{"id":"https://openalex.org/W3000260630","doi":"https://doi.org/10.1109/tcbb.2020.2966633","title":"Protein Family Classification from Scratch: A CNN Based Deep Learning Approach","display_name":"Protein Family Classification from Scratch: A CNN Based Deep Learning Approach","publication_year":2020,"publication_date":"2020-01-14","ids":{"openalex":"https://openalex.org/W3000260630","doi":"https://doi.org/10.1109/tcbb.2020.2966633","mag":"3000260630","pmid":"https://pubmed.ncbi.nlm.nih.gov/31944984"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2020.2966633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2020.2966633","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043","2998-4165"],"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/ACM Transactions on Computational Biology and Bioinformatics","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/A5100726923","display_name":"Da Zhang","orcid":"https://orcid.org/0000-0003-3321-1835"},"institutions":[{"id":"https://openalex.org/I145608581","display_name":"University of Miami","ror":"https://ror.org/02dgjyy92","country_code":"US","type":"education","lineage":["https://openalex.org/I145608581"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Da Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Miami, Coral Gables, FL, USA"],"raw_orcid":"https://orcid.org/0000-0003-3321-1835","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Miami, Coral Gables, FL, USA","institution_ids":["https://openalex.org/I145608581"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038550961","display_name":"Mansur R. Kabuka","orcid":"https://orcid.org/0000-0003-2516-7942"},"institutions":[{"id":"https://openalex.org/I145608581","display_name":"University of Miami","ror":"https://ror.org/02dgjyy92","country_code":"US","type":"education","lineage":["https://openalex.org/I145608581"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mansur R. Kabuka","raw_affiliation_strings":["University of Miami, Coral Gables, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Miami, Coral Gables, FL, USA","institution_ids":["https://openalex.org/I145608581"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145608581"],"apc_list":null,"apc_paid":null,"fwci":1.5659,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.82737898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"18","issue":"5","first_page":"1996","last_page":"2007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9986000061035156,"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/uniprot","display_name":"UniProt","score":0.8768913745880127},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5923932790756226},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5493577718734741},{"id":"https://openalex.org/keywords/protein-family","display_name":"Protein family","score":0.4891958236694336},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.48546674847602844},{"id":"https://openalex.org/keywords/structural-classification-of-proteins-database","display_name":"Structural Classification of Proteins database","score":0.4822200536727905},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.48156359791755676},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4492703974246979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42437565326690674},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.3455979526042938},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3416711091995239},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.301907479763031},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2937409281730652},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.172166645526886},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.15337806940078735},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.1352671980857849}],"concepts":[{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.8768913745880127},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5923932790756226},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5493577718734741},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.4891958236694336},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.48546674847602844},{"id":"https://openalex.org/C58773245","wikidata":"https://www.wikidata.org/wiki/Q4832556","display_name":"Structural Classification of Proteins