Leveraging R (LevR) for fast processing of mass spectrometry data and machine learning: Applications analyzing fingerprints and glycopeptides

Abstract

Applying machine learning strategies to interpret mass spectrometry data has the potential to revolutionize the way in which disease is diagnosed, prognosed, and treated. A persistent and tedious obstacle, however, is relaying mass spectrometry data to the machine learning algorithm. Given the native format and large size of mass spectrometry data files, preprocessing is a critical step. To ameliorate this challenge, we sought to create an easy-to-use, continuous pipeline that runs from data acquisition to the machine learning algorithm. Here, we present a start-to-finish pipeline designed to facilitate supervised and unsupervised classification of mass spectrometry data. The input can be any ESI data set collected by LC-MS or flow injection, and the output is a machine learning ready matrix, in which each row is a feature (an abundance of a particular m/z), and each column is a sample. This workflow provides automated handling of large mass spectrometry data sets for researchers seeking to implement machine learning strategies but who lack expertise in programming/coding to rapidly format the data. We demonstrate how the pipeline can be used on two different mass spectrometry data sets: 1) ESI-MS of fingerprint lipid compositions acquired by direct infusion and, 2) LC-MS of IgG glycopeptides. This workflow is uncomplicated and provides value via its simplicity and effectiveness.

Workflow for Evaluating Normalization Tools for Omics Data Using Supervised and Unsupervised Machine Learning

“…Mass spectra were acquired using the negative ion mode, with a spray voltage of 2.3 kV, a resolution of 60k, and a mass range of m / z 150 to 600. The ESI-MS conditions have been previously described . After data acquisition, raw spectral files (.RAW) were converted to .MS1 files using RawConverter (Scripps, Version 1.2.0.0) with the default settings.…”

“…■ METHODS Latent Fingerprint Sample Collection and Preparation. An ESI-MS dataset of latent fingerprints that had been collected for a separate project 12 was used for the studies herein. Briefly, groomed fingerprints were generated by one participant first touching facial regions with a high sebum content (cheek, neck, and forehead) and then depositing a fingerprint onto a piece of aluminum foil.…”

“…The ESI-MS conditions have been previously described. 12 After data acquisition, raw spectral files (.RAW) were converted to .MS1 files using RawConverter (Scripps, Version 1.2.0.0) with the default settings. The data were extracted into a matrix of samples and features of binned intensities using LevR.…”

“…The data were extracted into a matrix of samples and features of binned intensities using LevR. 12 The following settings for LevR were used: 25% empty cells allowed, number of lines in header is 20, lower m/z of 150, higher m/z of 600, and 0.0125 Da bin width.…”

Learning channel-selective and aberrance repressed correlation filter with memory model for unmanned aerial vehicle object tracking

“…In turn, the information serves as prior knowledge, helping people in dealing with similar problems better and adapting to new complex scenes faster. The core of artificial intelligence (AI) is to enable the machine to complete specific tasks independently through learning and using prior information (Connor et al, 2022 ; Foksinska et al, 2022 ; Nofallah et al, 2022 ; Pfeifer et al, 2022 ; Wang et al, 2022 ). The original scientific research mainly adopts the following two methods.…”