I am a Senior Statistician and Assistant Research Professor at the MRC Biostatistics Unit, University of Cambridge (United Kingdom). I also serve as an External Lecturer at EPFL (Switzerland). My research lies at the intersection of modern statistical learning and open problems in health and biomedicine.
My team develops Bayesian and statistical machine learning methodology, and accompanying software, for high-dimensional, longitudinal and multimodal data, with a focus on hierarchical modelling for variable selection, latent structure discovery and network estimation. We aim for methods that are interpretable, robust and computationally scalable. Our work is motivated by collaborative clinical and biological studies, with questions spanning patient trajectories, biomarkers and the molecular processes underlying health and disease.
Our overarching goal is to provide principled statistical and computational tools to help advance our understanding of the biological processes driving disease risk and progression.
I also provide statistical consulting for biomedical and life sciences research and R&D, supporting projects from study design through to data analysis and methodological review. Get in touch to discuss a potential collaboration.
I have the pleasure of working with talented researchers at the MRC Biostatistics Unit (MRC BSU):
Former team members (all current MRC BSU visiting researchers):
I also regularly supervise Bachelor and Master theses of students from Cambridge University and EPFL (Lausanne). I am also a co-organiser of the MRC BSU Internship Programme; applications for the 2026 summer internships are now open until April 15, get in touch if interested!
The Unit also provides a dynamic environment to begin a career in biostatistics, with a PhD Programme offering multiple positions annually.
Aug 2026: Co-launched the MRC BSU AI Discussion Group, a forum for peer learning and discussion around statistical and AI methods in biomedical research.
July 13, 2026: New preprint on a Partition FPCA model for time-course gene expression data – lead author Marion Kerioui, joint with Daniel Temko and Shahin Tavakoli.
July 1, 2026: I look forward to speaking at the Statistical and AI methods for multi-modal multi-scale modeling of biological systems Conference in Ascona about latent trajectory modelling for longitudinal molecular data – joint work with Salima Jaoua and Daniel Temko.
May 19, 2026: I look forward to presenting our work at the IBS-CEN2026 Conference in Warsaw, on Bayesian network inference with node-level information – joint work with Xiaoyue Xi.
Mar 21, 2026: New preprint on a Bayesian latent factor modelling framework to uncover coordinated biological dynamics from high-dimensional longitudinal data – joint with Salima Jaoua and Daniel Temko.
The landscape of biomedical research is changing rapidly, driven by technological advances for quantifying clinical and molecular data at scale. This evolution not only offers a more granular view of disease mechanisms, but also parallels a growing acknowledgment that pathogenic responses are tightly coordinated at the organismal level. Consequently, there is a need for modelling approaches capable of providing a holistic understanding of complex interplays across biological systems.
My team aims to provide principled statistical methodology for tackling this challenge, guided by collaborations with clinicians and researchers in areas such as immunology, infectiology and cancer. We have a particular interest in longitudinal and multimodal biomedical data, including patient trajectories, molecular dynamics and multimodal integration across omics, clinical, wearable and patient-reported data.
Our methodological work spans Bayesian hierarchical modelling, sparse regression, latent representation models, network models and functional data analysis. We develop scalable statistical and machine learning approaches to uncover latent and shared structure across biological systems, characterise within- and between-individual heterogeneity across biological contexts, and quantify uncertainty in the resulting inferences. We are particularly interested in addressing the tension between flexible joint estimation and practical feasibility at the scale of current biomedical studies, with a focus on accuracy, robustness and computational tractability. Common threads include (i) learning and leveraging shared biological structures across modalities, scales and contexts (molecular entities, tissues, cell types or disease subtypes), and (ii) developing approximate inference procedures, such as expectation-maximisation (EM) and model-specific variational schemes, for high-dimensional parameter spaces.
Our methods are tailored to specific scientific questions, yet remain adaptable to a broader range of applications. We support their use through accompanying statistical software and implementations (see Software).
I am strongly committed to open science and reproducible research. I contribute to these efforts through the BSU Open Science Committee, which promotes transparency, collaboration and the sharing of tools, data and methods, both within the Unit and across the wider scientific community.
Our research receives generous support from the Lopez–Loreta Foundation.
Variable selection in sparse regression with hierarchically-related responses
Bayesian functional principal component analysis suite – with Tui Nolan
Bayesian functional factor modelling framework
Source code for reproducing an example in a chapter published in the Handbook of Bayesian variable selection
FPCA estimates of patient disease trajectories after SARS-CoV-2 infection
Faithful replication and simulation of molecular and clinical data
Annotation-driven approach for large-scale joint regression with multiple responses
Joint graphical horseshoe for multiple network inference with shared information – creator and maintainer Camilla Lingjærde
Large-scale variational inference for variable selection in sparse multiple-response regression
Solutions and suggested code for the 1st practical session fo the Bayes4Health-CoSInES Masterclass in variational inference – with Camilla Lingjærde
Source code for reproducing a numerical example using the method “locus” on simulated data
Variable-guided network inference using Bayesian graphical spike-and-slab modelling – creator and maintainer Xiaoyue Xi
Bayesian approach to joint network estimation informed by ordinal covariates – creator and maintainer Joseph Feest
Online database gathering hits from a QTL mapping of human protein abundance in plasma
Source code for assessing the sensitivity of the method “atlasqtl” to hyperparameter settings
Source code for reproducing article on the atlasqtl R package published in the Software Corner of the IBS Bulletin