{"id":"https://openalex.org/W2158801725","doi":"https://doi.org/10.1145/1273496.1273524","title":"An integrated approach to feature invention and model construction for drug activity prediction","display_name":"An integrated approach to feature invention and model construction for drug activity prediction","publication_year":2007,"publication_date":"2007-06-20","ids":{"openalex":"https://openalex.org/W2158801725","doi":"https://doi.org/10.1145/1273496.1273524","mag":"2158801725"},"language":"en","primary_location":{"id":"doi:10.1145/1273496.1273524","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1273496.1273524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th international conference on Machine learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029479248","display_name":"Jesse Davis","orcid":"https://orcid.org/0000-0002-3748-9263"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesse Davis","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059093687","display_name":"V\u0131\u0301tor Santos Costa","orcid":"https://orcid.org/0000-0002-3344-8237"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"V\u00edtor Santos Costa","raw_affiliation_strings":["Universidade do Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade do Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055101678","display_name":"Soumya Ray","orcid":"https://orcid.org/0000-0002-6673-6796"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumya Ray","raw_affiliation_strings":["Oregon State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068251706","display_name":"David Page","orcid":"https://orcid.org/0000-0003-0576-2912"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Page","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"217","last_page":"224"},"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":0.9538999795913696,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9318000078201294,"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/computer-science","display_name":"Computer science","score":0.6710503101348877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6593436598777771},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.5971224904060364},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5756791234016418},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5754390954971313},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5423927307128906},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5419564843177795},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5252296924591064},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.48631319403648376},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.48253175616264343},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.428592324256897},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3560755252838135},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3514545261859894},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16635233163833618},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08501634001731873}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6710503101348877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6593436598777771},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.5971224904060364},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5756791234016418},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5754390954971313},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5423927307128906},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5419564843177795},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5252296924591064},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.48631319403648376},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.48253175616264343},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.428592324256897},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3560755252838135},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3514545261859894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16635233163833618},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08501634001731873},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1273496.1273524","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1273496.1273524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th international conference on Machine learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.6799","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.6799","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://imls.engr.oregonstate.edu/www/htdocs/proceedings/icml2007/papers/379.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.6299999952316284,"display_name":"Good health and well-being"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1503499665","https://openalex.org/W1534731256","https://openalex.org/W1543809641","https://openalex.org/W1550821944","https://openalex.org/W1608154539","https://openalex.org/W2020549326","https://openalex.org/W2040804024","https://openalex.org/W2043146319","https://openalex.org/W2046311259","https://openalex.org/W2063060349","https://openalex.org/W2068154266","https://openalex.org/W2069116068","https://openalex.org/W2077658674","https://openalex.org/W2077662675","https://openalex.org/W2110119381","https://openalex.org/W2118697091","https://openalex.org/W2119831128","https://openalex.org/W2123019231","https://openalex.org/W2152120395","https://openalex.org/W2156909104","https://openalex.org/W4233169031","https://openalex.org/W6677574362","https://openalex.org/W6683581212"],"related_works":["https://openalex.org/W2382340815","https://openalex.org/W1972650408","https://openalex.org/W2551736466","https://openalex.org/W1997566113","https://openalex.org/W3189652131","https://openalex.org/W31220157","https://openalex.org/W2288557197","https://openalex.org/W4233024177","https://openalex.org/W2101914902","https://openalex.org/W3174613421"],"abstract_inverted_index":{"We":[0,38,99],"present":[1],"a":[2,53,56],"new":[3],"machine":[4],"learning":[5,67],"approach":[6,25,102,145],"for":[7,80,118,141],"3D-QSAR,":[8],"the":[9,43,65,70,85,90,121],"task":[10],"of":[11,15,58,93],"predicting":[12],"binding":[13,27],"affinities":[14],"molecules":[16],"to":[17,42,61,77,83,95],"target":[18],"proteins":[19],"based":[20],"on":[21,32,103],"3D":[22,59],"structure.":[23],"Our":[24],"predicts":[26],"affinity":[28],"by":[29,35,146],"using":[30],"regression":[31,86,137],"substructures":[33,79],"discovered":[34],"relational":[36,66],"learning.":[37],"make":[39],"two":[40],"contributions":[41],"state-of-the-art.":[44],"First,":[45],"we":[46],"use":[47],"multiple-instance":[48],"(MI)":[49],"regression,":[50,119],"which":[51],"represents":[52],"molecule":[54],"as":[55],"set":[57],"conformations,":[60],"model":[62],"activity.":[63],"Second,":[64],"component":[68],"employs":[69],"\"Score":[71],"As":[72],"You":[73],"Use\"":[74],"(SAYU)":[75],"method":[76],"select":[78],"their":[81],"ability":[82],"improve":[84],"model.":[87],"This":[88],"is":[89,138],"first":[91],"application":[92],"SAYU":[94,110,134],"multiple-instance,":[96],"real-valued":[97],"prediction.":[98],"evaluate":[100],"our":[101],"three":[104],"tasks":[105],"and":[106,131],"demonstrate":[107],"that":[108],"(i)":[109],"outperforms":[111],"standard":[112,127],"coverage":[113],"measures":[114],"when":[115],"selecting":[116],"features":[117],"(ii)":[120],"MI":[122,136],"representation":[123],"improves":[124],"accuracy":[125],"over":[126],"single":[128],"feature-vector":[129],"encodings":[130],"(iii)":[132],"combining":[133],"with":[135],"more":[139],"accurate":[140],"3D-QSAR":[142],"than":[143],"either":[144],"itself.":[147]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}