{"id":"https://openalex.org/W2139747063","doi":null,"title":"Synthesizing Regularity Exposing Attributes in Large Protein Databases","display_name":"Synthesizing Regularity Exposing Attributes in Large Protein Databases","publication_year":1993,"publication_date":"1993-05-01","ids":{"openalex":"https://openalex.org/W2139747063","mag":"2139747063"},"language":"en","primary_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/6789","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/6789","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W2139747063"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/6789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026865865","display_name":"Michael de la Maza","orcid":"https://orcid.org/0009-0000-8821-0886","observed_orcids":["https://orcid.org/0009-0000-8821-0886"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Michael de la Maza","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0000-8821-0886","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5026865865"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1089,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.28790168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10044","display_name":"Protein Structure and Dynamics","score":0.88919997215271,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.88919997215271,"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":0.10109999775886536,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.0015999999595806003,"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-databases","display_name":"protein databases","score":0.6129999756813049},{"id":"https://openalex.org/keywords/protein-secondary-structure-prediction","display_name":"secondary structure prediction","score":0.9480000138282776},{"id":"https://openalex.org/keywords/protein-tertiary-structure-prediction","display_name":"protein tertiary structure prediction","score":0.9129999876022339},{"id":"https://openalex.org/keywords/protein-primary-structure","display_name":"protein primary structure","score":0.5709999799728394},{"id":"https://openalex.org/keywords/protein-secondary-structure","display_name":"protein secondary structure","score":0.9599999785423279},{"id":"https://openalex.org/keywords/neural-network-training","display_name":"neural network training","score":0.5479999780654907},{"id":"https://openalex.org/keywords/pac-learning","display_name":"PAC learning","score":0.7070000171661377}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7511900067329407},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7282705307006836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5994544625282288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5192906260490417},{"id":"https://openalex.org/C62614982","wikidata":"https://www.wikidata.org/wiki/Q904984","display_name":"Protein secondary structure","level":2,"score":0.4653518795967102},{"id":"https://openalex.org/C75599170","wikidata":"https://www.wikidata.org/wiki/Q898483","display_name":"Protein tertiary structure","level":2,"score":0.4535329341888428},{"id":"https://openalex.org/C2988224531","wikidata":"https://www.wikidata.org/wiki/Q20830730","display_name":"Network structure","level":2,"score":0.4534199833869934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44151121377944946},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3880856931209564},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36335766315460205},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34754058718681335},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3412851095199585},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.16646146774291992},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.07747271656990051},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:dspace.mit.edu:1721.1/6789","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/6789","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"mag:2139747063","doi":null,"is_oa":false,"landing_page_url":"http://dspace.mit.edu/handle/1721.1/6789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.56.6334","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.56.6334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://publications.ai.mit.edu/ai-publications/1000-1499/AITR-1444.ps.Z","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/6789","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/6789","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7407884558","display_name":null,"funder_award_id":"N00014-91-J-4038","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320309369","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2139747063.pdf","grobid_xml":"https://content.openalex.org/works/W2139747063.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2156865125","https://openalex.org/W2057157558","https://openalex.org/W2035066314","https://openalex.org/W2012515247","https://openalex.org/W1981132436","https://openalex.org/W2059512901","https://openalex.org/W1977387088","https://openalex.org/W7024224518","https://openalex.org/W4236601012","https://openalex.org/W185593474"],"abstract_inverted_index":{"This":[0],"thesis":[1,92],"describes":[2,93],"a":[3,60,77],"system":[4,22],"that":[5,28,69],"synthesizes":[6],"regularity":[7],"exposing":[8],"attributes":[9],"from":[10],"large":[11],"protein":[12],"databases.":[13],"After":[14],"processing":[15],"primary":[16],"and":[17,44,106],"secondary":[18,65,96],"structure":[19,48,66,97],"data,":[20],"this":[21,55],"discovers":[23],"an":[24,102],"amino":[25,39,86],"acid":[26,40,87],"representation":[27,58],"captures":[29],"what":[30],"are":[31],"thought":[32],"to":[33,72],"be":[34],"the":[35,64,73,82,91,107],"three":[36],"most":[37],"important":[38],"characteristics":[41],"(size,":[42],"charge,":[43],"hydrophobicity)":[45],"for":[46],"tertiary":[47],"prediction.":[49],"A":[50],"neural":[51,78],"network":[52,79],"trained":[53,80],"using":[54,81,101],"16":[56],"bit":[57,85],"achieves":[59],"performance":[61],"accuracy":[62],"on":[63,95],"prediction":[67,98],"problem":[68],"is":[70],"comparable":[71],"one":[74],"achieved":[75],"by":[76],"standard":[83],"24":[84],"representation.":[88],"In":[89],"addition,":[90],"bounds":[94],"accuracy,":[99],"derived":[100],"optimal":[103],"learning":[104],"algorithm":[105],"probably":[108],"approximately":[109],"correct":[110],"(PAC)":[111],"model.":[112]},"counts_by_year":[],"updated_date":"2026-11-15T12:55:33.944570","created_date":"2016-06-24T00:00:00"}