{"id":"https://openalex.org/W7225791882","doi":"https://doi.org/10.64898/2026.11.09.765464","title":"Beyond Sequence and Structure: Pretraining PLMs on Continuous Biophysical Fields","display_name":"Beyond Sequence and Structure: Pretraining PLMs on Continuous Biophysical Fields","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225791882","doi":"https://doi.org/10.64898/2026.11.09.765464"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.09.765464","doi":"https://doi.org/10.64898/2026.11.09.765464","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.09.765464","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"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://doi.org/10.64898/2026.11.09.765464","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051634441","display_name":"Patrick Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Patrick Jiang","raw_affiliation_strings":["Mayo Clinic;"],"raw_orcid":"https://orcid.org/0009-0008-5596-4532","affiliations":[{"raw_affiliation_string":"Mayo Clinic;","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070279915","display_name":"Abhishek Singharoy","orcid":"https://orcid.org/0000-0002-9000-2397","observed_orcids":["https://orcid.org/0000-0002-9000-2397"]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Singharoy","raw_affiliation_strings":["Arizona State University"],"raw_orcid":"https://orcid.org/0000-0002-9000-2397","affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051634441"],"corresponding_institution_ids":["https://openalex.org/I1330342723"],"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.5199999809265137,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.5199999809265137,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.4684999883174896,"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":0.0024999999441206455,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6085000038146973},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5375999808311462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4490000009536743},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C3019835501","wikidata":"https://www.wikidata.org/wiki/Q1310130","display_name":"Single shot","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3239000141620636},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.26910001039505005},{"id":"https://openalex.org/C80478641","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential analysis","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.09.765464","doi":"https://doi.org/10.64898/2026.11.09.765464","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.09.765464","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.09.765464","doi":"https://doi.org/10.64898/2026.11.09.765464","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.09.765464","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"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],"introduce":[1],"the":[2,27,35,51,55,73,78,107,112,119,126,153],"Biophysical":[3,127],"Transformer,":[4],"a":[5,15,68,147],"protein":[6],"language":[7],"model":[8,36],"that":[9,110],"adds":[10],"continuous":[11],"biophysical":[12],"fields":[13],"as":[14,50],"third":[16],"pretraining":[17,113,149],"signal":[18],"beside":[19],"sequence":[20,42],"and":[21,34,62,104,129,137],"structure.":[22],"A":[23,44],"Poisson-Boltzmann":[24],"solver":[25],"computes":[26],"electrostatic":[28],"potential":[29],"around":[30],"each":[31],"three-residue":[32],"token,":[33],"learns":[37],"to":[38],"predict":[39],"it":[40],"from":[41,161],"alone.":[43],"rotationally":[45],"invariant":[46],"spherical-harmonic":[47],"descriptor":[48],"serves":[49],"loss":[52],"target,":[53],"eliminating":[54],"need":[56],"for":[57,63],"frame":[58],"alignment":[59],"during":[60],"training":[61],"coordinates":[64],"at":[65],"inference.":[66],"Against":[67],"matched,":[69],"one-flag":[70],"control":[71,132],"on":[72,84,93,118,140,146],"FLIP":[74],"Meltome":[75],"thermostability":[76],"benchmark,":[77],"field":[79,159],"objective":[80],"raises":[81],"Spearman":[82],"correlation":[83],"every":[85,141],"trained":[86],"head":[87],"of":[88],"both":[89,125],"human":[90,94],"splits.The":[91],"gain":[92],"survives":[95,105,117],"residualizing":[96],"dipeptide":[97],"composition":[98],"under":[99],"two":[100],"architecturally":[101],"different":[102],"readouts":[103],"removing":[106],"test":[108],"proteins":[109],"overlap":[111],"corpus.":[114],"No":[115],"effect":[116],"organism-mixed":[120],"split.":[121,142],"At":[122],"1.1M":[123],"parameters,":[124],"Transformer":[128],"its":[130],"sequence-only":[131],"exceed":[133],"FLIP's":[134],"one-hot":[135],"CNN":[136],"untrained-ESM":[138],"baselines":[139],"All":[143],"results":[144],"rest":[145],"single":[148],"run":[150],"per":[151],"arm,and":[152],"current":[154],"design":[155],"does":[156],"not":[157],"separate":[158],"content":[160],"generic":[162],"regularization.":[163]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}