Gene Prediction in Metagenomic Fragments with Deep Learning

Zhang, Shaowu; Jin, Xuesong; Zhang, Teng

doi:10.1155/2017/4740354

Cited by 22 publications

(16 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…erefore, it is important to elucidate the relationships between rusty roots and microorganisms, including investigating changes in the composition of the entire microbiome coexisting in the rhizosphere of P. ginseng. Additionally, recent advances in metagenomic-based approaches [34][35][36] have expanded our ability to investigate the differences in the composition of rhizospheric microbial communities between healthy and rusty root-affected P. ginseng.…”

Section: Introductionmentioning

confidence: 99%

Microbial Community Changes in the Rhizosphere Soil of Healthy and Rusty Panax ginseng and Discovery of Pivotal Fungal Genera Associated with Rusty Roots

Wei

Wang

Cao

et al. 2020

BioMed Research International

View full text Add to dashboard Cite

Panax ginseng Meyer, a valuable medicinal plant, is severely threatened by rusty root, a condition that greatly affects its yield and quality. Studies investigating the relationship between soil microbial community composition and rusty roots are vital for the production of high-quality ginseng. Here, high-throughput sequencing was employed to systematically characterize changes in the soil microbial community associated with rusty roots. Fungal diversity was lower in the soils of rusty root-affected P. ginseng than in those of healthy plants. Importantly, principal coordinate analysis separated the fungal communities in the rhizosphere soils of rusty root-affected ginseng from those of healthy plants. The dominant bacterial and fungal genera differed significantly between rhizosphere soils of healthy and rusty root-affected P. ginseng, and linear discriminant analysis effect size (LEfSe) further indicated a strong imbalance in the soil microbial community of diseased plants. Significantly enriched bacterial genera (including Rhodomicrobium, Knoellia, Nakamurella, Asticcacaulis, and Actinomadura) were mainly detected in the soil of rusty root-affected P. ginseng, whereas significantly enriched fungal genera (including Xenopolyscytalum, Arthrobotrys, Chalara, Cryptococcus, and Scutellinia) were primarily detected in the soil of healthy plants. Importantly, five fungal genera (Cylindrocarpon, Acrophialophora, Alternaria, Doratomyces, and Fusarium) were significantly enriched in the soil of rusty root-affected plants compared with that of healthy plants, suggesting that an increase in the relative abundance of these pathogenic fungi (Cylindrocarpon, Alternaria, and Fusarium) may be associated with ginseng rusty roots. Additionally, this study is the first to report that an increase in the relative abundances of Acrophialophora and Doratomyces in the rhizosphere of P. ginseng may be associated with the onset of rusty root symptoms in this plant. Our findings provide potentially useful information for developing biological control strategies against rusty root, as well as scope for future screening of fungal pathogens in rusty roots of P. ginseng.

show abstract

Section: Introductionmentioning

confidence: 99%

Microbial Community Changes in the Rhizosphere Soil of Healthy and Rusty Panax ginseng and Discovery of Pivotal Fungal Genera Associated with Rusty Roots

Wei

Wang

Cao

et al. 2020

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…However, the main limitation of these models is that they require optimization of thousands of parameters, which limits their practical use (Zhang et al, 2017). Sequence similarity-based methods, on the other hand, are considered rather time-consuming and computationally demanding, especially when applied to shotgun metagenomic data.…”

Section: Machine Learning For Microbial Genome Characterizationmentioning

confidence: 99%

“…Moreover, RAST is known to have difficulties dealing with mixed or contaminated cultures, as its algorithm relies on closely related isolates (Quainoo et al, 2017). In addition, these methods are used to find genes with previously known homologous proteins and cannot predict novel genes (Zhang et al, 2017).…”

Section: Machine Learning For Microbial Genome Characterizationmentioning

confidence: 99%

“…For shotgun metagenomics, several ML-based methods have been proposed, such as Orphelia (Hoff et al, 2009), MGC (El Allali and Rose, 2013), MetaGUN (Liu et al, 2013), and Meta-MFDL (Zhang et al, 2017), e.g., the latter using a deep stacking networks learning model and multiple genomic features (i.e., the usage of monocodons and monoamino acids) for identifying genes from metagenomic fragments (Zhang et al, 2017).…”

