{"id":"https://openalex.org/W7057203522","doi":null,"title":"How to Speak Protein? - Representation Learning for Protein Prediction","display_name":"How to Speak Protein? - Representation Learning for Protein Prediction","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W7057203522"},"language":"en","primary_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1660317","doi":null,"is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1660317","pdf_url":"https://mediatum.ub.tum.de/doc/1660317/document.pdf","source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mediatum.ub.tum.de/doc/1660317/document.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075726670","display_name":"Michael Heinzinger","orcid":"https://orcid.org/0000-0002-9601-3580","observed_orcids":["https://orcid.org/0000-0002-9601-3580"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heinzinger, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Rost, Burkhard","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rost, Burkhard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Technische Universit\u00e4t M\u00fcnchen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Technische Universit\u00e4t M\u00fcnchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":true,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9794999957084656,"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":0.9794999957084656,"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":0.015599999576807022,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.000699999975040555,"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-function-prediction","display_name":"protein function prediction","score":0.9020000100135803},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"protein structure prediction","score":0.9900000095367432},{"id":"https://openalex.org/keywords/protein-sequence-representation","display_name":"protein sequence representation","score":0.7099999785423279},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.9900000095367432},{"id":"https://openalex.org/keywords/evolutionary-information","display_name":"evolutionary information","score":0.8360000252723694},{"id":"https://openalex.org/keywords/single-sequence-prediction","display_name":"single-sequence prediction","score":0.6340000033378601}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6801000237464905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6658999919891357},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6251000165939331},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5134999752044678},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.4147000014781952},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.3684999942779541},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.34470000863075256},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.3325999975204468},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C50292564","wikidata":"https://www.wikidata.org/wiki/Q2462783","display_name":"Computational learning theory","level":3,"score":0.2971999943256378},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.2750000059604645},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C111364199","wikidata":"https://www.wikidata.org/wiki/Q2915896","display_name":"Protein methods","level":4,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:mediatum.ub.tum.de:node/1660317","doi":null,"is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1660317","pdf_url":"https://mediatum.ub.tum.de/doc/1660317/document.pdf","source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"thesis"},{"id":"pmh:oai:aleph.bib-bvb.de:BVB01-034075867","doi":null,"is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/?id=1660317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Hochschulschrift"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1660317","doi":null,"is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1660317","pdf_url":"https://mediatum.ub.tum.de/doc/1660317/document.pdf","source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1270295441","display_name":null,"funder_award_id":"DFG-GZ: RO1320/4-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G505595760","display_name":null,"funder_award_id":"RO1320/4\u20101","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320308269","display_name":"Alexander von Humboldt-Stiftung","ror":"https://ror.org/012kf4317"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320334763","display_name":"Leibniz-Gemeinschaft","ror":"https://ror.org/01n6r0e97"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7057203522.pdf","grobid_xml":"https://content.openalex.org/works/W7057203522.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W2133564696","https://openalex.org/W2139294595","https://openalex.org/W2157585454","https://openalex.org/W2598634450","https://openalex.org/W2787560479","https://openalex.org/W2896457183","https://openalex.org/W2911109671","https://openalex.org/W2950954328","https://openalex.org/W2951143673","https://openalex.org/W2964121744","https://openalex.org/W2975059944","https://openalex.org/W2981852735","https://openalex.org/W2996035354","https://openalex.org/W3009202743","https://openalex.org/W3010387158","https://openalex.org/W3030163527","https://openalex.org/W3042271775","https://openalex.org/W3093517588","https://openalex.org/W3094502228","https://openalex.org/W3111174583","https://openalex.org/W3118936575","https://openalex.org/W3211795435","https://openalex.org/W4223581484","https://openalex.org/W4225868104","https://openalex.org/W4226082499","https://openalex.org/W4229042118","https://openalex.org/W4281291878","https://openalex.org/W4281790889","https://openalex.org/W4282984452","https://openalex.org/W4394670654","https://openalex.org/W7133208784","https://openalex.org/W7133225605"],"related_works":["https://openalex.org/W4283588627","https://openalex.org/W2410672604","https://openalex.org/W2995514860","https://openalex.org/W7165929369","https://openalex.org/W2993794083","https://openalex.org/W4411869473","https://openalex.org/W4220991280","https://openalex.org/W4389028818","https://openalex.org/W3166142427","https://openalex.org/W4399911287"],"abstract_inverted_index":{"Predicting":[0],"protein":[1,42,68],"function":[2],"and":[3,29],"structure":[4],"from":[5,38],"sequence":[6],"is":[7],"one":[8],"important":[9],"challenge":[10,25],"for":[11],"computational":[12],"biology.":[13],"For":[14],"nearly":[15],"3":[16],"decades,":[17],"most":[18],"approaches":[19],"that":[20],"took":[21],"up":[22],"on":[23,66],"this":[24],"combined":[26],"machine":[27],"learning":[28,40],"evolutionary":[30],"information":[31],"(EI).":[32],"Here,":[33],"I":[34],"introduced":[35],"novel":[36],"concepts":[37],"representation":[39],"to":[41,44,51],"sequences":[43],"bypass":[45],"some":[46],"of":[47],"the":[48],"limitations":[49],"inherent":[50],"EI.":[52],"The":[53],"proposed":[54],"solution":[55],"rivals":[56],"EI-based":[57],"methods":[58],"in":[59],"their":[60],"predictive":[61],"performance":[62],"while":[63],"relying":[64],"only":[65],"single":[67],"sequences.":[69]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}