{"title":"HybProm: An attention-assisted hybrid CNN-BiLSTM model for the interpretable prediction of DNA promoter","authors":"Rentao Luo, Jiawei Liu, Lixin Guan, Mengshan Li","doi":"10.1016/j.ymeth.2025.02.001","DOIUrl":null,"url":null,"abstract":"<div><div>Promoter prediction is essential for analyzing gene structures, understanding regulatory networks, transcription mechanisms, and precisely controlling gene expression. Recently, computational and deep learning methods for promoter prediction have gained attention. However, there is still room to improve their accuracy. To address this, we propose the HybProm model, which uses DNA2Vec to transform DNA sequences into low-dimensional vectors, followed by a CNN-BiLSTM-Attention architecture to extract features and predict promoters across species, including E. coli, humans, mice, and plants. Experiments show that HybProm consistently achieves high accuracy (90%-99%) and offers good interpretability by identifying key sequence patterns and positions that drive predictions.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"235 ","pages":"Pages 71-80"},"PeriodicalIF":4.2000,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Methods","FirstCategoryId":"99","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1046202325000349","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIOCHEMICAL RESEARCH METHODS","Score":null,"Total":0}
引用次数: 0
Abstract
Promoter prediction is essential for analyzing gene structures, understanding regulatory networks, transcription mechanisms, and precisely controlling gene expression. Recently, computational and deep learning methods for promoter prediction have gained attention. However, there is still room to improve their accuracy. To address this, we propose the HybProm model, which uses DNA2Vec to transform DNA sequences into low-dimensional vectors, followed by a CNN-BiLSTM-Attention architecture to extract features and predict promoters across species, including E. coli, humans, mice, and plants. Experiments show that HybProm consistently achieves high accuracy (90%-99%) and offers good interpretability by identifying key sequence patterns and positions that drive predictions.
期刊介绍:
Methods focuses on rapidly developing techniques in the experimental biological and medical sciences.
Each topical issue, organized by a guest editor who is an expert in the area covered, consists solely of invited quality articles by specialist authors, many of them reviews. Issues are devoted to specific technical approaches with emphasis on clear detailed descriptions of protocols that allow them to be reproduced easily. The background information provided enables researchers to understand the principles underlying the methods; other helpful sections include comparisons of alternative methods giving the advantages and disadvantages of particular methods, guidance on avoiding potential pitfalls, and suggestions for troubleshooting.