{"id":"https://openalex.org/W4290671900","doi":"https://doi.org/10.1145/3543377.3543385","title":"Deep-StRIP: Deep Learning Approach for Structural Repeat Identification in Proteins","display_name":"Deep-StRIP: Deep Learning Approach for Structural Repeat Identification in Proteins","publication_year":2022,"publication_date":"2022-05-27","ids":{"openalex":"https://openalex.org/W4290671900","doi":"https://doi.org/10.1145/3543377.3543385"},"language":"en","primary_location":{"id":"doi:10.1145/3543377.3543385","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543377.3543385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 14th International Conference on Bioinformatics and Biomedical Technology","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5005134353","display_name":"KANAK GARG","orcid":null},"institutions":[{"id":"https://openalex.org/I188963388","display_name":"International Institute of Information Technology","ror":"https://ror.org/02dernx73","country_code":"IN","type":"education","lineage":["https://openalex.org/I188963388"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"KANAK GARG","raw_affiliation_strings":["Center for Computational Natural Sciences and Bioinformatics (CCNSB), International Institute of Information Technology, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Natural Sciences and Bioinformatics (CCNSB), International Institute of Information Technology, India","institution_ids":["https://openalex.org/I188963388"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073509875","display_name":"Saksham Gupta","orcid":"https://orcid.org/0000-0002-1762-9185"},"institutions":[{"id":"https://openalex.org/I188963388","display_name":"International Institute of Information Technology","ror":"https://ror.org/02dernx73","country_code":"IN","type":"education","lineage":["https://openalex.org/I188963388"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"SAKSHAM GUPTA","raw_affiliation_strings":["Center for Computational Natural Sciences and Bioinformatics (CCNSB), International Institute of Information Technology, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Natural Sciences and Bioinformatics (CCNSB), International Institute of Information Technology, India","institution_ids":["https://openalex.org/I188963388"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I188963388"],"apc_list":null,"apc_paid":null,"fwci":0.0839,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40921939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"48","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","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"}},"topics":[{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","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/T11162","display_name":"Enzyme Structure and Function","score":0.998199999332428,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9965999722480774,"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/deep-learning","display_name":"Deep learning","score":0.6779451370239258},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6246987581253052},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.609054684638977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5298654437065125},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4362068772315979},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1640929877758026}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6779451370239258},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6246987581253052},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.609054684638977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5298654437065125},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4362068772315979},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1640929877758026},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543377.3543385","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543377.3543385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 14th International Conference on Bioinformatics and Biomedical Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1867763642","https://openalex.org/W1987393189","https://openalex.org/W1991731239","https://openalex.org/W2002240322","https://openalex.org/W2008560636","https://openalex.org/W2015224025","https://openalex.org/W2054681398","https://openalex.org/W2067330006","https://openalex.org/W2094104050","https://openalex.org/W2105961968","https://openalex.org/W2116426890","https://openalex.org/W2123130967","https://openalex.org/W2130479394","https://openalex.org/W2132505033","https://openalex.org/W2135007755","https://openalex.org/W2143370123","https://openalex.org/W2147595457","https://openalex.org/W2162085776","https://openalex.org/W2280283052","https://openalex.org/W2584635762","https://openalex.org/W2767106145","https://openalex.org/W2963121313","https://openalex.org/W3039636734","https://openalex.org/W3135881764","https://openalex.org/W4233120011"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W2939353110","https://openalex.org/W3009238340","https://openalex.org/W4230611425","https://openalex.org/W2948658236","https://openalex.org/W3038019660","https://openalex.org/W2920938200","https://openalex.org/W2991240825","https://openalex.org/W2731165298"],"abstract_inverted_index":{"Internal":[0,22],"repetitions":[1],"in":[2,11,27,86,94,106,113,184,201,235],"eukaryotic":[3,28],"proteins":[4,61,71,110,135],"are":[5,111,137],"three":[6],"times":[7],"more":[8],"prevalent":[9],"than":[10],"prokaryotic":[12],"proteins,":[13,34,36,39,43],"implying":[14],"that":[15],"the":[16,81,168,197,202,207],"organism":[17],"may":[18],"benefit":[19,65],"from":[20],"them.":[21,68],"repeats":[23,52,85,93,152,183],"have":[24,72],"been":[25,73],"found":[26],"functions":[29],"such":[30,79],"as":[31,80],"connective":[32],"tissue":[33],"cytoskeletal":[35],"ribonucleoproteins,":[37],"muscle":[38],"brain":[40],"and":[41,44,57,91,96,127,180,230],"synapse":[42],"cell":[45],"adhesion":[46],"proteins.":[47],"The":[48],"ability":[49],"of":[50,66,83,104,117,151,170,174,191,212],"protein":[51,214],"to":[53,75,100,144],"confer":[54],"multiple":[55],"binding":[56],"structural":[58,175,193,198],"roles":[59],"on":[60],"is":[62,156,218],"another":[63],"key":[64],"studying":[67],"Tandem":[69],"repeat":[70,134],"related":[74],"several":[76],"complex":[77],"diseases,":[78],"function":[82],"Leucine-rich":[84],"Parkinson's":[87],"disease,":[88],"ANK,":[89],"HEAT,":[90],"ARM":[92],"cancer,":[95],"so":[97],"on,":[98],"due":[99],"their":[101,118],"high":[102,119,122],"frequency":[103],"occurrence":[105],"humans":[107],"(30%).":[108],"Repeat":[109],"useful":[112],"biological":[114],"applications":[115],"because":[116],"surface-to-volume":[120],"ratio,":[121],"target":[123],"affinity,":[124],"compact":[125],"size,":[126],"shape":[128],"stability.":[129],"For":[130],"example,":[131],"designed":[132],"ankyrin":[133],"(DARPins)":[136],"being":[138],"developed":[139],"for":[140,167],"targeted":[141],"therapies.":[142],"Due":[143],"less":[145],"constraints":[146],"at":[147,153],"sequence":[148],"level,":[149],"detection":[150,169],"structure":[154],"level":[155],"desirable.":[157],"Here":[158],"we":[159],"propose":[160],"a":[161,213],"deep":[162],"learning-based":[163],"approach":[164],"called":[165],"Deep-StRIP":[166],"two":[171],"major":[172],"class":[173],"repeats,":[176],"namely,":[177],"Class":[178,181],"III":[179],"IV":[182],"Kajava's":[185],"classification,":[186],"which":[187,205],"covers":[188],"over":[189],"90%":[190],"known":[192],"repeats.":[194],"It":[195],"exploits":[196],"information":[199],"present":[200],"distance":[203],"matrix":[204],"captures":[206],"internal":[208],"distances":[209],"between":[210],"residues":[211],"chain.":[215],"Performance":[216],"evaluation":[217],"carried":[219],"out":[220],"by":[221],"comparison":[222],"with":[223,233],"other":[224],"state-of-the-art":[225],"methods":[226],"viz":[227],"Console,":[228],"TAPO":[229],"ReUPred":[231],"along":[232],"annotations":[234],"UniProt.":[236]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}