Kord M. Kober | Searcharxiv

arXiv2021

A dynamical system model for predicting gene expression from the epigenome

Gene regulation is an important fundamental biological process. The regulation of gene expression is managed through a variety of methods including epigenetic processes (e.g., DNA methylation). Understanding the role of epigenetic changes in gene expression is a fundamental question of molecular biology. Predictions of gene expression values from epigenetic data have tremendous research and clinical potential. Despite active research, studies to date have focused on using statistical models to predict gene expression from methylation data. In contrast, dynamical systems can be used to generate a model to predict gene expression using epigenetic data and a gene regulatory network (GRN) which can also serve as a mechanistic hypothesis. Here we present a novel stochastic dynamical systems model that predicts gene expression levels from methylation data of genes in a given GRN. We provide an evaluation of the model using real patient data and a GRN created from robust reference sources. Software for dataset preparation, model parameter fitting and prediction generation, and reporting are available at \verb|https://github.com/kordk/stoch_epi_lib|.

q-bio.MN↗

arXiv2021

A Hamiltonian Monte Carlo Model for Imputation and Augmentation of Healthcare Data

Missing values exist in nearly all clinical studies because data for a variable or question are not collected or not available. Inadequate handling of missing values can lead to biased results and loss of statistical power in analysis. Existing models usually do not consider privacy concerns or do not utilise the inherent correlations across multiple features to impute the missing values. In healthcare applications, we are usually confronted with high dimensional and sometimes small sample size datasets that need more effective augmentation or imputation techniques. Besides, imputation and augmentation processes are traditionally conducted individually. However, imputing missing values and augmenting data can significantly improve generalisation and avoid bias in machine learning models. A Bayesian approach to impute missing values and creating augmented samples in high dimensional healthcare data is proposed in this work. We propose folded Hamiltonian Monte Carlo (F-HMC) with Bayesian inference as a more practical approach to process the cross-dimensional relations by applying a random walk and Hamiltonian dynamics to adapt posterior distribution and generate large-scale samples. The proposed method is applied to a cancer symptom assessment dataset and confirmed to enrich the quality of data in precision, accuracy, recall, F1 score, and propensity metric.

cs.LG↗