{"id":"https://openalex.org/W7224681885","doi":"https://doi.org/10.64898/2026.10.27.762338","title":"Who contributes to whom: following the evidence behind protein language-model predictions of backbone variability","display_name":"Who contributes to whom: following the evidence behind protein language-model predictions of backbone variability","publication_year":2026,"publication_date":"2026-10-28","ids":{"openalex":"https://openalex.org/W7224681885","doi":"https://doi.org/10.64898/2026.10.27.762338"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.27.762338","doi":"https://doi.org/10.64898/2026.10.27.762338","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.27.762338","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/28/2026.10.27.762338.full.pdf","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","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/28/2026.10.27.762338.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126192297","display_name":"Ngoc Kim Ngan Tran","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35566140","display_name":"Loyola Marymount University","ror":"https://ror.org/00xhj8c72","country_code":"US","type":"education","lineage":["https://openalex.org/I35566140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ngoc Kim Ngan Tran","raw_affiliation_strings":["Computer Science, Loyola Marymount University, 1 LMU Drive, Los Angeles, 90045, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, Loyola Marymount University, 1 LMU Drive, Los Angeles, 90045, CA, USA","institution_ids":["https://openalex.org/I35566140"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147754171","display_name":"Thomas Rife","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35566140","display_name":"Loyola Marymount University","ror":"https://ror.org/00xhj8c72","country_code":"US","type":"education","lineage":["https://openalex.org/I35566140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Rife","raw_affiliation_strings":["Computer Science, Loyola Marymount University, 1 LMU Drive, Los Angeles, 90045, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, Loyola Marymount University, 1 LMU Drive, Los Angeles, 90045, CA, USA","institution_ids":["https://openalex.org/I35566140"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013714205","display_name":"Mandy Korpusik","orcid":"https://orcid.org/0000-0002-1721-4473","observed_orcids":["https://orcid.org/0000-0002-1721-4473"]},"institutions":[{"id":"https://openalex.org/I35566140","display_name":"Loyola Marymount University","ror":"https://ror.org/00xhj8c72","country_code":"US","type":"education","lineage":["https://openalex.org/I35566140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mandy Korpusik","raw_affiliation_strings":["Computer Science, Loyola Marymount University, 1 LMU Drive, Los Angeles, 90045, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, Loyola Marymount University, 1 LMU Drive, Los Angeles, 90045, CA, USA","institution_ids":["https://openalex.org/I35566140"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160089141","display_name":"Zara Alavi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35566140","display_name":"Loyola Marymount University","ror":"https://ror.org/00xhj8c72","country_code":"US","type":"education","lineage":["https://openalex.org/I35566140"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zara Alavi","raw_affiliation_strings":["Physics, Loyola Marymount University, 1 LMU Drive, Los Angeles, 90045, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Physics, Loyola Marymount University, 1 LMU Drive, Los Angeles, 90045, CA, USA","institution_ids":["https://openalex.org/I35566140"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5160089141"],"corresponding_institution_ids":["https://openalex.org/I35566140"],"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":0.9984999895095825,"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":0.9984999895095825,"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":0.000699999975040555,"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":9.999999747378752e-05,"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/protein-language-models","display_name":"protein language models","score":0.5529999732971191},{"id":"https://openalex.org/keywords/attention-weights","display_name":"attention weights","score":0.5189999938011169},{"id":"https://openalex.org/keywords/protein-blocks","display_name":"protein blocks","score":0.39500001072883606},{"id":"https://openalex.org/keywords/sequence-based-prediction","display_name":"sequence-based prediction","score":0.42800000309944153},{"id":"https://openalex.org/keywords/pegasus","display_name":"Pegasus","score":0.7070000171661377},{"id":"https://openalex.org/keywords/protein-conformational-sampling","display_name":"protein conformational sampling","score":0.4449999928474426}],"concepts":[{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4000000059604645},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.38179999589920044},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3628999888896942},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3474999964237213},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.33559998869895935},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.3321000039577484},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.2689000070095062},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C45475804","wikidata":"https://www.wikidata.org/wiki/Q6675846","display_name":"Loop modeling","level":4,"score":0.2612000107765198},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.27.762338","doi":"https://doi.org/10.64898/2026.10.27.762338","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.27.762338","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/28/2026.10.27.762338.full.pdf","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:10.64898/2026.10.27.762338","doi":"https://doi.org/10.64898/2026.10.27.762338","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.27.762338","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/28/2026.10.27.762338.full.pdf","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224681885.pdf","grobid_xml":"https://content.openalex.org/works/W7224681885.