{"id":"https://openalex.org/W4405270465","doi":"https://doi.org/10.1109/cvmi61877.2024.10781809","title":"TransProtFam: A Transformer Derived Deep Learning Model for Hierarchical Protein Family Annotation","display_name":"TransProtFam: A Transformer Derived Deep Learning Model for Hierarchical Protein Family Annotation","publication_year":2024,"publication_date":"2024-10-19","ids":{"openalex":"https://openalex.org/W4405270465","doi":"https://doi.org/10.1109/cvmi61877.2024.10781809"},"language":"en","primary_location":{"id":"doi:10.1109/cvmi61877.2024.10781809","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvmi61877.2024.10781809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","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/A5050446730","display_name":"Chinju John","orcid":"https://orcid.org/0000-0001-8431-0775"},"institutions":[{"id":"https://openalex.org/I68695296","display_name":"Indian Institute of Information Technology and Management, Kerala","ror":"https://ror.org/02w9cdh50","country_code":"IN","type":"education","lineage":["https://openalex.org/I68695296"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Chinju John","raw_affiliation_strings":["Indian Institute of Information Technology Kottayam,Department of Computer Science and Engineering,Pala,Kerala,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Kottayam,Department of Computer Science and Engineering,Pala,Kerala,India","institution_ids":["https://openalex.org/I68695296"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083804893","display_name":"Jayakrushna Sahoo","orcid":"https://orcid.org/0000-0002-4514-3916"},"institutions":[{"id":"https://openalex.org/I68695296","display_name":"Indian Institute of Information Technology and Management, Kerala","ror":"https://ror.org/02w9cdh50","country_code":"IN","type":"education","lineage":["https://openalex.org/I68695296"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jayakrushna Sahoo","raw_affiliation_strings":["Indian Institute of Information Technology Kottayam,Department of Computer Science and Engineering,Pala,Kerala,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Kottayam,Department of Computer Science and Engineering,Pala,Kerala,India","institution_ids":["https://openalex.org/I68695296"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050446730"],"corresponding_institution_ids":["https://openalex.org/I68695296"],"apc_list":null,"apc_paid":null,"fwci":0.2321,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59753718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9991000294685364,"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":0.9991000294685364,"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":0.996399998664856,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9936000108718872,"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/computer-science","display_name":"Computer science","score":0.6930632591247559},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6710661053657532},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6300215721130371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5498290061950684},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.108279287815094},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08118543028831482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6930632591247559},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6710661053657532},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6300215721130371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5498290061950684},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.108279287815094},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08118543028831482},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvmi61877.2024.10781809","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvmi61877.2024.10781809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328"],"abstract_inverted_index":{"Transformers":[0],"are":[1,32],"knowledge":[2,51],"reservoirs":[3],"trained":[4,147],"on":[5,71,148],"vast":[6],"and":[7,42,76,98,117,122,134,157],"heterogeneous":[8],"data":[9],"sets":[10],"with":[11,112],"the":[12,36,50,93,127,135],"potential":[13],"for":[14,24,34,61,152],"cross-functional":[15],"tasks.":[16],"These":[17],"large":[18,145],"corpus-trained":[19],"models":[20,68,146],"can":[21],"be":[22],"leveraged":[23],"cumbersome":[25],"tasks":[26,154],"like":[27,74],"Protein":[28],"family":[29,63],"annotations":[30],"which":[31,125],"pivotal":[33],"discerning":[35],"features":[37],"of":[38,66,95,115],"a":[39],"protein":[40,55,62,80,149],"sequence":[41,150],"its":[43],"functional":[44],"roles.":[45],"Here":[46],"we":[47,138],"have":[48],"harnessed":[49],"derived":[52],"from":[53],"such":[54,67],"sequence-based":[56],"transformers":[57],"to":[58,78,91,99],"fine-tune":[59],"them":[60],"annotation.The":[64],"performance":[65],"was":[69,89],"compared":[70],"benchmark":[72],"datasets":[73],"GPCR":[75],"PoG":[77],"annotate":[79],"sequences":[81],"at":[82,119],"hierarchical":[83],"levels.":[84],"Parameter":[85],"Efficient":[86],"Fine":[87],"Tuning":[88],"used":[90],"optimise":[92],"number":[94],"trainable":[96],"parameters":[97],"perform":[100],"less":[101],"computationally":[102],"expensive":[103],"training.":[104],"Our":[105,132],"proposed":[106],"model":[107],"-TransProtFam":[108],"could":[109],"come":[110],"up":[111],"accuracy":[113],"scores":[114],"99.43%,90.85%":[116],"84.49%":[118],"family,":[120],"sub-family":[121],"sub-subfamily":[123],"levels,":[124],"exceeds":[126],"state-of-the-art":[128],"neural":[129],"network":[130],"models.":[131],"findings":[133],"finetuning":[136],"process":[137],"employed":[139],"may":[140],"provide":[141],"insights":[142],"into":[143],"utilising":[144],"corpora":[151],"specific":[153],"in":[155],"Bioinformatics":[156],"related":[158],"domains.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}