Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Classification of Systems-I

Classification of Systems-I

Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:

Classification of Systems-II

Classification of Systems-II

Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

MSTune: A Data-Driven Approach to Parameter Tuning Using Grid Search and Differential Evolution for Gas Chromatography-Mass Spectrometry-Based Compound Identification.

Metabolites·2026

Same author

IFN-γ PET imaging stratifies and predicts response to CD137 agonism in a syngeneic colorectal tumor model.

Journal for immunotherapy of cancer·2026

Same author

Genomic Profiling of Adults with Pharmacoresistant Genetic Generalized Epilepsy.

Brain sciences·2026

Same author

Development and Characterization of a Novel Congenital Acute Erythroid Leukemia Cell Line with Unique Features.

Cancers·2026

Same author

Canagliflozin reprograms the aging hippocampus in genetically diverse UM-HET3 mice and attenuates Alzheimer's-like pathology.

bioRxiv : the preprint server for biology·2025

Same author

Inter-Relationship Between Melanoma Vemurafenib Tolerance Thresholds and Metabolic Pathway Choice.

Cells·2025

Same journal

Lactate Metabolism Dysregulation Drives the Pathogenesis of Acute Kidney Injury.

Metabolites·2026

Same journal

Librarian: An Open-Access Web Application for High-Resolution Mass Spectral Library Assembly.

Metabolites·2026

Same journal

Purine Metabolism Alterations in Patients with Chronic Heart Failure: A Cross-Sectional Study of Associations with Iron Status, Oxidative Stress, and Anemia.

Metabolites·2026

Same journal

The Gut Microbiome in Heart Failure: Pathways to Inflammation and Therapeutic Targets.

Metabolites·2026

Same journal

Metabolic Mechanisms of Hexavalent Chromium-Induced Splenic Immune Injury via Oxidative Stress and Ferroptosis Pathways in New Zealand Rabbits.

Metabolites·2026

Same journal

Improving Speed and Efficiency of DESI Imaging with the Xevo MRT Mass Spectrometer for Analyte Mapping.

Metabolites·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 22, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

A Comparative Study of Network-Based Machine Learning Approaches for Binary Classification in Metabolomics.

Hunter Dlugas^1,2, Seongho Kim^1,2

¹Biostatistics and Bioinformatics Core, Karmanos Cancer Institute, Detroit, MI 48201, USA.

|March 26, 2025

Summary

This summary is machine-generated.

Network-based machine learning models show varied performance in metabolomics classification. Bayesian neural networks (BNN), Kolmogorov-Arnold networks (KAN), and spiking neural networks (SNN) show promise but no single method consistently outperforms others.

Keywords:

Bayesian neural network Kolmogorov-Arnold network artificial neural network binary classification convolutional neural network deep learning machine learning metabolomics oncology spiking neural network

More Related Videos

Author Spotlight: Emerging Technologies and Advanced Tools for Decoding Metabolomics Data Analysis

Author Spotlight: Emerging Technologies and Advanced Tools for Decoding Metabolomics Data Analysis

Published on: November 10, 2023

Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics

Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics

Published on: November 29, 2024

Related Experiment Videos

Last Updated: Jun 22, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Author Spotlight: Emerging Technologies and Advanced Tools for Decoding Metabolomics Data Analysis

Author Spotlight: Emerging Technologies and Advanced Tools for Decoding Metabolomics Data Analysis

Published on: November 10, 2023

Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics

Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics

Published on: November 29, 2024

Area of Science:

Biological Sciences
Computational Biology
Bioinformatics

Background:

Metabolomics provides insights into metabolic pathways and processes.
Network-based machine learning is increasingly popular across fields.
Few network-based approaches have been applied to metabolomic classification.

Purpose of the Study:

To compare the performance of various network-based machine learning approaches for metabolomic classification.
To evaluate commonly used and recently developed network models.
To identify potential underutilized methods for metabolomic data analysis.

Main Methods:

Standard data preprocessing applied to 17 diverse metabolomic datasets.
Evaluation of Bayesian neural network (BNN), convolutional neural network (CNN), feedforward neural network (FNN), Kolmogorov-Arnold network (KAN), and spiking neural network (SNN).
Datasets varied in size, mass spectrometry method, and response variable.

Main Results:

No single network-based model consistently outperformed others across AUC, F1-score, or accuracy metrics.
Feedforward neural network (FNN) was the top performer in 5 out of 17 datasets for AUC.
Bayesian neural network (BNN), Kolmogorov-Arnold network (KAN), and spiking neural network (SNN) showed competitive performance across datasets.

Conclusions:

No network-based approach is universally superior for metabolomics-based classification.
Bayesian neural network (BNN), Kolmogorov-Arnold network (KAN), and spiking neural network (SNN) may be underappreciated.
Further investigation into BNN, KAN, and SNN for metabolomic tasks is warranted compared to CNN and FNN.