OSApredictor: A tool for prediction of moderate to severe obstructive sleep apnea-hypopnea using readily available patient characteristics.

Sleep apnea is a common sleep disorder. The availability of an easy-to-use sleep apnea predictor would provide a public health benefit by promoting early diagnosis and treatment. Our goal was to develop a prediction tool that used commonly available variables and was accessible to the public through a web site. Using data from polysomnography (PSG) studies that measured the apnea-hypopnea index (AHI), we built a machine learning tool to predict the presence of moderate to severe obstructive sleep apnea (OSA) (defined as AHI ≥15). Our tool employs only seven widely available predictor variables: age, sex, weight, height, pulse oxygen saturation, heart rate and respiratory rate. As a preliminary step, we used 16,958 PSG studies to examine eight machine learning algorithms via five-fold cross validation and determined that XGBoost exhibited superior predictive performance. We then refined the XGBoost predictor by randomly partitioning the data into a training and a test set (13,566 and 3392 PSGs, respectively) and repeatedly subsampling from the training set to construct 1000 training subsets. We evaluated each of the resulting 1000 XGBoost models on the single set-aside test set. The resulting classification tool correctly identified 72.5 % of those with moderate to severe OSA as having the condition (sensitivity) and 62.8 % of those without moderate to-severe OSA as not having it (specificity); overall accuracy was 66 %. We developed a user-friendly publicly available website (https://manticore.niehs.nih.gov/OSApredictor). We hope that our easy-to-use tool will serve as a screening vehicle that enables more patients to be clinically diagnosed and treated for OSA.

Differences in sleep spindle wave density between patients with diabetes mellitus and matched controls: implications for sensing and regulation of peripheral blood glucose.

Background: Brain waves during sleep are involved in sensing and regulating peripheral glucose level. Whether brain waves in patients with diabetes differ from those of healthy subjects is unknown. We examined the hypothesis that patients with diabetes have reduced sleep spindle waves, a form of brain wave implicated in periphery glucose regulation during sleep. Methods: From a retrospective analysis of polysomnography (PSG) studies on patients who underwent sleep apnea evaluation, we identified 1,214 studies of patients with diabetes mellitus (>66% type 2) and included a sex- and age-matched control subject for each within the scope of our analysis. We similarly identified 376 patients with prediabetes and their matched controls. We extracted spindle characteristics from artifact-removed PSG electroencephalograms and other patient data from records. We used rank-based statistical methods to test hypotheses. We validated our finding on an external PSG dataset. Results: Patients with diabetes mellitus exhibited on average about half the spindle density (median=0.38 spindles/min) during sleep as their matched control subjects (median=0.70 spindles/min) (P<2.2e-16). Compared to controls, spindle loss was more pronounced in female patients than in male patients in the frontal regions of the brain (P=0.04). Patients with prediabetes also exhibited signs of lower spindle density compared to matched controls (P=0.01-0.04). Conclusions: Patients with diabetes have fewer spindle waves that are implicated in glucose regulation than matched controls during sleep. Besides offering a possible explanation for neurological complications from diabetes, our findings open the possibility that reversing/reducing spindle loss could improve the overall health of patients with diabetes mellitus.

Comparison of power spectra from overnight electroencephalography between patients with Down syndrome and matched control subjects.

Electroencephalograms can capture brain oscillatory activities during sleep as a form of electrophysiological signals. We analysed electroencephalogram recordings from full-night in-laboratory polysomnography from 100 patients with Down syndrome, and 100 age- and sex-matched controls. The ages of patients with Down syndrome spanned 1 month to 31 years (median 4.4 years); 84 were younger than 12 years, and 54 were male. From each electroencephalogram, we extracted relative power in six frequency bands or rhythms (delta, theta, alpha, slow sigma, fast sigma, and beta) from six channels (frontal F3 and F4, central C3 and C4, and occipital O1 and O2) during five sleep stages (N3, N2, N1, R and W)-180 features in all. We examined differences in relative power between Down syndrome and control electroencephalograms for each feature separately. During wake and N1 sleep stages, alpha rhythms (8.0-10.5 Hz) had significantly lower power in patients with Down syndrome than controls. Moreover, the rate of increase in alpha power with age during rapid eye movement sleep was significantly slower in Down syndrome than control subjects. During wake and N1 sleep, delta rhythms (0.25-4.5 Hz) had higher power in patients with Down syndrome than controls. During N2 sleep, slow sigma rhythms (10.5-12.5 Hz) had lower power in patients with DS than controls. These findings extend previous research from routine electroencephalogram studies demonstrating that patients with Down syndrome had reduced circadian amplitude-the difference between wake alpha power and deep sleep delta power was smaller in Down syndrome than control subjects. We envision that these brain oscillatory activities may be used as surrogate markers for clinical trials for patients with Down syndrome.

