A causal view on compositional data

Ailer, Elisabeth; Müller, Christian L.; Kilbertus, Niki

doi:10.48550/arxiv.2106.11234

Cited by 4 publications

(4 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a diet intervention study, for instance, it is not unlikely that the intended direct effect on host health is mediated or confounded by the presence of certain microbes in the microbiome. While the instrumental variable (IV) approach 67 provides a powerful framework to uncover causal effects (see also Ailer et al 68 in the context of microbiome data), it requires that the instruments are strong and not confounded. A standard IV approach for continuous data estimates the parameters using two-stage least square.…”

Section: Discussionmentioning

confidence: 99%

Negative binomial factor regression with application to microbiome data analysis

Mishra

Müller

2022

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

The human microbiome provides essential physiological functions and helps maintain host homeostasis via the formation of intricate ecological host-microbiome relationships. While it is well established that the lifestyle of the host, dietary preferences, demographic background, and health status can influence microbial community composition and dynamics, robust generalizable associations between specific host-associated factors and specific microbial taxa have remained largely elusive. Here, we propose factor regression models that allow the estimation of structured parsimonious associations between host-related features and amplicon-derived microbial taxa. To account for the overdispersed nature of the amplicon sequencing count data, we propose negative binomial reduced rank regression (NB-RRR) and negative binomial co-sparse factor regression (NB-FAR). While NB-RRR encodes the underlying dependency among the microbial abundances as outcomes and the host-associated features as predictors through a rank-constrained coefficient matrix, NB-FAR uses a sparse singular value decomposition of the coefficient matrix. The latter approach avoids the notoriously difficult joint parameter estimation by extracting sparse unit-rank components of the coefficient matrix sequentially, effectively delivering interpretable bi-clusters of taxa and host-associated factors. To solve the nonconvex optimization problems associated with these factor regression models, we present a novel iterative block-wise majorization procedure. Extensive simulation studies and an application to the microbial abundance data from the American Gut Project (AGP) demonstrate the efficacy of the proposed procedure. In the AGP data, we identify several factors that strongly link dietary habits and host life style to specific microbial families.

show abstract

Section: Discussionmentioning

confidence: 99%

Negative binomial factor regression with application to microbiome data analysis

Mishra

Müller

2022

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…1). To enhance the interpretability of these log-contrasts and address potential issues regarding causality (Ailer et al, 2021), we incorporated the count of all topological roles into the equation. This ensured that an increase in the Connector balance was necessarily driven by an increase in the absolute count of connector nodes.…”

Section: Compositional Analysis Of the Language Connectomementioning

confidence: 99%

Modeling the Neurocognitive Dynamics of Language across the Lifespan

Guichet¹,

Banjac²,

Mermillod³

et al. 2023

Preprint

View full text Add to dashboard Cite

Healthy aging is associated with a heterogeneous decline across cognitive functions, typically observed in language performances. Examining resting-state fMRI and neuropsychological data from 628 healthy adults (age 18-88) from the CamCAN cohort, we performed state-of-the-art graph theoretical analysis to uncover the neural mechanisms underlying this cognitive variability. At the cognitive level, our findings suggest that language processing is not an isolated function but is modulated throughout an individual's lifespan by the extent of inter-cognitive synergy between language, long-term memory, and executive functions. At the cerebral level, we show that the coupling between DMN (Default Mode Network) and FPN (Fronto-Parietal Network) regions may be the way for the brain to compensate for the effects of dedifferentiation at a minimal cost, efficiently mitigating the age-related cognitive decline in language production, fluid processing, and verbal fluency. Notably, the dynamic of cognitive resilience provided by this synergistic coupling seems to follow the Seneca effect typically found in complex systems: a slow rise followed by an abrupt decline. Specifically, we argue that reducing the DMN-FPN coupling could trigger accelerated cognitive decline around age 50. We summarize our findings in a novel SENECA model (Synergistic, Economical, Nonlinear, Emergent, Cognitive Aging), integrating connectomic and cognitive perspectives within a complex system perspective. Our study furthers our understanding of the dedifferentiation-compensation mechanisms that uphold inter-cognitive functioning during healthy aging and suggests that the fifth decade of life could transition towards less synergistic processing.

show abstract

“…An attractive property of the log-contrast model is that its coefficients quantify the effect of a multiplicative perturbation (i.e., fractionally increasing one component while adjusting the others) on the response. While several extensions of the log-contrast model exist [e.g., [13][14][15][16][17], its parametric approach to supervised learning has two major shortcomings that become particularly severe when applied to high-dimensional and zero-inflated high-throughput sequencing data [18,19]. Firstly, since the logarithm is not defined at zero, the log-contrast model cannot be directly applied.…”

Section: Introductionmentioning

confidence: 99%

Supervised learning and model analysis with compositional data

et al. 2023

View full text Add to dashboard Cite

Supervised learning, such as regression and classification, is an essential tool for analyzing modern high-throughput sequencing data, for example in microbiome research. However, due to the compositionality and sparsity, existing techniques are often inadequate. Either they rely on extensions of the linear log-contrast model (which adjust for compositionality but cannot account for complex signals or sparsity) or they are based on black-box machine learning methods (which may capture useful signals, but lack interpretability due to the compositionality). We propose KernelBiome, a kernel-based nonparametric regression and classification framework for compositional data. It is tailored to sparse compositional data and is able to incorporate prior knowledge, such as phylogenetic structure. KernelBiome captures complex signals, including in the zero-structure, while automatically adapting model complexity. We demonstrate on par or improved predictive performance compared with state-of-the-art machine learning methods on 33 publicly available microbiome datasets. Additionally, our framework provides two key advantages: (i) We propose two novel quantities to interpret contributions of individual components and prove that they consistently estimate average perturbation effects of the conditional mean, extending the interpretability of linear log-contrast coefficients to nonparametric models. (ii) We show that the connection between kernels and distances aids interpretability and provides a data-driven embedding that can augment further analysis. KernelBiome is available as an open-source Python package on PyPI and at https://github.com/shimenghuang/KernelBiome.

show abstract

A causal view on compositional data

Cited by 4 publications

References 59 publications

Negative binomial factor regression with application to microbiome data analysis

Negative binomial factor regression with application to microbiome data analysis

Modeling the Neurocognitive Dynamics of Language across the Lifespan

Supervised learning and model analysis with compositional data

Contact Info

Product

Resources

About