{"id":"https://openalex.org/W4416285287","doi":"https://doi.org/10.1021/acs.jcim.5c01768","title":"From Signal to Symphony: Exploring 2D Sequence Representations for Protein Function Prediction","display_name":"From Signal to Symphony: Exploring 2D Sequence Representations for Protein Function Prediction","publication_year":2025,"publication_date":"2025-11-17","ids":{"openalex":"https://openalex.org/W4416285287","doi":"https://doi.org/10.1021/acs.jcim.5c01768","pmid":"https://pubmed.ncbi.nlm.nih.gov/41247925"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c01768","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c01768","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","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/A5051449178","display_name":"Yiquan Wang","orcid":"https://orcid.org/0000-0003-1417-5752"},"institutions":[{"id":"https://openalex.org/I173268674","display_name":"Texas A&M University System","ror":"https://ror.org/0034eay46","country_code":"US","type":"education","lineage":["https://openalex.org/I173268674"]},{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yiquan Wang","raw_affiliation_strings":["College of Mathematics and System Science","Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology","Xinjiang University","College of Mathematics and System Science, Xinjiang University, Urumqi 830046 Xinjiang, China"],"affiliations":[{"raw_affiliation_string":"College of Mathematics and System Science","institution_ids":["https://openalex.org/I173268674"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology","institution_ids":[]},{"raw_affiliation_string":"Xinjiang University","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"College of Mathematics and System Science, Xinjiang University, Urumqi 830046 Xinjiang, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Minnuo Cai","orcid":"https://orcid.org/0009-0007-7151-8068"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minnuo Cai","raw_affiliation_strings":["Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology","Xinjiang University","Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology, Xinjiang University, Urumqi 830049 Xinjiang, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology","institution_ids":[]},{"raw_affiliation_string":"Xinjiang University","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology, Xinjiang University, Urumqi 830049 Xinjiang, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110631224","display_name":"Yuhua Dong","orcid":"https://orcid.org/0009-0001-4314-6806"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4210134033","display_name":"Advanced Research Institute","ror":"https://ror.org/03e1yhr47","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210134033"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yuhua Dong","raw_affiliation_strings":["Advanced Research Institute of Multidisciplinary Sciences","Beijing Institute of Technology","Advanced Research Institute of Multidisciplinary Sciences, Beijing Institute of Technology, Beijing 100081, China"],"affiliations":[{"raw_affiliation_string":"Advanced Research Institute of Multidisciplinary Sciences","institution_ids":["https://openalex.org/I4210134033"]},{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Advanced Research Institute of Multidisciplinary Sciences, Beijing Institute of Technology, Beijing 100081, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101226885","display_name":"Yahui Ma","orcid":"https://orcid.org/0009-0004-7443-5645"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahui Ma","raw_affiliation_strings":["Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology","Xinjiang University","Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology, Xinjiang University, Urumqi 830049 Xinjiang, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology","institution_ids":[]},{"raw_affiliation_string":"Xinjiang University","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology, Xinjiang University, Urumqi 830049 Xinjiang, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043149936","display_name":"Kai Wei","orcid":"https://orcid.org/0000-0001-5431-8290"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Wei","raw_affiliation_strings":["Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology","Xinjiang University","Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology, Xinjiang University, Urumqi 830049 Xinjiang, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology","institution_ids":[]},{"raw_affiliation_string":"Xinjiang University","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology, Xinjiang University, Urumqi 830049 Xinjiang, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5043149936"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23575253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"65","issue":"23","first_page":"12723","last_page":"12736"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.3790000081062317,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.3790000081062317,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/T11642","display_name":"Genomics and Rare Diseases","score":0.06750000268220901,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.05810000002384186,"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/spectrogram","display_name":"Spectrogram","score":0.645799994468689},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5608999729156494},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5418999791145325},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4803999960422516},{"id":"https://openalex.org/keywords/casp","display_name":"CASP","score":0.4733000099658966},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4553000032901764},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.4178999960422516},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4174000024795532},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4036000072956085},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.39010000228881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6791999936103821},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.645799994468689},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5608999729156494},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5418999791145325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5235999822616577},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4803999960422516},{"id":"https://openalex.org/C66153294","wikidata":"https://www.wikidata.org/wiki/Q899291","display_name":"CASP","level":4,"score":0.4733000099658966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4553000032901764},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4036000072956085},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.39010000228881836},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.384799987077713},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.3603000044822693},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.3409000039100647},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.320499986410141},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.31299999356269836},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30250000953674316},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.29429998993873596},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.29159998893737793},{"id":"https://openalex.org/C111364199","wikidata":"https://www.wikidata.org/wiki/Q2915896","display_name":"Protein