Independent Component Analysis to Remove Batch Effects from Merged Microarray Datasets

Renard, Emilie; Branders, Samuel; Absil, Pierre-Antoine

doi:10.1007/978-3-319-43681-4_23

Cited by 5 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach is the most straightforward, and many methods have been proposed, such as ratio-based methods, ComBat, quantile based methods, and mean or median centering . Matrix factorization methods, such as SVD, ICA, and EigenMS, assume that the metabolites-by-samples matrix can be represented by a small set of one-rank components that can be estimated using matrix factorization. The components that correlate with the batch labels are then removed to obtain a data set without batch effects.…”

mentioning

confidence: 99%

NormAE: Deep Adversarial Learning Model to Remove Batch Effects in Liquid Chromatography Mass Spectrometry-Based Metabolomics Data

et al. 2020

View full text Add to dashboard Cite

Untargeted metabolomics based on liquid chromatography−mass spectrometry is affected by nonlinear batch effects, which cover up biological effects, result in nonreproducibility, and are difficult to be calibrate. In this study, we propose a novel deep learning model, called Normalization Autoencoder (NormAE), which is based on nonlinear autoencoders (AEs) and adversarial learning. An additional classifier and ranker are trained to provide adversarial regularization during the training of the AE model, latent representations are extracted by the encoder, and then the decoder reconstructs the data without batch effects. The NormAE method was tested on two real metabolomics data sets. After calibration by NormAE, the quality control samples (QCs) for both data sets gathered most closely in a PCA score plot (average distances decreased from 56.550 and 52.476 to 7.383 and 14.075, respectively) and obtained the highest average correlation coefficients (from 0.873 and 0.907 to 0.997 for both). Additionally, NormAE significantly improved biomarker discovery (median number of differential peaks increased from 322 and 466 to 1140 and 1622, respectively). NormAE was compared with four commonly used batch effect removal methods. The results demonstrated that using NormAE produces the best calibration results.

show abstract

mentioning

confidence: 99%

NormAE: Deep Adversarial Learning Model to Remove Batch Effects in Liquid Chromatography Mass Spectrometry-Based Metabolomics Data

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Another state-of-the-art tool WaveICA [ 22 ] was developed for the cases where QC samples are not available. WaveICA utilizes the wavelet transform [ 23 ] and independent component analysis (ICA) [ 24 , 25 ] to capture and remove technical variation. Based on the assumption that metabolite intensities may display temporal trends over the injection order, WaveICA first uses the wavelet transform to decompose the trend into multi-scale data with different frequencies.…”

Section: Introductionmentioning

confidence: 99%

TIGER: technical variation elimination for metabolomics data using ensemble learning architecture

Han

Huang

Foppiano

et al. 2022

Briefings in Bioinformatics

View full text Add to dashboard Cite

Large metabolomics datasets inevitably contain unwanted technical variations which can obscure meaningful biological signals and affect how this information is applied to personalized healthcare. Many methods have been developed to handle unwanted variations. However, the underlying assumptions of many existing methods only hold for a few specific scenarios. Some tools remove technical variations with models trained on quality control (QC) samples which may not generalize well on subject samples. Additionally, almost none of the existing methods supports datasets with multiple types of QC samples, which greatly limits their performance and flexibility. To address these issues, a non-parametric method TIGER (Technical variation elImination with ensemble learninG architEctuRe) is developed in this study and released as an R package (https://CRAN.R-project.org/package=TIGERr). TIGER integrates the random forest algorithm into an adaptable ensemble learning architecture. Evaluation results show that TIGER outperforms four popular methods with respect to robustness and reliability on three human cohort datasets constructed with targeted or untargeted metabolomics data. Additionally, a case study aiming to identify age-associated metabolites is performed to illustrate how TIGER can be used for cross-kit adjustment in a longitudinal analysis with experimental data of three time-points generated by different analytical kits. A dynamic website is developed to help evaluate the performance of TIGER and examine the patterns revealed in our longitudinal analysis (https://han-siyu.github.io/TIGER_web/). Overall, TIGER is expected to be a powerful tool for metabolomics data analysis.

show abstract

“…The biological importance of expression modes can be inferred by correlating them with known biological features. ICA has also been previously used to identify and remove batch effects by correlating expression modes with experimental features within the datasets ( 22 ). We will dub the expression modes as either biological or technical modes, based on the types of variables with which they correlate.…”

Section: Introductionmentioning

confidence: 99%

Factorial study of the RNA-seq computational workflow identifies biases as technical gene signatures

Simoneau

Gosselin

Scott

2020

NAR Genomics and Bioinformatics

View full text Add to dashboard Cite

RNA-seq is a modular experimental and computational approach aiming in identifying and quantifying RNA molecules. The modularity of the RNA-seq technology enables adaptation of the protocol to develop new ways to explore RNA biology, but this modularity also brings forth the importance of methodological thoroughness. Liberty of approach comes with the responsibility of choices, and such choices must be informed. Here, we present an approach that identifies gene group-specific quantification biases in current RNA-seq software and references by processing datasets using diverse RNA-seq computational pipelines, and by decomposing these expression datasets with an independent component analysis matrix factorization method. By exploring the RNA-seq pipeline using this systemic approach, we identify genome annotations as a design choice that affects to the same extent quantification results as does the choice of aligners and quantifiers. We also show that the different choices in RNA-seq methodology are not independent, identifying interactions between genome annotations and quantification software. Genes were mainly affected by differences in their sequence, by overlapping genes and genes with similar sequence. Our approach offers an explanation for the observed biases by identifying the common features used differently by the software and references, therefore providing leads for the betterment of RNA-seq methodology.

show abstract

Independent Component Analysis to Remove Batch Effects from Merged Microarray Datasets

Cited by 5 publications

References 16 publications

NormAE: Deep Adversarial Learning Model to Remove Batch Effects in Liquid Chromatography Mass Spectrometry-Based Metabolomics Data

NormAE: Deep Adversarial Learning Model to Remove Batch Effects in Liquid Chromatography Mass Spectrometry-Based Metabolomics Data

TIGER: technical variation elimination for metabolomics data using ensemble learning architecture

Factorial study of the RNA-seq computational workflow identifies biases as technical gene signatures

Contact Info

Product

Resources

About