{"id":"https://openalex.org/W2803094965","doi":"https://doi.org/10.1021/acs.jcim.7b00403","title":"Most Ligand-Based Classification Benchmarks Reward Memorization Rather than Generalization","display_name":"Most Ligand-Based Classification Benchmarks Reward Memorization Rather than Generalization","publication_year":2018,"publication_date":"2018-04-26","ids":{"openalex":"https://openalex.org/W2803094965","doi":"https://doi.org/10.1021/acs.jcim.7b00403","mag":"2803094965","pmid":"https://pubmed.ncbi.nlm.nih.gov/29698607"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.7b00403","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.7b00403","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":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1706.06619","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Izhar Wallach","orcid":"https://orcid.org/0000-0002-7212-3048"},"institutions":[{"id":"https://openalex.org/I4210128108","display_name":"Healthwise","ror":"https://ror.org/0379w2016","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210128108"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Izhar Wallach","raw_affiliation_strings":["Atomwise Inc., 221 Main Street, Suite 1350, San Francisco, California 94105, United States"],"affiliations":[{"raw_affiliation_string":"Atomwise Inc., 221 Main Street, Suite 1350, San Francisco, California 94105, United States","institution_ids":["https://openalex.org/I4210128108"]}]},{"author_position":"last","author":{"id":null,"display_name":"Abraham Heifets","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128108","display_name":"Healthwise","ror":"https://ror.org/0379w2016","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210128108"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abraham Heifets","raw_affiliation_strings":["Atomwise Inc., 221 Main Street, Suite 1350, San Francisco, California 94105, United States"],"affiliations":[{"raw_affiliation_string":"Atomwise Inc., 221 Main Street, Suite 1350, San Francisco, California 94105, United States","institution_ids":["https://openalex.org/I4210128108"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210128108"],"apc_list":null,"apc_paid":null,"fwci":18.1674,"has_fulltext":false,"cited_by_count":190,"citation_normalized_percentile":{"value":0.99491018,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"58","issue":"5","first_page":"916","last_page":"932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9456999897956848,"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":0.9456999897956848,"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":0.023099999874830246,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.005799999926239252,"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/overfitting","display_name":"Overfitting","score":0.8859000205993652},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6328999996185303},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6301000118255615},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5382000207901001},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.49889999628067017},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.478300005197525},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.42260000109672546}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8859000205993652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6705999970436096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6546000242233276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6367999911308289},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6328999996185303},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6301000118255615},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.49889999628067017},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.39169999957084656},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36419999599456787},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.32589998841285706},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2533999979496002},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2529999911785126}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.7b00403","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.7b00403","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:29698607","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29698607","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:arXiv.org:1706.06619","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1706.06619","pdf_url":"https://arxiv.org/pdf/1706.06619","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:1706.06619","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1706.06619","pdf_url":"https://arxiv.org/pdf/1706.06619","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1822127850","https://openalex.org/W1964513093","https://openalex.org/W1968319881","https://openalex.org/W1975875968","https://openalex.org/W1984480244","https://openalex.org/W1988037271","https://openalex.org/W1996722392","https://openalex.org/W1999798000","https://openalex.org/W2013520570","https://openalex.org/W2021748110","https://openalex.org/W2026910177","https://openalex.org/W2027376226","https://openalex.org/W2034553680","https://openalex.org/W2039526577","https://openalex.org/W2058820833","https://openalex.org/W2060531713","https://openalex.org/W2070789802","https://openalex.org/W2083339697","https://openalex.org/W2084512114","https://openalex.org/W2088436166","https://openalex.org/W2088970363","https://openalex.org/W2090277229","https://openalex.org/W2096560421","https://openalex.org/W2097472327","https://openalex.org/W2114704115","https://openalex.org/W2145578524","https://openalex.org/W2158703410","https://openalex.org/W2200017991","https://openalex.org/W2208175234","https://openalex.org/W2290847742","https://openalex.org/W2329862012","https://openalex.org/W2714724074"],"related_works":[],"abstract_inverted_index":{"Undetected":[0],"overfitting":[1,102],"can":[2,98],"occur":[3],"when":[4],"there":[5],"are":[6],"significant":[7],"redundancies":[8],"between":[9],"training":[10],"and":[11,49,51],"validation":[12],"data.":[13],"We":[14,40],"describe":[15],"AVE,":[16],"a":[17],"new":[18],"measure":[19],"of":[20,57,65,70,94],"training-validation":[21],"redundancy":[22],"for":[23,29,46],"ligand-based":[24,66,96],"classification":[25],"problems,":[26],"that":[27,54,89],"accounts":[28],"the":[30,55,63,71,87,90],"similarity":[31,76],"among":[32],"inactive":[33],"molecules":[34],"as":[35,37],"well":[36],"active":[38],"ones.":[39],"investigated":[41],"seven":[42],"widely":[43],"used":[44],"benchmarks":[45,104],"virtual":[47],"screening":[48],"classification,":[50],"we":[52],"show":[53],"amount":[56],"AVE":[58],"bias":[59],"strongly":[60],"correlates":[61],"with":[62],"performance":[64,93],"predictive":[67],"methods":[68,97],"irrespective":[69],"predicted":[72],"property,":[73],"chemical":[74],"fingerprint,":[75],"measure,":[77],"or":[78],"previously":[79,91],"applied":[80],"unbiasing":[81],"techniques.":[82],"Therefore,":[83],"it":[84],"may":[85],"be":[86,99],"case":[88],"reported":[92],"most":[95],"explained":[100],"by":[101],"to":[103],"rather":[105],"than":[106],"good":[107],"prospective":[108],"accuracy.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":41},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":5}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2018-05-17T00:00:00"}