Data imbalance is frequently encountered in biomedical applications. Resampling techniques can be used in binary classification to tackle this issue. However such solutions are not desired when the number of samples in the small class is limited. Moreover the use of inadequate performance metrics, such as accuracy, lead to poor generalization results because the classifiers tend to predict the largest size class. One of the good approaches to deal with this issue is to optimize performance metrics that are designed to handle data imbalance. Matthews Correlation Coefficient (MCC) is widely used in Bioinformatics as a performance metric. We are interested in developing a new classifier based on the MCC metric to handle imbalanced data. We derive an optimal Bayes classifier for the MCC metric using an approach based on Frechet derivative. We show that the proposed algorithm has the nice theoretical property of consistency. Using simulated data, we verify the correctness of our optimality result by searching in the space of all possible binary classifiers. The proposed classifier is evaluated on 64 datasets from a wide range data imbalance. We compare both classification performance and CPU efficiency for three classifiers: 1) the proposed algorithm (MCC-classifier), the Bayes classifier with a default threshold (MCC-base) and imbalanced SVM (SVM-imba). The experimental evaluation shows that MCC-classifier has a close performance to SVM-imba while being simpler and more efficient.

Using a collection of simulated and real benchmarks, we compare Bayesian and frequentist regularization approaches under a low informative constraint when the number of variables is almost equal to the number of observations on simulated and real datasets. This comparison includes new global noninformative approaches for Bayesian variable selection built on Zellner’s $g$-priors that are similar to Liang et al. (2008). The interest of those calibration-free proposals is discussed. The numerical experiments we present highlight the appeal of Bayesian regularization methods, when compared with non-Bayesian alternatives. They dominate frequentist methods in the sense that they provide smaller prediction errors while selecting the most relevant variables in a parsimonious way.

Vitamin D inadequacy appears to be on the rise globally, and it has been linked to an increased risk of osteoporosis, as well as metabolic, cardiovascular, and autoimmune diseases. Vitamin D concentrations are partially determined by genetic factors. Specific single nucleotide polymorphisms (SNPs) in genes involved in vitamin D transport, metabolism, or binding have been found to be associated with its serum concentration, and these SNPs differ among ethnicities. Vitamin D has also been suggested to be a regulator of the gut microbiota and vitamin D deficiency as the possible cause of gut microbial dysbiosis and inflammation. This pilot study aims to fill the gap in our understanding of the prevalence, cause, and implications of vitamin D inadequacy in a pediatric population residing in Qatar. Blood and fecal samples were collected from healthy subjects aged 4–14 years. Blood was used to measure serum metabolite of vitamin D, 25-hydroxycholecalciferol 25(OH)D. To evaluate the composition of the gut microbiota, fecal samples were subjected to 16S rRNA gene sequencing. High levels of vitamin D deficiency/insufficiency were observed in our cohort with 97% of the subjects falling into the inadequate category (with serum 25(OH)D < 75 nmol/L). The CT genotype in rs12512631, an SNP in the GC gene, was associated with low serum levels of vitamin D (ANOVA, p = 0.0356) and was abundant in deficient compared to non-deficient subjects. Overall gut microbial community structure was significantly different between the deficient (D) and non-deficient (ND) groups (Bray Curtis dissimilarity p = 0.049), with deficient subjects also displaying reduced gut microbial diversity. Significant differences were observed among the two major gut phyla, Firmicutes (F) and Bacteroidetes (B), where deficient subjects displayed a higher B/F ratio (p = 0.0097) compared to ND. Vitamin D deficient children also demonstrated gut enterotypes dominated by the genus Prevotella as opposed to Bacteroides. Our findings suggest that pediatric vitamin D inadequacy significantly impacts the gut microbiota. We also highlight the importance of considering host genetics and baseline gut microbiome composition in interpreting the clinical outcomes related to vitamin D deficiency as well as designing better personalized strategies for therapeutic interventions.

Studying the prescription pattern of medications will help in understanding potential unnecessary prescriptions, due to the trial-and-error method of prescribing, and the need for personalized medicine in a population. Therefore, in this study, our aim was to explore the prescribing pattern and off-label use of antidepressants in the Qatari population. We conducted a retrospective study of Qatari patients who received prescriptions for antidepressants from the major healthcare providers in Qatar, for a period of 24 months between June 2018 and May 2020. The number of patients, prescriptions, and diagnostic indications were analyzed. The chi-square test was used for identifying statistically significant association of the number of individuals prescribed with age category or gender. Of the 14,601 Qatari patients who were prescribed antidepressants, the majority were female (61%, p < 2.2 × 10⁻¹⁶), and were at or above 60 years of age (27%, p < 2.2 × 10⁻¹⁶). More numbers of selective serotonin reuptake inhibitors (SSRIs) (22,085 out of 48,031; 46%), were dispensed than other classes of antidepressants, with escitalopram (26%) at the top of the list. Preponderance of prescription of antidepressants for non-mental health diseases was observed. Population-level prescription trends, as we reported here, when combined with patient genetic variability and outcome data, will have the power to predict the potential for treatment failures and adverse effects of these medications in the population. We also recommend educating non-mental health prescribers about the adherence to evidence and guidelines to ensure patient safety while prescribing antidepressants.

Nowadays, High Performance Computing (HPC) systems commonly used in bioinformatics, such as genome sequencing, incorporate multi-processor architectures. Typically, most bioinformatics applications are multi-threaded and dominated by memory-intensive operations, which are not designed to take full advantage of these HPC capabilities. Therefore, the application end-user is responsible for optimizing the application performance and improving scalability with various performance engineering concepts. Additionally, most of the HPC systems are operated in a multi-user (or multi-job) environment; thus, Quality of Service (QoS) methods are essential for balancing between application performance, scalability and system utilization. We propose a QoS workflow that optimizes the balancing ratio between parallel efficiency and system utilization. Accordingly, our proposed optimization workflow will advise the end user of a selection criteria to apply toward resources and options for a given application and HPC system architecture. For example, the BWA-MEM algorithm is a popular and modern algorithm for aligning human genome sequences. We conducted various case studies on BWA-MEM using our optimization workflow, and as a result compared to a state-of-the-art baseline, the application performance is improved up to 67%, scalability extended up to 200%, parallel efficiency improved up to 39% and overall system utilization increased up to 38%