Bayesian hierarchical negative binomial models for multivariable analyses with applications to human microbiome count data

Composite quantile regression approach to batch effect correction in microbiome data

Background

Batch effects refer to data variations that arise from non-biological factors such as experimental conditions, equipment, and external factors. These effects are considered significant issues in the analysis of biological data since they can compromise data consistency and distort actual biological differences, which can severely skew the results of downstream analyses.

Method

In this study, we introduce a new approach that comprehensively addresses two types of batch effects: "systematic batch effects" which are consistent across all samples in a batch, and "nonsystematic batch effects" which vary depending on the variability of operational taxonomic units (OTUs) within each sample in the same batch. To address systematic batch effects, we apply a negative binomial regression model and correct for consistent batch influences by excluding fixed batch effects. Additionally, to handle nonsystematic batch effects, we employ composite quantile regression. By adjusting the distribution of OTUs to be similar based on a reference batch selected using the Kruskal-Walis test method, we consider the variability at the OTU level.

Results

The performance of the model is evaluated and compared with existing methods using PERMANOVA R-squared values, Principal Coordinates Analysis (PCoA) plots and Average Silhouette Coefficient calculated with diverse distance-based metrics. The model is applied to three real microbiome datasets: Metagenomic urine control data, Human Immunodeficiency Virus Re-analysis Consortium data, and Men and Women Offering Understanding of Throat HPV study data. The results demonstrate that the model effectively corrects for batch effects across all datasets.

Testing latent class of subjects with structural zeros in negative binomial models with applications to gut microbiome data

Human microbiome research has become a hot-spot in health and medical research in the past decade due to the rapid development of modern high-throughput. Typical data in a microbiome study consisting of the operational taxonomic unit counts may have over-dispersion and/or structural zero issues. In such cases, negative binomial models can be applied to address the over-dispersion issue, while zero-inflated negative binomial models can be applied to address both issues. In practice, it is essential to know if there is zero-inflation in the data before applying negative binomial or zero-inflated negative binomial models because zero-inflated negative binomial models may be unnecessarily complex and difficult to interpret, or may even suffer from convergence issues if there is no zero-inflation in the data. On the other hand, negative binomial models may yield invalid inferences if the data does exhibit excessive zeros. In this paper, we develop a new test for detecting zero-inflation resulting from a latent class of subjects with structural zeros in a negative binomial regression model by directly comparing the amount of observed zeros with what would be expected under the negative binomial regression model. A closed form of the test statistic as well as its asymptotic properties are derived based on estimating equations. Intensive simulation studies are conducted to investigate the performance of the new test and compare it with the classical Wald, likelihood ratio, and score tests. The tests are also applied to human gut microbiome data to test latent class in microbial genera.

Diet Quality and the Gut Microbiota in Women Living in Alabama

INTRODUCTION

The gut microbiota is associated with obesity and modulated by individual dietary components. However, the relationships between diet quality and the gut microbiota and their potential interactions with weight status in diverse populations are not well understood. This study examined the associations between overall diet quality, weight status, and the gut microbiota in a racially balanced sample of adult females.

METHODS

Female participants (N=71) residing in Birmingham, Alabama provided demographics, anthropometrics, biospecimens, and dietary data in this observational study from March 2014 to August 2014, and data analysis was conducted from August 2017 to March 2019. Weight status was defined as a BMI (weight [kg]/height [m²]) <30 kg/m² for non-obese participants and ≥30 kg/m² for participants who were obese. Dietary data collected included an Automated Self-Administered 24-Hour recall and Healthy Eating Index-2010 (HEI-2010) score. Diet quality was defined as having a high HEI score (≥median) or a low HEI score (<median). The fecal microbiota was collected, and the 16S ribosomal RNA gene was amplified to profile the microbiota composition. Differences in diet quality based on weight status were assessed using 2-sample t-tests. The associations between diet quality, gut microbiota, and weight status were analyzed using negative binomial models.

RESULTS

Participants (43 Black, 28 White) aged 40.39±13.86 years who were non-obese (56%) and obese (44%) were studied. Greater alpha diversity was observed among those with higher Healthy Eating Index scores (p=0.037) but did not differ by weight status. Higher abundances of Bacteroidetes (p=0.006) and Firmicutes (p=0.042) were associated with a higher HEI score. Higher Bacteriodetes levels were observed among non-obese (p=0.006).

CONCLUSIONS

Diet quality measured by the HEI was associated with alpha diversity of the gut microbiota among adult females. Abundances of phyla that have been linked with weight status (Bacteroidetes and Firmicutes) were positively associated with diet quality.

Modeling Microbial Community Networks: Methods and Tools

In the current research landscape, microbiota composition studies are of extreme interest, since it has been widely shown that resident microorganisms affect and shape the ecological niche they inhabit. This complex micro-world is characterized by different types of interactions. Understanding these relationships provides a useful tool for decoding the causes and effects of communities' organizations. Next-Generation Sequencing technologies allow to reconstruct the internal composition of the whole microbial community present in a sample. Sequencing data can then be investigated through statistical and computational method coming from network theory to infer the network of interactions among microbial species. Since there are several network inference approaches in the literature, in this paper we tried to shed light on their main characteristics and challenges, providing a useful tool not only to those interested in using the methods, but also to those who want to develop new ones. In addition, we focused on the frameworks used to produce synthetic data, starting from the simulation of network structures up to their integration with abundance models, with the aim of clarifying the key points of the entire generative process.

Some thoughts on counts in sequencing studies

Measurements in sequencing studies are mostly based on counts. There is a lack of theoretical developments for the analysis and modelling of this type of data. Some thoughts in this direction are presented, which might serve as a seed. The main issues addressed are the compositional character of multinomial probabilities and the corresponding representation in orthogonal (isometric) coordinates, and modelling distributions for sequencing data taking into account possible effects of amplification techniques.