{"id":"https://openalex.org/W6888568552","doi":"https://doi.org/10.21227/8zmv-e285","title":"High drug-likeness (QED>0.9) dataset 2 million molecues","display_name":"High drug-likeness (QED>0.9) dataset 2 million molecues","publication_year":2024,"publication_date":"2024-06-06","ids":{"openalex":"https://openalex.org/W6888568552","doi":"https://doi.org/10.21227/8zmv-e285"},"language":"en","primary_location":{"id":"doi:10.21227/8zmv-e285","is_oa":true,"landing_page_url":"https://doi.org/10.21227/8zmv-e285","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/8zmv-e285","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xing, Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xing, Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5335000157356262},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.3677999973297119},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.3005000054836273},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.2736999988555908},{"id":"https://openalex.org/keywords/conditional-probability","display_name":"Conditional probability","score":0.2660999894142151}],"concepts":[{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5335000157356262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5241000056266785},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.3677999973297119},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32190001010894775},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29840001463890076},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2904999852180481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C64903051","wikidata":"https://www.wikidata.org/wiki/Q2198549","display_name":"Drug development","level":3,"score":0.25619998574256897},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/8zmv-e285","is_oa":true,"landing_page_url":"https://doi.org/10.21227/8zmv-e285","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.21227/8zmv-e285","is_oa":true,"landing_page_url":"https://doi.org/10.21227/8zmv-e285","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"<h1>Development":[0],"and":[1,15,99],"Evaluation":[2],"of":[3,17,29,47,55,75],"a":[4,18,71,82],"Novel":[5],"GPT-like":[6,20],"Conditional":[7],"Molecule":[8],"Generator</h1><p> ":[9],"This":[10,87],"study":[11],"presents":[12],"the":[13,27,67,92],"development":[14],"evaluation":[16],"novel":[19],"conditional":[21],"molecule":[22],"generator":[23,68],"designed":[24],"to":[25],"optimize":[26],"synthesis":[28],"chemical":[30],"compounds":[31],"with":[32],"desirable":[33],"properties.":[34],"The":[35],"model":[36],"incorporates":[37],"six":[38],"pivotal":[39],"physicochemical":[40],"properties":[41],"as":[42],"conditions:</p><ul> ":[43],"<li>Molecular":[44],"weight</li> ":[45],"<li>Number":[46],"non-hydrogen":[48],"atoms</li> ":[49],"<li>Ring":[50],"count</li> ":[51],"<li>Hydrophobicity</li> ":[52],"<li>Quantitative":[53],"estimation":[54],"drug-likeness":[56],"(<em>QED</em>)</li> ":[57],"<li>Synthetic":[58],"accessibility":[59],"score":[60],"(<em>SAS</em>)</li></ul><p> ":[61],"By":[62],"integrating":[63],"these":[64],"specific":[65],"attributes,":[66],"successfully":[69],"produced":[70],"high-QED":[72],"database,":[73],"consisting":[74],"approximately":[76],"2":[77],"million":[78],"molecules,":[79],"all":[80],"exhibiting":[81],"QED":[83],"higher":[84],"than":[85],"0.9.":[86],"achievement":[88],"not":[89],"only":[90],"demonstrates":[91],"model's":[93],"effectiveness":[94],"in":[95,109],"generating":[96],"structurally":[97],"diverse":[98],"potentially":[100],"pharmacologically":[101],"viable":[102],"molecules":[103],"but":[104],"also":[105],"underscores":[106],"its":[107],"utility":[108],"accelerating":[110],"drug":[111],"discovery":[112],"processes.</p>":[113]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}