/ci200235e","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci200235e","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:21854053","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21854053","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 chemical information and modeling","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:4839782","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4839782","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Chem Inf Model","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:4839782","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4839782","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Chem Inf Model","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G170255286","display_name":null,"funder_award_id":"U54 GM072 970","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G1782054273","display_name":null,"funder_award_id":"GM 072970","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1707653742","https://openalex.org/W1988037271","https://openalex.org/W2009000921","https://openalex.org/W2018537808","https://openalex.org/W2024503898","https://openalex.org/W2027926002","https://openalex.org/W2056838301","https://openalex.org/W2057649987","https://openalex.org/W2058033857","https://openalex.org/W2063567677","https://openalex.org/W2087486479","https://openalex.org/W2096525273","https://openalex.org/W2099731392","https://openalex.org/W2110195531","https://openalex.org/W2117755361","https://openalex.org/W2127881761","https://openalex.org/W2153693853","https://openalex.org/W2158024647","https://openalex.org/W2161834869","https://openalex.org/W2176516200","https://openalex.org/W2176720124","https://openalex.org/W2200017991","https://openalex.org/W4244606935"],"related_works":["https://openalex.org/W170547082","https://openalex.org/W2136735429","https://openalex.org/W2595172197","https://openalex.org/W2587876411","https://openalex.org/W2358332176","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224"],"abstract_inverted_index":{"Similarity":[0],"measures":[1],"based":[2],"on":[3,76,114],"the":[4,31,39],"comparison":[5,104],"of":[6,10,46,56,101,111],"dense":[7,35],"bit":[8,36],"vectors":[9,37],"two-dimensional":[11],"chemical":[12,19],"features":[13,55],"are":[14],"a":[15,108],"dominant":[16],"method":[17],"in":[18,93],"informatics.":[20],"For":[21],"large-scale":[22],"problems,":[23],"including":[24],"compound":[25],"selection":[26],"and":[27,80,84,97,116],"machine":[28],"learning,":[29],"computing":[30],"intersection":[32],"between":[33],"two":[34],"is":[38,106],"overwhelming":[40],"bottleneck.":[41],"We":[42],"describe":[43,70],"efficient":[44],"implementations":[45],"this":[47],"primitive":[48],"as":[49,51],"well":[50],"example":[52],"applications":[53],"using":[54],"modern":[57,77],"CPUs":[58],"that":[59,88,112],"allow":[60],"20-40\u00d7":[61],"performance":[62],"increases":[63],"relative":[64],"to":[65],"typical":[66],"code.":[67],"Specifically,":[68],"we":[69],"fast":[71],"methods":[72],"for":[73],"population":[74],"count":[75],"x86":[78],"processors":[79],"cache-efficient":[81],"matrix":[82,95],"traversal":[83],"leader":[85],"clustering":[86],"algorithms":[87],"alleviate":[89],"memory":[90],"bandwidth":[91],"bottlenecks":[92],"similarity":[94],"construction":[96],"clustering.":[98],"The":[99],"speed":[100],"our":[102],"2D":[103],"primitives":[105],"within":[107],"small":[109],"factor":[110],"obtained":[113],"GPUs":[115],"does":[117],"not":[118],"require":[119],"specialized":[120],"hardware.":[121]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}