MetGem Software for the Generation of Molecular Networks Based on the t-SNE Algorithm

Abstract

Molecular networking (MN) is becoming a standard bioinformatics tool in the metabolomic community. Its paradigm is based on the observation that compounds with a high degree of chemical similarity share comparable MS2 fragmentation pathways. To afford a clear separation between MS2 spectral clusters, only the most relevant similarity scores are selected using dedicated filtering steps requiring time-consuming parameter optimization. Depending on the filtering values selected, some scores are arbitrarily deleted and a part of the information is ignored. The problem of creating a reliable representation of MS2 spectra data sets can be solved using algorithms developed for dimensionality reduction and pattern recognition purposes, such as t-distributed stochastic neighbor embedding (t-SNE). This multivariate embedding method pays particular attention to local details by using nonlinear outputs to represent the entire data space. To overcome the limitations inherent to the GNPS workflow and the networking architecture, we developed MetGem. Our software allows the parallel investigation of two complementary representations of the raw data set, one based on a classic GNPS-style MN and another based on the t-SNE algorithm. The t-SNE graph preserves the interactions between related groups of spectra, while the MN output allows an unambiguous separation of clusters. Additionally, almost all parameters can be tuned in real time, and new networks can be generated within a few seconds for small data sets. With the development of this unified interface (), we fulfilled the need for a dedicated, user-friendly, local software for MS2 comparison and spectral network generation.

Feature-based Molecular Networking in the GNPS Analysis Environment

“…The use of these tools with the MS 2 spectral summary file enables subsequent direct mapping of these annotations to the molecular networks produced by the feature-based molecular networking method. These tools include SIRIUS 22 , DEREPLICATOR, 39,40 NAP, 19 MS2LDA 20 , MolNetEnhancer 21 (see Supplementary Note 5), as well as other software such as MetWork 41 , CFM-ID 42 , MetGem 43 , MetFrag 44 .…”

MS-CleanR: A feature-filtering approach to improve annotation rate in untargeted LC-MS based metabolomics

“…MS-CleanR can also prioritize compounds based on “Compound_level” column tuned by the user in external DBs used for MS-FINDER annotation. Finally, the resulting annotated peaks list can be converted into an .msp format for mass spectral similarity networking as in GNPS 31 or MetGem 25 (for the detailed mathematics of the workflow, see Supporting Information Text 1).…”

Deep Learning Enable Untargeted Metabolite Extraction from High Throughput Coverage Data-Independent Acquisition

“…Finally, the results were export in MSP format. The MSP files were then parsed with the functions in libmetgem package 21 . Evaluation criterion.…”