The application of artificial neural networks in metabolomics: a historical perspective

Mendez, Kevin; Broadhurst, David; Reinke, Stacey N.

doi:10.1007/s11306-019-1608-0

Cited by 79 publications

(53 citation statements)

References 117 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Since those pioneering successful applications, numerous ML methods in diverse areas of NMR spectroscopy have been described. Many of them were extensively applied for the analysis of complex mixtures in the “omics” context (e.g., metabolomics/metabonomics, lipidomics, foodomics, etc.) as well as in clinical applications .…”

Section: Introductionmentioning

confidence: 99%

NMR signal processing, prediction, and structure verification with machine learning techniques

Cobas¹

2020

Magnetic Reson in Chemistry

View full text Add to dashboard Cite

Machine learning (ML) methods have been present in the field of NMR since decades, but it has experienced a tremendous growth in the last few years, especially thanks to the emergence of deep learning (DL) techniques taking advantage of the increased amounts of data and available computer power. These algorithms are successfully employed for classification, regression, clustering, or dimensionality reduction tasks of large data sets and have been intensively applied in different areas of NMR including metabonomics, clinical diagnosis, or relaxometry. In this article, we concentrate on the various applications of ML/DL in the areas of NMR signal processing and analysis of small molecules, including automatic structure verification and prediction of NMR observables in solution. K E Y W O R D S

show abstract

Section: Introductionmentioning

confidence: 99%

NMR signal processing, prediction, and structure verification with machine learning techniques

Cobas¹

2020

Magnetic Reson in Chemistry

View full text Add to dashboard Cite

show abstract

“…Many of the previously described methodologies may be called machine-learning techniques. Deep learning is a form of machine learning that requires less input from the operator [144]. The more complex the machine-learning algorithm, the more data it requires for proper training.…”

Section: Machine Learning and Deep Learningmentioning

confidence: 99%

Recent applications of chemometrics in one‐ and two‐dimensional chromatography

Bos

Knol

Molenaar

et al. 2020

J of Separation Science

View full text Add to dashboard Cite

The proliferation of increasingly more sophisticated analytical separation systems, often incorporating increasingly more powerful detection techniques, such as highresolution mass spectrometry, causes an urgent need for highly efficient dataanalysis and optimization strategies. This is especially true for comprehensive twodimensional chromatography applied to the separation of very complex samples. In this contribution, the requirement for chemometric tools is explained and the latest developments in approaches for (pre-)processing and analyzing data arising from oneand two-dimensional chromatography systems are reviewed. The final part of this review focuses on the application of chemometrics for method development and optimization.

show abstract

“…The key to the popularity of PLS over alternative methods can be distilled into a single word-interpretability. Historically, the primary aim of machine learning (ML) has been accurate prediction, not statistical inference (Mendez et al 2019a). As such, methods for statistically interpreting either the similarities between each individual metabolite profile, or the importance of individual metabolites across multiple samples, have been a secondary consideration.…”

Section: Introductionmentioning

confidence: 99%

“…1). ANNs can be generally considered a projection-based method which share a structural equivalence with PLS (Mendez et al 2019a). With non-linear ANNs the projection to latent structures ethos is preserved but now non-linear, rather than linear, latent structures can be modelled.…”

Section: Introductionmentioning

confidence: 99%

“…We recently showed that ANNs have similar predictive ability to PLS across multiple diverse metabolomics data sets (Mendez et al 2019c). However, within the domain of metabolomics, if ANNs are to become a truly viable alternative to PLS it will be necessary to develop similar standardised and robust methods for data visualisation, evaluation, and statistical inference (Mendez et al 2019a).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Migrating from partial least squares discriminant analysis to artificial neural networks: a comparison of functionally equivalent visualisation and feature contribution tools using jupyter notebooks

2020

Self Cite

View full text Add to dashboard Cite

Introduction Metabolomics data is commonly modelled multivariately using partial least squares discriminant analysis (PLS-DA). Its success is primarily due to ease of interpretation, through projection to latent structures, and transparent assessment of feature importance using regression coefficients and Variable Importance in Projection scores. In recent years several non-linear machine learning (ML) methods have grown in popularity but with limited uptake essentially due to convoluted optimisation and interpretation. Artificial neural networks (ANNs) are a non-linear projection-based ML method that share a structural equivalence with PLS, and as such should be amenable to equivalent optimisation and interpretation methods. Objectives We hypothesise that standardised optimisation, visualisation, evaluation and statistical inference techniques commonly used by metabolomics researchers for PLS-DA can be migrated to a non-linear, single hidden layer, ANN. Methods We compared a standardised optimisation, visualisation, evaluation and statistical inference techniques workflow for PLS with the proposed ANN workflow. Both workflows were implemented in the Python programming language. All code and results have been made publicly available as Jupyter notebooks on GitHub. Results The migration of the PLS workflow to a non-linear, single hidden layer, ANN was successful. There was a similarity in significant metabolites determined using PLS model coefficients and ANN Connection Weight Approach. Conclusion We have shown that it is possible to migrate the standardised PLS-DA workflow to simple non-linear ANNs. This result opens the door for more widespread use and to the investigation of transparent interpretation of more complex ANN architectures.

show abstract

The application of artificial neural networks in metabolomics: a historical perspective

Cited by 79 publications

References 117 publications

NMR signal processing, prediction, and structure verification with machine learning techniques

NMR signal processing, prediction, and structure verification with machine learning techniques

Recent applications of chemometrics in one‐ and two‐dimensional chromatography

Migrating from partial least squares discriminant analysis to artificial neural networks: a comparison of functionally equivalent visualisation and feature contribution tools using jupyter notebooks

Contact Info

Product

Resources

About