MRC Biostatistics Unit

Neurodegenerative disease risk associated with gene expression in peripheral monocytes across ancestries

Abstract It is hypothesised that peripheral immune states responding to regional environmental triggers contribute to central neurodegeneration. Region-specific genetic selection pressures require this hypothesis to be assessed in an ancestry-specific manner. Here, we utilise gen...

Cataract GWAS meta-analysis and multi-omics Mendelian randomisation inform disease mechanisms and candidate target prioritisation

Background Cataract is a highly prevalent cause of visual impairment and blindness worldwide. Although genome-wide association studies (GWAS) have mapped multiple cataract risk loci, further work is required towards translating these signals and integrating multi-omics evidence f...

Can discussions with patients and the public clarify missing data mechanisms for digital outcome measures?

Abstract Background Analysis of clinical trials with missing data requires statistical assumptions. When novel digital outcome measures are used, it is particularly important to understand trial participants’ experiences with the device. This can illuminate the reasons for and sp...

Longitudinal dynamics of gene expression and metabolomics in an aging population cohort

Multiomic profiling provides a comprehensive physiological overview at the molecular level, but understanding of its spatiotemporal dynamics remains limited in human populations. We profiled longitudinal whole-blood gene expression and metabolite levels in 335 females over 8 year...

Multi-stromal organoid co-culture modelling reveals epithelial–fibroblast heterogeneity in pancreatic cancer and pancreatitis

Abstract Interactions between epithelial cells and fibroblasts influence disease progression and treatment response in pancreatic ductal adenocarcinoma (PDAC). While the diversity of fibroblasts in PDAC is increasingly recognized, it remains unclear how these cells differ from fi...

The interplay between Bayesian inference and conformal prediction

Conformal prediction (CP) has emerged as a cutting-edge methodology in statistics and machine learning, providing prediction intervals with finite-sample frequentist coverage guarantees. Yet, its interplay with Bayesian statistics-often criticized for lacking frequentist guarante...

Comparison of parametric versus machine-learning multiple imputation in clinical trials with missing continuous outcomes

Abstract Background Flexible machine-learning (ML) models to generate imputations within the Multiple Imputation (MI) framework has recently gained traction, particularly in non-randomised observational settings. For randomised controlled trials (RCTs), it is unclear whether ML a...