{"id":"https://openalex.org/W7225812649","doi":"https://doi.org/10.26434/chemrxiv.15011962/v1","title":"A knowledge-aware, constraint-guaranteed decoder for cyclic peptides","display_name":"A knowledge-aware, constraint-guaranteed decoder for cyclic peptides","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225812649","doi":"https://doi.org/10.26434/chemrxiv.15011962/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15011962/v1","doi":"https://doi.org/10.26434/chemrxiv.15011962/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011962/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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"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.15011962/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138262802","display_name":"Yaoyun Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1313298211","display_name":"St. Jude Children's Research Hospital","ror":"https://ror.org/02r3e0967","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1313298211","https://openalex.org/I2802152183"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaoyun Zhang","raw_affiliation_strings":["BioMate AI, LLC","Department of Structural Biology","St.\u00a0Jude Children\u2019s Research Hospital"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BioMate AI, LLC","institution_ids":[]},{"raw_affiliation_string":"Department of Structural Biology","institution_ids":[]},{"raw_affiliation_string":"St.\u00a0Jude Children\u2019s Research Hospital","institution_ids":["https://openalex.org/I1313298211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005579107","display_name":"Xingyao Li","orcid":"https://orcid.org/0000-0002-9820-8664","observed_orcids":["https://orcid.org/0000-0002-9820-8664"]},"institutions":[{"id":"https://openalex.org/I1343551460","display_name":"The University of Texas MD Anderson Cancer Center","ror":"https://ror.org/04twxam07","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1343551460"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingyao Li","raw_affiliation_strings":["Department of Gastrointestinal Medical Oncology","University of Texas MD Anderson Cancer Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Gastrointestinal Medical Oncology","institution_ids":[]},{"raw_affiliation_string":"University of Texas MD Anderson Cancer Center","institution_ids":["https://openalex.org/I1343551460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161334771","display_name":"Yuhan Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1313298211","display_name":"St. Jude Children's Research Hospital","ror":"https://ror.org/02r3e0967","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1313298211","https://openalex.org/I2802152183"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhan Zhang","raw_affiliation_strings":["BioMate AI, LLC","Department of Structural Biology","St.\u00a0Jude Children\u2019s Research Hospital"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BioMate AI, LLC","institution_ids":[]},{"raw_affiliation_string":"Department of Structural Biology","institution_ids":[]},{"raw_affiliation_string":"St.\u00a0Jude Children\u2019s Research Hospital","institution_ids":["https://openalex.org/I1313298211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5161307784","display_name":"Andrew Dike","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Dike","raw_affiliation_strings":["BioMate AI, LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BioMate AI, LLC","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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/T10911","display_name":"Chemical Synthesis and Analysis","score":0.6675000190734863,"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"}},"topics":[{"id":"https://openalex.org/T10911","display_name":"Chemical Synthesis and Analysis","score":0.6675000190734863,"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"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.3197999894618988,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.0020000000949949026,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5978999733924866},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.5471000075340271},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5253999829292297},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4519999921321869},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4074000120162964},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3734999895095825},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3443000018596649},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3400999903678894},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.33880001306533813},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C21951064","wikidata":"https://www.wikidata.org/wiki/Q899212","display_name":"Combinatorial chemistry","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3280999958515167},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3086000084877014},{"id":"https://openalex.org/C60984968","wikidata":"https://www.wikidata.org/wiki/Q389172","display_name":"Cyclic peptide","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C166940927","wikidata":"https://www.wikidata.org/wiki/Q178827","display_name":"Monomer","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C120882062","wikidata":"https://www.wikidata.org/wiki/Q28352","display_name":"Permeability (electromagnetism)","level":3,"score":0.27889999747276306}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15011962/v1","doi":"https://doi.org/10.26434/chemrxiv.15011962/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011962/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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15011962/v1","doi":"https://doi.org/10.26434/chemrxiv.15011962/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011962/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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cyclic":[0],"peptides":[1,45],"reach":[2],"a":[3,32,47,51,108,118,140,161,177,219],"prized":[4],"middle":[5],"ground":[6],"between":[7],"small":[8],"molecules":[9,174],"and":[10,40,60,186],"biologics:":[11],"large":[12,67],"enough":[13,27],"to":[14,28,68,80,214],"grip":[15],"the":[16,91,123,128,196,206,215],"flat":[17],"protein\u2013protein":[18],"interfaces":[19],"that":[20,63,93,121,217],"defeat":[21],"conventional":[22],"drugs,":[23],"yet":[24],"sometimes":[25],"lipophilic":[26],"be":[29,212,240],"taken":[30],"as":[31,170,175,191],"pill.":[33],"Deep":[34],"generative":[35],"models":[36,73],"have":[37],"transformed":[38],"small-molecule":[39],"protein":[41],"design,":[42],"but":[43],"cyclic":[44],"are":[46,77,83,154],"harder":[48],"frontier,":[49],"with":[50,98],"design":[52,124,238],"space":[53],"of":[54,209],"non-canonical":[55],"residues,":[56],"N-methylation,":[57],"D-amino":[58],"acids":[59],"macrocyclic":[61],"rings":[62],"is":[64,201,232],"far":[65],"too":[66],"search":[69],"by":[70,86,90,137],"hand.":[71],"The":[72,150],"built":[74],"for":[75,195],"it":[76,133,144,165],"also":[78,145],"hard":[79],"evaluate:":[81],"they":[82],"often":[84],"scored":[85],"distribution":[87],"metrics,":[88],"judged":[89],"predictor":[92],"trained":[94],"them,":[95],"or":[96],"compared":[97],"untuned":[99],"baselines":[100,159],"at":[101,160],"unequal":[102],"budgets":[103],"\u2014":[104,222,230],"tests":[105],"on":[106],"which":[107,231],"weak":[109],"method":[110],"can":[111,211],"look":[112],"strong.":[113],"Here":[114],"we":[115],"present":[116],"IH-LM,":[117],"cyclic-peptide":[119,237],"generator":[120],"compiles":[122],"rules":[125],"directly":[126],"into":[127],"decoder,":[129],"so":[130],"every":[131],"molecule":[132],"completes":[134],"satisfies":[135],"them":[136],"construction;":[138],"across":[139],"900-molecule":[141],"test":[142],"set":[143],"discarded":[146],"no":[147],"rule-satisfying":[148],"string.":[149],"preliminary":[151],"experimental":[152],"results":[153],"promising.":[155],"Benchmarked":[156],"against":[157],"tuned":[158],"matched":[162],"sampling":[163],"budget,":[164],"produces":[166],"about":[167,188],"three":[168,189],"times":[169,190],"many":[171,192],"valid,":[172],"novel":[173],"enumerating":[176],"monomer":[178],"library":[179],"(773":[180],"versus":[181],"246":[182],"per":[183],"1,000":[184],"samples)":[185],"spans":[187],"distinct":[193],"scaffolds":[194],"same":[197],"effort.":[198],"Because":[199],"validity":[200],"guaranteed":[202],"rather":[203],"than":[204],"scored,":[205],"full":[207],"strength":[208],"evaluation":[210],"devoted":[213],"properties":[216],"decide":[218],"candidate\u2019s":[220],"fate":[221],"chemical":[223],"diversity,":[224],"permeability":[225],"and,":[226],"ultimately,":[227],"target":[228],"activity":[229],"where":[233],"real":[234],"progress":[235],"in":[236],"will":[239],"won.":[241]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}
