Dataset Information

Identification of Proteins of Tobacco Mosaic Virus by Using a Method of Feature Extraction.

ABSTRACT: Tobacco mosaic virus, TMV for short, is widely distributed in the global tobacco industry and has a significant impact on tobacco production. It can reduce the amount of tobacco grown by 50-70%. In this research of study, we aimed to identify tobacco mosaic virus proteins and healthy tobacco leaf proteins by using machine learning approaches. The experiment's results showed that the support vector machine algorithm achieved high accuracy in different feature extraction methods. And 188-dimensions feature extraction method improved the classification accuracy. In that the support vector machine algorithm and 188-dimensions feature extraction method were finally selected as the final experimental methods. In the 10-fold cross-validation processes, the SVM combined with 188-dimensions achieved 93.5% accuracy on the training set and 92.7% accuracy on the independent validation set. Besides, the evaluation index of the results of experiments indicate that the method developed by us is valid and robust.

SUBMITTER: Chen YM

PROVIDER: S-EPMC7581905 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identification of Proteins of Tobacco Mosaic Virus by Using a Method of Feature Extraction.

Chen Yu-Miao YM Zu Xin-Ping XP Li Dan D

Frontiers in genetics 20201009

Tobacco mosaic virus, TMV for short, is widely distributed in the global tobacco industry and has a significant impact on tobacco production. It can reduce the amount of tobacco grown by 50-70%. In this research of study, we aimed to identify tobacco mosaic virus proteins and healthy tobacco leaf proteins by using machine learning approaches. The experiment's results showed that the support vector machine algorithm achieved high accuracy in different feature extraction methods. And 188-dimension ...[more]

PMID: 33193664

Similar Datasets

Project description:BACKGROUND: Although tobacco mosaic virus (TMV) coat protein (CP) has been isolated from virus particles and its crystals have grown in ammonium sulfate buffers for many years, to date, no one has reported on the crystallization of recombinant TMV-CP connecting peptides expressed in E. coli. METHODS: In the present papers genetically engineered TMV-CP was expressed, into which hexahistidine (His) tags or glutathione-S-transferase (GST) tags were incorporated. Considering that GST-tags are long peptides and His-tags are short peptides, an attempt was made to grow crystals of TMV-CP cleaved GST-tags (WT-TMV-CP32) and TMV-CP incorporated His-tags (WT-His-TMV-CP12) simultaneously in ammonium sulfate buffers and commercial crystallization reagents. It was found that the 20S disk form of WT-TMV-CP32 and WT-His-TMV-CP12 did not form high resolution crystals by using various crystallization buffers and commercial crystallization reagents. Subsequently, a new experimental method was adopted in which a range of truncated TMV-CP was constructed by removing several amino acids from the N- or the C-terminal, and high resolution crystals were grown in ammonium sulfate buffers and commercial crystallization reagents. RESULTS: The new crystallization method was developed and 3.0 Å resolution macromolecular crystal was thereby obtained by removing four amino acids at the C-terminal of His-TMV-CP and connecting six His-tags at the N-terminal of His-TMV-CP (TR-His-TMV-CP19). The Four-layer aggregate disk structure of TR-His-TMV-CP19 was solved. This phenomenon showed that peptides at the C-terminus hindered the growth of high resolution crystals and the peptides interactions at the N-terminus were attributed to the quality of TMV-CP crystals. CONCLUSION: A 3.0 Å resolution macromolecular crystal of TR-His-TMV-CP19 was obtained and the corresponding structure was solved by removing four amino acids at the C-terminus of TMV-CP and connecting His-tags at the N-terminus of TMV-CP. It indicated that short peptides influenced the resolution of TMV-CP crystals.

Dataset Information

Identification of Proteins of Tobacco Mosaic Virus by Using a Method of Feature Extraction.

Publications

Identification of Proteins of Tobacco Mosaic Virus by Using a Method of Feature Extraction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets