{"id":"https://openalex.org/W2171451338","doi":"https://doi.org/10.1186/1471-2105-11-s3-s8","title":"Application of kernel functions for accurate similarity search in large chemical databases","display_name":"Application of kernel functions for accurate similarity search in large chemical databases","publication_year":2010,"publication_date":"2010-04-01","ids":{"openalex":"https://openalex.org/W2171451338","doi":"https://doi.org/10.1186/1471-2105-11-s3-s8","mag":"2171451338","pmid":"https://pubmed.ncbi.nlm.nih.gov/20438655"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-11-s3-s8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-s3-s8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-S3-S8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-S3-S8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100455472","display_name":"Xiaohong Wang","orcid":"https://orcid.org/0000-0003-2636-8260"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohong Wang","raw_affiliation_strings":["School of Electrical Engineering and Computer Science University of Kansas, Lawrence, 66045, USA","School of Electrical Engineering and Computer Science University of Kansas, Lawrence, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science University of Kansas, Lawrence, 66045, USA","institution_ids":["https://openalex.org/I146416000"]},{"raw_affiliation_string":"School of Electrical Engineering and Computer Science University of Kansas, Lawrence, USA","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105352906","display_name":"Jun Huan","orcid":"https://orcid.org/0000-0003-4929-2617"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jun Huan","raw_affiliation_strings":["School of Electrical Engineering and Computer Science University of Kansas, Lawrence, Kansas, 66045, USA","School of Electrical Engineering and Computer Science University of Kansas, Lawrence, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science University of Kansas, Lawrence, Kansas, 66045, USA","institution_ids":["https://openalex.org/I146416000"]},{"raw_affiliation_string":"School of Electrical Engineering and Computer Science University of Kansas, Lawrence, USA","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045324120","display_name":"Aaron Smalter","orcid":null},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron Smalter","raw_affiliation_strings":["School of Electrical Engineering and Computer Science University of Kansas, Lawrence, Kansas, 66045, USA","School of Electrical Engineering and Computer Science University of Kansas, Lawrence, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science University of Kansas, Lawrence, Kansas, 66045, USA","institution_ids":["https://openalex.org/I146416000"]},{"raw_affiliation_string":"School of Electrical Engineering and Computer Science University of Kansas, Lawrence, USA","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061260927","display_name":"Gerald H. Lushington","orcid":"https://orcid.org/0000-0001-5821-4253"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald H Lushington","raw_affiliation_strings":["Molecular Graphics and Modeling Laboratory, University of Kansas, Lawrence, Kansas, 66045, USA","Molecular Graphics and Modeling Laboratory, University of Kansas, Lawrence, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular Graphics and Modeling Laboratory, University of Kansas, Lawrence, Kansas, 66045, USA","institution_ids":["https://openalex.org/I146416000"]},{"raw_affiliation_string":"Molecular Graphics and Modeling Laboratory, University of Kansas, Lawrence, USA","institution_ids":["https://openalex.org/I146416000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5105352906"],"corresponding_institution_ids":["https://openalex.org/I146416000"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.3724,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82553963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"11","issue":"S3","first_page":"S8","last_page":"S8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.880299985408783,"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":0.880299985408783,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.06639999896287918,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.00800000037997961,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7011328935623169},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.6338187456130981},{"id":"https://openalex.org/keywords/chemical-database","display_name":"Chemical database","score":0.6204990148544312},{"id":"https://openalex.org/keywords/graph-kernel","display_name":"Graph kernel","score":0.6002240180969238},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5373818278312683},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.525718629360199},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5217465162277222},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5055999755859375},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4603874683380127},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44828781485557556},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.4438442885875702},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4393242299556732},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35568901896476746},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.31624364852905273},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.27063649892807007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.216629296541214},{"id":"https://openalex.org/keywords/polynomial-kernel","display_name":"Polynomial kernel","score":0.18494412302970886},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1736813485622406},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.10276558995246887},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.08471959829330444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7011328935623169},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.6338187456130981},{"id":"https://openalex.org/C203394866","wikidata":"https://www.wikidata.org/wiki/Q2881060","display_name":"Chemical database","level":2,"score":0.6204990148544312},{"id":"https://openalex.org/C100595998","wikidata":"https://www.wikidata.org/wiki/Q11731931","display_name":"Graph kernel","level":5,"score":0.6002240180969238},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5373818278312683},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.525718629360199},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5217465162277222},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4603874683380127},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44828781485557556},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4438442885875702},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4393242299556732},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35568901896476746},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.31624364852905273},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27063649892807007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.216629296541214},{"id":"https://openalex.org/C160446489","wikidata":"https://www.wikidata.org/wiki/Q7226642","display_name":"Polynomial