Machine learning within the Parkinson's progression markers initiative: Review of the current state of affairs

The Parkinson's Progression Markers Initiative (PPMI) has collected more than a decade's worth of longitudinal and multi-modal data from patients, healthy controls, and at-risk individuals, including imaging, clinical, cognitive, and 'omics' biospecimens. Such a rich dataset presents unprecedented opportunities for biomarker discovery, patient subtyping, and prognostic prediction, but it also poses challenges that may require the development of novel methodological approaches to solve. In this review, we provide an overview of the application of machine learning methods to analyzing data from the PPMI cohort. We find that there is significant variability in the types of data, models, and validation procedures used across studies, and that much of what makes the PPMI data set unique (multi-modal and longitudinal observations) remains underutilized in most machine learning studies. We review each of these dimensions in detail and provide recommendations for future machine learning work using data from the PPMI cohort.

The Big Picture of Neurodegeneration: A Meta Study to Extract the Essential Evidence on Neurodegenerative Diseases in a Network-Based Approach

The common features of all neurodegenerative diseases, including Alzheimer's disease, Parkinson's disease, Amyotrophic Lateral Sclerosis (ALS), and Huntington's disease, are the accumulation of aggregated and misfolded proteins and the progressive loss of neurons, leading to cognitive decline and locomotive dysfunction. Still, they differ in their ultimate manifestation, the affected brain region, and the kind of proteinopathy. In the last decades, a vast number of processes have been described as associated with neurodegenerative diseases, making it increasingly harder to keep an overview of the big picture forming from all those data. In this meta-study, we analyzed genomic, transcriptomic, proteomic, and epigenomic data of the aforementioned diseases using the data of 234 studies in a network-based approach to study significant general coherences but also specific processes in individual diseases or omics levels. In the analysis part, we focus on only some of the emerging findings, but trust that the meta-study provided here will be a valuable resource for various other researchers focusing on specific processes or genes contributing to the development of neurodegeneration.

STATegra: Multi-Omics Data Integration - A Conceptual Scheme With a Bioinformatics Pipeline

Technologies for profiling samples using different omics platforms have been at the forefront since the human genome project. Large-scale multi-omics data hold the promise of deciphering different regulatory layers. Yet, while there is a myriad of bioinformatics tools, each multi-omics analysis appears to start from scratch with an arbitrary decision over which tools to use and how to combine them. Therefore, it is an unmet need to conceptualize how to integrate such data and implement and validate pipelines in different cases. We have designed a conceptual framework (STATegra), aiming it to be as generic as possible for multi-omics analysis, combining available multi-omic anlaysis tools (machine learning component analysis, non-parametric data combination, and a multi-omics exploratory analysis) in a step-wise manner. While in several studies, we have previously combined those integrative tools, here, we provide a systematic description of the STATegra framework and its validation using two The Cancer Genome Atlas (TCGA) case studies. For both, the Glioblastoma and the Skin Cutaneous Melanoma (SKCM) cases, we demonstrate an enhanced capacity of the framework (and beyond the individual tools) to identify features and pathways compared to single-omics analysis. Such an integrative multi-omics analysis framework for identifying features and components facilitates the discovery of new biology. Finally, we provide several options for applying the STATegra framework when parametric assumptions are fulfilled and for the case when not all the samples are profiled for all omics. The STATegra framework is built using several tools, which are being integrated step-by-step as OpenSource in the STATegRa Bioconductor package.

Premature Activation of Immune Transcription Programs in Autoimmune-Predisposed Mouse Embryonic Stem Cells and Blastocysts

Autoimmune diabetes is a complex multifactorial disease with genetic and environmental factors playing pivotal roles. While many genes associated with the risk of diabetes have been identified to date, the mechanisms by which external triggers contribute to the genetic predisposition remain unclear. Here, we derived embryonic stem (ES) cell lines from diabetes-prone non-obese diabetic (NOD) and healthy C57BL/6 (B6) mice. While overall pluripotency markers were indistinguishable between newly derived NOD and B6 ES cells, we discovered several differentially expressed genes that normally are not expressed in ES cells. Several genes that reside in previously identified insulin-dependent diabetics (Idd) genomic regions were up-regulated in NOD ES cells. Gene set enrichment analysis showed that different groups of genes associated with immune functions are differentially expressed in NOD. Transcriptomic analysis of NOD blastocysts validated several differentially overexpressed Idd genes compared to B6. Genome-wide mapping of active histone modifications using ChIP-Seq supports active expression as the promoters and enhancers of activated genes are also marked by active histone modifications. We have also found that NOD ES cells secrete more inflammatory cytokines. Our data suggest that the known genetic predisposition of NOD to autoimmune diabetes leads to epigenetic instability of several Idd regions.

Propionibacterium acnes and Acne Vulgaris: New Insights from the Integration of Population Genetic, Multi-Omic, Biochemical and Host-Microbe Studies

The anaerobic bacterium Propionibacterium acnes is believed to play an important role in the pathophysiology of the common skin disease acne vulgaris. Over the last 10 years our understanding of the taxonomic and intraspecies diversity of this bacterium has increased tremendously, and with it the realisation that particular strains are associated with skin health while others appear related to disease. This extensive review will cover our current knowledge regarding the association of P. acnes phylogroups, clonal complexes and sequence types with acne vulgaris based on multilocus sequence typing of isolates, and direct ribotyping of the P. acnes strain population in skin microbiome samples based on 16S rDNA metagenomic data. We will also consider how multi-omic and biochemical studies have facilitated our understanding of P. acnes pathogenicity and interactions with the host, thus providing insights into why certain lineages appear to have a heightened capacity to contribute to acne vulgaris development, while others are positively associated with skin health. We conclude with a discussion of new therapeutic strategies that are currently under investigation for acne vulgaris, including vaccination, and consider the potential of these treatments to also perturb beneficial lineages of P. acnes on the skin.