{"id":"https://openalex.org/W7207531159","doi":"https://doi.org/10.26434/chemrxiv.15008225/v1","title":"Population-aware Generative Modeling of Lignin Ensemble","display_name":"Population-aware Generative Modeling of Lignin Ensemble","publication_year":2026,"publication_date":"2026-09-02","ids":{"openalex":"https://openalex.org/W7207531159","doi":"https://doi.org/10.26434/chemrxiv.15008225/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15008225/v1","doi":"https://doi.org/10.26434/chemrxiv.15008225/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008225/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008225/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":"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://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008225/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065397770","display_name":"Anthony Val Canillas Camposano","orcid":"https://orcid.org/0000-0001-9207-8697","observed_orcids":["https://orcid.org/0000-0001-9207-8697"]},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Anthony Val Camposano","raw_affiliation_strings":["Laboratory of Organic Electronics, Department of Science and Technology","Link\u00f6ping University"],"raw_orcid":"https://orcid.org/0000-0001-9207-8697","affiliations":[{"raw_affiliation_string":"Laboratory of Organic Electronics, Department of Science and Technology","institution_ids":[]},{"raw_affiliation_string":"Link\u00f6ping University","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021208329","display_name":"Hampus Gummesson Svensson","orcid":"https://orcid.org/0000-0003-0765-1837","observed_orcids":["https://orcid.org/0000-0003-0765-1837"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hampus Gummesson Svensson","raw_affiliation_strings":["AI4S AB"],"raw_orcid":"https://orcid.org/0000-0003-0765-1837","affiliations":[{"raw_affiliation_string":"AI4S AB","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130910061","display_name":"Karl Lowenmark","orcid":"https://orcid.org/0000-0002-0188-9337","observed_orcids":["https://orcid.org/0000-0002-0188-9337"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karl L\u00f6wenmark","raw_affiliation_strings":["AI4S AB"],"raw_orcid":"https://orcid.org/0000-0002-0188-9337","affiliations":[{"raw_affiliation_string":"AI4S AB","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041884181","display_name":"Aleksandar Y. Mehandzhiyski","orcid":"https://orcid.org/0000-0001-5671-4545","observed_orcids":["https://orcid.org/0000-0001-5671-4545"]},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]},{"id":"https://openalex.org/I4210124641","display_name":"Wallenberg Wood Science Center","ror":"https://ror.org/039qvmf95","country_code":"SE","type":"facility","lineage":["https://openalex.org/I102134673","https://openalex.org/I4210124641","https://openalex.org/I66862912","https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Aleksandar Y. Mehandzhiyski","raw_affiliation_strings":["Laboratory of Organic Electronics, Department of Science and Technology","Link\u00f6ping University","Wallenberg Wood Science Center"],"raw_orcid":"https://orcid.org/0000-0001-5671-4545","affiliations":[{"raw_affiliation_string":"Laboratory of Organic Electronics, Department of Science and Technology","institution_ids":[]},{"raw_affiliation_string":"Link\u00f6ping University","institution_ids":["https://openalex.org/I102134673"]},{"raw_affiliation_string":"Wallenberg Wood Science Center","institution_ids":["https://openalex.org/I4210124641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039480222","display_name":"Igor V. Zozoulenko","orcid":"https://orcid.org/0000-0002-6078-3006","observed_orcids":["https://orcid.org/0000-0002-6078-3006"]},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]},{"id":"https://openalex.org/I4210124641","display_name":"Wallenberg Wood Science Center","ror":"https://ror.org/039qvmf95","country_code":"SE","type":"facility","lineage":["https://openalex.org/I102134673","https://openalex.org/I4210124641","https://openalex.org/I66862912","https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Igor Zozoulenko","raw_affiliation_strings":["Laboratory of Organic Electronics, Department of Science and Technology","Link\u00f6ping University","Wallenberg Wood Science Center"],"raw_orcid":"https://orcid.org/0000-0002-6078-3006","affiliations":[{"raw_affiliation_string":"Laboratory of Organic Electronics, Department of Science and Technology","institution_ids":[]},{"raw_affiliation_string":"Link\u00f6ping University","institution_ids":["https://openalex.org/I102134673"]},{"raw_affiliation_string":"Wallenberg Wood Science Center","institution_ids":["https://openalex.org/I4210124641"]}]}],"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":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/T11208","display_name":"Lignin and Wood Chemistry","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1508","display_name":"Process Chemistry and Technology"},"field":{"id":"https://openalex.org/fields/15","display_name":"Chemical Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11208","display_name":"Lignin and Wood Chemistry","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1508","display_name":"Process Chemistry and Technology"},"field":{"id":"https://openalex.org/fields/15","display_name":"Chemical Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.005900000222027302,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.0020000000949949026,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lignin","display_name":"lignin","score":0.9729999899864197},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.6610000133514404},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8679999709129333},{"id":"https://openalex.org/keywords/molecular-heterogeneity","display_name":"molecular heterogeneity","score":0.6909999847412109},{"id":"https://openalex.org/keywords/monomer-composition","display_name":"monomer composition","score":0.6349999904632568},{"id":"https://openalex.org/keywords/polydispersity","display_name":"polydispersity","score":0.8190000057220459},{"id":"https://openalex.org/keywords/molecular-dynamics-simulation","display_name":"molecular