{"id":"https://openalex.org/W7225273151","doi":"https://doi.org/10.64898/2026.11.03.763913","title":"All-Atom Structure Tokenizer: AtomLM-9b for Biomolecular Structure Prediction","display_name":"All-Atom Structure Tokenizer: AtomLM-9b for Biomolecular Structure Prediction","publication_year":2026,"publication_date":"2026-11-04","ids":{"openalex":"https://openalex.org/W7225273151","doi":"https://doi.org/10.64898/2026.11.03.763913"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.03.763913","doi":"https://doi.org/10.64898/2026.11.03.763913","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.03.763913","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.64898/2026.11.03.763913","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102976320","display_name":"Jiaxian Yan","orcid":"https://orcid.org/0009-0006-5610-2948","observed_orcids":["https://orcid.org/0009-0006-5610-2948"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxian Yan","raw_affiliation_strings":["Scinetics Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scinetics Company","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160636269","display_name":"Dongchu Xie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongchu Xie","raw_affiliation_strings":["Scinetics Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scinetics Company","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158286857","display_name":"Zhicai Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhicai Wang","raw_affiliation_strings":["Scinetics Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scinetics Company","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132648766","display_name":"Mingyang Xu","orcid":"https://orcid.org/0009-0004-6882-9576","observed_orcids":["https://orcid.org/0009-0004-6882-9576"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingyang Xu","raw_affiliation_strings":["Scinetics Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scinetics Company","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063733770","display_name":"Zaixi Zhang","orcid":"https://orcid.org/0000-0002-0380-6558","observed_orcids":["https://orcid.org/0000-0002-0380-6558"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zaixi Zhang","raw_affiliation_strings":["Scinetics Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scinetics Company","institution_ids":[]}]}],"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/T10044","display_name":"Protein Structure and Dynamics","score":0.986299991607666,"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":0.986299991607666,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.004999999888241291,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.0038999998942017555,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C2778858076","wikidata":"https://www.wikidata.org/wiki/Q5249539","display_name":"Decodes","level":3,"score":0.8177000284194946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6926000118255615},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46149998903274536},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35350000858306885},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3447999954223633},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.3222000002861023},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3212999999523163},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3059999942779541},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2957000136375427},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C80551277","wikidata":"https://www.wikidata.org/wiki/Q11210","display_name":"Coordinate system","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C8010536","wikidata":"https://www.wikidata.org/wiki/Q160398","display_name":"Crystallography","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2596000134944916},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.03.763913","doi":"https://doi.org/10.64898/2026.11.03.763913","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.03.763913","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.03.763913","doi":"https://doi.org/10.64898/2026.11.03.763913","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.03.763913","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","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":[],"abstract_inverted_index":{"We":[0,95],"develop":[1],"an":[2,72,110,143],"All-atom":[3],"Structure":[4],"Tokenizer":[5],"that":[6,79],"compresses":[7],"biomolecular":[8],"geometry":[9],"into":[10,91],"discrete":[11,139],"structural":[12,81,112],"tokens":[13,82],"and":[14,23,46,58,62,86,88,150],"achieves":[15,52,121],"high-accuracy":[16],"all-atom":[17,53,140],"reconstruction.":[18],"A":[19],"hierarchical":[20],"geometric":[21],"encoder":[22],"finite":[24],"scalar":[25],"quantization":[26],"map":[27],"chemical":[28],"units":[29],"to":[30,106],"a":[31,38,122],"shared":[32],"vocabulary":[33],"of":[34,56,125,134],"8,192":[35],"tokens,":[36],"while":[37],"joint":[39],"coordinate":[40],"de-tokenizer":[41],"reconstructs":[42],"backbone,":[43],"side-chain,":[44],"nucleic-acid,":[45],"ligand":[47],"heavy":[48],"atoms.":[49],"The":[50],"tokenizer":[51],"lDDT":[54],"scores":[55],"0.832":[57],"0.835":[59],"on":[60,66,77,115],"CASP14":[61],"CASP15,":[63],"respectively.":[64],"Building":[65],"this":[67],"tokenizer,":[68],"we":[69],"train":[70],"AtomLM-9b,":[71],"autoregressive":[73],"language":[74,113],"model":[75],"based":[76],"Qwen3.5-9B":[78],"predicts":[80],"from":[83],"molecular":[84],"identities":[85],"connectivity":[87],"decodes":[89],"them":[90],"complete":[92],"atomic":[93,148],"structures.":[94],"demonstrate,":[96],"for":[97],"the":[98,116,129],"first":[99],"time,":[100],"protein":[101],"structure":[102,152],"prediction":[103],"performance":[104],"comparable":[105],"AlphaFold":[107,131],"3":[108,132],"with":[109,128],"all-atom-tokenizer-based":[111],"model:":[114],"FoldBench":[117],"protein-protein":[118],"task,":[119],"AtomLM-9b":[120],"success":[123],"rate":[124],"75.01%,":[126],"compared":[127],"published":[130],"result":[133],"72.93%.":[135],"These":[136],"results":[137],"establish":[138],"tokenization":[141],"as":[142],"effective":[144],"interface":[145],"between":[146],"high-fidelity":[147],"reconstruction":[149],"language-model-based":[151],"prediction.":[153]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-05T00:00:00"}