{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T18:36:18Z","timestamp":1775673378338,"version":"3.50.1"},"reference-count":32,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T00:00:00Z","timestamp":1743033600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Millennium Nucleus Bioproducts, Genomics and Environmental Microbiology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Advances in bacterial promoter predictors based on machine learning have greatly improved identification metrics. However, existing models overlooked the impact of negative datasets, previously identified in GC-content discrepancies between positive and negative datasets in single-species models. This study aims to investigate whether multiple-species models for promoter classification are inherently biased due to the selection criteria of negative datasets. We further explore whether the generation of synthetic random sequences (SRS) that mimic GC-content distribution of promoters can partly reduce this bias.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Multiple-species predictors exhibited GC-content bias when using CDS as a negative dataset, suggested by specificity and sensibility metrics in a species-specific manner, and investigated by dimensionality reduction. We demonstrated a reduction in this bias by using the SRS dataset, with less detection of background noise in real genomic data. In both scenarios DNABERT showed the best metrics. These findings suggest that GC-balanced datasets can enhance the generalizability of promoter predictors across Bacteria.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The source code of the experiments is freely available at https:\/\/github.com\/maigonzalezh\/MultispeciesPromoterClassifier.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf135","type":"journal-article","created":{"date-parts":[[2025,4,12]],"date-time":"2025-04-12T23:58:11Z","timestamp":1744502291000},"source":"Crossref","is-referenced-by-count":3,"title":["Negative dataset selection impacts machine learning-based predictors for multiple bacterial species promoters"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6880-5499","authenticated-orcid":false,"given":"Marcelo","family":"Gonz\u00e1lez","sequence":"first","affiliation":[{"name":"Departamento de Electr\u00f3nica, Universidad T\u00e9cnica Federico Santa Mar\u00eda , Avenida Espa\u00f1a 1680 , Valpara\u00edso 2390123,","place":["Chile"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0077-9483","authenticated-orcid":false,"given":"Roberto E","family":"Dur\u00e1n","sequence":"additional","affiliation":[{"name":"Laboratorio de Microbiolog\u00eda Molecular y Biotecnolog\u00eda Ambiental, Department of Chemistry & Center of Biotechnology Daniel Alkalay Lowitt, Universidad T\u00e9cnica Federico Santa Mar\u00eda , Avenida Espa\u00f1a 1680 , Valpara\u00edso 2390123,","place":["Chile"]},{"name":"Millennium Nucleus Bioproducts, Genomics and Environmental Microbiology (BioGEM) , Avenida Espa\u00f1a 1680 , Valpara\u00edso 2390123,","place":["Chile"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3925-1996","authenticated-orcid":false,"given":"Michael","family":"Seeger","sequence":"additional","affiliation":[{"name":"Laboratorio de Microbiolog\u00eda Molecular y Biotecnolog\u00eda Ambiental, Department of Chemistry & Center of Biotechnology Daniel Alkalay Lowitt, Universidad T\u00e9cnica Federico Santa Mar\u00eda , Avenida Espa\u00f1a 1680 , Valpara\u00edso 2390123,","place":["Chile"]},{"name":"Millennium Nucleus Bioproducts, Genomics and Environmental Microbiology (BioGEM) , Avenida Espa\u00f1a 1680 , Valpara\u00edso 2390123,","place":["Chile"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3472-4130","authenticated-orcid":false,"given":"Mauricio","family":"Araya","sequence":"additional","affiliation":[{"name":"Departamento de Electr\u00f3nica, Universidad T\u00e9cnica Federico Santa Mar\u00eda , Avenida Espa\u00f1a 1680 , Valpara\u00edso 2390123,","place":["Chile"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2495-8929","authenticated-orcid":false,"given":"Nicol\u00e1s","family":"Jara","sequence":"additional","affiliation":[{"name":"Departamento de Electr\u00f3nica, Universidad T\u00e9cnica Federico Santa Mar\u00eda , Avenida Espa\u00f1a 1680 , Valpara\u00edso 2390123,","place":["Chile"]}]}],"member":"286","published-online":{"date-parts":[[2025,3,27]]},"reference":[{"key":"2025041602165764700_btaf135-B1","doi-asserted-by":"publisher","first-page":"4289","DOI":"10.1007\/s00253-020-10577-0","article-title":"Prokaryotic sigma factors and their transcriptional counterparts in Archaea and Eukarya","volume":"104","author":"Abril","year":"2020","journal-title":"Appl Microbiol