methods","level":4,"score":0.2906999886035919},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2897000014781952},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2847000062465668},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C154428179","wikidata":"https://www.wikidata.org/wiki/Q24721050","display_name":"PDZ domain","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25220000743865967}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.5c01768","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c01768","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:41247925","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41247925","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":"Journal of chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8320439784","display_name":null,"funder_award_id":"2024D01C216","funder_id":"https://openalex.org/F4320311028","funder_display_name":"Natural Science Foundation of Xinjiang Province"}],"funders":[{"id":"https://openalex.org/F4320311028","display_name":"Natural Science Foundation of Xinjiang Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1520649887","https://openalex.org/W1941659294","https://openalex.org/W1969231606","https://openalex.org/W1979915001","https://openalex.org/W2010356367","https://openalex.org/W2010927954","https://openalex.org/W2028440694","https://openalex.org/W2058788751","https://openalex.org/W2060238374","https://openalex.org/W2094889474","https://openalex.org/W2103863014","https://openalex.org/W2122111042","https://openalex.org/W2122802607","https://openalex.org/W2122854841","https://openalex.org/W2127618892","https://openalex.org/W2127811140","https://openalex.org/W2132136181","https://openalex.org/W2137712029","https://openalex.org/W2141340645","https://openalex.org/W2143011057","https://openalex.org/W2146341019","https://openalex.org/W2156125289","https://openalex.org/W2173732482","https://openalex.org/W2379594833","https://openalex.org/W2415301444","https://openalex.org/W2548083763","https://openalex.org/W2771308870","https://openalex.org/W2886636886","https://openalex.org/W2927437977","https://openalex.org/W2949867299","https://openalex.org/W2955138922","https://openalex.org/W2999044305","https://openalex.org/W3091921516","https://openalex.org/W3092624702","https://openalex.org/W3094051077","https://openalex.org/W3099496190","https://openalex.org/W3146944767","https://openalex.org/W3162614523","https://openalex.org/W3166142427","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3199695506","https://openalex.org/W3204444856","https://openalex.org/W3209573755","https://openalex.org/W3211795435","https://openalex.org/W4291746372","https://openalex.org/W4309506674","https://openalex.org/W4312443924","https://openalex.org/W4320730830","https://openalex.org/W4327550249","https://openalex.org/W4367052125","https://openalex.org/W4388870515","https://openalex.org/W4389505380","https://openalex.org/W4392544734","https://openalex.org/W4395961984","https://openalex.org/W4397031816","https://openalex.org/W4399510571","https://openalex.org/W4404494425","https://openalex.org/W4405632792","https://openalex.org/W4406682058","https://openalex.org/W4408135088","https://openalex.org/W4409112594","https://openalex.org/W4414084747","https://openalex.org/W4415795402","https://openalex.org/W4415799131"],"related_works":[],"abstract_inverted_index":{"Predicting":[0],"protein":[1,32,64,241],"function":[2],"from":[3,74,108,162,268],"its":[4,188,206,269],"primary":[5],"sequence":[6,23,77],"is":[7,94,120],"a":[8,42,53,75,79,84,121,129,132,156,222,233,273],"fundamental":[9],"challenge":[10],"in":[11,193,236,262],"computational":[12,250],"biology.":[13],"While":[14],"deep":[15],"learning":[16],"has":[17],"excelled,":[18],"the":[19,71,88,109,117,209,226,258],"optimal":[20],"representation":[21,43,118],"of":[22,35,44,57,124,179,228,260],"data":[24,55,166,191],"remains":[25],"an":[26],"open":[27],"question.":[28],"This":[29,92],"study":[30],"explores":[31],"sonification\u2500the":[33],"conversion":[34],"amino":[36],"acid":[37],"sequences":[38,59],"into":[39],"2D":[40,80],"spectrograms\u2500as":[41],"this":[45,49,125,194,263],"task.":[46],"To":[47],"facilitate":[48],"investigation,":[50],"we":[51,224],"developed":[52],"benchmark":[54],"set":[56],"18,000":[58],"spanning":[60],"12":[61],"functionally":[62],"diverse":[63],"classes.":[65],"Our":[66,252],"systematic":[67],"evaluation":[68],"suggests":[69],"that":[70,116,150,178,257],"structural":[72,247],"transformation":[73],"1D":[76],"to":[78,87,174,231],"spectrogram":[81,110],"may":[82,154,265],"be":[83],"key":[85,122],"contributor":[86],"model's":[89,198],"predictive":[90],"performance.":[91],"observation":[93],"supported":[95,204],"by":[96,205],"ablation":[97],"studies":[98],"where":[99,215],"models":[100],"using":[101,131,249],"either":[102],"purely":[103],"visual":[104],"or":[105,175],"acoustic":[106],"features":[107],"demonstrated":[111],"effective":[112],"stand-alone":[113],"performance,":[114],"suggesting":[115,187,256],"itself":[119],"source":[123],"capability.":[126],"For":[127],"instance,":[128],"model":[130,146,170,235],"sonification":[133,261],"map":[134],"without":[135],"explicit":[136],"biophysical":[137],"meaning":[138],"achieved":[139,171,217],"81.08%":[140],"accuracy,":[141],"while":[142],"our":[143,165,168,229],"biophysically":[144],"informed":[145],"reached":[147],"84.00%,":[148],"indicating":[149],"such":[151],"domain":[152],"knowledge":[153],"offer":[155],"modest":[157],"performance":[158,172,207],"benefit.":[159],"When":[160],"trained":[161],"scratch":[163],"on":[164,208,275],"set,":[167],"fusion":[169],"comparable":[173],"slightly":[176],"exceeding":[177],"standard":[180],"transformer":[181],"architectures":[182],"like":[183],"ESM-2":[184],"and":[185],"ProtBERT,":[186],"potential":[189,199],"for":[190,200,246,278],"efficiency":[192],"specific":[195],"context.":[196],"The":[197],"generalizability":[201],"was":[202],"further":[203],"external":[210],"CARE":[211],"enzyme":[212],"classification":[213],"benchmark,":[214],"it":[216],"90.44%":[218],"accuracy.":[219],"Finally,":[220],"as":[221],"proof-of-concept,":[223],"explore":[225],"utility":[227,259],"encoding":[230],"guide":[232],"diffusion":[234],"generating":[237],"novel":[238],"green":[239],"fluorescent":[240],"variants,":[242],"which":[243],"were":[244],"assessed":[245],"viability":[248],"methods.":[251],"work":[253],"provides":[254],"evidence":[255],"context":[264],"stem":[266],"largely":[267],"representational":[270],"structure,":[271],"offering":[272],"perspective":[274],"feature":[276],"engineering":[277],"biological":[279],"sequences.":[280]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-17T00:00:00"}
