{"id":"https://openalex.org/W4394769874","doi":"https://doi.org/10.1093/bioinformatics/btae196","title":"Effect of tokenization on transformers for biological sequences","display_name":"Effect of tokenization on transformers for biological sequences","publication_year":2024,"publication_date":"2024-03-29","ids":{"openalex":"https://openalex.org/W4394769874","doi":"https://doi.org/10.1093/bioinformatics/btae196","pmid":"https://pubmed.ncbi.nlm.nih.gov/38608190"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btae196","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae196","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae196/57226869/btae196.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/btae196/57226869/btae196.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063512895","display_name":"Edo Dotan","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]},{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Edo Dotan","raw_affiliation_strings":["The Henry and Marilyn Taub Faculty of Computer Science, Technion \u2013 Israel Institute of Technology , Haifa 3200003, Israel","The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University , Tel Aviv 69978, Israel","The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University, Tel Aviv, 69978, Israel"],"affiliations":[{"raw_affiliation_string":"The Henry and Marilyn Taub Faculty of Computer Science, Technion \u2013 Israel Institute of Technology , Haifa 3200003, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University , Tel Aviv 69978, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University, Tel Aviv, 69978, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092802853","display_name":"Gal Jaschek","orcid":"https://orcid.org/0000-0001-7555-4575"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gal Jaschek","raw_affiliation_strings":["Department of Genetics, Yale University School of Medicine , New Haven, CT 06510, United States"],"affiliations":[{"raw_affiliation_string":"Department of Genetics, Yale University School of Medicine , New Haven, CT 06510, United States","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070736617","display_name":"Tal Pupko","orcid":"https://orcid.org/0000-0001-9463-2575"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Tal Pupko","raw_affiliation_strings":["The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University , Tel Aviv 69978, Israel","The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University, Tel Aviv, 69978, Israel"],"affiliations":[{"raw_affiliation_string":"The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University , Tel Aviv 69978, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University, Tel Aviv, 69978, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051184573","display_name":"Yonatan Belinkov","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Yonatan Belinkov","raw_affiliation_strings":["The Henry and Marilyn Taub Faculty of Computer Science, Technion \u2013 Israel Institute of Technology , Haifa 3200003, Israel"],"affiliations":[{"raw_affiliation_string":"The Henry and Marilyn Taub Faculty of Computer Science, Technion \u2013 Israel Institute of Technology , Haifa 3200003, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051184573","https://openalex.org/A5070736617"],"corresponding_institution_ids":["https://openalex.org/I16391192","https://openalex.org/I174306211"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":8.3363,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.98453337,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"40","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9997000098228455,"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":0.9993000030517578,"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/lexical-analysis","display_name":"Lexical analysis","score":0.8078000545501709},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7731170058250427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6983676552772522},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4602580964565277},{"id":"https://openalex.org/keywords/biological-network","display_name":"Biological network","score":0.44246217608451843},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4271355867385864},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.41298577189445496},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36184823513031006},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.22183218598365784},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18771815299987793}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.8078000545501709},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731170058250427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6983676552772522},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4602580964565277},{"id":"https://openalex.org/C28225019","wikidata":"https://www.wikidata.org/wiki/Q4915005","display_name":"Biological network","level":2,"score":0.44246217608451843},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4271355867385864},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.41298577189445496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36184823513031006},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.22183218598365784},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18771815299987793},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","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":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","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":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","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":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"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":"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":"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":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btae196","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae196","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae196/57226869/btae196.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:38608190","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38608190","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:pubmedcentral.nih.gov:11055402","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11055402","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11055402/pdf/btae196.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/btae196","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae196","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae196/57226869/btae196.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":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2883622317","display_name":null,"funder_award_id":"2818/21","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"},{"id":"https://openalex.org/F4320322596","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49"},{"id":"https://openalex.org/F4320323139","display_name":"Azrieli Foundation","ror":"https://ror.org/009svts64"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394769874.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1999051528","https://openalex.org/W2055043387","https://openalex.org/W2097107919","https://openalex.org/W2109553965","https://openalex.org/W2130909239","https://openalex.org/W2135530477","https://openalex.org/W2140412940","https://openalex.org/W2146683382","https://openalex.org/W2305323034","https://openalex.org/W2379594833","https://openalex.org/W2518553291","https://openalex.org/W2615066396","https://openalex.org/W2735621019","https://openalex.org/W2794284562","https://openalex.org/W2889498145","https://openalex.org/W2912459817","https://openalex.org/W2919115771","https://openalex.org/W2935703330","https://openalex.org/W2950954328","https://openalex.org/W2951433247","https://openalex.org/W2953008890","https://openalex.org/W2971227267","https://openalex.org/W2984761660","https://openalex.org/W2990618091","https://openalex.org/W3036780692","https://openalex.org/W3081278968","https://openalex.org/W3087561936","https://openalex.org/W3095583226","https://openalex.org/W3097876879","https://openalex.org/W3127238141","https://openalex.org/W3132607382","https://openalex.org/W3162530389","https://openalex.org/W3177828909","https://openalex.org/W3197918389","https://openalex.org/W4205773061","https://openalex.org/W4220999759","https://openalex.org/W4252684946","https://openalex.org/W4287447409","https://openalex.org/W4298006192","https://openalex.org/W4307871192","https://openalex.org/W4320908344","https://openalex.org/W6763868836","https://openalex.org/W6785197911"],"related_works":["https://openalex.org/W4298195702","https://openalex.org/W4300598845","https://openalex.org/W2601638452","https://openalex.org/W3093768914","https://openalex.org/W2285263069","https://openalex.org/W2945402993","https://openalex.org/W4376107815","https://openalex.org/W4319309603","https://openalex.org/W4319309671","https://openalex.org/W1599985958"],"abstract_inverted_index":{"Code,":[0],"data,":[1],"and":[2],"trained":[3],"tokenizers":[4],"are":[5],"available":[6],"on":[7],"https://github.com/technion-cs-nlp/BiologicalTokenizers.":[8]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}
