{"id":"https://openalex.org/W7160417183","doi":"https://doi.org/10.1021/acs.jcim.6c00288","title":"PSMa: Learning Protein Surface Representations with Physicochemical Masked Autoencoders","display_name":"PSMa: Learning Protein Surface Representations with Physicochemical Masked Autoencoders","publication_year":2026,"publication_date":"2026-05-06","ids":{"openalex":"https://openalex.org/W7160417183","doi":"https://doi.org/10.1021/acs.jcim.6c00288","pmid":"https://pubmed.ncbi.nlm.nih.gov/42090297"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.6c00288","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.6c00288","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","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":"https://openalex.org/A5015681671","display_name":"Qianyu Chen","orcid":"https://orcid.org/0000-0002-1273-7988"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianyu Chen","raw_affiliation_strings":["School of Information Science and Technology, ShanghaiTech University, 393 Middle Huaxia Road, Pudong New Area, Shanghai 201210, China","Shanghai Institute for Advanced Immunochemical Studies, ShanghaiTech University, 393 Middle Huaxia Road, Pudong\rNew Area, Shanghai 201210, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, 393 Middle Huaxia Road, Pudong New Area, Shanghai 201210, China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Shanghai Institute for Advanced Immunochemical Studies, ShanghaiTech University, 393 Middle Huaxia Road, Pudong\rNew Area, Shanghai 201210, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135478540","display_name":"Xinyue Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyue Ma","raw_affiliation_strings":["School of Information Science and Technology, ShanghaiTech University, 393 Middle Huaxia Road, Pudong New Area, Shanghai 201210, China","Shanghai Institute for Advanced Immunochemical Studies, ShanghaiTech University, 393 Middle Huaxia Road, Pudong\rNew Area, Shanghai 201210, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, 393 Middle Huaxia Road, Pudong New Area, Shanghai 201210, China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Shanghai Institute for Advanced Immunochemical Studies, ShanghaiTech University, 393 Middle Huaxia Road, Pudong\rNew Area, Shanghai 201210, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135482425","display_name":"Hao Yang","orcid":"https://orcid.org/0009-0008-0040-276X"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["School of Life Science and Technology, ShanghaiTech University, 393 Middle Huaxia Road, Pudong New Area, Shanghai 201210, China","Shanghai Institute for Advanced Immunochemical Studies, ShanghaiTech University, 393 Middle Huaxia Road, Pudong\rNew Area, Shanghai 201210, China"],"raw_orcid":"https://orcid.org/0009-0008-0040-276X","affiliations":[{"raw_affiliation_string":"School of Life Science and Technology, ShanghaiTech University, 393 Middle Huaxia Road, Pudong New Area, Shanghai 201210, China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Shanghai Institute for Advanced Immunochemical Studies, ShanghaiTech University, 393 Middle Huaxia Road, Pudong\rNew Area, Shanghai 201210, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135470196","display_name":"Shenghua Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151021","display_name":"Shanghai Institute of Computing Technology","ror":"https://ror.org/05ek0ze18","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210151021"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Shenghua Gao","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Pokfulam Road, Hong Kong, HKSAR 999077, China","HKU Shanghai lntelligent Computing Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Pokfulam Road, Hong Kong, HKSAR 999077, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"HKU Shanghai lntelligent Computing Research Center","institution_ids":["https://openalex.org/I4210151021","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135531982","display_name":"Fang Bai","orcid":"https://orcid.org/0000-0003-1468-5568"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fang Bai","raw_affiliation_strings":["School of Information Science and Technology, ShanghaiTech University, 393 Middle Huaxia Road, Pudong New Area, Shanghai 201210, China","School of Life Science and Technology, ShanghaiTech University, 393 Middle Huaxia Road, Pudong New Area, Shanghai 201210, China","Shanghai Institute for Advanced Immunochemical Studies, ShanghaiTech University, 393 Middle Huaxia Road, Pudong\rNew Area, Shanghai 201210, China"],"raw_orcid":"https://orcid.org/0000-0003-1468-5568","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, 393 Middle Huaxia Road, Pudong New Area, Shanghai 201210, China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Life Science and Technology, ShanghaiTech University, 393 Middle Huaxia Road, Pudong New Area, Shanghai 201210, China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"Shanghai Institute for Advanced Immunochemical Studies, ShanghaiTech University, 393 Middle Huaxia Road, Pudong\rNew Area, Shanghai 201210, China","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5135470196","https://openalex.org/A5135531982"],"corresponding_institution_ids":["https://openalex.org/I30809798","https://openalex.org/I4210151021","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44997175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"66","issue":"10","first_page":"5736","last_page":"5746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.42739999294281006,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.42739999294281006,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.1362999975681305,"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":0.13500000536441803,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4521999955177307},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3391000032424927},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3366999924182892},{"id":"https://openalex.org/keywords/statistical-learning","display_name":"Statistical