A New Enzymatic Distance Concept Enables Machine Learning Regression of Metabolite Chemical Representation Features to Distance in Metabolism
Overview
Understanding and reconstructing pathways in metabolism can help identify biomarkers and metabolic changes associated with systemic diseases, such as cancer and cardiovascular diseases. However, in most metabolomics datasets, more than half of the experimentally detected metabolites can be unannotated, making their pathway-specific involvement largely unknown. This study suggests that a distance concept can help place an unannotated metabolite into specific parts of a metabolic network by finding its “distance” in relation to known metabolites. The new concept of “Enzymatic Distance” was created to quantify the separation of any two metabolites in metabolism in terms of enzymatic steps and the flow of mass between them. Enzymatic Distance was scored by two metrics: counts of shared atom mappings and reaction center atoms averaged over the reaction paths separating two compounds. Then, univariate and multivariate multi-layered perception regression models were trained and evaluated over 100 epochs and 30 cross-validation iterations to predict enzymatic distance metrics between target metabolites given only their chemical structural features. While atom mappings were robustly predicted by univariate (R2=0.961) and multivariate (R2=0.958) regression, reaction centers were predicted significantly less accurately by univariate (R2=0.876) and multivariate (R2=0.859) regression. The univariate regression model predicted both metrics more accurately than the multivariate regression (p-value<0.001), as predicting both metrics separately renders higher prediction accuracy. Quantifying and predicting the relationships between known and unknown metabolites helps interpret unannotated metabolites in the human body, aiding the detection and interpretation of metabolic diseases.
Competition history
- ISEF 2025
Resources
Related projects
ISEF · 2024
Overlooked Covariates in Metabolite Abundance Levels: Systematically Quantifying the Information Overlap Between Gene Expression and Metabolism Across Multiple Cancer Types
ISEF · 2024
An Innovative Pipeline Integrating Mendelian Randomization for Personalized Disease Risk Assessment and Therapeutic Drug Identification
ISEF · 2023
A Novel Approach to Systemic in silico Drug Discovery Using a Machine Learning-Based Prediction of Binding Affinity
ISEF · 2017
Metabolic Analysis as a Method of Breast Cancer Diagnosis
ISEF · 2026
A Multi-Layer AI-Assisted in silico Pipeline for Generalizable Enzyme Engineering via Computational Directed Evolution
ISEF · 2022
Predicting Structural Similarity Between Molecules Using Graph Neural Networks
ISEF · 2016
Self Driving Pharma: A Novel Cognitive Knowledge Harvesting Approach to Train a Self-Learning System For Drug Predictive Models through Multi-Dimensional Bio-Entity Feature-Vector Based Topological Data Analyses
ISEF · 2026
A Multi-Omics and Machine Learning Approach for Identifying Potential Salivary Biomarkers of and Treating Major Depressive Disorder
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: Regeneron International Science and Engineering Fair