Section: Machine Learning For Microbial Genome Characterizationmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Approaches for Epidemiological Investigations of Food-Borne Disease Outbreaks

et al. 2019

View full text Add to dashboard Cite

Foodborne diseases (FBDs) are infections of the gastrointestinal tract caused by foodborne pathogens (FBPs) such as bacteria [ Salmonella, Listeria monocytogenes and Shiga toxin-producing E. coli (STEC)] and several viruses, but also parasites and some fungi. Artificial intelligence (AI) and its sub-discipline machine learning (ML) are re-emerging and gaining an ever increasing popularity in the scientific community and industry, and could lead to actionable knowledge in diverse ranges of sectors including epidemiological investigations of FBD outbreaks and antimicrobial resistance (AMR). As genotyping using whole-genome sequencing (WGS) is becoming more accessible and affordable, it is increasingly used as a routine tool for the detection of pathogens, and has the potential to differentiate between outbreak strains that are closely related, identify virulence/resistance genes and provide improved understanding of transmission events within hours to days. In most cases, the computational pipeline of WGS data analysis can be divided into four (though, not necessarily consecutive) major steps: de novo genome assembly, genome characterization, comparative genomics, and inference of phylogeny or phylogenomics. In each step, ML could be used to increase the speed and potentially the accuracy (provided increasing amounts of high-quality input data) of identification of the source of ongoing outbreaks, leading to more efficient treatment and prevention of additional cases. In this review, we explore whether ML or any other form of AI algorithms have already been proposed for the respective tasks and compare those with mechanistic model-based approaches.

show abstract

“…Compared with traditional machine learning methods that rely on feature engineering, deep learning is proved to have advantages of automatically discovering representations needed for classification from raw data (LeCun et al, 2015 ). In bioinformatics, deep learning also has been successfully applied to predict protein structure, gene prediction and protein function (Spencer et al, 2015 ; Zhang S. W. et al, 2017 ; Zou et al, 2017 ; Wei et al, 2018 ).…”

Section: Introductionmentioning

confidence: 99%

Identification of Antioxidant Proteins With Deep Learning From Sequence Information

et al. 2018

View full text Add to dashboard Cite

Antioxidant proteins have been found closely linked to disease control for its ability to eliminate excess free radicals. Because of its medicinal value, the study of identifying antioxidant proteins is on the upsurge. Many machine-learning classifiers have performed poorly owing to the nonlinear and unbalanced nature of biological data. Recently, deep learning techniques showed advantages over many state-of-the-art machine learning methods in various fields. In this study, a deep learning based classifier was proposed to identify antioxidant proteins based on mixed g-gap dipeptide composition feature vector. The classifier employed deep autoencoder to extract nonlinear representation from raw input. The t-Distributed Stochastic Neighbor Embedding (t-SNE) was used for dimensionality reduction. Support vector machine was finally performed for classification. The classifier achieved F1 score of 0.8842 and MCC of 0.7409 in 10-fold cross validation. Experimental results show that our proposed method outperformed the traditional machine learning methods and could be a promising tool for antioxidant protein identification. For the convenience of others' scientific research, we have developed a user-friendly web server called IDAod for antioxidant protein identification, which can be accessed freely at http://bigroup.uestc.edu.cn/IDAod/.

show abstract

Gene Prediction in Metagenomic Fragments with Deep Learning

Cited by 22 publications

References 56 publications

Microbial Community Changes in the Rhizosphere Soil of Healthy and Rusty Panax ginseng and Discovery of Pivotal Fungal Genera Associated with Rusty Roots

Microbial Community Changes in the Rhizosphere Soil of Healthy and Rusty Panax ginseng and Discovery of Pivotal Fungal Genera Associated with Rusty Roots

Machine Learning Approaches for Epidemiological Investigations of Food-Borne Disease Outbreaks

Identification of Antioxidant Proteins With Deep Learning From Sequence Information

Contact Info

Product

Resources

About