SSAVE: A tool for analysis and visualization of sleep periods using electroencephalography data.

Human sleep architecture is structured with repeated episodes of rapid-eye-movement (REM) and non-rapid-eye-movement (NREM) sleep. An overnight sleep study facilitates identification of macro and micro changes in the pattern and duration of sleep stages associated with sleep disorders and other aspects of human mental and physical health. Overnight sleep studies record, in addition to electroencephalography (EEG) and other electro-physiological signals, a sequence of sleep-stage annotations. SSAVE, introduced here, is open-source software that takes sleep-stage annotations and EEG signals as input, identifies and characterizes periods of NREM and REM sleep, and produces a hypnogram and its time-matched EEG spectrogram. SSAVE fills an important gap for the rapidly growing field of sleep medicine by providing an easy-to-use tool for sleep-period identification and visualization. SSAVE can be used as a Python package, a desktop standalone tool or through a web portal. All versions of the SSAVE tool can be found on: https://manticore.niehs.nih.gov/ssave.

A deep learning method for miRNA/isomiR target detection.

Accurate identification of microRNA (miRNA) targets at base-pair resolution has been an open problem for over a decade. The recent discovery of miRNA isoforms (isomiRs) adds more complexity to this problem. Despite the existence of many methods, none considers isomiRs, and their performance is still suboptimal. We hypothesize that by taking the isomiR-mRNA interactions into account and applying a deep learning model to study miRNA-mRNA interaction features, we may improve the accuracy of miRNA target predictions. We developed a deep learning tool called DMISO to capture the intricate features of miRNA/isomiR-mRNA interactions. Based on tenfold cross-validation, DMISO showed high precision (95%) and recall (90%). Evaluated on three independent datasets, DMISO had superior performance to five tools, including three popular conventional tools and two recently developed deep learning-based tools. By applying two popular feature interpretation strategies, we demonstrated the importance of the miRNA regions other than their seeds and the potential contribution of the RNA-binding motifs within miRNAs/isomiRs and mRNAs to the miRNA/isomiR-mRNA interactions.

A systematic evaluation of the computational tools for lncRNA identification.

The computational identification of long non-coding RNAs (lncRNAs) is important to study lncRNAs and their functions. Despite the existence of many computation tools for lncRNA identification, to our knowledge, there is no systematic evaluation of these tools on common datasets and no consensus regarding their performance and the importance of the features used. To fill this gap, in this study, we assessed the performance of 17 tools on several common datasets. We also investigated the importance of the features used by the tools. We found that the deep learning-based tools have the best performance in terms of identifying lncRNAs, and the peptide features do not contribute much to the tool accuracy. Moreover, when the transcripts in a cell type were considered, the performance of all tools significantly dropped, and the deep learning-based tools were no longer as good as other tools. Our study will serve as an excellent starting point for selecting tools and features for lncRNA identification.

Interpretation of deep learning in genomics and epigenomics.

Machine learning methods have been widely applied to big data analysis in genomics and epigenomics research. Although accuracy and efficiency are common goals in many modeling tasks, model interpretability is especially important to these studies towards understanding the underlying molecular and cellular mechanisms. Deep neural networks (DNNs) have recently gained popularity in various types of genomic and epigenomic studies due to their capabilities in utilizing large-scale high-throughput bioinformatics data and achieving high accuracy in predictions and classifications. However, DNNs are often challenged by their potential to explain the predictions due to their black-box nature. In this review, we present current development in the model interpretation of DNNs, focusing on their applications in genomics and epigenomics. We first describe state-of-the-art DNN interpretation methods in representative machine learning fields. We then summarize the DNN interpretation methods in recent studies on genomics and epigenomics, focusing on current data- and computing-intensive topics such as sequence motif identification, genetic variations, gene expression, chromatin interactions and non-coding RNAs. We also present the biological discoveries that resulted from these interpretation methods. We finally discuss the advantages and limitations of current interpretation approaches in the context of genomic and epigenomic studies. Contact:xiaoman@mail.ucf.edu, haihu@cs.ucf.edu.

