{"id":"https://openalex.org/W7220954298","doi":"https://doi.org/10.64898/2026.09.30.755750","title":"Position-wise Fold-Switch Prediction in Metamorphic Proteins: A Comparison of Handcrafted and Language Model Features","display_name":"Position-wise Fold-Switch Prediction in Metamorphic Proteins: A Comparison of Handcrafted and Language Model Features","publication_year":2026,"publication_date":"2026-10-08","ids":{"openalex":"https://openalex.org/W7220954298","doi":"https://doi.org/10.64898/2026.09.30.755750"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.30.755750","doi":"https://doi.org/10.64898/2026.09.30.755750","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.30.755750","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/08/2026.09.30.755750.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-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://www.biorxiv.org/content/biorxiv/early/2026/10/08/2026.09.30.755750.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002847053","display_name":"Pranav Machingal","orcid":"https://orcid.org/0009-0002-7850-9598","observed_orcids":["https://orcid.org/0009-0002-7850-9598"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pranav Machingal","raw_affiliation_strings":["Department of Industrial Engineering and Operations Research"],"raw_orcid":"https://orcid.org/0009-0002-7850-9598","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084320426","display_name":"N. Hemachandra","orcid":"https://orcid.org/0000-0003-2917-1551","observed_orcids":["https://orcid.org/0000-0003-2917-1551"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nandyala Hemachandra","raw_affiliation_strings":["Department of Industrial Engineering and Operations Research"],"raw_orcid":"https://orcid.org/0000-0003-2917-1551","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006668020","display_name":"Petety V. Balaji","orcid":"https://orcid.org/0000-0002-6018-6957","observed_orcids":["https://orcid.org/0000-0002-6018-6957"]},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Petety V Balaji","raw_affiliation_strings":["Department of Biosciences and Bioengineering Indian Institute of Technology Bombay, 400076 Mumbai, India"],"raw_orcid":"https://orcid.org/0000-0002-6018-6957","affiliations":[{"raw_affiliation_string":"Department of Biosciences and Bioengineering Indian Institute of Technology Bombay, 400076 Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002847053"],"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":0.8428000211715698,"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":0.8428000211715698,"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":0.15410000085830688,"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/T11162","display_name":"Enzyme Structure and Function","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1315","display_name":"Structural 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/metamorphic-proteins","display_name":"metamorphic proteins","score":0.9660000205039978},{"id":"https://openalex.org/keywords/protein-structure","display_name":"protein structure","score":0.45100000500679016},{"id":"https://openalex.org/keywords/handcrafted-features","display_name":"handcrafted features","score":0.7900000214576721},{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.8149999976158142},{"id":"https://openalex.org/keywords/protein-embeddings","display_name":"protein embeddings","score":0.6700000166893005},{"id":"https://openalex.org/keywords/data-leakage","display_name":"data leakage","score":0.9330000281333923},{"id":"https://openalex.org/keywords/error-analysis","display_name":"error analysis","score":0.6620000004768372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7365999817848206},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6880999803543091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6819999814033508},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6499000191688538},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5115000009536743},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43070000410079956},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39010000228881836},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3370000123977661},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2838999927043915},{"id":"https://openalex.org/C128040838","wikidata":"https://www.wikidata.org/wiki/Q1810628","display_name":"Pseudorandom binary sequence","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.30.755750","doi":"https://doi.org/10.64898/2026.09.30.755750","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.30.755750","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/08/2026.09.30.755750.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-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:10.64898/2026.09.30.755750","doi":"https://doi.org/10.64898/2026.09.30.755750","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.30.755750","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/08/2026.09.30.755750.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-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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220954298.pdf","grobid_xml":"https://content.openalex.org/works/W7220954298.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1554521867","https://openalex.org/W2803256436","https://openalex.org/W2949676527","https://openalex.org/W3049420534","https://openalex.org/W3104537585","https://openalex.org/W3130225815","https://openalex.org/W3177828909","https://openalex.org/W4399998351","https://openalex.org/W4405366206","https://openalex.org/W4412654209","https://openalex.org/W7119522430"],"related_works":["https://openalex.org/W4407618089","https://openalex.org/W4416682786","https://openalex.org/W3049420534","https://openalex.org/W2899239597","https://openalex.org/W3197371681","https://openalex.org/W4417293732","https://openalex.org/W3008866840","https://openalex.org/W4225891318","https://openalex.org/W3125460433","https://openalex.org/W4391636778"],"abstract_inverted_index":{"Abstract":[0],"In":[1,100],"this":[2],"work,":[3],"we":[4],"focus":[5],"on":[6,95,126,187],"predicting":[7],"fold-switching":[8,18,169,184],"phenomena":[9],"observed":[10],"in":[11,27,146],"certain":[12],"protein":[13,74,149],"structures.":[14],"Proteins":[15],"that":[16,60,156],"undergo":[17],"are":[19],"called":[20],"metamorphic":[21,148],"proteins.":[22],"We":[23,34,51,68,82],"model":[24],"fold-switch":[25],"prediction":[26,110],"proteins":[28],"as":[29,43,45,111],"a":[30,40,53,66,142],"position/residue-wise":[31],"classification":[32,104],"task.":[33],"use":[35,70],"various":[36],"features":[37,59,119],"extracted":[38],"from":[39,72],"protein\u2019s":[41],"sequence":[42,188],"well":[44],"structure":[46],"to":[47,78,113,165,167],"train":[48,79,83],"the":[49,62,80,89,96,123,138,147,157,172],"classifiers.":[50,81],"propose":[52],"novel":[54,168],"class":[55],"of":[56,65,98,176],"handcrafted":[57,179],"parametrised":[58],"encode":[61],"structural":[63],"context":[64],"residue.":[67],"also":[69,154],"embeddings":[71,125],"existing":[73],"language":[75],"models":[76],"(PLMs)":[77],"binary":[84,109],"and":[85,163],"3-class":[86,90,114],"classifiers,":[87],"with":[88,122],"classifiers":[91],"providing":[92],"granular":[93,115],"information":[94],"type":[97],"fold-switch.":[99],"our":[101,127,177],"computations,":[102],"higher":[103],"performance":[105],"is":[106],"achieved":[107],"for":[108],"compared":[112],"prediction.":[116],"The":[117],"hand-crafted":[118],"perform":[120],"comparably":[121],"PLM":[124],"standard":[128],"test":[129,150],"set.":[130],"A":[131],"rigorous":[132],"error":[133],"analysis":[134,153],"by":[135],"us":[136],"during":[137],"review":[139],"period":[140],"revealed":[141,155],"critical":[143],"data-leakage":[144],"vulnerability":[145],"data.":[151],"This":[152],"PLM-based":[158],"classifier":[159,182],"suffers":[160],"sequence-memorisation":[161],"bias":[162],"fails":[164],"generalise":[166],"sequences.":[170],"On":[171],"other":[173],"hand,":[174],"one":[175],"domain-informed":[178],"feature":[180],"based":[181],"detects":[183],"without":[185],"relying":[186],"memory.":[189]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-09T00:00:00"}