A protein‐free chemically defined medium for the cultivation of various micro‐organisms with food safety significance

Wang, Danhui; Greenwood, Peyton; Klein, Matthias S.

doi:10.1111/jam.15005

Cited by 4 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These differences can impede long-term reproducibility. Therefore, we chose a new, protein-free, chemically defined medium that allows cultivation of a broad range of microbes for this study [10]. Media was inoculated with 10 6 CFU/mL of each microbial strain and medium samples were collected after 4 h of growth.…”

Section: Discussionmentioning

confidence: 99%

“…An aliquot of 100 µL of the suspension was used to inoculate 10 mL of a protein-free defined medium in a 50 mL culture flask to result in a final starting cell count of 10 6 CFU/mL. The protein-free defined medium was prepared as described recently [10]. Three replicates of each strain were incubated at 37 • C for 4 h, after which medium samples were collected and immediately filtered using a 0.22 µm filter membrane to remove microbes.…”

Section: Microorganism Cultivationmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning for Rapid Identification of Microbes Using Metabolomics Profiles

2021

Self Cite

View full text Add to dashboard Cite

Rapid detection of viable microbes remains a challenge in fields such as microbial food safety. We here present the application of deep learning algorithms to the rapid detection of pathogenic and non-pathogenic microbes using metabolomics data. Microbes were incubated for 4 h in a protein-free defined medium, followed by 1D 1H nuclear magnetic resonance (NMR) spectroscopy measurements. NMR spectra were analyzed by spectral binning in an untargeted metabolomics approach. We trained multilayer (“deep”) artificial neural networks (ANN) on the data and used the resulting models to predict spectra of unknown microbes. ANN predicted unknown microbes in this laboratory setting with an average accuracy of 99.2% when using a simple feature selection method. We also describe learning behavior of the employed ANN and the optimization strategies that worked well with these networks for our datasets. Performance was compared to other current data analysis methods, and ANN consistently scored higher than random forest models and support vector machines, highlighting the potential of deep learning in metabolomics data analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Microorganism Cultivationmentioning

confidence: 99%

Deep Learning for Rapid Identification of Microbes Using Metabolomics Profiles

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…We tested the FIA algorithm on data from an experiment on microbial metabolism (Wang et al, 2021a). Ten microbial strains were cultivated in a de ned medium at 37 °C (Wang et al, 2021b). After 4 hours, medium samples were collected and measured by 1D 1 H Nuclear Magnetic Resonance (NMR) spectroscopy on an 850 MHz Avance III HD Ascend spectrometer (Bruker BioSpin, Billerica, MA, USA).…”

Section: Methodsmentioning

confidence: 99%

Feature Impact Assessment: A New Score to Identify Relevant Metabolomics Features in Artificial Neural Networks

Wang

Greenwood

Klein

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Introduction Artificial Neural Networks (ANN) are increasingly used in metabolomics. Objectives Given the multitude of implementations of ANN, there is no straightforward way to identify important features (metabolites). We developed a simple numeric score, the FIA score, to identify features of high importance. Methods FIA analysis was implemented in R and tested on microbial and human datasets. Results FIA scores correlated significantly to p -values and can provide information on the stability of ANN models. Conclusion FIA scores are a novel, simple score to assess the impact of features that will help interpreting ANN outcomes in the metabolomics area.

show abstract