learning","score":0.3131999969482422},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30630001425743103},{"id":"https://openalex.org/keywords/surface","display_name":"Surface (topology)","score":0.30059999227523804}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.683899998664856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6171000003814697},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3391000032424927},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C2776799497","wikidata":"https://www.wikidata.org/wiki/Q484298","display_name":"Surface (topology)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2784999907016754},{"id":"https://openalex.org/C3019232848","wikidata":"https://www.wikidata.org/wiki/Q29548","display_name":"Surface protein","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2676999866962433},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2515000104904175}],"mesh":[{"descriptor_ui":"D000098446","descriptor_name":"Autoencoder","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098446","descriptor_name":"Autoencoder","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098446","descriptor_name":"Autoencoder","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098446","descriptor_name":"Autoencoder","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","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":"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":"D013499","descriptor_name":"Surface Properties","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013499","descriptor_name":"Surface Properties","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013499","descriptor_name":"Surface Properties","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013499","descriptor_name":"Surface Properties","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.6c00288","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.6c00288","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:42090297","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42090297","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":"Journal of chemical information and modeling","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2700968060","display_name":null,"funder_award_id":"24JS2850100","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G4918318075","display_name":null,"funder_award_id":"25DX2800400","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G5234590680","display_name":null,"funder_award_id":"24JS2850200","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320327675","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2560722161","https://openalex.org/W2617750324","https://openalex.org/W2944679105","https://openalex.org/W2955690154","https://openalex.org/W2979750740","https://openalex.org/W2990689232","https://openalex.org/W2992752586","https://openalex.org/W3080498684","https://openalex.org/W3197696221","https://openalex.org/W4214755140","https://openalex.org/W4309862248","https://openalex.org/W4309908854","https://openalex.org/W4327550249","https://openalex.org/W4366239108","https://openalex.org/W4386634093","https://openalex.org/W4388336654","https://openalex.org/W4389126617","https://openalex.org/W4392885247","https://openalex.org/W4393055192","https://openalex.org/W4394907732","https://openalex.org/W4394989104","https://openalex.org/W4396620639","https://openalex.org/W4396721167","https://openalex.org/W4396849244","https://openalex.org/W4399880448","https://openalex.org/W4404210051","https://openalex.org/W4404226808","https://openalex.org/W4404789378","https://openalex.org/W4406440058","https://openalex.org/W4406530061","https://openalex.org/W4407284294","https://openalex.org/W4413311999","https://openalex.org/W7133191943"],"related_works":[],"abstract_inverted_index":{"Protein":[0],"modeling":[1],"has":[2],"largely":[3],"centered":[4],"on":[5,31,63],"sequence":[6],"representations,":[7],"leaving":[8],"the":[9,107],"geometry":[10],"and":[11,37,60,72,79,94],"physicochemical":[12,38],"context":[13],"of":[14],"molecular":[15],"surfaces":[16],"underused.":[17],"We":[18],"introduce":[19],"PSMa":[20,57],"(Protein":[21],"Surface":[22],"Masked":[23],"autoencoder),":[24],"a":[25,117],"self-supervised":[26],"framework":[27],"that":[28,113],"operates":[29],"directly":[30],"molecular-surface":[32],"point":[33],"clouds":[34],"with":[35,102],"geometric":[36],"attributes,":[39],"reconstructing":[40],"masked":[41],"surface":[42],"patches":[43],"to":[44,106],"learn":[45],"transferable":[46],"representations":[47,89],"at":[48],"scale":[49],"from":[50],"\u223c220,000":[51],"PDB":[52],"structures.":[53],"On":[54],"held-out":[55],"proteins,":[56],"outperforms":[58],"sequence-only":[59],"structure-only":[61],"baselines":[62],"two":[64],"downstream":[65],"tasks\u2500(i)":[66],"protein-protein":[67],"interface":[68],"(PPI)":[69],"binding-site":[70],"identification":[71],"(ii)":[73],"protein":[74,123],"thermal-stability":[75],"prediction\u2500matching":[76],"state-of-the-art":[77],"AUROC":[78],"AUPRC":[80],"while":[81],"substantially":[82],"improving":[83],"threshold-dependent":[84],"classification":[85],"performance.":[86],"The":[87],"learned":[88],"generalize":[90],"across":[91,95],"protein-length":[92],"ranges":[93],"experimental":[96],"as":[97,99],"well":[98],"predicted":[100],"structures,":[101],"decision":[103],"thresholds":[104],"closer":[105],"neutral":[108],"prior;":[109],"these":[110],"findings":[111],"show":[112],"surface-centric":[114],"pretraining":[115],"provides":[116],"strong,":[118],"generalizable":[119],"foundation":[120],"for":[121],"structure-aware":[122],"machine":[124],"learning.":[125]},"counts_by_year":[],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2026-05-07T00:00:00"}