kernel","level":4,"score":0.18494412302970886},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1736813485622406},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.10276558995246887},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.08471959829330444},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009930","descriptor_name":"Organic Chemicals","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009930","descriptor_name":"Organic Chemicals","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009930","descriptor_name":"Organic Chemicals","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009930","descriptor_name":"Organic Chemicals","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1186/1471-2105-11-s3-s8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-s3-s8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-S3-S8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:20438655","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20438655","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:kuscholarworks.ku.edu:1808/18903","is_oa":true,"landing_page_url":"http://hdl.handle.net/1808/18903","pdf_url":"https://kuscholarworks.ku.edu/bitstreams/e2b8ae36-d347-4cae-9c73-a1ee27d80b42/download","source":{"id":"https://openalex.org/S4306400421","display_name":"KU ScholarWorks (The University of Kansas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I146416000","host_organization_name":"University of Kansas","host_organization_lineage":["https://openalex.org/I146416000"],"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":"","raw_type":"Article"},{"id":"pmh:oai:kuscholarworks.ku.edu:1808/12913","is_oa":true,"landing_page_url":"http://hdl.handle.net/1808/12913","pdf_url":null,"source":{"id":"https://openalex.org/S4306400421","display_name":"KU ScholarWorks (The University of Kansas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I146416000","host_organization_name":"University of Kansas","host_organization_lineage":["https://openalex.org/I146416000"],"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":"","raw_type":"Article"},{"id":"pmh:oai:kuscholarworks.ku.edu:2271/842","is_oa":false,"landing_page_url":"http://hdl.handle.net/2271/842","pdf_url":null,"source":{"id":"https://openalex.org/S4306400421","display_name":"KU ScholarWorks (The University of Kansas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I146416000","host_organization_name":"University of Kansas","host_organization_lineage":["https://openalex.org/I146416000"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2863067","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2863067","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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-11-s3-s8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-s3-s8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-S3-S8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2952321339","display_name":null,"funder_award_id":"U54 HG005031","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G815996558","display_name":"CAREER: Mining Genome-wide Chemical-Structure Activity Relationships in Emergent Chemical Genomics Databases","funder_award_id":"0845951","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2171451338.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1638267571","https://openalex.org/W1640748652","https://openalex.org/W1974124880","https://openalex.org/W2027943354","https://openalex.org/W2035753075","https://openalex.org/W2050137450","https://openalex.org/W2056524360","https://openalex.org/W2075186867","https://openalex.org/W2077440882","https://openalex.org/W2096864392","https://openalex.org/W2100080493","https://openalex.org/W2110034858","https://openalex.org/W2117169652","https://openalex.org/W2136109916","https://openalex.org/W2141955227","https://openalex.org/W2142965177","https://openalex.org/W2145546477","https://openalex.org/W2145631416","https://openalex.org/W2154418770","https://openalex.org/W2155894387","https://openalex.org/W2177508090","https://openalex.org/W2314727869","https://openalex.org/W2324789149"],"related_works":["https://openalex.org/W2754607325","https://openalex.org/W1984925645","https://openalex.org/W2078320823","https://openalex.org/W2043334680","https://openalex.org/W3099811568","https://openalex.org/W2797819729","https://openalex.org/W2901290148","https://openalex.org/W4297909034","https://openalex.org/W4285213554","https://openalex.org/W3008854474"],"abstract_inverted_index":{"BACKGROUND:":[0],"Similarity":[1],"search":[2,90,102,228,233,243],"in":[3,14,59,87,103,114,244,254],"chemical":[4,15,21,75,104,153,182,214,245,255],"structure":[5,31,177],"databases":[6,183,215],"is":[7,27,178,216],"an":[8,35],"important":[9],"problem":[10],"with":[11,184],"many":[12],"applications":[13],"genomics,":[16],"drug":[17],"design,":[18],"and":[19,63,84,100,141,174,188,204,226],"efficient":[20,36,139],"probe":[22],"screening":[23],"among":[24],"others.":[25],"It":[26],"widely":[28],"believed":[29],"that":[30,158],"based":[32],"methods":[33,198],"provide":[34],"way":[37,239],"to":[38,50,73,79,117,132,151,180,195,221,240],"do":[39],"the":[40,52,80,85,159,171,175,250],"query.":[41],"Recently":[42],"various":[43],"graph":[44,66,97,121,135],"kernel":[45,67,98,136],"functions":[46,68],"have":[47,145],"been":[48],"designed":[49],"capture":[51],"intrinsic":[53],"similarity":[54,89,101,111,119,172,208,227,232,242],"of":[55,120,252],"graphs.":[56],"Though":[57],"successful":[58],"constructing":[60],"accurate":[61],"predictive":[62],"classification":[64],"models,":[65],"can":[69],"not":[70],"be":[71],"applied":[72,107,146],"large":[74,92,152,181,213],"compound":[76],"database":[77],"due":[78],"high":[81],"computational":[82],"complexity":[83],"difficulties":[86],"indexing":[88,186,197],"for":[91,165,212],"databases.":[93,154,246,256],"RESULTS:":[94],"To":[95],"bridge":[96],"function":[99,137],"databases,":[105],"we":[106,127,219],"a":[108,129,237],"novel":[109],"kernel-based":[110],"measurement,":[112],"developed":[113],"our":[115,125,147],"team,":[116],"measure":[118],"represented":[122],"chemicals.":[123],"In":[124],"method,":[126,148,234],"utilize":[128],"hash":[130],"table":[131],"support":[133],"new":[134,238],"definition,":[138],"storage":[140],"fast":[142],"search.":[143],"We":[144],"named":[149],"G-hash,":[150,235],"Our":[155,230],"results":[156],"show":[157],"G-hash":[160,253],"method":[161,211],"achieves":[162],"state-of-the-art":[163,196],"performance":[164],"k-nearest":[166],"neighbor":[167],"(k-NN)":[168],"classification.":[169],"Moreover,":[170],"measurement":[173],"index":[176],"scalable":[179],"smaller":[185],"size,":[187],"faster":[189],"query":[190,209],"processing":[191,210],"time":[192,224],"as":[193,200],"compared":[194],"such":[199],"Daylight":[201],"fingerprints,":[202],"C-tree":[203],"GraphGrep.":[205],"CONCLUSIONS:":[206],"Efficient":[207],"challenging":[217],"since":[218],"need":[220],"balance":[222],"running":[223],"efficiency":[225],"accuracy.":[229],"previous":[231],"provides":[236],"perform":[241],"Experimental":[247],"study":[248],"validates":[249],"utility":[251]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}