{"id":"https://openalex.org/W7204243218","doi":"https://doi.org/10.64898/2026.08.24.746797","title":"ProtEnrich: Residual Multimodal Enrichment of Protein Sequence Embeddings","display_name":"ProtEnrich: Residual Multimodal Enrichment of Protein Sequence Embeddings","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204243218","doi":"https://doi.org/10.64898/2026.08.24.746797"},"language":"en","primary_location":{"id":"doi:10.64898/2026.08.24.746797","doi":"https://doi.org/10.64898/2026.08.24.746797","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.24.746797","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/25/2026.08.24.746797.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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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://www.biorxiv.org/content/biorxiv/early/2026/08/25/2026.08.24.746797.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148272616","display_name":"Gabriel Bianchin de Oliveira","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gabriel Bianchin de Oliveira","raw_affiliation_strings":["Knight Foundation School of Computing and Information Sciences Florida International University, Miami, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knight Foundation School of Computing and Information Sciences Florida International University, Miami, FL, USA","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102729196","display_name":"Fahad Saeed","orcid":"https://orcid.org/0000-0002-3410-9552","observed_orcids":["https://orcid.org/0000-0002-3410-9552"]},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fahad Saeed","raw_affiliation_strings":["Knight Foundation School of Computing and Information Sciences Florida International University, Miami, FL, USA"],"raw_orcid":"https://orcid.org/0000-0002-3410-9552","affiliations":[{"raw_affiliation_string":"Knight Foundation School of Computing and Information Sciences Florida International University, Miami, FL, USA","institution_ids":["https://openalex.org/I19700959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5102729196"],"corresponding_institution_ids":["https://openalex.org/I19700959"],"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.6104000210762024,"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":0.6104000210762024,"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":0.37549999356269836,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.0012000000569969416,"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-sequence-embeddings","display_name":"protein sequence embeddings","score":0.8399999737739563},{"id":"https://openalex.org/keywords/biophysical-properties","display_name":"biophysical properties","score":0.6019999980926514},{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.7900000214576721},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"protein structure prediction","score":0.5170000195503235}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7021999955177307},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6984999775886536},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6736000180244446},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.64410001039505},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6359999775886536},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6062999963760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.567300021648407},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4666999876499176},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.39910000562667847},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36309999227523804},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.3441999852657318},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.3061000108718872},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3027999997138977},{"id":"https://openalex.org/C169627665","wikidata":"https://www.wikidata.org/wiki/Q5767913","display_name":"Homology modeling","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C30711495","wikidata":"https://www.wikidata.org/wiki/Q289411","display_name":"Sequence space","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.28139999508857727},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.08.24.746797","doi":"https://doi.org/10.64898/2026.08.24.746797","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.24.746797","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/25/2026.08.24.746797.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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.08.24.746797","doi":"https://doi.org/10.64898/2026.08.24.746797","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.24.746797","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/25/2026.08.24.746797.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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/W7204243218.pdf","grobid_xml":"https://content.openalex.org/works/W7204243218.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2908510526","https://openalex.org/W4297808394","https://openalex.org/W4317374308"],"related_works":["https://openalex.org/W4410572064","https://openalex.org/W7160862027","https://openalex.org/W7116210942","https://openalex.org/W4413148535","https://openalex.org/W4397043191","https://openalex.org/W7166848678","https://openalex.org/W4413105633","https://openalex.org/W7214893335","https://openalex.org/W7134823360","https://openalex.org/W4318751307"],"abstract_inverted_index":{"Abstract":[0],"Protein":[1],"language":[2],"models":[3,87,182,250],"effectively":[4],"capture":[5,90],"evolutionary":[6,63],"and":[7,25,46,74,97,129,144,200,206,224,251],"functional":[8],"signals":[9],"from":[10,62,142],"sequence":[11,52,78,115,127,160,238],"data":[12],"but":[13],"lack":[14],"explicit":[15],"representation":[16,103,155],"of":[17,50,69],"the":[18,48,51,58,91,158,169],"biophysical":[19,92,135],"properties":[20,93],"that":[21,125,133],"govern":[22],"protein":[23,95,180],"structure":[24,96],"dynamics.":[26],"Existing":[27],"multimodal":[28,41,110,139,172],"approaches":[29],"attempt":[30],"to":[31,71,88,146,204,222,232],"integrate":[32],"such":[33],"physical":[34,154],"information":[35,140],"through":[36],"direct":[37],"fusion,":[38],"often":[39],"requiring":[40,236],"inputs":[42,173],"at":[43,174,240,246,255],"inference":[44,175],"time":[45],"distorting":[47],"geometry":[49],"embedding":[53,161],"space,":[54],"which":[55],"can":[56],"disrupt":[57],"semantic":[59,83,166],"organization":[60],"learned":[61],"information.":[64],"Consequently,":[65],"a":[66,102,108,147],"fundamental":[67],"challenge":[68],"how":[70],"incorporate":[72],"structural":[73],"dynamical":[75],"knowledge":[76],"into":[77,117],"representations":[79],"without":[80],"disrupting":[81],"their":[82,164],"organization,":[84],"enabling":[85],"sequence-based":[86],"better":[89],"governing":[94],"function.":[98],"We":[99],"introduce":[100],"ProtEnrich,":[101],"learning":[104],"framework":[105],"based":[106],"on":[107,184,213],"residual":[109,149],"enrichment":[111],"paradigm.":[112],"Pro-tEnrich":[113],"decomposes":[114],"embeddings":[116,192],"two":[118],"complementary":[119],"latent":[120],"subspaces,":[121],"an":[122,130],"anchor":[123],"subspace":[124,132],"preserves":[126],"semantics,":[128],"alignment":[131],"encodes":[134],"relationships.":[136],"By":[137],"converting":[138],"derived":[141],"ProstT5":[143],"RocketSHP":[145],"low-energy":[148],"component,":[150],"our":[151],"approach":[152],"injects":[153],"while":[156,162,235],"maintaining":[157],"original":[159,165],"preserving":[163],"geometry,":[167],"avoiding":[168],"need":[170],"for":[171],"time.":[176],"Across":[177],"eight":[178],"diverse":[179],"foundational":[181],"trained":[183],"550,120":[185],"SwissProt":[186],"proteins":[187],"with":[188],"AlphaFold":[189],"structures,":[190],"enriched":[191],"improved":[193,212],"zero-shot":[194],"remote":[195],"homology":[196],"retrieval,":[197],"increasing":[198,225],"Precision@10":[199],"MRR":[201],"by":[202,220,230],"up":[203,221,231],"0.13":[205],"0.11,":[207],"respectively.":[208],"Downstream":[209],"performance":[210],"also":[211],"structure-dependent":[214],"tasks,":[215],"reducing":[216],"fluorescence":[217],"prediction":[218],"error":[219],"16%":[223],"metal":[226],"ion":[227],"binding":[228],"AUCROC":[229],"2.4":[233],"points,":[234],"only":[237],"input":[239],"inference.":[241],"Source":[242],"code":[243],"is":[244],"available":[245,254],"https://github.com/pcdslab/ProtEnrich":[247],",":[248],"pretrained":[249],"datasets":[252],"are":[253],"https://huggingface.co/collections/SaeedLab/protenrich":[256],".":[257]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-08-27T00:00:00"}