{"id":"https://openalex.org/W7225374233","doi":"https://doi.org/10.58257/ijprems55091","title":"A RAG-CONDITIONED MODEL FOR DE NOVO MOLECULAR GENERATION USING SAFE","display_name":"A RAG-CONDITIONED MODEL FOR DE NOVO MOLECULAR GENERATION USING SAFE","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225374233","doi":"https://doi.org/10.58257/ijprems55091"},"language":"en","primary_location":{"id":"doi:10.58257/ijprems55091","doi":"https://doi.org/10.58257/ijprems55091","is_oa":true,"landing_page_url":"https://doi.org/10.58257/ijprems55091","pdf_url":"https://doi.org/10.58257/ijprems55091","source":{"id":"https://openalex.org/S4387284908","display_name":"International Journal of Progressive Research in Engineering Management and Science","issn_l":"2583-1062","issn":["2583-1062"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Progressive Research in Engineering Management and Science","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.58257/ijprems55091","any_repository_has_fulltext":false},"authorships":[],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.0003000000142492354,"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/T14099","display_name":"Synthesis and Characterization of Heterocyclic Compounds","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1605","display_name":"Organic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/de-novo-molecular-generation","display_name":"de novo molecular generation","score":0.9660000205039978},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9900000095367432},{"id":"https://openalex.org/keywords/smiles-generation","display_name":"SMILES generation","score":0.7020000219345093},{"id":"https://openalex.org/keywords/chemical-validity","display_name":"chemical validity","score":0.6669999957084656},{"id":"https://openalex.org/keywords/drug-like-molecules","display_name":"drug-like molecules","score":0.574999988079071},{"id":"https://openalex.org/keywords/quantum-electrodynamics","display_name":"quantum electrodynamics","score":0.5649999976158142},{"id":"https://openalex.org/keywords/octanol-water-partition-coefficient","display_name":"octanol-water partition coefficient","score":0.8550000190734863},{"id":"https://openalex.org/keywords/synthetic-accessibility","display_name":"synthetic accessibility","score":0.8600000143051147},{"id":"https://openalex.org/keywords/beam-search","display_name":"beam search","score":0.6639999747276306}],"concepts":[{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.8392999768257141},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.6687999963760376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5250999927520752},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4625999927520752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45210000872612},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.4302000105381012},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4092000126838684},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C2780557392","wikidata":"https://www.wikidata.org/wiki/Q523796","display_name":"Linker","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.38179999589920044},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C161624437","wikidata":"https://www.wikidata.org/wiki/Q1988322","display_name":"Small molecule","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C2994228675","wikidata":"https://www.wikidata.org/wiki/Q512599","display_name":"Property value","level":3,"score":0.3407000005245209},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33230000734329224},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.28999999165534973},{"id":"https://openalex.org/C71240020","wikidata":"https://www.wikidata.org/wiki/Q186011","display_name":"Stereochemistry","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2700999975204468},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C21951064","wikidata":"https://www.wikidata.org/wiki/Q899212","display_name":"Combinatorial chemistry","level":1,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.58257/ijprems55091","doi":"https://doi.org/10.58257/ijprems55091","is_oa":true,"landing_page_url":"https://doi.org/10.58257/ijprems55091","pdf_url":"https://doi.org/10.58257/ijprems55091","source":{"id":"https://openalex.org/S4387284908","display_name":"International Journal of Progressive Research in Engineering Management and Science","issn_l":"2583-1062","issn":["2583-1062"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Progressive Research in Engineering Management and Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.58257/ijprems55091","doi":"https://doi.org/10.58257/ijprems55091","is_oa":true,"landing_page_url":"https://doi.org/10.58257/ijprems55091","pdf_url":"https://doi.org/10.58257/ijprems55091","source":{"id":"https://openalex.org/S4387284908","display_name":"International Journal of Progressive Research in Engineering Management and Science","issn_l":"2583-1062","issn":["2583-1062"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Progressive Research in Engineering Management and Science","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225374233.pdf","grobid_xml":"https://content.openalex.org/works/W7225374233.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415800720","https://openalex.org/W7164184120","https://openalex.org/W7213278533","https://openalex.org/W4400320632","https://openalex.org/W3216027012","https://openalex.org/W4401090344","https://openalex.org/W7165962694","https://openalex.org/W7124853081","https://openalex.org/W7084040993","https://openalex.org/W3007702560"],"abstract_inverted_index":{"De":[0],"novo":[1],"molecular":[2,60,142],"generation":[3,82,90],"aims":[4],"to":[5,35,91],"produce":[6],"drug-like":[7,157],"compounds":[8],"with":[9,64,156],"desirable":[10],"pharmacological":[11],"properties.Most":[12],"generative":[13],"models,":[14],"however,":[15],"offer":[16],"limited":[17],"contextual":[18],"conditioning":[19],"or":[20],"ignore":[21],"fragment-fragment":[22],"interactions":[23],"during":[24,89],"synthesis,":[25],"so":[26],"combinations":[27],"of":[28,79,98,121,132,137,144],"individually":[29],"promising":[30],"fragments":[31,104,127,153],"often":[32],"turn":[33],"out":[34],"be":[36],"chemically":[37],"unsatisfactory.To":[38],"address":[39],"these":[40],"issues,":[41],"this":[42],"paper":[43],"presents":[44],"a":[45],"Retrieval-Augmented":[46],"Generation":[47],"(RAG)":[48],"conditioned":[49],"system":[50],"that":[51,149],"uses":[52,86],"SAFE-GPT":[53],"(Sequential":[54],"Attachment-based":[55],"Fragment":[56],"Embedding)":[57],"for":[58],"SMILES-based":[59],"design.To":[61],"balance":[62],"novelty":[63],"chemical":[65,94,158],"validity,":[66],"the":[67,80,108,117,122],"framework":[68],"combines":[69],"interaction-aware":[70,164],"fragment":[71,96,113],"scoring,":[72],"conditional":[73],"dataset":[74,110],"sampling":[75],"and":[76,84,102,111,139,169,174,179],"controlled":[77],"adjustment":[78],"SAFE":[81],"settings,":[83],"it":[85],"beam":[87],"search":[88],"explore":[92],"high-scoring":[93],"routes.A":[95],"vocabulary":[97],"5,612":[99],"unique":[100],"arm":[101],"linker":[103],"was":[105,114],"built":[106],"from":[107],"ZINC250K":[109],"each":[112],"scored":[115],"by":[116],"average":[118,130,135,141],"property":[119,170],"value":[120],"molecules":[123],"containing":[124],"it.The":[125],"retrieved":[126],"have":[128],"an":[129,134,140],"QED":[131],"0.5688,":[133],"logP":[136,173],"0.6874":[138],"weight":[143],"151.16":[145],"Da,":[146],"which":[147],"shows":[148],"property-based":[150],"scoring":[151,165],"ranks":[152],"in":[154],"line":[155],"space.Planned":[159],"experiments":[160],"will":[161],"test":[162],"whether":[163],"improves":[166],"diversity,":[167],"validity":[168],"optimisation":[171],"(QED,":[172],"synthetic":[175],"accessibility)":[176],"over":[177],"fragment-based":[178],"non-retrieval":[180],"baselines.":[181]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}