Search

The development of mobile-health technology has the potential to revolutionize personalized medicine. Biomedical sensors (e.g. wearables) can assist with determining treatment plans for individuals, provide quantitative information to healthcare providers, and give objective measurements of health, leading to the goal of precise phenotypic correlates for genotypes. Even though treatments and interventions are becoming more specific and datasets more abundant, measuring the causal impact of health interventions requires careful considerations of complex covariate structures, as well as knowledge of the temporal and spatial properties of the data. Thus, interpreting biomedical sensor data needs to make use of specialized statistical models. Here, we show how the Bayesian structural time series framework, widely used in economics, can be applied to these data. This framework corrects for covariates to provide accurate assessments of the significance of interventions. Furthermore, it allows for a time-dependent confidence interval of impact, which is useful for considering individualized assessments of intervention efficacy. We provide a customized biomedical adaptor tool, MhealthCI, around a specific implementation of the Bayesian structural time series framework that uniformly processes, prepares, and registers diverse biomedical data. We apply the software implementation of MhealthCI to a structured set of examples in biomedicine to showcase the ability of the framework to evaluate interventions with varying levels of data richness and covariate complexity and also compare the performance to other models. Specifically, we show how the framework is able to evaluate an exercise intervention's effect on stabilizing blood glucose in a diabetes dataset. We also provide a future-anticipating illustration from a behavioral dataset showcasing how the framework integrates complex spatial covariates. Overall, we show the robustness of the Bayesian structural time series framework when applied to biomedical sensor data, highlighting its increasing value for current and future datasets. Author summary: In this paper, we propose and describe a robust and flexible modelling framework called MhealthCI based on the Bayesian structural time series, for which we have found to excel at analyzing diverse biosensor data. While Bayesian modelling is often employed in various fields such as finance, marketing, and weather forecasting, it is rarely used in biomedicine, specifically for biosensor and wearable data relating to human health and behavior. We use and apply this framework with the goal of interpreting and quantifying the causal impact of an intervention, a widespread goal of biomedicine. We describe the diversity of data types to which it could apply, provide intuition to its mechanics, collect relevant data in various fields, provide a wrapper tool around well-known R packages that prepares and registers diverse biosensor data to be analyzed, and finally apply the method to showcase its strength in quantifying the impact of interventions. [ABSTRACT FROM AUTHOR]

Metabolic syndrome is a cluster of risk factors, such as obesity, insulin resistance, and hyperlipidemia that increases the individual’s likelihood of developing cardiovascular diseases. Patients inflicted with metabolic disorders also suffer from tissue repair defect. Mitsugumin 53 (MG53) is a protein essential to cellular membrane repair. It facilitates the nucleation of intracellular vesicles to sites of membrane disruption to create repair patches, contributing to the regenerative capacity of skeletal and cardiac muscle tissues upon injury. Since individuals suffering from metabolic syndrome possess tissue regeneration deficiency and MG53 plays a crucial role in restoring membrane integrity, we studied MG53 activity in mice models exhibiting metabolic disorders induced by a 6 month high-fat diet (HFD) feeding. Western blotting showed that MG53 expression is not altered within the skeletal and cardiac muscles of mice with metabolic syndrome. Rather, we found that MG53 levels in blood circulation were actually reduced. This data directly contradicts findings presented by Song et. al that indict MG53 as a causative factor for metabolic syndrome (Nature 494, 375-379). The diminished MG53 serum level observed may contribute to the inadequate tissue repair aptitude exhibited by diabetic patients. Furthermore, immunohistochemical analyses reveal that skeletal muscle fibers of mice with metabolic disorders experience localization of subcellular MG53 around mitochondria. This clustering may represent an adaptive response to oxidative stress resulting from HFD feeding and may implicate MG53 as a guardian to protect damaged mitochondria. Therapeutic approaches that elevate MG53 expression in serum circulation may be a novel method to treat the degenerative tissue repair function of diabetic patients. [ABSTRACT FROM AUTHOR]

Given the increased use of air cleaners as a prevention measure in classrooms during the COVID-19 pandemic, this study aimed to investigate the effects of portable air cleaners with HEPA filters and window A/C fans on real-time (1 minute) concentrations of PM less than 2.5 microns (PM2.5) or less than 1 microns (PM1.0) in two classrooms in a non-urban elementary school in Rhode Island. For half of each school day, settings were randomized to "high" or "low" for the air cleaner and "on" or "off" for the fan. Descriptive statistics and linear mixed models were used to evaluate the impacts of each set of conditions on PM2.5 and PM1.0 concentrations. The mean half-day concentrations ranged from 3.4–4.1 μg/m3 for PM2.5 and 3.4–3.9 μg/m3 for PM1.0. On average, use of the fan when the air cleaner was on the low setting decreased PM2.5 by 0.53 μg/m3 [95% CI: -0.64, -0.42] and use of the filter on high (compared to low) when the fan was off decreased PM2.5 by 0.10 μg/m3 [95% CI: -0.20, 0.005]. For PM1.0, use of the fan when the air cleaner was on low decreased concentrations by 0.18 μg/m3 [95% CI: -0.36, -0.01] and use of the filter on high (compared to low) when the fan was off decreased concentrations by 0.38 μg/m3 [95% CI: -0.55, -0.21]. In general, simultaneous use of the fan and filter on high did not result in additional decreases in PM concentrations compared to the simple addition of each appliance's individual effect estimates. Our study suggests that concurrent or separate use of an A/C fan and air cleaner in non-urban classrooms with low background PM may reduce classroom PM concentrations. [ABSTRACT FROM AUTHOR]

Alternative RNA splicing provides an important means to expand metazoan transcriptome diversity. Contrary to what was accepted previously, splicing is now thought to predominantly take place during transcription. Motivated by emerging data showing the physical proximity of the spliceosome to Pol II, we surveyed the effect of epigenetic context on co-transcriptional splicing. In particular, we observed that splicing factors were not necessarily enriched at exon junctions and that most epigenetic signatures had a distinctly asymmetric profile around known splice sites. Given this, we tried to build an interpretable model that mimics the physical layout of splicing regulation where the chromatin context progressively changes as the Pol II moves along the guide DNA. We used a recurrent-neural-network architecture to predict the inclusion of a spliced exon based on adjacent epigenetic signals, and we showed that distinct spatio-temporal features of these signals were key determinants of model outcome, in addition to the actual nucleotide sequence of the guide DNA strand. After the model had been trained and tested (with >80% precision-recall curve metric), we explored the derived weights of the latent factors, finding they highlight the importance of the asymmetric time-direction of chromatin context during transcription. Author summary: In humans, only about 2% of the genome is comprised of so-called coding regions and can give rise to protein products. However, the human transcriptome is much more diverse than the number of genes found in these coding regions. Each gene can give rise to multiple transcripts through a process during transcription called alternative splicing. There is a limited understanding of the regulation of splicing and the underlying splicing code that determines cell-type-specific splicing. Here, we studied epigenetic features that characterize splicing regulation in humans using a recurrent neural network model. Unlike feedforward neural networks, this method contains an internal memory state that learns from spatiotemporal patterns–like the context in language–from a sequence of genomic and epigenetic information, making it better suited for characterizing splicing. We demonstrated that our method improves the prediction of spicing outcomes compared to previous methods. Furthermore, we applied our method to 49 cell types in ENCODE to investigate splicing regulation and found that not only spatial but also temporal epigenomic context can influence splicing regulation during transcription. [ABSTRACT FROM AUTHOR]

There has been much effort to prioritize genomic variants with respect to their impact on “function”. However, function is often not precisely defined: sometimes it is the disease association of a variant; on other occasions, it reflects a molecular effect on transcription or epigenetics. Here, we coupled multiple genomic predictors to build GRAM, a GeneRAlized Model, to predict a well-defined experimental target: the expression-modulating effect of a non-coding variant on its associated gene, in a transferable, cell-specific manner. Firstly, we performed feature engineering: using LASSO, a regularized linear model, we found transcription factor (TF) binding most predictive, especially for TFs that are hubs in the regulatory network; in contrast, evolutionary conservation, a popular feature in many other variant-impact predictors, has almost no contribution. Moreover, TF binding inferred from in vitro SELEX is as effective as that from in vivo ChIP-Seq. Second, we implemented GRAM integrating only SELEX features and expression profiles; thus, the program combines a universal regulatory score with an easily obtainable modifier reflecting the particular cell type. We benchmarked GRAM on large-scale MPRA datasets, achieving AUROC scores of 0.72 in GM12878 and 0.66 in a multi-cell line dataset. We then evaluated the performance of GRAM on targeted regions using luciferase assays in the MCF7 and K562 cell lines. We noted that changing the insertion position of the construct relative to the reporter gene gave very different results, highlighting the importance of carefully defining the exact prediction target of the model. Finally, we illustrated the utility of GRAM in fine-mapping causal variants and developed a practical software pipeline to carry this out. In particular, we demonstrated in specific examples how the pipeline could pinpoint variants that directly modulate gene expression within a larger linkage-disequilibrium block associated with a phenotype of interest (e.g., for an eQTL). [ABSTRACT FROM AUTHOR]