Christopher Yau

Antenatal outcomes for women with multiple long-term conditions in pregnancy: a UK-wide retrospective cohort study

Lisa Kent, Steven Wambua, Megha Singh, Ayodele Opatola et autres

BACKGROUND: Around 20% of pregnant women in the UK have multiple long-term conditions (MLTCs), defined as two or more physical or mental health conditions. The current evidence related to adverse maternal outcomes at a population level is scarce. The aim of this …

gb, es (code pays fourni par la source)

Pregnancy complications and risk of cardiometabolic-renal conditions:a longitudinal study of 1.4 million women from England

Steven Wambua, Megha Singh, Rishard Mohammed, Nadia Sarween et autres

Deep learning enables cross-species annotation and attribution of ageing states in haematopoietic stem and immune cells

Simiao Zhao, Bowen Zhang, Melinda Czéh-Bhardwaj, Xuehao Zhai et autres

Abstract Mouse single-cell ageing studies provide experimentally controlled age contrasts, but using mouse-labelled data to annotate human ageing states is limited by species, donor and assay effects in sparse transcriptomic and chromatin profiles. We developed a cross-species annotation workflow that treats mouse-to-human …

gb (code pays fourni par la source)

Transcriptomic analysis of tissue-resident memory T cells of the fallopian tube reveals a precursor immune surveillance network for ovarian cancer prevention

Luyao Wang, Breeshey Roskams-Hieter, Nosheen Hussain, Joel Nulsen et autres

The fallopian tube (FT) is increasingly recognized as the origin of high-grade serous ovarian cancer (HGSOC), yet its immune landscape remains poorly understood. Here, we employ single-cell RNA sequencing and paired T-cell receptor sequencing to profile tissue-resident memory-like T cells (TRML) from …

gb, us, Égypte (code pays fourni par la source)

MIND: multimodal integration with neighbourhood-aware distributions

Hanwen Xing, Christopher Yau

Multimodal data integration combines different data modalities to improve predictive and classification performance. In biology, multi-omics profiling has become a powerful tool for applications such as cancer patient stratification. However, integration of multi-omics data remains challenging because of missingness and inherent heterogeneity. …

gb (code pays fourni par la source)

Understanding the spatial determinants of the Oxford Classic prognostic signature for high-grade serous ovarian cancer

Alexandru Stihi, Christopher Yau

BACKGROUND: The Oxford Classic (OxC) prognostic signature classifies high-grade serous ovarian cancer (HGSOC) into five transcriptional programs, with epithelial-to-mesenchymal transition (EMT) marking poor prognosis. While successful in bulk transcriptomics, the spatial organisation of these programs within the tumour microenvironment remains unexplored. METHODS: …

gb (code pays fourni par la source)

MIND: multimodal integration with neighbourhood-aware distributions

Hanwen Xing, Christopher Yau

Abstract Multimodal data integration combines different data modalities to improve predictive and classification performance. In biology, multi-omics profiling has become a powerful tool for applications such as cancer patient stratification. However, integration of multi-omics data remains challenging because of missingness and inherent …

SurvivEHR: a competing risks, time-to-event foundation model for multiple long-term conditions from primary care electronic health records

C. J. Gadd, Krishna Margadhamane Gokhale, Aditya Acharya, Jennifer N. Cooper et autres

Multiple long-term conditions (MLTCs), or multimorbidity-the co-occurrence of multiple chronic conditions-present a growing challenge for primary care. Existing predictive models typically focus on single outcomes and often fail to capture the temporal and competing-risk structure inherent in longitudinal electronic health records (EHRs). …

gb (code pays fourni par la source)

Imputation Free Deep Survival Prediction with Conditional Variational Autoencoders

Natalia Hong, Aditya Acharya, Krishna Margadhamane Gokhale, Jenny Cooper et autres

Electronic Health Records (EHRs) provide rich opportunities for developing risk prediction tools to support clinical decision-making, yet they are inherently incomplete because data are recorded selectively during routine care. Such missingness may be informative, reflecting clinical judgment and patient status, and missing …

gb, us (code pays fourni par la source)

Hybrid Restricted Master Problem for Boolean Matrix Factorisation

Ellen Visscher, Michael A. Forbes, Christopher Yau

We present bfact, a Python package for performing accurate low-rank Boolean matrix factorisation (BMF). bfact uses a hybrid combinatorial optimisation approach based on a priori candidate factors generated from clustering algorithms. It selects the best disjoint factors before performing either a second …

Untangling biological complexity: A deep learning approach to separating multiple signals in single-cell data

Christopher Yau

Single-cell RNA sequencing (scRNA-seq) provides an instantaneous snapshot of the transcriptional state of a cell, which results from the simultaneous activity of many cellular processes. In this issue of Cell Genomics , Chen et al. 1 describe the development of CellUntangler, a …

gb (code pays fourni par la source)

A transformer-based survival model for prediction of all-cause mortality in patients with heart failure: a multi-cohort study

Shishir Rao, Nouman Ahmed, Gholamreza Salimi-Khorshidi, Christopher Yau et autres

Heart failure (HF) patients have complex health profiles that existing risk models fail to capture. We developed TRisk, a Transformer-based artificial intelligence survival model for predicting mortality using routine electronic health records (EHR) in HF patients. Using UK data from 403,534 HF …

gb, be, nl, au, nz (code pays fourni par la source)