A two-stream convolutional neural network for microRNA transcription start site feature integration and identification.

MicroRNAs (miRNAs) play important roles in post-transcriptional gene regulation and phenotype development. Understanding the regulation of miRNA genes is critical to understand gene regulation. One of the challenges to study miRNA gene regulation is the lack of condition-specific annotation of miRNA transcription start sites (TSSs). Unlike protein-coding genes, miRNA TSSs can be tens of thousands of nucleotides away from the precursor miRNAs and they are hard to be detected by conventional RNA-Seq experiments. A number of studies have been attempted to computationally predict miRNA TSSs. However, high-resolution condition-specific miRNA TSS prediction remains a challenging problem. Recently, deep learning models have been successfully applied to various bioinformatics problems but have not been effectively created for condition-specific miRNA TSS prediction. Here we created a two-stream deep learning model called D-miRT for computational prediction of condition-specific miRNA TSSs ( http://hulab.ucf.edu/research/projects/DmiRT/ ). D-miRT is a natural fit for the integration of low-resolution epigenetic features (DNase-Seq and histone modification data) and high-resolution sequence features. Compared with alternative computational models on different sets of training data, D-miRT outperformed all baseline models and demonstrated high accuracy for condition-specific miRNA TSS prediction tasks. Comparing with the most recent approaches on cell-specific miRNA TSS identification using cell lines that were unseen to the model training processes, D-miRT also showed superior performance.

An intriguing characteristic of enhancer-promoter interactions.

BACKGROUND: It is still challenging to predict interacting enhancer-promoter pairs (IEPs), partially because of our limited understanding of their characteristics. To understand IEPs better, here we studied the IEPs in nine cell lines and nine primary cell types. RESULTS: By measuring the bipartite clustering coefficient of the graphs constructed from these experimentally supported IEPs, we observed that one enhancer is likely to interact with either none or all of the target genes of another enhancer. This observation implies that enhancers form clusters, and every enhancer in the same cluster synchronously interact with almost every member of a set of genes and only this set of genes. We perceived that an enhancer can be up to two megabase pairs away from other enhancers in the same cluster. We also noticed that although a fraction of these clusters of enhancers do overlap with super-enhancers, the majority of the enhancer clusters are different from the known super-enhancers. CONCLUSIONS: Our study showed a new characteristic of IEPs, which may shed new light on distal gene regulation and the identification of IEPs.

Computational annotation of miRNA transcription start sites.

MOTIVATION: MicroRNAs (miRNAs) are small noncoding RNAs that play important roles in gene regulation and phenotype development. The identification of miRNA transcription start sites (TSSs) is critical to understand the functional roles of miRNA genes and their transcriptional regulation. Unlike protein-coding genes, miRNA TSSs are not directly detectable from conventional RNA-Seq experiments due to miRNA-specific process of biogenesis. In the past decade, large-scale genome-wide TSS-Seq and transcription activation marker profiling data have become available, based on which, many computational methods have been developed. These methods have greatly advanced genome-wide miRNA TSS annotation. RESULTS: In this study, we summarized recent computational methods and their results on miRNA TSS annotation. We collected and performed a comparative analysis of miRNA TSS annotations from 14 representative studies. We further compiled a robust set of miRNA TSSs (RSmirT) that are supported by multiple studies. Integrative genomic and epigenomic data analysis on RSmirT revealed the genomic and epigenomic features of miRNA TSSs as well as their relations to protein-coding and long non-coding genes. CONTACT: xiaoman@mail.ucf.edu, haihu@cs.ucf.edu.

Position-wise binding preference is important for miRNA target site prediction.

MOTIVATION: It is a fundamental task to identify microRNAs (miRNAs) targets and accurately locate their target sites. Genome-scale experiments for miRNA target site detection are still costly. The prediction accuracies of existing computational algorithms and tools are often not up to the expectation due to a large number of false positives. One major obstacle to achieve a higher accuracy is the lack of knowledge of the target binding features of miRNAs. The published high-throughput experimental data provide an opportunity to analyze position-wise preference of miRNAs in terms of target binding, which can be an important feature in miRNA target prediction algorithms. RESULTS: We developed a Markov model to characterize position-wise pairing patterns of miRNA-target interactions. We further integrated this model as a scoring method and developed a dynamic programming (DP) algorithm, MDPS (Markov model-scored Dynamic Programming algorithm for miRNA target site Selection) that can screen putative target sites of miRNA-target binding. The MDPS algorithm thus can take into account both the dependency of neighboring pairing positions and the global pairing information. Based on the trained Markov models from both miRNA-specific and general datasets, we discovered that the position-wise binding information specific to a given miRNA would benefit its target prediction. We also found that miRNAs maintain region-wise similarity in their target binding patterns. Combining MDPS with existing methods significantly improves their precision while only slightly reduces their recall. Therefore, position-wise pairing patterns have the promise to improve target prediction if incorporated into existing software tools. AVAILABILITY AND IMPLEMENTATION: The source code and tool to calculate MDPS score is available at http://hulab.ucf.edu/research/projects/MDPS/index.html. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

