EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Biotext with SWeePtex: Bioinformatics Tricks to Perform Fast, Accurate, and Content-specific String Embedding

Diogo de J. S. Machado, Camilla R. De Pierri, Antonio C. da Silva Filho, Flávia de F. Costa, Nelson A. de M. Lemos, Camila P. Perico, Letícia G. C. Santos, Maricel G. Kann, Fábio de O. Pedrosa, Roberto T. Raittz

Journal of the Brazilian Computer Society · 04.05.2026 · 32 (1) · 1155-1164

DOI: 10.5753/jbcs.2026.6198 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Brazilian Computer Society, online erschienen am 04.05.2026. Verfasst von Diogo de J. S. Machado und 9 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The escalating demand for adaptable Artificial Intelligence (AI) systems presents a critical hurdle: generating efficient text embeddings tailored to specific problems. While Large Language Models (LLMs) excel in general contexts, they struggle in specialized domains due to their massive data requirements, opaque embedding strategies, and high computational costs. We introduce Biotext, featuring SWeePtex, a novel framework that adapts successful Bioinformatics techniques for text embedding. By converting text to the Biological Sequence-Like (BSL) format, our Python package enables the application of SWeeP, a tool originally developed for biological sequences, to create content-addressable vectors in natural language, employing the random projection paradigm. Using unsupervised machine learning, we validated this finding by analyzing data from 14,984 MEDLINE abstracts on the thioredoxin theme. Biotext, through SWeePtex, constructs a unified vector space for words and documents from scratch, capturing rich contextual relationships and offering scalable processing. Our usage example demonstrates that this Bioinformatics-inspired method effectively addresses key challenges in Natural Language Processing (NLP), providing interpretable, computationally efficient, and content-addressable linguistic representations for document exploration. Ultimately, Biotext demonstrates that bridging Bioinformatics and NLP yields powerful, efficient, and accessible text analysis tools that balance analytical power with interpretability, particularly valuable in specialized domains and resource-constrained environments. Biotext Python package is freely available at the PyPI repository.

Zitieren

APA

Machado, D. D. J. S., Pierri, C. R. D., Filho, A. C. D. S., Costa, F. D. F., Lemos, N. A. D. M., Perico, C. P., Santos, L. G. C., Kann, M. G., Pedrosa, F. D. O., & Raittz, R. T. (2026). Biotext with SWeePtex: Bioinformatics Tricks to Perform Fast, Accurate, and Content-specific String Embedding. Journal of the Brazilian Computer Society, 32(1), 1155-1164. https://doi.org/10.5753/jbcs.2026.6198

Vancouver

Machado DDJS, Pierri CRD, Filho ACDS, Costa FDF, Lemos NADM, Perico CP, et al. Biotext with SWeePtex: Bioinformatics Tricks to Perform Fast, Accurate, and Content-specific String Embedding. Journal of the Brazilian Computer Society. 2026;32(1):1155-1164. doi:10.5753/jbcs.2026.6198

BibTeX
@article{Machado2026,
  author = {Machado, Diogo de J. S. and Pierri, Camilla R. De and Filho, Antonio C. da Silva and Costa, Flávia de F. and Lemos, Nelson A. de M. and Perico, Camila P. and Santos, Letícia G. C. and Kann, Maricel G. and Pedrosa, Fábio de O. and Raittz, Roberto T.},
  title = {Biotext with SWeePtex: Bioinformatics Tricks to Perform Fast, Accurate, and Content-specific String Embedding},
  journal = {Journal of the Brazilian Computer Society},
  year = {2026},
  volume = {32},
  number = {1},
  pages = {1155--1164},
  doi = {10.5753/jbcs.2026.6198}
}
Kostenlos starten →