Biotechnol"},{"key":"2025041602165764700_btaf135-B2","doi-asserted-by":"publisher","first-page":"3255","DOI":"10.1111\/1462-2920.16511","article-title":"R\/K selection of GC content in prokaryotes","volume":"25","author":"Aliperti","year":"2023","journal-title":"Environ Microbiol"},{"key":"2025041602165764700_btaf135-B3","doi-asserted-by":"publisher","first-page":"4869","DOI":"10.1093\/bioinformatics\/btaa609","article-title":"ipromoter-BNCNN: a novel branched CNN-based predictor for identifying and classifying sigma promoters","volume":"36","author":"Amin","year":"2020","journal-title":"Bioinformatics"},{"key":"2025041602165764700_btaf135-B4","doi-asserted-by":"publisher","first-page":"2133","DOI":"10.1093\/nar\/gky010","article-title":"A sigma factor toolbox for orthogonal gene expression in Escherichia coli","volume":"46","author":"Bervoets","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2025041602165764700_btaf135-B5","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1484","article-title":"Hyperparameter optimization: foundations, algorithms, best practices, and open challenges","volume":"13","author":"Bischl","year":"2023","journal-title":"WIREs Data Mining Knowledge Discov"},{"key":"2025041602165764700_btaf135-B6","doi-asserted-by":"publisher","first-page":"e00439\u201320","DOI":"10.1128\/msystems.00439-20","article-title":"Benchmarking bacterial promoter prediction tools: potentialities and limitations","volume":"5","author":"Cassiano","year":"2020","journal-title":"mSystems"},{"key":"2025041602165764700_btaf135-B7","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1186\/s13059-021-02514-9","article-title":"Promotech: a general tool for bacterial promoter recognition","volume":"22","author":"Chevez-Guardado","year":"2021","journal-title":"Genome Biol"},{"key":"2025041602165764700_btaf135-B8","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1038\/s41592-024-02523-z","volume-title":"Nat Methods","author":"Dalla-Torre"},{"key":"2025041602165764700_btaf135-B9","author":"Devlin","year":"2018"},{"key":"2025041602165764700_btaf135-B10","doi-asserted-by":"publisher","first-page":"3150","DOI":"10.1093\/bioinformatics\/bts565","article-title":"CD-HIT: accelerated for clustering the next-generation sequencing data","volume":"28","author":"Fu","year":"2012","journal-title":"Bioinformatics"},{"key":"2025041602165764700_btaf135-B11","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1038\/s42256-023-00629-1","article-title":"Synthetic data accelerates the development of generalizable learning-based algorithms for X-ray image analysis","volume":"5","author":"Gao","year":"2023","journal-title":"Nat Mach Intell"},{"key":"2025041602165764700_btaf135-B12","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1146\/annurev.micro.57.030502.090913","article-title":"Multiple sigma subunits and the partitioning of bacterial transcription space","volume":"57","author":"Gruber","year":"2003","journal-title":"Annu Rev Microbiol"},{"key":"2025041602165764700_btaf135-B13","doi-asserted-by":"publisher","first-page":"1126","DOI":"10.3390\/genes13071126","article-title":"PromoterLCNN: a light CNN-based promoter prediction and classification model","volume":"13","author":"Hern\u00e1ndez","year":"2022","journal-title":"Genes (Basel)"},{"key":"2025041602165764700_btaf135-B14","doi-asserted-by":"publisher","first-page":"2112","DOI":"10.1093\/bioinformatics\/btab083","article-title":"DNABERT: pre-trained bidirectional encoder representations from transformers model for DNA-language in genome","volume":"37","author":"Ji","year":"2021","journal-title":"Bioinformatics"},{"key":"2025041602165764700_btaf135-B15","doi-asserted-by":"publisher","first-page":"24399","DOI":"10.1038\/s41598-021-03817-4","article-title":"The bacterial promoter spacer modulates promoter strength and timing by length, TG-motifs and DNA supercoiling sensitivity","volume":"11","author":"Klein","year":"2021","journal-title":"Sci Rep"},{"key":"2025041602165764700_btaf135-B16","doi-asserted-by":"publisher","first-page":"107732","DOI":"10.1016\/j.compbiolchem.2022.107732","article-title":"BERT-Promoter: an improved sequence-based predictor of DNA promoter using BERT pre-trained model and SHAP feature selection","volume":"99","author":"Le","year":"2022","journal-title":"Comput Biol Chem"},{"key":"2025041602165764700_btaf135-B17","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1186\/s12915-024-01923-z","article-title":"msBERT-Promoter: a multi-scale ensemble predictor based on BERT pre-trained model for the two-stage prediction of DNA promoters and their strengths","volume":"22","author":"Li","year":"2024","journal-title":"BMC Biol"},{"key":"2025041602165764700_btaf135-B18","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1093\/bioinformatics\/btx579","article-title":"iPromoter-2L: A two-layer predictor for identifying promoters and their types by multi-window-based pseknc","volume":"34","author":"Liu","year":"2018","journal-title":"Bioinformatics"},{"key":"2025041602165764700_btaf135-B19","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1111\/mmi.14307","article-title":"Discovery of the extracytoplasmic function \u03c3 factors","volume":"112","author":"Lonetto","year":"2019","journal-title":"Mol Microbiol"},{"key":"2025041602165764700_btaf135-B20","doi-asserted-by":"publisher","first-page":"861","DOI":"10.21105\/joss.00861","volume-title":"J Open Source Softw","year":"2018"},{"key":"2025041602165764700_btaf135-B21","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1038\/s41576-020-0254-8","article-title":"Redefining fundamental concepts of transcription initiation in bacteria","volume":"21","author":"Mej\u00eda-Almonte","year":"2020","journal-title":"Nat Rev Genet"},{"key":"2025041602165764700_btaf135-B22","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1186\/s12859-024-05849-9","article-title":"iProL: identifying DNA promoters from sequence information based on longformer pre-trained model","volume":"25","author":"Peng","year":"2024","journal-title":"BMC Bioinformatics"},{"key":"2025041602165764700_btaf135-B23","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/s00438-018-1487-5","article-title":"iPro70-FMWin: identifying Sigma70 promoters using multiple windowing and minimal features","volume":"294","author":"Rahman","year":"2019","journal-title":"Mol Genet Genomics"},{"key":"2025041602165764700_btaf135-B24","doi-asserted-by":"publisher","first-page":"D255","DOI":"10.1093\/nar\/gkad1072","article-title":"RegulonDB v12.0: a comprehensive resource of transcriptional regulation in E. coli k-12","volume":"52","author":"Salgado","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2025041602165764700_btaf135-B25","doi-asserted-by":"publisher","first-page":"1529","DOI":"10.3390\/genes11121529","article-title":"pcpromoter-CNN: a CNN-based prediction and classification of promoters","volume":"11","author":"Shujaat","year":"2020","journal-title":"Genes (Basel)"},{"key":"2025041602165764700_btaf135-B26","doi-asserted-by":"publisher","first-page":"166860","DOI":"10.1016\/j.jmb.2021.166860","article-title":"PPD: a manually curated database for experimentally verified prokaryotic promoters","volume":"433","author":"Su","year":"2021","journal-title":"J Mol Biol"},{"key":"2025041602165764700_btaf135-B27","doi-asserted-by":"publisher","first-page":"e0171410","DOI":"10.1371\/journal.pone.0171410","article-title":"Recognition of prokaryotic and eukaryotic promoters using convolutional deep learning neural networks","volume":"12","author":"Umarov","year":"2017","journal-title":"PLoS One"},{"key":"2025041602165764700_btaf135-B28","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s12918-018-0570-1","article-title":"70ProPred: a predictor for discovering sigma70 promoters based on combining multiple features","volume":"12","author":"Wenying","year":"2018","journal-title":"BMC Syst Biol"},{"key":"2025041602165764700_btaf135-B29","doi-asserted-by":"publisher","first-page":"10278","DOI":"10.1093\/nar\/gkac824","article-title":"iPro-WAEL: a comprehensive and robust framework for identifying promoters in multiple species","volume":"50","author":"Zhang","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2025041602165764700_btaf135-B30","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab374","article-title":"Assessing deep learning methods in cis-regulatory motif finding based on genomic sequencing data","volume":"23","author":"Zhang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2025041602165764700_btaf135-B31","author":"Zhou","year":"2023"},{"key":"2025041602165764700_btaf135-B32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/bib\/bbad209","article-title":"TIMER is a Siamese neural network-based framework for identifying both general and species-specific bacterial promoters","volume":"24","author":"Zhu","year":"2023","journal-title":"Brief Bioinf"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/4\/btaf135\/62786146\/btaf135.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/4\/btaf135\/62786146\/btaf135.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T06:17:05Z","timestamp":1744784225000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf135\/8098048"}},"subtitle":[],"editor":[{"given":"Jianlin","family":"Cheng","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,3,27]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,3,29]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf135","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,4]]},"published":{"date-parts":[[2025,3,27]]},"article-number":"btaf135"}}