SMILE: systems metabolomics using interpretable learning and evolution

Background: Direct link between metabolism and cell and organism phenotype in health and disease makes metabolomics, a high throughput study of small molecular metabolites, an essential methodology for understanding and diagnosing disease development and progression. Machine learning methods have se...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:BMC bioinformatics Jg. 22; H. 1; S. 1 - 17
Hauptverfasser: Sha, Chengyuan, Cuperlovic-Culf, Miroslava, Hu, Ting
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London BMC 28.05.2021
BioMed Central
BioMed Central Ltd
Springer Nature B.V
Schlagworte:
Algorithms
Alzheimer's disease
Analysis
Applications programs
Bioinformatics
Biomedical and Life Sciences
Computational Biology/Bioinformatics
Computer Appl. in Life Sciences
Computer applications
Computer graphics
Data analysis
Decision making
Evaluation
Evolutionary algorithm
Evolutionary algorithms
Feature interaction
Genetic algorithms
Graphical user interface
Information management
Interpretable machine learning
Learning algorithms
Life Sciences
Machine learning
Medical research
Metabolites
Metabolomics
Methods
Microarrays
Neurodegenerative diseases
Phenotypes
Prediction models
Canada
Interpretable machine learning
Metabolomics
Alzheimer’s disease
Evolutionary algorithm
Feature interaction
ISSN:1471-2105, 1471-2105
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Background: Direct link between metabolism and cell and organism phenotype in health and disease makes metabolomics, a high throughput study of small molecular metabolites, an essential methodology for understanding and diagnosing disease development and progression. Machine learning methods have seen increasing adoptions in metabolomics thanks to their powerful prediction abilities. However, the “black-box” nature of many machine learning models remains a major challenge for wide acceptance and utility as it makes the interpretation of decision process difficult. This challenge is particularly predominant in biomedical research where understanding of the underlying decision making mechanism is essential for insuring safety and gaining new knowledge. Results: In this article, we proposed a novel computational framework, Systems Metabolomics using Interpretable Learning and Evolution (SMILE), for supervised metabolomics data analysis. Our methodology uses an evolutionary algorithm to learn interpretable predictive models and to identify the most influential metabolites and their interactions in association with disease. Moreover, we have developed a web application with a graphical user interface that can be used for easy analysis, interpretation and visualization of the results. Performance of the method and utilization of the web interface is shown using metabolomics data for Alzheimer’s disease. Conclusions: SMILE was able to identify several influential metabolites on AD and to provide interpretable predictive models that can be further used for a better understanding of the metabolic background of AD. SMILE addresses the emerging issue of interpretability and explainability in machine learning, and contributes to more transparent and powerful applications of machine learning in bioinformatics.
NRC publication: Yes
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1471-2105
1471-2105
DOI:10.1186/s12859-021-04209-1