{"id":"https://openalex.org/W7224952622","doi":"https://doi.org/10.26434/chemrxiv.15011316/v1","title":"Folding and Function as Two Sides of One Coin: Statistical Mechanics, Information Theory, and Deep Learning of Binding, Catalysis, and Allostery in an Exactly Enumerable Lattice Protein","display_name":"Folding and Function as Two Sides of One Coin: Statistical Mechanics, Information Theory, and Deep Learning of Binding, Catalysis, and Allostery in an Exactly Enumerable Lattice Protein","publication_year":2026,"publication_date":"2026-10-30","ids":{"openalex":"https://openalex.org/W7224952622","doi":"https://doi.org/10.26434/chemrxiv.15011316/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15011316/v1","doi":"https://doi.org/10.26434/chemrxiv.15011316/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011316/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011316/v1","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011316/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062471687","display_name":"Shubin Liu","orcid":"https://orcid.org/0000-0001-9331-0427","observed_orcids":["https://orcid.org/0000-0001-9331-0427"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shubin Liu","raw_affiliation_strings":["Department of Chemistry","Research Computing Center","University of North Carolina"],"raw_orcid":"https://orcid.org/0000-0001-9331-0427","affiliations":[{"raw_affiliation_string":"Department of Chemistry","institution_ids":[]},{"raw_affiliation_string":"Research Computing Center","institution_ids":[]},{"raw_affiliation_string":"University of North Carolina","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5062471687"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9965999722480774,"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"}},"topics":[{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9965999722480774,"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"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.0017999999690800905,"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"}},{"id":"https://openalex.org/T10911","display_name":"Chemical Synthesis and Analysis","score":0.0003000000142492354,"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":[{"id":"https://openalex.org/keywords/lattice-proteins","display_name":"lattice proteins","score":0.7480000257492065},{"id":"https://openalex.org/keywords/protein-folding","display_name":"protein folding","score":0.8180000185966492},{"id":"https://openalex.org/keywords/protein-function","display_name":"protein function","score":0.8820000290870667},{"id":"https://openalex.org/keywords/binding","display_name":"binding","score":0.4359999895095825},{"id":"https://openalex.org/keywords/catalysis","display_name":"catalysis","score":0.9879999756813049},{"id":"https://openalex.org/keywords/allosteric-regulation","display_name":"allosteric regulation","score":0.921999990940094},{"id":"https://openalex.org/keywords/conformational-ensembles","display_name":"conformational ensembles","score":0.8410000205039978},{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.8169999718666077},{"id":"https://openalex.org/keywords/renyi-divergence","display_name":"R\u00e9nyi divergence","score":0.9100000262260437},{"id":"https://openalex.org/keywords/allosteric-communication","display_name":"allosteric communication","score":0.8479999899864197},{"id":"https://openalex.org/keywords/sequence-design","display_name":"sequence design","score":0.531000018119812}],"concepts":[{"id":"https://openalex.org/C166342909","wikidata":"https://www.wikidata.org/wiki/Q845326","display_name":"Allosteric regulation","level":3,"score":0.8877000212669373},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5688999891281128},{"id":"https://openalex.org/C109964505","wikidata":"https://www.wikidata.org/wiki/Q3321436","display_name":"Allosteric enzyme","level":4,"score":0.5526000261306763},{"id":"https://openalex.org/C204328495","wikidata":"https://www.wikidata.org/wiki/Q847556","display_name":"Protein folding","level":2,"score":0.4293999969959259},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4011000096797943},{"id":"https://openalex.org/C2776545253","wikidata":"https://www.wikidata.org/wiki/Q5464292","display_name":"Folding (DSP implementation)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.37130001187324524},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C166014724","wikidata":"https://www.wikidata.org/wiki/Q337217","display_name":"Cooperativity","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C152769699","wikidata":"https://www.wikidata.org/wiki/Q410814","display_name":"Protein