Cross-validation for training and testing co-occurrence network inference algorithms

Microorganisms are found in almost every environment, including soil, water, air and inside other organisms, such as animals and plants. While some microorganisms cause diseases, most of them help in biological processes such as decomposition, fermentation and nutrient cycling. Much research has bee...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:BMC bioinformatics Ročník 26; číslo 1; s. 74 - 24
Hlavní autoři: Agyapong, Daniel, Propster, Jeffrey Ryan, Marks, Jane, Hocking, Toby Dylan
Médium: Journal Article
Jazyk:angličtina
Vydáno: England BioMed Central Ltd 06.03.2025
Springer Nature B.V
BioMed Central
BMC
Témata:
Algorithms
Bacteria
Biological activity
Co-occurrence network inference
Computational Biology - methods
Cross-Validation
Ecological function
Ecology
Environmental aspects
Evaluation
Fermentation
Food chains
Food webs
Inference
LASSO
Machine learning
Microbial activity
Microbiome Analysis
Microbiomes
Microbiota
Microorganisms
Network analysis
Network Validation
Next-generation sequencing
Nutrient cycles
Parameters
Pathogens
Robustness
Sparsity
Taxonomy
Canada
Ecological Networks
Co-occurrence network inference
Cross-Validation
LASSO
Machine learning
Network Validation
Microbiome Analysis
High-dimensional Statistics
Compositional Data
ISSN:1471-2105, 1471-2105
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Microorganisms are found in almost every environment, including soil, water, air and inside other organisms, such as animals and plants. While some microorganisms cause diseases, most of them help in biological processes such as decomposition, fermentation and nutrient cycling. Much research has been conducted on the study of microbial communities in various environments and how their interactions and relationships can provide insight into various diseases. Co-occurrence network inference algorithms help us understand the complex associations of micro-organisms, especially bacteria. Existing network inference algorithms employ techniques such as correlation, regularized linear regression, and conditional dependence, which have different hyper-parameters that determine the sparsity of the network. These complex microbial communities form intricate ecological networks that are fundamental to ecosystem functioning and host health. Understanding these networks is crucial for developing targeted interventions in both environmental and clinical settings. The emergence of high-throughput sequencing technologies has generated unprecedented amounts of microbiome data, necessitating robust computational methods for network inference and validation. Previous methods for evaluating the quality of the inferred network include using external data, and network consistency across sub-samples, both of which have several drawbacks that limit their applicability in real microbiome composition data sets. We propose a novel cross-validation method to evaluate co-occurrence network inference algorithms, and new methods for applying existing algorithms to predict on test data. Our method demonstrates superior performance in handling compositional data and addressing the challenges of high dimensionality and sparsity inherent in real microbiome datasets. The proposed framework also provides robust estimates of network stability. Our empirical study shows that the proposed cross-validation method is useful for hyper-parameter selection (training) and comparing the quality of inferred networks between different algorithms (testing). This advancement represents a significant step forward in microbiome network analysis, providing researchers with a reliable tool for understanding complex microbial interactions. The method's applicability extends beyond microbiome studies to other fields where network inference from high-dimensional compositional data is crucial, such as gene regulatory networks and ecological food webs. Our framework establishes a new standard for validation in network inference, potentially accelerating discoveries in microbial ecology and human health.
Bibliografie: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/s12859-025-06083-7