Machine Learning

Congratulations to Woojung Kim on having his paper accepted at ML4H 2024.

This paper introduces the Mixed Type Multimorbidity Variational Autoencoder (M3VAE), a deep probabilistic generative model developed for supervised dimensionality reduction in the context of multimorbidity analysis. The model is designed to overcome the limitations of purely supervised or unsupervised approaches in this field. M3VAE focuses on identifying latent representations of mixed-type health-related attributes essential for predicting patient survival outcomes. It integrates datasets with multiple modalities (by which we mean data of multiple types), encompassing health measurements, demographic details, and (potentially censored) survival outcomes. A key feature of M3VAE is its ability to reconstruct latent representations that exhibit clustering patterns, thereby revealing important patterns in disease co-occurrence. This functionality provides insights for understanding and predicting health outcomes. The efficacy of M3VAE has been demonstrated through experiments with both synthetic and real-world electronic health record data, showing its capability in identifying interpretable morbidity groupings related to future survival outcomes. The paper is available on OpenReview.

Congratulations to Charles Gadd on having his paper accepted at MLCB 2024.

Changes in the number of copies of certain parts of the genome, known as copy number alterations (CNAs), due to somatic mutation processes are a hallmark of many cancers. This genomic complexity is known to be associated with poorer outcomes for patients but describing its contribution in detail has been difficult. Copy number alterations can affect large regions spanning whole chromosomes or the entire genome itself but can also be localised to only small segments of the genome and no methods exist that allow this multi-scale nature to be quantified. In this paper, we address this using Wave-LSTM, a signal decomposition approach designed to capture the multi-scale structure of complex whole genome copy number profiles. Using wavelet-based source separation in combination with deep learning-based attention mechanisms. We show that Wave-LSTM can be used to derive multi-scale representations from copy number profiles which can be used to decipher sub-clonal structures from single-cell copy number data and to improve survival prediction performance from patient tumour profiles.

Congratulations to Kaspar Martens on having his paper accepted in Bioinformatics.

Cell type identification plays an important role in the analysis and interpretation of single-cell data and can be carried out via supervised or unsupervised clustering approaches. Supervised methods are best suited where we can list all cell types and their respective marker genes a priori, while unsupervised clustering algorithms look for groups of cells with similar expression properties. This property permits the identification of both known and unknown cell populations, making unsupervised methods suitable for discovery. Success is dependent on the relative strength of the expression signature of each group as well as the number of cells. Rare cell types therefore present a particular challenge that is magnified when they are defined by differentially expressing a small number of genes.

Congratulations to Joel Nulsen on having his paper accepted in BMC Bioinformatics.

Genomic insights in settings where tumour sample sizes are limited to just hundreds or even tens of cells hold great clinical potential, but also present significant technical challenges. We previously developed the DigiPico sequencing platform to accurately identify somatic mutations from such samples.

Congratulations to Kaspar Martens on having his paper accepted at MLCB 2023.

Generative models for multimodal data permit the identification of latent factors that may be associated with important determinants of observed data heterogeneity. Common or shared factors could be important for explaining variation across modalities whereas other factors may be private and important only for the explanation of a single modality. Multimodal Variational Autoencoders, such as MVAE and MMVAE, are a natural choice for inferring those underlying latent factors and separating shared variation from private. In this work, we investigate their capability to reliably perform this disentanglement. In particular, wehighlight a challenging problem setting where modality-specific variation dominates the shared signal. Taking a cross-modal prediction perspective, we demonstrate limitations of existing models, and propose a modification how to make them more robust to modalityspecific variation. Our findings are supported by experiments on synthetic as well as various real-world multi-omics data sets. The paper is available on PMLR.

Congratulations to group members Charles Gadd, Woojung Kim and Dominic Danks on the following papers accepted at ML4H and NeurIPS:

• mmVAE: multimorbidity clustering using Relaxed Bernoulli β-Variational Autoencoders

• Feature Allocation Approach for Multimorbidity Trajectory Modelling

My name is Christopher Yau and I am Professor of Artificial Intelligence at the University of Oxford and Health Data Research UK.

I am carrying out a survey of UK PhD students who are working in any area of data science and I need your help! We hope to get survey responses from over 300 PhD students so please help us by sparing 10-15 minutes of your time to answer some questions.

The workshop series was developed in partnership with Ovarian Cancer Action (OCA) as part of my Turing AI Fellowship.

Congratulations to PhD student Dominic Danks whose paper Derivative-Based Neural Modelling of Cumulative Distribution Functions for Survival Analysis has been accepted for presentation at AISTATS 2022.

Christopher Yau has supported Health Data Research UK (HDRUK) PhD students Fabian Falck and Haoting Zhang in the development of work that has now been published as a paper at the NeurIPS 2021 conference. The work entitled Multi-Facet Clustering Variational Autoencoders is a novel class of variational autoencoders with a hierarchy of latent variables, each with a Mixture-of-Gaussians prior, that learns multiple clusterings simultaneously, and is trained fully unsupervised and end-to-end. Chris, who directs the HDRUK PhD programme, writes about the work of the students in this blog.