database","level":3,"score":0.4822200536727905},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.48156359791755676},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4492703974246979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42437565326690674},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.3455979526042938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3416711091995239},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.301907479763031},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2937409281730652},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.172166645526886},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.15337806940078735},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.1352671980857849},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","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":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2020.2966633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2020.2966633","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043","2998-4165"],"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/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:31944984","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31944984","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/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4290690937","display_name":null,"funder_award_id":"R44CA206782","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"}],"funders":[{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1019830208","https://openalex.org/W1501531009","https://openalex.org/W1832693441","https://openalex.org/W1938755728","https://openalex.org/W1982267716","https://openalex.org/W1984794455","https://openalex.org/W1991022130","https://openalex.org/W1997102766","https://openalex.org/W2020816856","https://openalex.org/W2039465881","https://openalex.org/W2085277871","https://openalex.org/W2107717979","https://openalex.org/W2127941101","https://openalex.org/W2143720865","https://openalex.org/W2152705149","https://openalex.org/W2153579005","https://openalex.org/W2158899491","https://openalex.org/W2162931300","https://openalex.org/W2166962853","https://openalex.org/W2253430994","https://openalex.org/W2336509392","https://openalex.org/W2340589369","https://openalex.org/W2433743436","https://openalex.org/W2493916176","https://openalex.org/W2508498860","https://openalex.org/W2549717400","https://openalex.org/W2611907773","https://openalex.org/W2616246685","https://openalex.org/W2749122933","https://openalex.org/W2777094228","https://openalex.org/W2792764867","https://openalex.org/W2807818025","https://openalex.org/W2885583144","https://openalex.org/W2900896604","https://openalex.org/W2921685418","https://openalex.org/W2951559648","https://openalex.org/W2952230511","https://openalex.org/W2962851944","https://openalex.org/W2963457143","https://openalex.org/W2963921497","https://openalex.org/W2964159778","https://openalex.org/W2964257300","https://openalex.org/W4294170691","https://openalex.org/W4299676335","https://openalex.org/W6640598943","https://openalex.org/W6655478935","https://openalex.org/W6682691769","https://openalex.org/W6683738474","https://openalex.org/W6683965311","https://openalex.org/W6685133223","https://openalex.org/W6725018381","https://openalex.org/W6749825310"],"related_works":["https://openalex.org/W2103435205","https://openalex.org/W2161189461","https://openalex.org/W2926533301","https://openalex.org/W2972635466","https://openalex.org/W2803517106","https://openalex.org/W2157190239","https://openalex.org/W2164753093","https://openalex.org/W4318897997","https://openalex.org/W2041862730","https://openalex.org/W2019177511"],"abstract_inverted_index":{"Next-generation":[0],"sequencing":[1],"techniques":[2],"provide":[3],"us":[4],"with":[5,24,82,105,136],"an":[6],"opportunity":[7],"for":[8],"generating":[9],"sequenced":[10],"proteins":[11,28,37,108],"and":[12,17,67,85],"identifying":[13],"the":[14,35,39,111,121,129,141],"biological":[15],"families":[16,88,116,138],"functions":[18],"of":[19,30,34,113],"these":[20],"proteins.":[21],"However,":[22],"compared":[23],"identified":[25],"proteins,":[26],"uncharacterized":[27],"consist":[29],"a":[31],"notable":[32],"percentage":[33],"overall":[36],"in":[38],"bioinformatics":[40],"research":[41],"field.":[42],"Traditional":[43],"family":[44],"classification":[45],"methods":[46],"often":[47],"devote":[48],"themselves":[49],"to":[50,78,109,131,144],"extracting":[51],"N-Gram":[52],"features":[53,81],"from":[54,140],"sequences":[55,135],"while":[56],"ignoring":[57],"motif":[58],"information":[59,64],"as":[60,62],"well":[61],"affinity":[63],"between":[65],"motifs":[66],"adjacent":[68],"amino":[69,101,122],"acids.":[70],"Previous":[71],"clustering-based":[72],"algorithms":[73],"have":[74],"typically":[75,163],"been":[76],"used":[77],"define":[79],"protein":[80,87,115,134,159],"domain":[83],"knowledge":[84],"annotate":[86],"based":[89,100],"on":[90],"extensive":[91],"data":[92],"samples.":[93],"In":[94],"this":[95],"paper,":[96],"we":[97,127,152],"apply":[98,128],"CNN":[99],"acid":[102,123],"representation":[103],"learning":[104],"limited":[106],"characterized":[107],"explore":[110],"performances":[112],"annotated":[114],"by":[117,165],"taking":[118],"into":[119],"account":[120],"location":[124],"information.":[125],"Additionally,":[126],"method":[130],"all":[132],"reviewed":[133],"their":[137],"retrieved":[139],"UniProt":[142],"database":[143],"evaluate":[145],"our":[146,154],"approach.":[147],"Last":[148],"but":[149],"not":[150],"least,":[151],"verify":[153],"model":[155],"using":[156],"those":[157],"unreviewed":[158],"records,":[160],"which":[161],"is":[162],"ignored":[164],"other":[166],"methods.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}