design","level":3,"score":0.3400999903678894},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3174000084400177},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3005000054836273},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C162838799","wikidata":"https://www.wikidata.org/wiki/Q596077","display_name":"Counterexample","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28859999775886536},{"id":"https://openalex.org/C107824862","wikidata":"https://www.wikidata.org/wiki/Q616005","display_name":"Binding site","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27160000801086426},{"id":"https://openalex.org/C51639874","wikidata":"https://www.wikidata.org/wiki/Q167149","display_name":"Plasma protein binding","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15011316/v1","doi":"https://doi.org/10.26434/chemrxiv.15011316/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011316/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011316/v1","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15011316/v1","doi":"https://doi.org/10.26434/chemrxiv.15011316/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011316/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011316/v1","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224952622.pdf","grobid_xml":"https://content.openalex.org/works/W7224952622.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W1959608418"],"related_works":["https://openalex.org/W7224175749","https://openalex.org/W2164581268","https://openalex.org/W2060935724","https://openalex.org/W2072843928","https://openalex.org/W2807573182","https://openalex.org/W2006115567","https://openalex.org/W1978741482","https://openalex.org/W2002584752","https://openalex.org/W2606064117","https://openalex.org/W4324354220"],"abstract_inverted_index":{"Folding":[0],"and":[1,38,48,58,70,110,141,159,163,199,202],"function":[2],"depend":[3],"on":[4,138],"the":[5,14,124,127,139],"same":[6,15],"conformational":[7,64],"ensemble,":[8],"but":[9,166],"they":[10],"need":[11],"not":[12,167],"favor":[13,73],"population":[16,49,94,204,209],"distribution.":[17],"We":[18],"examine":[19],"this":[20],"relationship":[21,195],"in":[22,56,176],"a":[23,63,74,84,91,193],"27-residue":[24],"lattice":[25],"protein":[26],"with":[27,83,98,102],"103,346":[28],"exactly":[29],"enumerated":[30],"compact":[31,76],"conformations,":[32],"combining":[33],"statistical":[34],"mechanics,":[35],"information-theoretic":[36],"analysis,":[37],"variational":[39],"autoencoders.":[40],"Exact":[41],"identities":[42],"separate":[43],"binding":[44,69,109,130,162],"into":[45],"native-site":[46],"recognition":[47,207],"terms,":[50],"distinguish":[51,203],"transition-state":[52],"complementarity":[53],"from":[54,126,208],"reorganization":[55],"catalysis,":[57],"express":[59],"allosteric":[60,134,168,178,212],"coupling":[61,88,135],"as":[62],"covariance.":[65],"Under":[66],"composition-conserving":[67],"selection,":[68],"turnover":[71],"optimization":[72,89],"dominant":[75],"fold,":[77],"whereas":[78],"strong":[79],"allostery":[80],"can":[81],"coexist":[82],"distributed":[85],"ensemble:":[86],"pure":[87],"gives":[90],"median":[92],"native":[93],"of":[95,143,185],"0.47,":[96],"compared":[97],"0.85":[99],"when":[100],"designs":[101],"additional":[103,173],"stability":[104],"rewards":[105],"are":[106],"pooled.":[107],"Composition-free":[108],"catalytic":[111,164],"selection":[112,198],"provide":[113],"further":[114],"counterexamples":[115],"to":[116],"an":[117,156],"unconditional":[118],"function-to-folding":[119],"implication.":[120],"R\u00e9nyi":[121],"divergences":[122],"quantify":[123],"shortfall":[125],"best":[128],"available":[129],"or":[131],"transition-state-recognition":[132],"conformation;":[133],"instead":[136],"depends":[137],"magnitude":[140],"alignment":[142],"two":[144],"ligand-induced":[145],"responses.":[146],"A":[147],"sequence":[148],"VAE":[149],"generates":[150],"target-fold-compatible":[151],"sequences":[152],"more":[153],"frequently":[154],"than":[155],"independent-site":[157],"baseline":[158],"partially":[160],"retains":[161],"properties,":[165],"coupling.":[169],"Time-lagged":[170],"VAEs":[171],"resolve":[172],"basin":[174],"information":[175],"selected":[177],"trajectories,":[179],"although":[180],"incomplete":[181],"interconversion":[182],"prevents":[183],"inference":[184],"equilibrium":[186],"switching":[187],"kinetics.":[188],"Together,":[189],"these":[190],"results":[191],"identify":[192],"conditional":[194],"between":[196],"functional":[197],"fold":[200],"specificity,":[201],"concentration":[205],"for":[206,211],"redistribution":[210],"communication.":[213]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-31T00:00:00"}
