Estimating Nutrient Concentration in Food Using Untargeted Metabolomics
Sebek, M. L.; Menichetti, G.; Barabasi, A.-L.
Show abstract
Untargeted metabolomics can detect hundreds of biochemicals in food, yet without standards, it cannot quantify them. Here we show that we can take advantage of the universal scaling of nutrient concentrations to estimate the concentration of all biochemicals detected by untargeted metabolomics. We validate our method on 20 raw foods, finding an excellent agreement between the predicted and the experimentally observed concentrations.
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Matrix-corrected mass spectrometry enables sensitive detection of food allergens and reveals widespread soy contamination of processed foods 94%
- Concepts and Software Package for Efficient Quality Control in Targeted Metabolomics Studies - MeTaQuaC 93%
- SMART: an approach for accurate formula assignment in spatially-resolved metabolomics 93%
Similar papers in this journal
- TidyMass2: Advancing LC-MS Untargeted Metabolomics Through Metabolite Origin Inference and Metabolic Feature-based Functional Module Analysis 94%
- hRUV: Hierarchical approach to removal of unwanted variation for large-scale metabolomics data 93%
- Predicting metabolite response to dietary intervention using deep learning 93%
Similar papers in this journal
- Exploring Food Contents in Scientific Literature with FoodMine 93%
- Quantitative Mass Spectrometry Imaging Reveals Mutation Status-independent Lack of Imatinib Penetration into Liver Metastases of Gastrointestinal Stromal Tumors 92%
- Influences of chemotype and parental genotype on metabolic fingerprints of tansy plants uncovered by predictive metabolomics. 90%
Similar papers in this journal
Similar papers in this journal
- Biological Function Assignment Across Taxonomic Levels in Mass-Spectrometry-Based Metaproteomics via a Modified Expectation Maximization Algorithm 93%
- Pairwise Attention: Leveraging Mass Differences to Enhance De Novo Sequencing of Mass Spectra 92%
- Automated analysis of large-scale NMR data generates metabolomic signatures and links them to candidate metabolites 92%
"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.