MPLasso: Inferring microbial association networks using prior microbial knowledge

Chieh Lo, Radu MarculescuPLOS Computational Biology 2017 · DOI · OpenReview

Introduction

The human microbiome is a complex ecosystem where microbial interactions play a pivotal role in maintaining health or driving disease. Mapping these "social networks" of microbes is essential for precision medicine. However, inferring these networks from high-throughput sequencing data is fraught with statistical challenges. In this paper, the authors present Microbial Prior Lasso (MPLasso), a framework that integrates automated text mining of scientific literature with graphical models to improve the accuracy and reproducibility of microbial association networks.

The Challenges of Microbial Network Inference

Traditional methods for inferring microbial associations face two primary hurdles:

  1. Compositionality: Sequencing data provides relative abundances rather than absolute counts. This "pie problem" means that an increase in one species' abundance forces a mathematical decrease in others, leading to spurious correlations that do not reflect biological reality.
  2. High-Dimensionality ($p \gg n$): Microbiome studies often measure thousands of species ($p$) across a limited number of samples ($n$). This creates a situation where the number of possible interactions far exceeds the available data points, making it difficult to distinguish true biological signals from statistical noise.

The MPLasso Framework

MPLasso addresses these challenges by incorporating prior biological knowledge into a modified Graphical Lasso (GLasso) algorithm. The framework consists of three main components:

Data Transformation

To mitigate the effects of compositionality, the authors employ a centered log-ratio (clr) transformation. This shifts the data into a coordinate system where standard statistical assumptions are more valid, allowing for more robust inference of conditional dependencies.

Automated Text Mining

The "prior" knowledge is derived from millions of scientific abstracts in the PubMed database. The researchers used two distinct methods:

  • Fisher’s Exact Test: This statistical test identifies pairs of microbes that appear together in the literature more frequently than would be expected by chance.
  • Machine Learning Classification: A Support Vector Machine (SVM) was trained to classify whether literature mentions of microbial pairs implied a functional interaction (positive, negative, or none).

Integrated Algorithm

The core of MPLasso is a modified GLasso algorithm that estimates a precision matrix to find conditional dependencies. The text-mined data is used to construct a penalty matrix. If existing literature suggests a likely interaction between two microbes, the algorithm applies a smaller penalty to that specific connection, making it easier for the model to detect the edge within the noisy sequencing data.

Results and Validation

The authors validated MPLasso using both synthetic and real-world datasets, comparing its performance against state-of-the-art methods like SparCC, CCLasso, and SPIEC-EASI.

Synthetic Benchmarks

In simulations mimicking various network structures (cluster, band, and scale-free), MPLasso achieved an edge recovery rate of up to 95%. Crucially, the model proved robust to noise; even when the prior knowledge was 90% "incorrect" (containing spurious edges), MPLasso still outperformed its competitors, demonstrating that literature acts as a guide rather than a rigid constraint.

Human Microbiome Project (HMP) Application

When applied to real 16S rRNA and shotgun metagenomic data from the Human Microbiome Project, MPLasso demonstrated 90% reproducibility when datasets were split. The inferred networks revealed "assortativity," where phylogenetically related microbes (e.g., within the same genus) tended to cluster together. Furthermore, the model successfully identified known biological partnerships, such as the co-aggregation of Streptococcus mitis and Actinomyces naeslundiii in dental plaque.

Conclusion

MPLasso represents a significant advancement in microbial network inference. By bridging the gap between automated text mining and high-dimensional statistics, it provides a more accurate and reproducible way to map the complex interactions within the human microbiome. While the current model focuses on static snapshots, future work aims to extend this "prior-informed" approach to dynamic, time-series data to better understand community evolution during disease or treatment.

Summary updated

Abstract

Author summary Microbial communities exhibit rich dynamics including the way they adapt, develop, and interact with the human body and the surrounding environment. The associations among microbes can provide a solid foundation to model the interplay between the (host) human body and the microbial populations. However, due to the unique properties of compositional and high-dimensional nature of microbial data, standard statistical methods are likely to produce spurious results. Although several existing methods can estimate the associations among microbes under the sparsity assumption, they still have major difficulties to infer the associations among microbes given such high-dimensional data. To enhance the model accuracy on inferring microbial associations, we propose to integrate multiple levels of biological information by mining the co-occurrence patterns and interactions directly from large amount of scientific literature. We first show that our proposed method can outperform existing methods in synthetic experiments. Next, we obtain credible inference results from Human Microbiome Project datasets when compared against laboratory data. By creating a more accurate microbial association network, scientists in this field will be able to better focus their efforts when experimentally verifying microbial associations by eliminating the need to perform exhaustive searches on all possible pairs of associations.
BibTeX
@article{lo2017mplasso,
  author = {Chieh Lo and Radu Marculescu},
  title = {{MPLasso: Inferring microbial association networks using prior microbial knowledge}},
  journal = {PLOS Computational Biology},
  year = {2017},
  doi = {10.1371/journal.pcbi.1005915},
}
Figure