2017/08/15 by David Sinclair, Giles Hooker, Sinclair, David +1
Biochemistry, Genetics and Molecular Biology · #Applications (stat.AP) #Bioinformatics and Genomic Networks #Computation (stat.CO) #FOS: Computer and information sciences #Gene expression and cancer classification #Genomics and Chromatin Dynamics #Methodology (stat.ME)
paper · pdf · doi:10.48550/arxiv.1708.04490
openalex publication_date 2017/08/15 · openalex created_date 2022/10/04 · openalex updated_date 2026/07/28
We introduce the Poisson Log-Normal Graphical Model for count data, and\npresent a normality transformation for data arising from this distribution. The\nmodel and transformation are feasible for high-throughput microRNA (miRNA)\nsequencing data and directly account for known overdispersion relationships\npresent in this data set. The model allows for network dependencies to be\nmodeled, and we provide an algorithm which utilizes a one-step EM based result\nin order to allow for a provable increase in performance in determining the\nnetwork structure. The model is shown to provide an increase in performance in\nsimulation settings over a range of network structures. The model is applied to\nhigh-throughput miRNA sequencing data from patients with breast cancer from The\nCancer Genome Atlas (TCGA). By selecting the most highly connected miRNA\nmolecules in the fitted network we find that nearly all of them are known to be\ninvolved in the regulation of breast cancer.\n