González Marcelo, Durán Roberto E, Seeger Michael, Araya Mauricio, Jara Nicolás
Departamento de Electrónica, Universidad Técnica Federico Santa María, Avenida España 1680, Valparaíso 2390123, Chile.
Laboratorio de Microbiología Molecular y Biotecnología Ambiental, Department of Chemistry & Center of Biotechnology Daniel Alkalay Lowitt, Universidad Técnica Federico Santa María, Avenida España 1680, Valparaíso 2390123, Chile.
Bioinformatics. 2025 Mar 29;41(4). doi: 10.1093/bioinformatics/btaf135.
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.
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.
The source code of the experiments is freely available at https://github.com/maigonzalezh/MultispeciesPromoterClassifier.
基于机器学习的细菌启动子预测器的进展极大地改善了识别指标。然而，现有模型忽略了负数据集的影响，此前在单物种模型的正、负数据集之间的GC含量差异中已发现该影响。本研究旨在调查用于启动子分类的多物种模型是否因负数据集的选择标准而存在固有偏差。我们进一步探讨模拟启动子GC含量分布的合成随机序列（SRS）的生成是否可以部分减少这种偏差。
当使用CDS作为负数据集时，多物种预测器表现出GC含量偏差，这通过物种特异性方式的特异性和敏感性指标表明，并通过降维进行研究。我们证明使用SRS数据集可减少这种偏差，在真实基因组数据中检测到的背景噪声更少。在这两种情况下，DNABERT都显示出最佳指标。这些发现表明，GC平衡的数据集可以提高启动子预测器在细菌中的通用性。
实验的源代码可在https://github.com/maigonzalezh/MultispeciesPromoterClassifier上免费获取。
