{"id":"https://openalex.org/W2978332810","doi":"https://doi.org/10.1109/ijcnn.2019.8852381","title":"Representation-dimensionality Trade-off in Biological Sequence-based Inference","display_name":"Representation-dimensionality Trade-off in Biological Sequence-based Inference","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2978332810","doi":"https://doi.org/10.1109/ijcnn.2019.8852381","mag":"2978332810"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8852381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","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/A5103870011","display_name":"Bahman Asadi","orcid":null},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Bahman Asadi","raw_affiliation_strings":["School of Electronics and Computer Science, University of Southampton, Southampton, UK"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Computer Science, University of Southampton, Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033579333","display_name":"Mahesan Niranjan","orcid":"https://orcid.org/0000-0001-7021-140X"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mahesan Niranjan","raw_affiliation_strings":["School of Electronics and Computer Science, University of Southampton, Southampton, UK"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Computer Science, University of Southampton, Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103870011"],"corresponding_institution_ids":["https://openalex.org/I43439940"],"apc_list":null,"apc_paid":null,"fwci":0.0852,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.47393507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9968000054359436,"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/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6949560642242432},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6449306011199951},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.6163239479064941},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5715424418449402},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5286800265312195},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5205895900726318},{"id":"https://openalex.org/keywords/statistical-inference","display_name":"Statistical inference","score":0.45551198720932007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43906939029693604},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4126984477043152},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3781619071960449},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37750548124313354}],"concepts":[{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6949560642242432},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6449306011199951},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6163239479064941},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5715424418449402},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5286800265312195},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5205895900726318},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.45551198720932007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43906939029693604},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4126984477043152},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3781619071960449},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37750548124313354},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2019.8852381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W339865234","https://openalex.org/W1969837908","https://openalex.org/W1978326290","https://openalex.org/W1982267716","https://openalex.org/W1982652137","https://openalex.org/W2009086942","https://openalex.org/W2009570821","https://openalex.org/W2022058405","https://openalex.org/W2042209813","https://openalex.org/W2052376307","https://openalex.org/W2060178110","https://openalex.org/W2073727170","https://openalex.org/W2078328390","https://openalex.org/W2087928415","https://openalex.org/W2097175728","https://openalex.org/W2104857116","https://openalex.org/W2104972430","https://openalex.org/W2109363337","https://openalex.org/W2119387367","https://openalex.org/W2119423166","https://openalex.org/W2120683379","https://openalex.org/W2120770540","https://openalex.org/W2122189635","https://openalex.org/W2122945697","https://openalex.org/W2124158580","https://openalex.org/W2126957978","https://openalex.org/W2128801478","https://openalex.org/W2129905273","https://openalex.org/W2132064154","https://openalex.org/W2135909366","https://openalex.org/W2144948767","https://openalex.org/W2153635508","https://openalex.org/W2157892451","https://openalex.org/W2170960297","https://openalex.org/W2341171179","https://openalex.org/W2796639075","https://openalex.org/W2882319491","https://openalex.org/W4205699531","https://openalex.org/W4230276186","https://openalex.org/W4245668478","https://openalex.org/W4254721730","https://openalex.org/W6678649364","https://openalex.org/W6679484955"],"related_works":["https://openalex.org/W1995622179","https://openalex.org/W4391160746","https://openalex.org/W1484111231","https://openalex.org/W1909208367","https://openalex.org/W1552543208","https://openalex.org/W2994280181","https://openalex.org/W2074396517","https://openalex.org/W2166963679","https://openalex.org/W2187269125","https://openalex.org/W1641615907"],"abstract_inverted_index":{"Statistical":[0,188],"inference":[1,237],"from":[2,168,191],"the":[3,12,24,67,71,89,93,103,107,117,145,169,186,192,232,248],"analysis":[4],"of":[5,14,19,26,70,73,81,83,86,92,129,185,203,206,219],"biological":[6],"sequences":[7],"is":[8,45,154,198,258,267],"widely":[9,241],"used":[10],"in":[11,48,109,116,125,144,156,239,247],"prediction":[13],"structure":[15,139],"and":[16,34,88,137,244],"biochemical":[17,176,256],"functions":[18],"newly":[20],"found":[21],"macromolecules.":[22],"For":[23],"application":[25],"machine":[27],"learning":[28],"methodologies":[29],"such":[30,39],"as":[31],"kernel":[32],"methods":[33],"artificial":[35],"neural":[36],"networks":[37],"for":[38],"inference,":[40,131],"variable":[41],"length":[42],"sequence":[43,214],"data":[44,215],"often":[46,59,149],"embedded":[47],"a":[49,77,114,254,269],"finite":[50],"dimensional":[51],"real-valued":[52],"space.":[53,95,120,222],"The":[54],"corresponding":[55,118],"embedding":[56,94],"dimensions":[57,218],"are":[58,172],"high,":[60],"leading":[61],"to":[62,152,260,263],"technical":[63],"difficulties":[64],"centred":[65],"around":[66],"statistical":[68,130,270],"concept":[69],"curse":[72],"dimensionality.":[74],"We":[75,121,141,162],"demonstrate":[76],"trade-off":[78,124],"between":[79],"fidelity":[80],"representation":[82,197,207],"amino":[84,99,195,233],"acids":[85],"proteins":[87],"resulting":[90],"dimensionality":[91,227],"Clustering":[96],"chemically":[97],"similar":[98,151],"acids,":[100],"thereby":[101],"reducing":[102],"alphabet":[104,164,235],"size,":[105],"reduces":[106],"accuracy":[108],"their":[110],"variation,":[111],"but":[112],"achieves":[113],"reduction":[115,165,228],"feature":[119,189,264],"show":[122,142],"this":[123],"three":[126],"different":[127],"problems":[128,243],"namely,":[132],"protein-protein":[133],"interaction,":[134],"remote":[135],"homology":[136],"secondary":[138],"prediction.":[140],"that":[143,226],"reduced":[146],"space":[147],"performance":[148,238],"improves":[150,236],"what":[153],"seen":[155],"\"diminishing":[157],"returns\"":[158],"type":[159],"reward-effort":[160],"curves.":[161],"find":[163],"schemes":[166],"taken":[167],"literature,":[170],"which":[171,252,266],"based":[173,229],"on":[174,230],"some":[175],"rationale,":[177],"perform":[178],"significantly":[179],"better":[180],"than":[181],"arbitrary":[182],"random":[183],"clustering":[184],"alphabets.":[187],"selection":[190,265],"full":[193],"20":[194],"acid":[196,234],"not":[199],"competitive":[200],"with":[201],"any":[202],"these.":[204],"Dimensionality":[205],"has":[208,253],"an":[209,220],"important":[210],"role":[211],"when":[212],"mapping":[213],"onto":[216],"fixed":[217],"Euclidean":[221],"This":[223],"work":[224],"shows":[225],"compressing":[231],"two":[240],"studied":[242],"degrades":[245],"gracefully":[246],"third.":[249],"Alphabet":[250],"reduction,":[251],"principled":[255],"basis,":[257],"shown":[259],"be":[261],"superior":[262],"purely":[268],"exercise.":[271]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}