Journal
BMC BIOINFORMATICS
Volume 22, Issue 1, Pages -Publisher
BMC
DOI: 10.1186/s12859-021-04209-1
Keywords
Metabolomics; Alzheimer's disease; Interpretable machine learning; Feature interaction; Evolutionary algorithm
Categories
Funding
- National Research Council Canada through the AI for Design program
Ask authors/readers for more resources
The article proposed a novel computational framework called SMILE for supervised metabolomics data analysis, using an evolutionary algorithm to learn interpretable predictive models and identify influential metabolites associated with disease. The development of a web application with a graphical user interface showcased the performance and utilization of the method using metabolomics data for Alzheimer's disease. SMILE addresses the issue of interpretability and explainability in machine learning, contributing to more transparent and powerful applications in bioinformatics.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available