{"id":"https://openalex.org/W7057995331","doi":null,"title":"Making Sense of Protein Representation Learning in the Wild","display_name":"Making Sense of Protein Representation Learning in the Wild","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W7057995331"},"language":"en","primary_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt8z4384wt","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/8z4384wt","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"etd"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5010673369","display_name":"Nicholas Bhattacharya","orcid":"https://orcid.org/0000-0003-1697-7177","observed_orcids":["https://orcid.org/0000-0003-1697-7177"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bhattacharya, Nicholas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5010673369"],"corresponding_institution_ids":[],"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":true,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.923799991607666,"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":0.923799991607666,"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":0.054099999368190765,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.009999999776482582,"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-representation-learning","display_name":"protein representation learning","score":0.9909999966621399},{"id":"https://openalex.org/keywords/self-supervised-pretraining","display_name":"self-supervised pre-training","score":0.9919999837875366},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.8109999895095825},{"id":"https://openalex.org/keywords/protein-sequence-data","display_name":"protein sequence data","score":0.4970000088214874},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.41999998688697815},{"id":"https://openalex.org/keywords/potts-model","display_name":"Potts model","score":0.9789999723434448},{"id":"https://openalex.org/keywords/antibody-antigen-binding","display_name":"antibody-antigen binding","score":0.8799999952316284},{"id":"https://openalex.org/keywords/ovalbumin","display_name":"ovalbumin","score":0.9729999899864197},{"id":"https://openalex.org/keywords/protein-clustering","display_name":"protein clustering","score":0.4350000023841858},{"id":"https://openalex.org/keywords/small-labeled-datasets","display_name":"small labeled datasets","score":0.5410000085830688}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6995000243186951},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.6930000185966492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6189000010490417},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4643999934196472},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45080000162124634},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44780001044273376},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:escholarship.org:ark:/13030/qt8z4384wt","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/8z4384wt","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"etd"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3111553449","https://openalex.org/W4412718912","https://openalex.org/W2951599627","https://openalex.org/W4297243376","https://openalex.org/W4365444089","https://openalex.org/W3197123494","https://openalex.org/W3108423942","https://openalex.org/W4389126617","https://openalex.org/W4413010596","https://openalex.org/W4404354833"],"abstract_inverted_index":{"Data-driven":[0],"systems":[1,54],"used":[2,174],"to":[3,23,55,109,215,227,238],"inform":[4],"design":[5],"or":[6,29],"characterization":[7],"of":[8,26,31,39,44,52,65,77,113,140,147,160,208,210,212,235],"proteins":[9],"in":[10,34],"the":[11,32,133,171,179,203,233],"wet-labtypically":[12],"face":[13],"two":[14],"challenges.":[15,79],"First,":[16],"relevant":[17],"labeled":[18,89,126],"data":[19,90,97,118,230],"are":[20,91,98],"scarce":[21],"due":[22],"cost,":[24],"lack":[25],"public":[27],"availability,":[28],"novelty":[30],"experiment":[33,194],"question.":[35],"Second,":[36],"each":[37],"round":[38],"experimentation":[40],"requires":[41],"significant":[42],"investment":[43],"resources":[45],"and":[46,100,119,142,167,181,231],"labor,":[47],"putting":[48],"pressure":[49],"on":[50,124,186],"developers":[51],"data-driven":[53],"achieve":[56],"reasonable":[57],"results":[58],"with":[59],"very":[60],"little":[61],"data.":[62],"The":[63,80],"paradigm":[64],"transfer":[66],"learning":[67],"via":[68],"self-supervised":[69,134],"pretraining":[70,104,135],"presents":[71],"a":[72,111,138,144,153,192,223],"possibility":[73],"for":[74,157,175,199],"addressing":[75],"both":[76],"these":[78,116,229],"key":[81],"insight":[82],"leveraged":[83],"by":[84],"this":[85,129],"approach":[86,136],"is":[87],"that":[88,155,195],"rare,":[92],"but":[93],"unlabeled":[94,117],"protein":[95],"sequence":[96],"abundant":[99],"easily":[101],"downloaded.":[102],"Self-supervised":[103],"allows":[105,156],"large-scale":[106],"neural":[107,177],"networks":[108],"extract":[110],"library":[112],"patterns":[114,123],"from":[115,137],"potentially":[120],"wield":[121],"those":[122],"small":[125],"datasets.":[127],"In":[128],"work,":[130],"we":[131,164,190],"explore":[132],"number":[139],"angles":[141],"develop":[143,152,222],"broader":[145],"picture":[146],"its":[148],"efficacy.":[149],"We":[150,221],"first":[151],"benchmark":[154],"informative":[158],"comparison":[159],"pretrained":[161,176,236],"models.":[162,188],"Next,":[163],"demonstrate":[165],"mathematical":[166],"empirical":[168],"connections":[169],"between":[170],"predominant":[172],"architecture":[173],"networks,":[178],"transformer,":[180],"established":[182],"protein-modeling":[183],"techniques":[184],"based":[185],"Potts":[187],"Lastly,":[189],"introduce":[191],"novel":[193,224],"measures":[196],"antibody-antigen":[197,240],"binding":[198,241],"various":[200],"antibodies":[201],"against":[202],"model":[204],"antigen":[205],"Ovalbumin.":[206],"Use":[207],"hundreds":[209],"alanine-variants":[211],"Ovalbumin":[213],"leads":[214],"higher":[216],"resolution":[217],"than":[218],"existing":[219],"approaches.":[220],"clustering":[225],"algorithm":[226],"analyze":[228],"test":[232],"ability":[234],"models":[237],"predict":[239],"measured":[242],"experimentally.":[243]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2025-10-10T00:00:00"}