{"id":"https://openalex.org/W7160603077","doi":"https://doi.org/10.5753/jbcs.2026.6198","title":"Biotext with SWeePtex: Bioinformatics Tricks to Perform Fast, Accurate, and Content-specific String Embedding","display_name":"Biotext with SWeePtex: Bioinformatics Tricks to Perform Fast, Accurate, and Content-specific String Embedding","publication_year":2026,"publication_date":"2026-05-04","ids":{"openalex":"https://openalex.org/W7160603077","doi":"https://doi.org/10.5753/jbcs.2026.6198"},"language":null,"primary_location":{"id":"doi:10.5753/jbcs.2026.6198","is_oa":true,"landing_page_url":"https://doi.org/10.5753/jbcs.2026.6198","pdf_url":null,"source":{"id":"https://openalex.org/S69801987","display_name":"Journal of the Brazilian Computer Society","issn_l":"0104-6500","issn":["0104-6500","1678-4804"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Brazilian Computer Society","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5753/jbcs.2026.6198","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135657223","display_name":"Diogo de J. S. Machado","orcid":"https://orcid.org/0009-0001-3885-6774"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diogo de J. S. Machado","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0001-3885-6774","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135696626","display_name":"Camilla R. De Pierri","orcid":"https://orcid.org/0000-0002-6114-1734"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Camilla R. De Pierri","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6114-1734","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135684577","display_name":"Antonio C. da Silva Filho","orcid":"https://orcid.org/0000-0003-0669-4528"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio C. da Silva Filho","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0669-4528","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135693000","display_name":"Fl\u00e1via de F. Costa","orcid":"https://orcid.org/0000-0003-4092-4673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fl\u00e1via de F. Costa","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4092-4673","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135653630","display_name":"Nelson A. de M. Lemos","orcid":"https://orcid.org/0000-0001-9382-9982"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nelson A. de M. Lemos","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9382-9982","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135648021","display_name":"Camila P. Perico","orcid":"https://orcid.org/0000-0003-0186-4022"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Camila P. Perico","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0186-4022","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135702091","display_name":"Leticia Concei\u00e7\u00e3o dos Santos","orcid":"https://orcid.org/0000-0002-0206-2294"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Let\u00edcia G. C. Santos","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0206-2294","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013292761","display_name":"Maricel G. Kann","orcid":"https://orcid.org/0000-0003-0116-3883"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maricel G. Kann","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0116-3883","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135715226","display_name":"F\u00e1bio de O. Pedrosa","orcid":"https://orcid.org/0000-0003-3711-969X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"F\u00e1bio de O. Pedrosa","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3711-969X","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135684897","display_name":"Roberto T. Raittz","orcid":"https://orcid.org/0000-0002-5271-991X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto T. Raittz","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5271-991X","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1390,"currency":"USD","value_usd":1390},"apc_paid":{"value":1390,"currency":"USD","value_usd":1390},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48224155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"1","first_page":"1155","last_page":"1164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.3813999891281128,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.3813999891281128,"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/T10028","display_name":"Topic Modeling","score":0.16050000488758087,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.06610000133514404,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.8030999898910522},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5548999905586243},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5126000046730042},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4885999858379364},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"Biomedical text mining","score":0.4839000105857849},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.43220001459121704},{"id":"https://openalex.org/keywords/random-projection","display_name":"Random projection","score":0.4129999876022339},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.33160001039505005},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.3310000002384186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507999777793884},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8030999898910522},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5548999905586243},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.4839000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4553999900817871},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4408000111579895},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C2777036070","wikidata":"https://www.wikidata.org/wiki/Q18393452","display_name":"Random projection","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3887999951839447},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28139999508857727},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C87186988","wikidata":"https://www.wikidata.org/wiki/Q452197","display_name":"SBML","level":4,"score":0.27140000462532043},{"id":"https://openalex.org/C2777002779","wikidata":"https://www.wikidata.org/wiki/Q42478","display_name":"Perl","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2630999982357025},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5753/jbcs.2026.6198","is_oa":true,"landing_page_url":"https://doi.org/10.5753/jbcs.2026.6198","pdf_url":null,"source":{"id":"https://openalex.org/S69801987","display_name":"Journal of the Brazilian Computer Society","issn_l":"0104-6500","issn":["0104-6500","1678-4804"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Brazilian Computer Society","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.5753/jbcs.2026.6198","is_oa":true,"landing_page_url":"https://doi.org/10.5753/jbcs.2026.6198","pdf_url":null,"source":{"id":"https://openalex.org/S69801987","display_name":"Journal of the Brazilian Computer Society","issn_l":"0104-6500","issn":["0104-6500","1678-4804"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Brazilian Computer Society","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1501531009","https://openalex.org/W1560851690","https://openalex.org/W2011301426","https://openalex.org/W2024932032","https://openalex.org/W2055247046","https://openalex.org/W2100495367","https://openalex.org/W2110485445","https://openalex.org/W2114850508","https://openalex.org/W2135508918","https://openalex.org/W2144211451","https://openalex.org/W2202042777","https://openalex.org/W2563280541","https://openalex.org/W2950996529","https://openalex.org/W2953641512","https://openalex.org/W2979473749","https://openalex.org/W3000394202","https://openalex.org/W3000466293","https://openalex.org/W3035965352","https://openalex.org/W3120048903","https://openalex.org/W3216518700","https://openalex.org/W4233444068","https://openalex.org/W4285006369","https://openalex.org/W4312187866","https://openalex.org/W4377234252","https://openalex.org/W4400007232","https://openalex.org/W4402582138","https://openalex.org/W4410851895"],"related_works":[],"abstract_inverted_index":{"The":[0],"escalating":[1],"demand":[2],"for":[3,61,85,127,166],"adaptable":[4],"Artificial":[5],"Intelligence":[6],"(AI)":[7],"systems":[8],"presents":[9],"a":[10,53,81,123],"critical":[11],"hurdle:":[12],"generating":[13],"efficient":[14],"text":[15,62,66,182],"embeddings":[16],"tailored":[17],"to":[18,36,67,88],"specific":[19],"problems.":[20],"While":[21],"Large":[22],"Language":[23,155],"Models":[24],"(LLMs)":[25],"excel":[26],"in":[27,32,92,153,193],"general":[28],"contexts,":[29],"they":[30],"struggle":[31],"specialized":[33,194],"domains":[34,195],"due":[35],"their":[37],"massive":[38],"data":[39,110],"requirements,":[40],"opaque":[41],"embedding":[42],"strategies,":[43],"and":[44,129,137,162,175,180,196],"high":[45],"computational":[46],"costs.":[47],"We":[48],"introduce":[49],"Biotext,":[50,119],"featuring":[51],"SWeePtex,":[52,121],"novel":[54],"framework":[55],"that":[56,145,172,185],"adapts":[57],"successful":[58],"Bioinformatics":[59,174],"techniques":[60],"embedding.":[63],"By":[64],"converting":[65],"the":[68,77,96,116,206],"Biological":[69],"Sequence-Like":[70],"(BSL)":[71],"format,":[72],"our":[73],"Python":[74,200],"package":[75,201],"enables":[76],"application":[78],"of":[79],"SWeeP,":[80],"tool":[82],"originally":[83],"developed":[84],"biological":[86],"sequences,":[87],"create":[89],"content-addressable":[90,163],"vectors":[91],"natural":[93],"language,":[94],"employing":[95],"random":[97],"projection":[98],"paradigm.":[99],"Using":[100],"unsupervised":[101],"machine":[102],"learning,":[103],"we":[104],"validated":[105],"this":[106,146],"finding":[107],"by":[108],"analyzing":[109],"from":[111,131],"14,984":[112],"MEDLINE":[113],"abstracts":[114],"on":[115],"thioredoxin":[117],"theme.":[118],"through":[120],"constructs":[122],"unified":[124],"vector":[125],"space":[126],"words":[128],"documents":[130],"scratch,":[132],"capturing":[133],"rich":[134],"contextual":[135],"relationships":[136],"offering":[138],"scalable":[139],"processing.":[140],"Our":[141],"usage":[142],"example":[143],"demonstrates":[144,171],"Bioinformatics-inspired":[147],"method":[148],"effectively":[149],"addresses":[150],"key":[151],"challenges":[152],"Natural":[154],"Processing":[156],"(NLP),":[157],"providing":[158],"interpretable,":[159],"computationally":[160],"efficient,":[161,179],"linguistic":[164],"representations":[165],"document":[167],"exploration.":[168],"Ultimately,":[169],"Biotext":[170,199],"bridging":[173],"NLP":[176],"yields":[177],"powerful,":[178],"accessible":[181],"analysis":[183],"tools":[184],"balance":[186],"analytical":[187],"power":[188],"with":[189],"interpretability,":[190],"particularly":[191],"valuable":[192],"resource-constrained":[197],"environments.":[198],"is":[202],"freely":[203],"available":[204],"at":[205],"PyPI":[207],"repository.":[208]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-05-09T00:00:00"}