dynamics simulation","score":0.49799999594688416}],"concepts":[{"id":"https://openalex.org/C2781052789","wikidata":"https://www.wikidata.org/wiki/Q184817","display_name":"Lignin","level":2,"score":0.6230000257492065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5813999772071838},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5472000241279602},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.541700005531311},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.4848000109195709},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42289999127388},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C166940927","wikidata":"https://www.wikidata.org/wiki/Q178827","display_name":"Monomer","level":3,"score":0.34310001134872437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3050000071525574},{"id":"https://openalex.org/C2778636629","wikidata":"https://www.wikidata.org/wiki/Q422649","display_name":"Biopolymer","level":3,"score":0.2847999930381775},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.2709999978542328},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15008225/v1","doi":"https://doi.org/10.26434/chemrxiv.15008225/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008225/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008225/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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15008225/v1","doi":"https://doi.org/10.26434/chemrxiv.15008225/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008225/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008225/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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7207531159.pdf","grobid_xml":"https://content.openalex.org/works/W7207531159.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2786672974","https://openalex.org/W2909063104","https://openalex.org/W4388765324","https://openalex.org/W7160945995"],"related_works":["https://openalex.org/W4407051992","https://openalex.org/W7143395802","https://openalex.org/W2466901368","https://openalex.org/W2730673775","https://openalex.org/W2152755716","https://openalex.org/W4284899943","https://openalex.org/W7204246674","https://openalex.org/W4307097261","https://openalex.org/W4388765324","https://openalex.org/W2904777742"],"abstract_inverted_index":{"Lignin":[0],"is":[1,27,37],"a":[2,63,102,109,125,157],"structurally":[3],"heterogeneous":[4],"biopolymer":[5],"whose":[6],"monomer":[7,172],"composition,":[8],"interunit":[9],"linkage":[10,174],"types,":[11],"branching,":[12,176],"and":[13,20,33,48,74,94,159,178,182,185,230,236,291,303],"molecular-weight":[14],"distribution":[15,112],"vary":[16],"across":[17],"plant":[18],"sources":[19],"among":[21],"individual":[22,270],"polymer":[23],"chains.":[24],"This":[25,105],"heterogeneity":[26,283,298],"essential":[28],"for":[29,67,113,257],"understanding":[30],"lignin":[31,72,89,117,254,300],"self-assembly":[32],"morphology,":[34,302],"but":[35],"it":[36],"difficult":[38],"to":[39,54,99,162,165,225,251,284],"represent":[40],"in":[41,208],"molecular":[42,79,84,180,214,259,265,271,282,297],"dynamics":[43,260],"simulations":[44,290],"because":[45],"existing":[46],"rule-based":[47],"stochastic":[49],"generators":[50],"are":[51,153],"generally":[52],"limited":[53],"relatively":[55],"small":[56],"structures":[57,90,118,192,205],"or":[58],"populations.":[59],"Here,":[60],"we":[61,219],"present":[62],"machine":[64],"learning":[65,128],"workflow":[66,224],"generating":[68],"statistically":[69],"controlled,":[70],"polydisperse":[71,253],"ensembles":[73],"converting":[75],"them":[76],"into":[77,288],"simulation-ready":[78],"systems.":[80],"We":[81,122],"trained":[82],"autoregressive":[83],"language":[85],"models":[86],"on":[87],"1.16M":[88],"generated":[91,143,151,191],"with":[92,217],"LigninGraphs":[93],"represented":[95],"as":[96,101,156,273],"canonical":[97],"SMILES":[98],"serve":[100],"generative":[103,106,133,277],"prior.":[104],"prior":[107],"provides":[108,242],"chemically":[110],"informed":[111,248],"efficient":[114],"sampling":[115],"of":[116,276,295],"during":[119],"reinforcement":[120,127],"learning.":[121],"then":[123],"introduce":[124],"population-aware":[126],"scheme":[129],"that":[130,189],"conditions":[131],"the":[132,147,150,167,190,195,200,209,222,264,274],"model":[134],"toward":[135,146],"feedstock-specific":[136],"ensemble":[137,169],"properties.":[138],"Rather":[139],"than":[140,268],"optimizing":[141],"each":[142],"molecule":[144],"independently":[145],"target":[148,168,275],"properties,":[149],"molecules":[152],"evaluated":[154],"collectively":[155],"population":[158,249],"rewarded":[160],"according":[161],"their":[163],"contribution":[164],"reproducing":[166],"statistics,":[170],"including":[171],"fractions,":[173],"distributions,":[175],"number-":[177],"weight-average":[179],"weights,":[181],"polydispersity.":[183],"Molecular-fingerprint":[184],"dimensionality-reduction":[186],"analyses":[187],"showed":[188],"remained":[193],"within":[194],"chemical":[196],"manifold":[197],"learned":[198],"from":[199,246],"training":[201],"data":[202],"while":[203],"producing":[204],"not":[206],"duplicated":[207],"original":[210],"library.":[211],"To":[212],"connect":[213],"generation":[215],"directly":[216],"simulation,":[218],"further":[220],"extended":[221],"structure-construction":[223],"automate":[226],"three-dimensional":[227],"conversion,":[228],"residue":[229],"linkage-patch":[231],"assignment,":[232],"force-field":[233],"topology":[234],"generation,":[235],"solvent":[237],"packing.":[238],"The":[239],"resulting":[240],"framework":[241],"an":[243,269],"end-to-end":[244],"route":[245],"experimentally":[247],"statistics":[250],"diverse,":[252],"systems":[255],"suitable":[256],"large-scale":[258],"simulations.":[261],"By":[262],"treating":[263],"population,":[266],"rather":[267],"structure,":[272],"modeling,":[278],"this":[279],"approach":[280],"enables":[281,292],"be":[285],"incorporated":[286],"explicitly":[287],"atomistic":[289],"systematic":[293],"investigation":[294],"how":[296],"governs":[299],"aggregation,":[301],"self-assembly.":[304]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-04T00:00:00"}