{"id":"https://openalex.org/W4391517803","doi":"https://doi.org/10.1093/bioinformatics/btae061","title":"Protein language models meet reduced amino acid alphabets","display_name":"Protein language models meet reduced amino acid alphabets","publication_year":2024,"publication_date":"2024-02-01","ids":{"openalex":"https://openalex.org/W4391517803","doi":"https://doi.org/10.1093/bioinformatics/btae061","pmid":"https://pubmed.ncbi.nlm.nih.gov/38310333"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btae061","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae061","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae061/56580314/btae061.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae061/56580314/btae061.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082343661","display_name":"Ioan Ieremie","orcid":"https://orcid.org/0000-0003-2897-2541"},"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":"Ioan Ieremie","raw_affiliation_strings":["Vision, Learning & Control Group, University of Southampton , Southampton SO17 1BJ, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Vision, Learning & Control Group, University of Southampton , Southampton SO17 1BJ, United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061685303","display_name":"Rob M. Ewing","orcid":"https://orcid.org/0000-0001-6510-4001"},"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":"Rob M Ewing","raw_affiliation_strings":["Biological Sciences, University of Southampton , Southampton SO17 1BJ, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Biological Sciences, University of Southampton , Southampton SO17 1BJ, United Kingdom","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":["Vision, Learning & Control Group, University of Southampton , Southampton SO17 1BJ, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Vision, Learning & Control Group, University of Southampton , Southampton SO17 1BJ, United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082343661"],"corresponding_institution_ids":["https://openalex.org/I43439940"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.7477,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.90233436,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"40","issue":"2","first_page":null,"last_page":null},"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/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/T10521","display_name":"RNA and protein synthesis mechanisms","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"}}],"keywords":[{"id":"https://openalex.org/keywords/alphabet","display_name":"Alphabet","score":0.7095614671707153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6736799478530884},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6006942391395569},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5935839414596558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46596506237983704},{"id":"https://openalex.org/keywords/amino-acid","display_name":"Amino acid","score":0.4600088894367218},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4551657438278198},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45072224736213684},{"id":"https://openalex.org/keywords/folding","display_name":"Folding (DSP implementation)","score":0.4494004249572754},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.44871950149536133},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41855254769325256},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40385085344314575},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4022746980190277},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.17766398191452026},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.10743215680122375},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10548987984657288}],"concepts":[{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.7095614671707153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6736799478530884},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6006942391395569},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5935839414596558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46596506237983704},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.4600088894367218},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4551657438278198},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45072224736213684},{"id":"https://openalex.org/C2776545253","wikidata":"https://www.wikidata.org/wiki/Q5464292","display_name":"Folding (DSP implementation)","level":2,"score":0.4494004249572754},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.44871950149536133},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41855254769325256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40385085344314575},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4022746980190277},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.17766398191452026},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.10743215680122375},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10548987984657288},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000588","descriptor_name":"Amines","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000588","descriptor_name":"Amines","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000588","descriptor_name":"Amines","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000588","descriptor_name":"Amines","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000588","descriptor_name":"Amines","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":"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":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"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":"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":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btae061","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae061","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae061/56580314/btae061.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:38310333","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38310333","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:eprints.soton.ac.uk:495957","is_oa":true,"landing_page_url":"http://doi.org/10.1093/bioinformatics/btae061>).","pdf_url":"https://eprints.soton.ac.uk/495957/1/btae061.pdf","source":{"id":"https://openalex.org/S4306401020","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:pubmedcentral.nih.gov:10872054","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10872054","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10872054/pdf/btae061.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btae061","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae061","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae061/56580314/btae061.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1015103927","display_name":null,"funder_award_id":"P/S000356/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G11400541","display_name":"Artificial and Augmented Intelligence for Automated Scientific Discovery","funder_award_id":"EP/S000356/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1934935867","display_name":null,"funder_award_id":"Engineering and Physical Sciences R","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3069159407","display_name":null,"funder_award_id":"EP/S000356/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320277","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391517803.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1530641120","https://openalex.org/W1978326290","https://openalex.org/W2005120335","https://openalex.org/W2028841335","https://openalex.org/W2045204781","https://openalex.org/W2052376307","https://openalex.org/W2076048958","https://openalex.org/W2080646340","https://openalex.org/W2097892623","https://openalex.org/W2140673705","https://openalex.org/W2483469645","https://openalex.org/W2900674118","https://openalex.org/W2950954328","https://openalex.org/W2951433247","https://openalex.org/W2953008890","https://openalex.org/W2971227267","https://openalex.org/W2980789587","https://openalex.org/W3015921770","https://openalex.org/W3127426316","https://openalex.org/W3146944767","https://openalex.org/W3177828909","https://openalex.org/W3198923619","https://openalex.org/W3203459683","https://openalex.org/W4230276186","https://openalex.org/W4281790889","https://openalex.org/W4283795415","https://openalex.org/W4295312788","https://openalex.org/W4392302569","https://openalex.org/W6763868836","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W2074481494","https://openalex.org/W4250156143","https://openalex.org/W4247156967","https://openalex.org/W4239207432","https://openalex.org/W2808448365","https://openalex.org/W2808006995","https://openalex.org/W4394777662","https://openalex.org/W582626623","https://openalex.org/W2808496111","https://openalex.org/W4240940369"],"abstract_inverted_index":{"Trained":[0],"models":[1],"and":[2],"code":[3],"are":[4],"available":[5],"at":[6],"github.com/Ieremie/reduced-alph-PLM.":[7]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
