1. Comprehensive identification of plant peroxisome targeting signal type 1 tripeptides.
- Author
-
Deng, Qianwen, Hong, Xiao, Xia, Yuqing, Gong, Zhicheng, Dai, Huaxin, Chen, Jiarong, Feng, Yanlei, Zhang, Jianfeng, Xie, Xiaodong, Li, Nannan, Shen, Xingxing, Hu, Jianping, Zhang, Qiang, Lang, Xuye, and Pan, Ronghui
- Subjects
LIFE sciences ,ARTIFICIAL neural networks ,EXTRACELLULAR matrix proteins ,MACHINE learning ,FISHER discriminant analysis ,SPINACH - Abstract
This article discusses a study that used machine learning to identify and validate plant peroxisome targeting signal type 1 (PTS1) tripeptides. Peroxisomes are organelles in eukaryotic cells that are involved in metabolic pathways. The researchers trained machine learning models using a dataset of functional PTS1 sequences and non-PTS1 sequences, achieving high accuracy and recall rates in predicting peroxisome targeting. They then used the models to predict novel PTS1 tripeptides and confirmed their peroxisome targeting through experimental validation. The study expands our understanding of peroxisomes in plants and has implications for predicting peroxisomal proteins and metabolic pathways in different plant species. However, it is important to consider that the presence of a PTS1 tripeptide does not guarantee peroxisome targeting, as other factors may also influence protein localization. [Extracted from the article]
- Published
- 2024
- Full Text
- View/download PDF