{"id":"https://openalex.org/W7221636626","doi":"https://doi.org/10.26434/chemrxiv.15010348/v1","title":"Structure-Independent Genetic Algorithm-Based Molecular Optimization Using Pocket-Aware Molecular Representations","display_name":"Structure-Independent Genetic Algorithm-Based Molecular Optimization Using Pocket-Aware Molecular Representations","publication_year":2026,"publication_date":"2026-10-13","ids":{"openalex":"https://openalex.org/W7221636626","doi":"https://doi.org/10.26434/chemrxiv.15010348/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15010348/v1","doi":"https://doi.org/10.26434/chemrxiv.15010348/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010348/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"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":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.26434/chemrxiv.15010348/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5158605441","display_name":"Abhishek Kumar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhishek Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330194","display_name":"Hyun Woo Kim","orcid":"https://orcid.org/0000-0002-2472-2046","observed_orcids":["https://orcid.org/0000-0002-2472-2046"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyun Woo Kim","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2472-2046","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":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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":0.0,"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-design","display_name":"de novo molecular design","score":0.9039999842643738},{"id":"https://openalex.org/keywords/structure-activity-relationship","display_name":"structure-activity relationship","score":0.9190000295639038},{"id":"https://openalex.org/keywords/kriging-surrogate-model","display_name":"Kriging surrogate model","score":0.7680000066757202},{"id":"https://openalex.org/keywords/bace1","display_name":"BACE1","score":0.6990000009536743},{"id":"https://openalex.org/keywords/scaffold-diversity","display_name":"scaffold diversity","score":0.6140000224113464},{"id":"https://openalex.org/keywords/solvent-accessible-surface-area","display_name":"solvent accessible surface area","score":0.8500000238418579},{"id":"https://openalex.org/keywords/kinase-inhibitors","display_name":"kinase inhibitors","score":0.5860000252723694},{"id":"https://openalex.org/keywords/serine-protease-inhibitors","display_name":"serine protease inhibitors","score":0.9169999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6409000158309937},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.40639999508857727},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3919999897480011},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35929998755455017},{"id":"https://openalex.org/C166393388","wikidata":"https://www.wikidata.org/wiki/Q856529","display_name":"Molecular evolution","level":4,"score":0.3422999978065491},{"id":"https://openalex.org/C178910836","wikidata":"https://www.wikidata.org/wiki/Q2196961","display_name":"Molecular model","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3091999888420105},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.3089999854564667},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3075999915599823},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.28630000352859497},{"id":"https://openalex.org/C179303850","wikidata":"https://www.wikidata.org/wiki/Q4300362","display_name":"Molecular recognition","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15010348/v1","doi":"https://doi.org/10.26434/chemrxiv.15010348/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010348/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"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":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15010348/v1","doi":"https://doi.org/10.26434/chemrxiv.15010348/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010348/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"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":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414359247","https://openalex.org/W4399912004","https://openalex.org/W1988548997","https://openalex.org/W7211865481","https://openalex.org/W7097616431","https://openalex.org/W3213118454","https://openalex.org/W7032975839","https://openalex.org/W7160962612","https://openalex.org/W2737188397","https://openalex.org/W2025277814"],"abstract_inverted_index":{"De":[0],"novo":[1,150],"molecular":[2,25,32,46,74,133,151,163,186,198,240],"design":[3,152,164],"typically":[4],"depends":[5],"on":[6,83,115],"target":[7,66,155],"structures":[8,47,178],"or":[9,179],"ligand":[10,180],"poses,":[11],"limiting":[12],"its":[13],"applicability":[14],"when":[15],"structural":[16,107,217],"information":[17],"is":[18],"unavailable.":[19],"Here,":[20],"we":[21],"introduce":[22],"the":[23,68,229],"pocket-aware":[24,37,185],"representation-guided":[26],"genetic":[27,72],"algorithm":[28],"(PAMR-GA),":[29],"a":[30,77,120,140,184,234],"target-structure-independent":[31],"optimization":[33,75,99],"framework":[34,237],"that":[35,86,188,207],"learns":[36],"representations":[38,70],"from":[39,62,170,224],"structure\u2013activity":[40,172],"relationship":[41,173],"(SAR)":[42],"data":[43],"using":[44],"only":[45],"represented":[48],"as":[49,139,233],"SMILES":[50],"strings":[51],"and":[52,94,109,124,193],"experimental":[53],"pIC50":[54],"values.":[55],"By":[56,182],"encoding":[57],"latent":[58],"spatial":[59,146],"constraints":[60,147,168],"inferred":[61],"SAR":[63],"without":[64,153,175],"requiring":[65,154,176],"structures,":[67],"learned":[69],"guide":[71],"algorithm-based":[73],"through":[76],"Gaussian":[78],"process":[79],"surrogate":[80],"model.":[81],"Benchmarking":[82],"BACE-1":[84],"demonstrated":[85],"PAMR-GA":[87,138,160,196,232],"achieved":[88],"comparable":[89],"predictive":[90],"performance,":[91],"docking":[92],"scores,":[93],"drug-likeness":[95],"profiles":[96],"to":[97],"existing":[98],"approaches":[100],"while":[101],"generating":[102],"molecules":[103],"with":[104,200],"substantially":[105],"greater":[106],"novelty":[108],"higher":[110],"Murcko":[111],"scaffold":[112],"diversity.":[113],"Evaluation":[114,219],"four":[116,225],"additional":[117],"targets,":[118],"including":[119],"kinase,":[121],"serine":[122],"proteases,":[123],"an":[125],"NADbinding":[126],"enzyme,":[127],"further":[128],"showed":[129],"consistent":[130],"improvements":[131],"in":[132],"novelty.":[134,218],"These":[135],"results":[136,205],"highlight":[137],"complementary":[141],"approach":[142],"for":[143,238],"incorporating":[144],"SAR-derived":[145],"into":[148],"de":[149],"structures.":[156],"1":[157],"Scientific":[158],"Contribution":[159],"enables":[161],"structure-independent":[162],"by":[165],"learning":[166],"binding":[167,202],"implicitly":[169],"2D":[171],"data,":[174],"protein":[177,226],"poses.":[181],"introducing":[183],"representation":[187],"integrates":[189],"solvent-accessible":[190],"surface":[191],"area":[192],"partial-charge":[194],"features,":[195],"bridges":[197],"topology":[199],"3D":[201],"compatibility.":[203],"Our":[204],"demonstrate":[206],"constrained":[208],"generation,":[209],"rather":[210],"than":[211],"improved":[212],"activity":[213],"prediction":[214],"alone,":[215],"drives":[216],"across":[220],"five":[221],"diverse":[222],"targets":[223],"classes":[227],"highlights":[228],"generalizability":[230],"of":[231],"broadly":[235],"applicable":[236],"target-aware":[239],"design.":[241]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-14T00:00:00"}