DPProm: A Two-Layer Predictor for Identifying Promoters and Their Types on Phage Genome Using Deep Learning
| العنوان: | DPProm: A Two-Layer Predictor for Identifying Promoters and Their Types on Phage Genome Using Deep Learning |
|---|---|
| المؤلفون: | Chen Wang, Junyin Zhang, Li Cheng, Jiawei Wu, Minfeng Xiao, Junfeng Xia, Yannan Bin |
| المصدر: | IEEE Journal of Biomedical and Health Informatics. 26:5258-5266 |
| بيانات النشر: | Institute of Electrical and Electronics Engineers (IEEE), 2022. |
| سنة النشر: | 2022 |
| مصطلحات موضوعية: | Deep Learning, Health Information Management, Humans, Bacteriophages, Health Informatics, DNA, Genomics, Electrical and Electronic Engineering, Promoter Regions, Genetic, Computer Science Applications |
| الوصف: | With the number of phage genomes increasing, it is urgent to develop new bioinformatics methods for phage genome annotation. Promoter, a DNA region, is important for gene transcriptional regulation. In the era of post-genomics, the availability of data makes it possible to establish computational models for promoter identification with robustness. In this work, we introduce DPProm, a two-layer model composed of DPProm-1L and DPProm-2L, to predict promoters and their types for phages. On the first layer, as a dual-channel deep neural network ensemble method fusing multi-view features (sequence feature and handcrafted feature), the model DPProm-1L is proposed to identify whether a DNA sequence is a promoter or non-promoter. The sequence feature is extracted with convolutional neural network (CNN). And the handcrafted feature is the combination of free energy, GC content, cumulative skew, and Z curve features. On the second layer, DPProm-2L based on CNN is trained to predict the promoters' types (host or phage). For the realization of prediction on the whole genomes, the model DPProm, combines with a novel sequence data processing workflow, which contains sliding window and merging sequences modules. Experimental results show that DPProm outperforms the state-of-the-art methods, and decreases the false positive rate effectively on whole genome prediction. Furthermore, we provide a user-friendly web at http://bioinfo.ahu.edu.cn/DPProm. We expect that DPProm can serve as a useful tool for identification of promoters and their types. |
| تدمد: | 2168-2208 2168-2194 |
| DOI: | 10.1109/jbhi.2022.3193224 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4e1e9cd21db28792eb3e73ed5b88da63 https://doi.org/10.1109/jbhi.2022.3193224 |
| Rights: | CLOSED |
| رقم الانضمام: | edsair.doi.dedup.....4e1e9cd21db28792eb3e73ed5b88da63 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 21682208 21682194 |
|---|---|
| DOI: | 10.1109/jbhi.2022.3193224 |