metaPathwayMap: A tool to predict metabolic pathway neighborhoods from structural classes of untargeted metabolomics peaks
Moghe, G.; Strickler, S.
Show abstract
SummaryThousands of peaks detected via untargeted tandem liquid chromatography mass spectrometry (LC-MS/MS) of natural extracts typically go unannotated, limiting our understanding of the metabolic pathways perturbed under different conditions. Current tools for predicting metabolic pathways from untargeted metabolomics data either require prior compound identification or are more focused on specific model species. metaPathwayMap makes use of recent advances in computational metabolomics to map peaks detected in untargeted LC-MS/MS experiments to MetaCyc pathway representations using their structural class predictions. This approach enables better insights into metabolomes of model and non-model species. Availability and ImplementationRequired Python scripts can be downloaded from the moghelab/metaPathwayMap GitHub repository and implemented on a Unix machine. This tool is also available for use through the SolCyc website (https://metapathwaymap.solgenomics.net) and via DockerHub (srs57/metapathwaymap). Contactgdm67@cornell.edu Supplementary InformationAdditional information is provided in Supplementary Methods, Supplementary Files 1-3 and on GitHub (https://github.com/moghelab/metaPathwayMap)
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- MetaFetcheR: An R package for complete mapping of small compound data 94%
- Benchmark dataset for training machine learning models to predict the pathway involvement of metabolites 91%
- A Chalcone Synthase-Like Bacterial Protein Catalyzes Heterocyclic C-Ring Cleavage of Naringenin to Alter Bioactivity Against Nuclear Receptors in Colonic Epithelial Cells 90%
Similar papers in this journal
- The LOTUS Initiative for Open Natural Products Research: Knowledge Management through Wikidata 91%
- A novel in silico method employs chemical and protein similarity algorithms to accurately identify chemical transformations in the human gut microbiome 90%
- Integrating taxonomic, functional, and strain-level profiling of diverse microbial communities with bioBakery 3 90%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.