An artificial neural network and Random Forest identify glyphosate-impacted brackish communities based on 16S rRNA amplicon MiSeq read counts

Janßen, René; Zabel, Jakob; Lukas, Uwe von; Labrenz, Matthias

doi:10.1016/j.marpolbul.2019.110530

Cited by 15 publications

(15 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several OTUs detected in our study belonged to genera whose abundance increased following glyphosate treatment (Methylotenera, Pseudomonas, Sphingobium, Thalassobaculum), demonstrating the ability of glyphosate to cause favorable conditions for these genera across various habitats. On a further note, the herein identified Rhodobacteraceae and Rhizobiaceae OTUs were confirmed in a novel approach using artificial neural networks and Random Forest to detect responding OTUs (Janßen et al, 2019).…”

Section: Differences In the Responses Of Water Column And Biofilm Comsupporting

confidence: 54%

See 1 more Smart Citation

A Glyphosate Pulse to Brackish Long-Term Microcosms Has a Greater Impact on the Microbial Diversity and Abundance of Planktonic Than of Biofilm Assemblages

et al. 2019

Self Cite

View full text Add to dashboard Cite

The widespread herbicide glyphosate has been detected in aquatic coastal zones of the southern Baltic Sea. We monitored community dynamics in glyphosateimpacted chemostats for 20 weeks to evaluate the potential impact of the herbicide on free-living and biofilm-associated bacterial community assemblages in a brackish ecosystem. A HPLC-MS/MS method was developed to measure glyphosate, aminomethylphosphonic acid and sarcosine concentrations within a brackish matrix. These concentrations were analyzed weekly, together with prokaryotic succession, determined by total cell counts and next generation 16S rRNA (gene) amplicon sequencing. Shotgun metagenomics provided insights into the glyphosate degradation potential of the microbial communities. Temporal increases in total cell counts, bacterial diversity and the abundances of distinct bacterial operational taxonomic units were identified in the water column. Biofilm communities proved to be less affected than pelagic ones, but their responses were of longer duration. The increase of glyphosate oxidoreductase (gox) and thiO gene as well as the phn operon abundance indicated glyphosate degradation by first the aminomethylphosphonic acid pathway and possibly a subsequent cleavage of the C-P bond. However, although glyphosate concentrations were reduced by 99%, 1 µM of the herbicide remained until the end of the experiment. Thus, when present at low concentrations, glyphosate may evade bacterial degradation and persist in Baltic Sea waters.

show abstract

Section: Differences In the Responses Of Water Column And Biofilm Comsupporting

confidence: 54%

“…Monitoring went on until day +71. For further details on experimental procedures see Janßen et al (2019).…”

Section: Microcosm Experimentsmentioning

confidence: 99%

A Glyphosate Pulse to Brackish Long-Term Microcosms Has a Greater Impact on the Microbial Diversity and Abundance of Planktonic Than of Biofilm Assemblages

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…These changes in microbial community composition can often occur in a predictable manner. SML has been used in both natural and industrial settings to use microbial information to aid in predicting environmental quality [85] , contamination state [86] , [87] as well as rates of various processes including copper bioleaching [88] , Previous studies have used microbial biomarkers as indicators of particular environmental processes or outcomes. Indicator species analysis has been used to identify taxa that are related to particular phenomena or treatments that could be used as biomarkers for that phenomena.…”

Section: Optimizing Model Construction and Evaluationmentioning

confidence: 99%

“…The ability to predict contamination in the environment has been expanded to other systems including prediction of the herbicide glyphosate in the Baltic Sea [86] . In the Janßen et al (2019) study, the authors employed artificial neural networks and RF to predict the presence of glyphosate.…”

Section: Optimizing Model Construction and Evaluationmentioning

confidence: 99%

Machine learning applications in microbial ecology, human microbiome studies, and environmental monitoring

Ghannam

Techtmann

2021

Computational and Structural Biotechnology Journal

145

View full text Add to dashboard Cite

show abstract

“…To address this, various machine learning approaches such as random forest (RF) [13,14] and artificial neural network (ANN) [15] were utilized. The single or combined use of these algorithms has contributed much in gene expression data classification [16], disease diagnosis [17], cell migration [18], and microbiome research [19]. Given their high classification accuracy and convenience, they have become powerful tools to learn feature representations.…”

Section: Introductionmentioning

confidence: 99%

Establishment and Analysis of a Combined Diagnostic Model of Polycystic Ovary Syndrome with Random Forest and Artificial Neural Network

Xie

Wang

Zhou

et al. 2020

BioMed Research International

View full text Add to dashboard Cite

Polycystic ovary syndrome (PCOS) is one of the most common metabolic and reproductive endocrinopathies. However, few studies have tried to develop a diagnostic model based on gene biomarkers. In this study, we applied a computational method by combining two machine learning algorithms, including random forest (RF) and artificial neural network (ANN), to identify gene biomarkers and construct diagnostic model. We collected gene expression data from Gene Expression Omnibus (GEO) database containing 76 PCOS samples and 57 normal samples; five datasets were utilized, including one dataset for screening differentially expressed genes (DEGs), two training datasets, and two validation datasets. Firstly, based on RF, 12 key genes in 264 DEGs were identified to be vital for classification of PCOS and normal samples. Moreover, the weights of these key genes were calculated using ANN with microarray and RNA-seq training dataset, respectively. Furthermore, the diagnostic models for two types of datasets were developed and named neuralPCOS. Finally, two validation datasets were used to test and compare the performance of neuralPCOS with other two set of marker genes by area under curve (AUC). Our model achieved an AUC of 0.7273 in microarray dataset, and 0.6488 in RNA-seq dataset. To conclude, we uncovered gene biomarkers and developed a novel diagnostic model of PCOS, which would be helpful for diagnosis.

show abstract

An artificial neural network and Random Forest identify glyphosate-impacted brackish communities based on 16S rRNA amplicon MiSeq read counts

Cited by 15 publications

References 29 publications

A Glyphosate Pulse to Brackish Long-Term Microcosms Has a Greater Impact on the Microbial Diversity and Abundance of Planktonic Than of Biofilm Assemblages

A Glyphosate Pulse to Brackish Long-Term Microcosms Has a Greater Impact on the Microbial Diversity and Abundance of Planktonic Than of Biofilm Assemblages

Machine learning applications in microbial ecology, human microbiome studies, and environmental monitoring

Establishment and Analysis of a Combined Diagnostic Model of Polycystic Ovary Syndrome with Random Forest and Artificial Neural Network

Contact Info

Product

Resources

About