A Deep-Learning Pipeline for TSS Coverage Imputation From Shallow Cell-Free DNA Sequencing

Cell-free DNA (cfDNA) serves as a footprint of the nucleosome occupancy status of transcription start sites (TSSs), and has been subject to wide development for use in noninvasive health monitoring and disease detection. However, the requirement for high sequencing depth limits its clinical use. Here, we introduce a deep-learning pipeline designed for TSS coverage profiles generated from shallow cfDNA sequencing called the Autoencoder of cfDNA TSS (AECT) coverage profile. AECT outperformed existing single-cell sequencing imputation algorithms in terms of improvements to TSS coverage accuracy and the capture of latent biological features that distinguish sex or tumor status. We built classifiers for the detection of breast and rectal cancer using AECT-imputed shallow sequencing data, and their performance was close to that achieved by high-depth sequencing, suggesting that AECT could provide a broadly applicable noninvasive screening approach with high accuracy and at a moderate cost.

Palliative Care Coverage across European National Health Systems: Proposal of a Synthetic Indicator

Background: The coverage of palliative care (PC) may be understood as a country’s capacity to offer prevention and relief from serious health-related suffering in relation to an existing need. The aim of this study is to estimate European countries´ coverage capacities. Method: Secondary analysis of three indicators, including the number of specialized services (SSPC), integration capacity scores (ICS) and the PC needs. By means of a K-medians clustering supervised algorithm, three coverage profiles were obtained: (1) Advanced: countries with high ICS and SSPC, and low PC needs; (2) Limited: countries with low ICS and SSPC, and low PC needs; and (3) Low: countries with low ICS and SSPC and high PC needs. Results: On average, the ratio of specialized services per population was 0.79 per 100,000 inhabitants, the average ICS was 19.62 and the average number of deceased patients with SHS per 100,000 inhabitants was 5.69. Twenty countries (41%) reached an advanced coverage profile. Nine countries (18%) demonstrated a limited coverage profile; and 20 countries (41%) fell under a low-coverage capacity. Conclusion: The level of palliative care coverage across Europe shows that 59% of European countries have either limited or very low availability of PC resources as regards their palliative care needs.

Learning What a Good Structural Variant Looks Like

Structural variations (SVs) are an important class of genetic mutations, yet SV detectors still suffer from high false-positive rates. In many cases, humans can quickly determine whether a putative SV is real by merely looking at a visualization of the SV’s coverage profile. To that end, we developed Samplot-ML, a convolutional neural network (CNN) trained to genotype genomic deletions using Samplot visualizations that incorporate various forms of evidence such as genome coverage, discordant pairs, and split reads. Using Samplot-ML, we were able to reduce false positives by 47% while keeping 97% of true positives on average across several test samples.

Analysis of 4G mobile network coverage in UTeM technology campus

<p><span>This paper proposes an analysis of the coverage performance of 4G cellular services in UTeM Technology Campus. The performance of the cellular services is presented as the network’s coverage profile which is based on the received signal strength indicator (RSSI). The area under study is virtually divided into 64 grid points where the average RSSI measurements are captured by using an open source software namely G-Mon. The measured values are mapped into the network coverage profile which represents the signal reception quality at each of the grid points. A statistical analysis called Two-Way ANOVA is performed to investigate the correlation of the performance of 4G cellular services in UTeM Technology Campus with the mobile phone brands and service operators. Based on the analysis, it is found that the signal reception in outdoor areas are better than that of indoor areas. In addition, the analysis shows that the propagation loss and signal degradation are two factors that contribute to the 4G services’ performance in UTeM Technology Campus. </span></p>

Directly observed treatment for tuberculosis in the State of São Paulo

ABSTRACT Objectives: To describe and analyze the coverage profile of directly observed treatment for tuberculosis in 59 priority municipalities in the state of São Paulo, Brazil, through the creation and comparison of groups homogenized by the number of people in each municipality from 2006 to 2012. Method: Quantitative, epidemiological and descriptive study based on the data available in the EPI-TB and the Statistica 7.0 software databases. Results: The mean and standard deviation of directly observed treatment for the 59 priority municipalities of the state of São Paulo were 77.0 ± 24.3%. The coverage of directly observed treatment increased in 34 municipalities (57.6%) but decreased in 25 (42.4%). Conclusion: Some municipalities could not keep the coverage reached at some point. This coverage heterogeneity should be examined in detail by searching for possible reasons in political-management, technical-operational and funding dimensions.

Coverage profile correction of shallow-depth circulating cell-free DNA sequencing via multi-distance learning

Shallow-depth whole-genome sequencing (WGS) of circulating cell-free DNA (ccfDNA) is a popular approach for non-invasive genomic screening assays, including liquid biopsy for early detection of invasive tumors as well as non-invasive prenatal screening (NIPS) for common fetal trisomies. In contrast to nuclear DNA WGS, ccfDNA WGS exhibits extensive inter- and intra-sample coverage variability that is not fully explained by typical sources of variation in WGS, such as GC content. This variability may inflate false positive and false negative screening rates of copy-number alterations and aneuploidy, particularly if these features are present at a relatively low proportion of total sequenced content. Herein, we propose an empirically-driven coverage correction strategy that leverages prior annotation information in a multi-distance learning context to improve within-sample coverage profile correction. Specifically, we train a weighted k-nearest neighbors-style method on non-pregnant female donor ccfDNA WGS samples, and apply it to NIPS samples to evaluate coverage profile variability reduction. We additionally characterize improvement in the discrimination of positive fetal trisomy cases relative to normal controls, and compare our results against a more traditional regression-based approach to profile coverage correction based on GC content and mappability. Under cross-validation, performance measures indicated benefit to combining the two feature sets relative to either in isolation. We also observed substantial improvement in coverage profile variability reduction in leave-out clinical NIPS samples, with variability reduced by 26.5-53.5% relative to the standard regression-based method as quantified by median absolute deviation. Finally, we observed improvement discrimination for screening positive trisomy cases reducing ccfDNA WGS coverage variability while additionally improving NIPS trisomy screening assay performance. Overall, our results indicate that machine learning approaches can substantially improve ccfDNA WGS coverage profile correction and downstream analyses.