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

Abstract

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.

Longitudinal Metabolomics of Human Plasma Reveals Robust Prognostic Markers of COVID-19 Disease Severity

“…Next, we aimed to assess the robustness of the metabolites selected by the ML model. We used bootstrap resampling of our training dataset to construct confidence intervals for the variable importance of each of the 707 metabolites profiled (Mendez et al, 2020). The analysis led to the identification of 25 metabolites that significantly contributed to the model's fit.…”

Longitudinal metabolomics of human plasma reveals prognostic markers of COVID-19 disease severity

“…We used bootstrap resampling of our training dataset to construct confidence intervals for the variable importance of each of the 707 metabolites we profiled. 35 The analysis led to the identification of 22 predictor metabolites that significantly contributed to the model's fit. The structural identities of these metabolites were rigorously confirmed (see method details).…”

Approaches to Integrating Metabolomics and Multi-Omics Data: A Primer

“…In particular, Witten and Tibshirani [43] developed a supervised sparse canonical correlation model in order to find significant linear combinations between copy number and gene expression data. For an extensive reading on the extended family of PCA and PLS methods we refer the reader to Mishra et al [28], O'Shea and Misra [35], Gromski et al [94], Mendez et al [95].…”