Infants’ gut microbiome data: A Bayesian Marginal Zero-inflated Negative Binomial regression model for multivariate analyses of count data

Hajihosseini, Morteza; Amini, Payam; Saidi‐Mehrabad, Alireza; Dinu, Irina

doi:10.1016/j.csbj.2023.02.027

Cited by 4 publications

(2 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zero-inflation is a inevitable property in gut microbiome count data, but previous some models such as BhGLM and glmFit ignore this property and primarily utilize a negative binomial distribution[57]. Conversely, some other studies have used certain statistical models that may not be appropriate, producing results that overemphasize the zero-bloat nature of the gut microbiome data[25, 58, 12, 59]. In the current study, our data processing results by using the ZINB model showed that only a small number of microbial taxa counts belonged to zero-inflated distributions, and the probability of zero-inflation decreases continuously with an increase of taxonomic rank.…”

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Association of Body Index with Fecal Microbiome in Children Cohorts with Ethnic-Geographic Factor Interaction: Accurately Using a Bayesian Zero-inflated Negative Binomial Regression Model

Huang,

Lu,

Tian

et al. 2024

Preprint

View full text Add to dashboard Cite

The exponential growth of High-Throughput Sequencing (HTS) data on the microbial communities presents researchers with an unparalleled opportunity to delve deeper into the association of microorganisms with host phenotype. However, this growth also poses a challenge, as microbial data is complex, sparse, discrete, and prone to zero-inflation. Moreover, current methods for integrating microbiome data and other covariates are severely lacking. Hence, we propose a Bayesian zero-inflated negative binomial (ZINB) regression model that is capable of identifying differentially abundant taxa with distinct phenotypes and quantifying the effects of covariates on these taxa. Our model exhibits excellent performance when tested on simulated data. Upon successfully applying our model to a real multi-ethnic cohort study, we discovered that the prevailing understanding of microbial count data from previous research was overly dogmatic, because only a subset of taxa demonstrated zero inflation in real data. Moreover, we have discovered that dispersion parameters significantly influence the accuracy of model results, and increasing sample size can alleviate this issue. In all, we have presented an innovative integrative Bayesian regression model and a comprehensive pipeline for conducting a multi-ethnic cohort study of children, which facilitates bacterial differential abundance analysis and quantification of microbiome-covariate effects. This approach can be applied to general microbiome studies.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Association of Body Index with Fecal Microbiome in Children Cohorts with Ethnic-Geographic Factor Interaction: Accurately Using a Bayesian Zero-inflated Negative Binomial Regression Model

Huang,

Lu,

Tian

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

A comparative analysis of mutual information methods for pairwise relationship detection in metagenomic data

Francis,

Sun

2024

BMC Bioinformatics

View full text Add to dashboard Cite

Background Construction of co-occurrence networks in metagenomic data often employs correlation to infer pairwise relationships between microbes. However, biological systems are complex and often display qualities non-linear in nature. Therefore, the reliance on correlation alone may overlook important relationships and fail to capture the full breadth of intricacies presented in underlying interaction networks. It is of interest to incorporate metrics that are not only robust in detecting linear relationships, but non-linear ones as well. Results In this paper, we explore the use of various mutual information (MI) estimation approaches for quantifying pairwise relationships in biological data and compare their performances against two traditional measures–Pearson’s correlation coefficient, r , and Spearman’s rank correlation coefficient, ρ. Metrics are tested on both simulated data designed to mimic pairwise relationships that may be found in ecological systems and real data from a previous study on C. diff infection. The results demonstrate that, in the case of asymmetric relationships, mutual information estimators can provide better detection ability than Pearson’s or Spearman’s correlation coefficients. Specifically, we find that these estimators have elevated performances in the detection of exploitative relationships, demonstrating the potential benefit of including them in future metagenomic studies. Conclusions Mutual information (MI) can uncover complex pairwise relationships in biological data that may be missed by traditional measures of association. The inclusion of such relationships when constructing co-occurrence networks can result in a more comprehensive analysis than the use of correlation alone. Supplementary Information The online version contains supplementary material available at 10.1186/s12859-024-05883-7.

show abstract

Count Data Prediction with Poisson Regressions on Poisson-Mixture Locations: Application to Traffic Counts in Prague Areas

Uglickich,

Nagy

2024

Preprint

View full text Add to dashboard Cite

Infants’ gut microbiome data: A Bayesian Marginal Zero-inflated Negative Binomial regression model for multivariate analyses of count data

Cited by 4 publications

References 82 publications

Association of Body Index with Fecal Microbiome in Children Cohorts with Ethnic-Geographic Factor Interaction: Accurately Using a Bayesian Zero-inflated Negative Binomial Regression Model

Association of Body Index with Fecal Microbiome in Children Cohorts with Ethnic-Geographic Factor Interaction: Accurately Using a Bayesian Zero-inflated Negative Binomial Regression Model

A comparative analysis of mutual information methods for pairwise relationship detection in metagenomic data

Count Data Prediction with Poisson Regressions on Poisson-Mixture Locations: Application to Traffic Counts in Prague Areas

Contact Info

Product

Resources

About