Dataset Information

Semi-Supervised Non-Parametric Bayesian Modelling of Spatial Proteomics.

ABSTRACT: Understanding sub-cellular protein localisation is an essential component in the analysis of context specific protein function. Recent advances in quantitative mass-spectrometry (MS) have led to high resolution mapping of thousands of proteins to sub-cellular locations within the cell. Novel modelling considerations to capture the complex nature of these data are thus necessary. We approach analysis of spatial proteomics data in a non-parametric Bayesian framework, using K-component mixtures of Gaussian process regression models. The Gaussian process regression model accounts for correlation structure within a sub-cellular niche, with each mixture component capturing the distinct correlation structure observed within each niche. The availability of marker proteins (i.e. proteins with a priori known labelled locations) motivates a semi-supervised learning approach to inform the Gaussian process hyperparameters. We moreover provide an efficient Hamiltonian-within-Gibbs sampler for our model. Furthermore, we reduce the computational burden associated with inversion of covariance matrices by exploiting the structure in the covariance matrix. A tensor decomposition of our covariance matrices allows extended Trench and Durbin algorithms to be applied to reduce the computational complexity of inversion and hence accelerate computation. We provide detailed case-studies on Drosophila embryos and mouse pluripotent embryonic stem cells to illustrate the benefit of semi-supervised functional Bayesian modelling of the data.

SUBMITTER: Crook OM

PROVIDER: S-EPMC7613899 | biostudies-literature | 2022 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Semi-Supervised Non-Parametric Bayesian Modelling of Spatial Proteomics.

Crook Oliver M OM Lilley Kathryn S KS Gatto Laurent L Kirk Paul D W PDW

The annals of applied statistics 20221201 4

Understanding sub-cellular protein localisation is an essential component in the analysis of context specific protein function. Recent advances in quantitative mass-spectrometry (MS) have led to high resolution mapping of thousands of proteins to sub-cellular locations within the cell. Novel modelling considerations to capture the complex nature of these data are thus necessary. We approach analysis of spatial proteomics data in a non-parametric Bayesian framework, using K-component mixtures of ...[more]

PMID: 36507469

Similar Datasets

Project description:BackgroundIntimate partner violence (IPV) is an important public health problem with health and socioeconomic consequences and is endemic in Namibia. Studies assessing risk factors for IPV often use logistic and Poisson regression without geographical location information and spatial effects. We used a Bayesian spatial semi-parametric regression model to determine the risk factors for IPV in Namibia; assess the non-linear effects of age difference between partners and determine spatial effects in the different regions on IPV prevalence.MethodsWe used the couples' dataset of the 2013-2014 Namibia Demographic and Health Survey (DHS) obtained on request from Measure DHS. The DHS domestic violence module included 2226 women. We generated a binary variable measuring IPV from the questions "ever experienced physical, sexual or emotional violence?" Covariates included respondent's educational level, age, couples' age difference, place of residence and partner's educational level. All estimation was done with the full Bayesian approach using R version 3.5.2 implementing the R2BayesX package.ResultsIPV country prevalence was 33.3% (95% CI = 30.1-36.5%); Kavango had the highest [50.6% (95% CI = 41.2-60.1%)] and Oshana the lowest [11.5% (95% CI = 3.2-19.9%)] regional prevalence. IPV prevalence was highest among teenagers [60.8% (95% CI = 36.9-84.7%)]). The spatial semi-parametric model used for adjusted results controlled for regional spatial effects, respondent's age, age difference, respondent's years of education, residence, wealth, and education levels. Women with higher education were 50% less likely to experience IPV [aOR: 0.46, 95% CI = 0.23-0.87]. For non-linear effects, the risk of IPV was high for women ≥ 5 years older or ≥ 25 years younger than their partners. Younger and older women had higher risks of IPV than those between 25 and 45 years. For spatial variation of IPV prevalence, northern regions had low spatial effects while western regions had very high spatial effects.ConclusionThe prevalence of IPV among Namibia women was high especially among teenagers, with higher educational levels being protective. The risk of IPV was lower in rural than urban areas and higher with wide partner age differences. Interventions and policies for IPV prevention in Namibia are needed for couples with wide age differences as well as for younger women, women with lower educational attainment and in urban and western regions.

Project description:MotivationThe negative binomial distribution has been shown to be a good model for counts data from both bulk and single-cell RNA-sequencing (RNA-seq). Gaussian process (GP) regression provides a useful non-parametric approach for modelling temporal or spatial changes in gene expression. However, currently available GP regression methods that implement negative binomial likelihood models do not scale to the increasingly large datasets being produced by single-cell and spatial transcriptomics.ResultsThe GPcounts package implements GP regression methods for modelling counts data using a negative binomial likelihood function. Computational efficiency is achieved through the use of variational Bayesian inference. The GP function models changes in the mean of the negative binomial likelihood through a logarithmic link function and the dispersion parameter is fitted by maximum likelihood. We validate the method on simulated time course data, showing better performance to identify changes in over-dispersed counts data than methods based on Gaussian or Poisson likelihoods. To demonstrate temporal inference, we apply GPcounts to single-cell RNA-seq datasets after pseudotime and branching inference. To demonstrate spatial inference, we apply GPcounts to data from the mouse olfactory bulb to identify spatially variable genes and compare to two published GP methods. We also provide the option of modelling additional dropout using a zero-inflated negative binomial. Our results show that GPcounts can be used to model temporal and spatial counts data in cases where simpler Gaussian and Poisson likelihoods are unrealistic.Availability and implementationGPcounts is implemented using the GPflow library in Python and is available at https://github.com/ManchesterBioinference/GPcounts along with the data, code and notebooks required to reproduce the results presented here. The version used for this paper is archived at https://doi.org/10.5281/zenodo.5027066.Supplementary informationSupplementary data are available at Bioinformatics online.

Dataset Information

Semi-Supervised Non-Parametric Bayesian Modelling of Spatial Proteomics.

Publications

Semi-Supervised Non-Parametric Bayesian Modelling of Spatial Proteomics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets