{"id":"https://openalex.org/W4417183526","doi":"https://doi.org/10.1109/jbhi.2025.3608273","title":"MPSol: A Multimodal Prompt Learning Framework for Protein Solubility Prediction","display_name":"MPSol: A Multimodal Prompt Learning Framework for Protein Solubility Prediction","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W4417183526","doi":"https://doi.org/10.1109/jbhi.2025.3608273","pmid":"https://pubmed.ncbi.nlm.nih.gov/41359723"},"language":"en","primary_location":{"id":"doi:10.1109/jbhi.2025.3608273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3608273","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuhang Zhang","orcid":"https://orcid.org/0000-0003-2761-8751"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2761-8751","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Peilin Chen","orcid":"https://orcid.org/0000-0001-6636-522X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Peilin Chen","raw_affiliation_strings":["City University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-6636-522X","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032086683","display_name":"Keyan Ding","orcid":"https://orcid.org/0000-0003-2900-7313"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyan Ding","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2900-7313","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349058","display_name":"Han Liu","orcid":"https://orcid.org/0000-0003-0647-6627"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Han Liu","raw_affiliation_strings":["City University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385178","display_name":"Shiqi Wang","orcid":"https://orcid.org/0000-0002-3583-959X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shiqi Wang","raw_affiliation_strings":["City University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-3583-959X","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100748969","display_name":"Qi Song","orcid":"https://orcid.org/0000-0002-1726-7858"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Song","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1726-7858","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4868,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70079057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"29","issue":"12","first_page":"8807","last_page":"8814"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.19220000505447388,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.19220000505447388,"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":0.17100000381469727,"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":0.15489999949932098,"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/encode","display_name":"ENCODE","score":0.6890000104904175},{"id":"https://openalex.org/keywords/protein\u2013protein-interaction","display_name":"Protein\u2013protein interaction","score":0.43299999833106995},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.41600000858306885},{"id":"https://openalex.org/keywords/solubility","display_name":"Solubility","score":0.40709999203681946},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"Protein structure prediction","score":0.3779999911785126},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.336899995803833},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.32269999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.734499990940094},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6890000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6061999797821045},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42899999022483826},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C155574463","wikidata":"https://www.wikidata.org/wiki/Q170731","display_name":"Solubility","level":2,"score":0.40709999203681946},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.3779999911785126},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2517000138759613}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D012995","descriptor_name":"Solubility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012995","descriptor_name":"Solubility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012995","descriptor_name":"Solubility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/jbhi.2025.3608273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3608273","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},{"id":"pmid:41359723","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41359723","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE journal of biomedical and health informatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2069506489","https://openalex.org/W2102592002","https://openalex.org/W2318099008","https://openalex.org/W2794004073","https://openalex.org/W2918676206","https://openalex.org/W2957625277","https://openalex.org/W3022229786","https://openalex.org/W3119780302","https://openalex.org/W3129073614","https://openalex.org/W3177500196","https://openalex.org/W3198377975","https://openalex.org/W3216325381","https://openalex.org/W4289653737","https://openalex.org/W4312310776","https://openalex.org/W4317374308","https://openalex.org/W4317853066","https://openalex.org/W4327550249","https://openalex.org/W4375858802","https://openalex.org/W4391136507","https://openalex.org/W4401021891","https://openalex.org/W4406261125"],"related_works":[],"abstract_inverted_index":{"Protein":[0],"solubility":[1,16,48],"is":[2,70],"a":[3,19,39,73,78],"critical":[4],"determinant":[5],"of":[6,112,131,134,138,158,161,165,172],"biologic":[7],"candidates'":[8],"developability,":[9],"stability,":[10],"and":[11,60,136,146,163,178],"therapeutic":[12],"efficacy.":[13],"However,":[14],"accurate":[15],"prediction":[17,49],"remains":[18],"central":[20],"challenge":[21],"in":[22],"computational":[23],"protein":[24,32,47,114,180],"engineering":[25],"due":[26],"to":[27,116,149],"the":[28,110,141,150,170],"inherent":[29],"complexity":[30],"within":[31],"sequences.":[33],"In":[34,89],"this":[35],"work,":[36],"we":[37,91],"propose":[38],"multimodal":[40,75,174],"prompt":[41],"learning":[42,175],"framework,":[43],"called":[44],"MPSol,":[45],"for":[46,176],"that":[50,83,95,123],"integrates":[51],"complementary":[52],"representations":[53,115],"derived":[54],"from":[55],"primary":[56],"sequences,":[57],"structural":[58],"proxies,":[59],"textual":[61],"descriptions":[62],"generated":[63],"by":[64],"large":[65],"language":[66],"models":[67],"(LLMs).":[68],"MPSol":[69,124],"built":[71],"upon":[72],"unified":[74],"backbone":[76],"with":[77,101,155],"dedicated":[79],"cross-modal":[80],"fusion":[81],"module":[82],"captures":[84],"fine-grained":[85],"interactions":[86],"across":[87],"modalities.":[88],"addition,":[90],"design":[92],"label-aware":[93],"prompts":[94,105],"encode":[96],"solubility-specific":[97],"semantic":[98,107,118],"cues":[99],"associated":[100],"each":[102],"class.":[103],"These":[104,167],"provide":[106],"supervision,":[108],"guiding":[109],"alignment":[111],"fused":[113],"promote":[117],"consistency.":[119],"Extensive":[120],"experiments":[121],"demonstrate":[122],"achieves":[125],"state-of-the-art":[126],"performance,":[127],"reaching":[128],"an":[129,156],"accuracy":[130,157],"0.815,":[132],"AUC":[133,160],"0.867":[135],"MCC":[137,164],"0.642":[139],"on":[140],"standard":[142],"PDBSol":[143],"test":[144,153],"set,":[145],"generalizes":[147],"well":[148],"external":[151],"out-of-distribution":[152],"dataset":[154],"0.632,":[159],"0.653":[162],"0.332.":[166],"results":[168],"underscore":[169],"potential":[171],"prompt-driven":[173],"interpretable":[177],"effective":[179],"property":[181],"prediction.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-08T00:00:00"}