EPIP: a novel approach for condition-specific enhancer-promoter interaction prediction.

MOTIVATION: The identification of enhancer-promoter interactions (EPIs), especially condition-specific ones, is important for the study of gene transcriptional regulation. Existing experimental approaches for EPI identification are still expensive, and available computational methods either do not consider or have low performance in predicting condition-specific EPIs. RESULTS: We developed a novel computational method called EPIP to reliably predict EPIs, especially condition-specific ones. EPIP is capable of predicting interactions in samples with limited data as well as in samples with abundant data. Tested on more than eight cell lines, EPIP reliably identifies EPIs, with an average area under the receiver operating characteristic curve of 0.95 and an average area under the precision-recall curve of 0.73. Tested on condition-specific EPIPs, EPIP correctly identified 99.26% of them. Compared with two recently developed methods, EPIP outperforms them with a better accuracy. AVAILABILITY AND IMPLEMENTATION: The EPIP tool is freely available at http://www.cs.ucf.edu/˜xiaoman/EPIP/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Differential open chromatin profile and transcriptomic signature define depot-specific human subcutaneous preadipocytes: primary outcomes.

BACKGROUND: Increased lower body fat is associated with reduced cardiometabolic risk. The molecular basis for depot-specific differences in gluteofemoral (GF) compared with abdominal (A) subcutaneous adipocyte function is poorly understood. In the current report, we used a combination of Assay for Transposase-Accessible Chromatin followed by sequencing (ATAC-seq), RNA-seq, and chromatin immunoprecipitation (ChIP)-qPCR analyses that provide evidence that depot-specific gene expression patterns are associated with differential epigenetic chromatin signatures. METHODS: Preadipocytes cultured from A and GF adipose tissue obtained from premenopausal apple-shaped women were used to perform transcriptome analysis by RNA-seq and assess accessible chromatin regions by ATAC-seq. We measured mRNA expression and performed ChIP-qPCR experiments for histone modifications of active (H3K4me3) and repressed chromatin (H3K27me3) regions respectively on the promoter regions of differentially expressed genes. RESULTS: RNA-seq experiments revealed an A-fat and GF-fat selective gene expression signature, with 126 genes upregulated in abdominal preadipocytes and 90 genes upregulated in GF cells. ATAC-seq identified almost 10-times more A-specific chromatin-accessible regions. Using a combined analysis of ATAC-seq and global gene expression data, we identified 74 of the 126 abdominal-specific genes (59%) with A-specific accessible chromatin sites within 200 kb of the transcription start site (TSS), including HOXA3, HOXA5, IL8, IL1b, and IL6. Interestingly, only 14 of the 90 GF-specific genes (15%) had GF-specific accessible chromatin sites within 200 kb of the corresponding TSS, including HOXC13 and HOTAIR, whereas 25 of them (28%) had abdominal-specific accessible chromatin sites. ChIP-qPCR experiments confirmed that the active H3K4me3 chromatin mark was significantly enriched at the promoter regions of HOXA5 and HOXA3 genes in abdominal preadipocytes, while H3K27me3 was less abundant relative to chromatin from GF. This is consistent with their A-fat specific gene expression pattern. Conversely, analysis of the promoter regions of the GF specific HOTAIR and HOXC13 genes exhibited high H3K4me3 and low H3K27me3 levels in GF chromatin compared to A chromatin. CONCLUSIONS: Global transcriptome and open chromatin analyses of depot-specific preadipocytes identified their gene expression signature and differential open chromatin profile. Interestingly, A-fat-specific open chromatin regions can be observed in the proximity of GF-fat genes, but not vice versa. TRIAL REGISTRATION: Clinicaltrials.gov, NCT01745471 . Registered 5 December 2012.