Steele, A. J. | bioRxiv Science

bioRxiv2022

Network analysis reveals a major role for 14q32 cluster miRNAs in determining transcriptional differences between IGHV-mutated and unmutated CLL

Tumour cells from patients with chronic lymphocytic leukaemia (CLL) can express unmutated (U-CLL) or mutated (M-CLL) immunoglobulin heavy chain (IGHV) genes with differing clinical behaviours, variable B cell receptor (BCR) signalling capacity and distinct transcriptional profiles. As it remains unclear to what extent these differences reflect the tumour cells innate pre/post germinal centre origin or their BCR signalling competence, we applied RNA sequencing, small RNA sequencing and DNA methylation array analysis to 38 CLL cases categorised into three groups by IGHV mutational status and BCR signalling capacity. We identified 492 mRNAs and 38 miRNAs differentially expressed between U-CLL and M-CLL, but only 9 mRNAs and 0 miRNAs associated with BCR competence within M-CLL. A significant proportion of the IGHV-associated miRNAs derived from chr14q32 clusters (14/38 (37%)), where all miRNAs were co-expressed with the MEG3 lncRNA, as part of the DLK1-DIO3 genomic imprinted region, a locus of known importance in the pathogenesis of other human tumours. Integrative in silico analysis of miRNA/mRNA data revealed pronounced regulatory potential for the 14q32 miRNAs, potentially accounting for up to 25% of the IGHV-related transcriptome signature. GAB1, a positive regulator of BCR signalling, was predicted to be regulated by five 14q32 miRNAs and we confirmed that two of these (miR-409-3p and miR-411-3p) significantly repressed activity of the GAB1 3UTR. Our analysis demonstrates a potential key role of the 14q32 miRNA locus in the regulation of CLL-related gene regulation.

cancer biology↗

bioRxiv2018

Machine learning models in electronic health records can outperform conventional survival models for predicting patient mortality in coronary artery disease

Prognostic modelling is important in clinical practice and epidemiology for patient management and research. Electronic health records (EHR) provide large quantities of data for such models, but conventional epidemiological approaches require significant researcher time to implement. Expert selection of variables, fine-tuning of variable transformations and interactions, and imputing missing values in datasets are time-consuming and could bias subsequent analysis, particularly given that missingness in EHR is both high, and may carry meaning.\n\nUsing a cohort of over 80,000 patients from the CALIBER programme, we performed a systematic comparison of several machine-learning approaches in EHR. We used Cox models and random survival forests with and without imputation on 27 expert-selected variables to predict all-cause mortality. We also used Cox models, random forests and elastic net regression on an extended dataset with 586 variables to build prognostic models and identify novel prognostic factors without prior expert input.\n\nWe observed that data-driven models used on an extended dataset can outperform conventional models for prognosis, without data preprocessing or imputing missing values, and with no need to scale or transform continuous data. An elastic net Cox regression based with 586 unimputed variables with continuous values discretised achieved a C-index of 0.801 (bootstrapped 95% CI 0.799 to 0.802), compared to 0.793 (0.791 to 0.794) for a traditional Cox model comprising 27 expert-selected variables with imputation for missing values.\n\nWe also found that data-driven models allow identification of novel prognostic variables; that the absence of values for particular variables carries meaning, and can have significant implications for prognosis; and that variables often have a nonlinear association with mortality, which discretised Cox models and random forests can elucidate.\n\nThis demonstrates that machine-learning approaches applied to raw EHR data can be used to build reliable models for use in research and clinical practice, and identify novel predictive variables and their effects to inform future research.

epidemiology↗