Cross-Validation for Training and Testing Co-occurrence Network Inference Algorithms

TL;DR

This paper introduces a novel cross-validation approach for evaluating and comparing co-occurrence network inference algorithms in microbiome studies, improving hyper-parameter tuning and network quality assessment.

Contribution

It proposes a new cross-validation method and application techniques for existing algorithms, addressing limitations of previous evaluation methods.

Findings

The proposed method effectively aids hyper-parameter selection.

It improves the comparison of different network inference algorithms.

The approach enhances the reliability of inferred microbial networks.

Abstract

Microorganisms are found in almost every environment, including the soil, water, air, and inside other organisms, like animals and plants. While some microorganisms cause diseases, most of them help in biological processes such as decomposition, fermentation and nutrient cycling. A lot of research has gone into studying microbial communities in various environments and how their interactions and relationships can provide insights 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. Previous methods for evaluating the quality of the inferred network include using external data, and network consistency across sub-samples, both 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 empirical study shows that the proposed method is useful for hyper-parameter selection (training) and comparing the quality of the inferred networks between different algorithms (testing).