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1031578623","https://openalex.org/W1976499671","https://openalex.org/W2034338411","https://openalex.org/W2064675550","https://openalex.org/W2079735306","https://openalex.org/W2130479394","https://openalex.org/W2555870966","https://openalex.org/W2559738700","https://openalex.org/W2950954328","https://openalex.org/W2952837430","https://openalex.org/W3083406432","https://openalex.org/W4281993476","https://openalex.org/W4387928738","https://openalex.org/W4388870515","https://openalex.org/W4391645344","https://openalex.org/W4404826794","https://openalex.org/W4406440058","https://openalex.org/W4407194157","https://openalex.org/W4412488876","https://openalex.org/W4414162128","https://openalex.org/W7125523255","https://openalex.org/W7223444084"],"related_works":["https://openalex.org/W7130583241","https://openalex.org/W4412488876","https://openalex.org/W7083312723","https://openalex.org/W4403824354","https://openalex.org/W6950292117","https://openalex.org/W1551212125","https://openalex.org/W1965309761","https://openalex.org/W7131626167","https://openalex.org/W4389947019","https://openalex.org/W7100174544"],"abstract_inverted_index":{"Abstract":[0],"Background":[1],"A":[2],"protein":[3,80],"can":[4,18],"retain":[5],"its":[6,10,67,143,207],"overall":[7],"fold":[8],"while":[9],"backbone":[11,60,249],"explores":[12],"different":[13],"local":[14,59,311],"conformations.":[15],"Sequence-based":[16],"models":[17],"predict":[19,58],"this":[20],"variability,":[21],"but":[22],"an":[23,109],"accurate":[24],"prediction":[25,293],"does":[26],"not":[27],"tell":[28],"us":[29],"how":[30,198],"the":[31,64,112,136,157,184,299],"model":[32,102,308],"arrived":[33],"at":[34,43,139],"it.":[35,304],"Attention":[36],"weights":[37],"alone":[38],"cannot":[39],"show":[40],"whether":[41],"information":[42],"a":[44,50,104,200,295],"sequence":[45,131,190],"position":[46,201],"supports":[47],"or":[48,78,321],"opposes":[49],"prediction.":[51],"Results":[52],"We":[53],"developed":[54],"ESM":[55,175,289,324],"fluc":[56,176,290,325],"to":[57,83,133,204,280,282,302],"variability":[61,150],"and":[62,163,218,254,313],"examine":[63],"evidence":[65,193,208,300,309],"behind":[66],"decisions.":[68],"Trained":[69],"on":[70,120],"ATLAS":[71,123],"molecular":[72],"dynamics":[73],"simulations,":[74],"it":[75],"uses":[76],"ESM2":[77],"ESM3":[79,106],"language-model":[81],"representations":[82],"distinguish":[84],"residues":[85,138,253],"that":[86,95,221],"sample":[87,96],"one":[88,285],"Protein":[89],"Block":[90],"(PB)":[91],"state":[92],"from":[93,205,278],"those":[94],"several.":[97],"The":[98,210,305],"best":[99],"of":[100,118,183,216,298,331],"seven":[101],"conditions,":[103],"fine-tuned":[105],"model,":[107],"reached":[108],"area":[110],"under":[111],"receiver":[113],"operating":[114],"characteristic":[115],"curve":[116],"(AUROC)":[117],"0.889":[119],"208":[121],"held-out":[122],"proteins.":[124],"In":[125],"985":[126],"mdCATH":[127],"domains":[128],"filtered":[129],"for":[130,156],"similarity":[132],"ATLAS,":[134],"excluding":[135],"two":[137],"each":[140,195],"chain":[141],"end,":[142],"mean":[144],"within-domain":[145],"Spearman":[146],"correlation":[147],"with":[148,154,165,177,236,271,294,310],"PB-state":[149],"was":[151],"0.616,":[152],"compared":[153],"0.589":[155],"strongest":[158],"external":[159,169],"predictor,":[160],"PEGASUS":[161],"(0.634":[162],"0.527":[164],"all":[166],"positions).":[167],"Several":[168],"predictors":[170,330],"agreed":[171],"more":[172,226],"closely":[173],"than":[174,228,284,328],"root-mean-square":[178],"fluctuations.":[179,333],"An":[180],"exact":[181],"decomposition":[182],"final":[185],"attention\u2013classifier":[186],"stage":[187],"reveals":[188],"which":[189],"positions":[191],"supply":[192],"toward":[194],"class,":[196],"separating":[197],"strongly":[199],"is":[202],"attended":[203],"what":[206],"supports.":[209],"resulting":[211],"influence":[212,220],"profiles":[213],"identified":[214],"bands":[215,277],"positive":[217],"negative":[219],"recurred":[222],"across":[223],"training":[224],"seeds":[225],"often":[227],"expected":[229],"after":[230],"circularly":[231],"shifting":[232],"their":[233],"positions.":[234],"Compared":[235],"matched":[237],"non-band":[238],"residues,":[239],"peaks":[240],"supporting":[241,261],"multi-PB":[242],"predictions":[243,263],"showed":[244,264],"larger":[245],"differences":[246],"in":[247,257],"predicted":[248],"angles":[250],"between":[251],"neighboring":[252],"fewer":[255,283],"contacts":[256],"experimental":[258],"structures.":[259],"Peaks":[260],"single-PB":[262],"smaller":[265],"angular":[266],"differences.":[267],"Replacing":[268],"learned":[269],"attention":[270,273],"uniform":[272],"reduced":[274],"candidate":[275],"multi-PB-supporting":[276],"five":[279],"six":[281],"per":[286],"protein.":[287],"Conclusions":[288],"connects":[291],"sequence-based":[292],"direct":[296],"view":[297],"used":[301],"make":[303],"maps":[306],"associate":[307],"geometry":[312],"structural":[314],"surroundings,":[315],"without":[316],"establishing":[317],"physical":[318],"communication":[319],"pathways":[320],"mutation":[322],"effects.":[323],"complements,":[326],"rather":[327],"replaces,":[329],"positional":[332]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-30T00:00:00"}