![metaclean metaclean](https://www.adarsus.com/wp-content/uploads/2021/03/Remove-metadata-in-windows.png)
2 and shown in the top table, the original development set consisting of 500 labeled peaks was randomly partitioned into five equally sized subsets. For each of the three metric sets M4, M7 and M11, calculated as illustrated in Fig. Schematic of the cross-validation-based machine learning framework utilized in this study and our MetaClean package. f Optionally, a dataset can first be pre-processed using RSD filtering, in which case the quality metric calculation and MetaClean are applied to the filtered subset of the original 500 peaks in each dataset (Table 1) e This process is repeated for all the peaks to obtain a matrix with integration quality metrics (11 total detailed in Table 2) as columns, and peaks (the originally labeled 500 in each of our datasets described in Table 1) as rows. d The quality metric for a peak is calculated as the mean of the corresponding values (marked by horizontal bars) for the group of samples constituting the peak. c The metrics listed in Table 2 are applied to these intensity (and the corresponding retention time) vectors to calculate the corresponding values for each sample. Note that the lengths of the intensity vectors ( X, Y, …, Z) may or may not be equal. b Vectors for intensity, I i, and time (not shown here) are extracted for every sample, S n ( n =, where F is the total number of peaks). a Intensity and retention time information is extracted for every peak in a dataset. Schematic describing our calculation of the peak integration quality metrics. Machine learning Metabolomics Peak integration Pre-processing Quality control Untargeted. Our work represents an important step forward in developing an automated tool for filtering out unreliable peak integrations in untargeted LC-MS metabolomics data. An R implementation of these classifiers and the overall computational approach is available as the MetaClean package at. As a complementary approach, applying our framework to peaks retained after filtering by 30% RSD across pooled QC samples was able to further distinguish poorly integrated peaks that were not removed from filtering alone. The best performing classifier was found to be a combination of the AdaBoost algorithm and a set of 11 peak quality metrics previously explored in untargeted metabolomics and proteomics studies. These classifiers were compared to using a residual standard deviation (RSD) cut-off in pooled quality-control (QC) samples, which aims to remove peaks with analytical error. Specifically, we comprehensively and systematically compared the performance of 24 different classifiers generated by combining eight classification algorithms and three sets of peak quality metrics on the task of distinguishing reliably integrated peaks from poorly integrated ones. To address this problem, we propose a computational methodology that combines machine learning and peak quality metrics to filter out low quality peaks.
#METACLEAN SOFTWARE#
As a result, the output of these pre-processing software may retain incorrectly calculated metabolite abundances that can perpetuate in downstream analyses. Despite the availability of several pre-processing software, poor peak integration remains a prevalent problem in untargeted metabolomics data generated using liquid chromatography high-resolution mass spectrometry (LC-MS).