Digital wearable insole-based identification of knee arthropathies and gait signatures using machine learning.

Gait is impaired in musculoskeletal conditions, such as knee arthropathy. Gait analysis is used in clinical practice to inform diagnosis and monitor disease progression or intervention response. However, clinical gait analysis relies on subjective visual observation of walking as objective gait analysis has not been possible within clinical settings due to the expensive equipment, large-scale facilities, and highly trained staff required. Relatively low-cost wearable digital insoles may offer a solution to these challenges. In this work, we demonstrate how a digital insole measuring osteoarthritis-specific gait signatures yields similar results to the clinical gait-lab standard. To achieve this, we constructed a machine learning model, trained on force plate data collected in participants with knee arthropathy and controls. This model was highly predictive of force plate data from a validation set (area under the receiver operating characteristics curve [auROC] = 0.86; area under the precision-recall curve [auPR] = 0.90) and of a separate, independent digital insole dataset containing control and knee osteoarthritis subjects (auROC = 0.83; auPR = 0.86). After showing that digital insole-derived gait characteristics are comparable to traditional gait measurements, we next showed that a single stride of raw sensor time-series data could be accurately assigned to each subject, highlighting that individuals using digital insoles can be identified by their gait characteristics. This work provides a framework for a promising alternative to traditional clinical gait analysis methods, adds to the growing body of knowledge regarding wearable technology analytical pipelines, and supports clinical development of at-home gait assessments, with the potential to improve the ease, frequency, and depth of patient monitoring.

The way we walk ­ our 'gait' ­ is a key indicator of health. Gait irregularities like limping, shuffling or a slow pace can be signs of muscle or joint problems. Assessing a patient's gait is therefore an important element in diagnosing these conditions, and in evaluating whether treatments are working. Gait is often assessed via a simple visual inspection, with patients being asked to walk back and forth in a doctor's office. While quick and easy, this approach is highly subjective and therefore imprecise. 'Objective gait analysis' is a more accurate alternative, but it relies on tests being conducted in specialised laboratories with large-scale, expensive equipment operated by highly trained staff. Unfortunately, this means that gait laboratories are not accessible for everyday clinical use. In response, Wipperman et al. aimed to develop a low-cost alternative to the complex equipment used in gait laboratories. To do this, they harnessed wearable sensor technologies ­ devices that can directly measure physiological data while embedded in clothing or attached to the user. Wearable sensors have the advantage of being cheap, easy to use, and able to provide clinically useful information without specially trained staff. Wipperman et al. analysed data from classic gait laboratory devices, as well as 'digital insoles' equipped with sensors that captured foot movements and pressure as participants walked. The analysis first 'trained' on data from gait laboratories (called force plates) and then applied the method to gait measurements obtained from digital insoles worn by either healthy participants or patients with knee problems. Analysis of the pressure data from the insoles confirmed that they could accurately predict which measurements were from healthy individuals, and which were from patients. The gait characteristics detected by the insoles were also comparable to lab-based measurements ­ in other words, the insoles provided similar type and quality of data as a gait laboratory. Further analysis revealed that information from just a single step could reveal additional information about the subject's walking. These results support the use of wearable devices as a simple and relatively inexpensive way to measure gait in everyday clinical practice, without the need for specialised laboratories and visits to the doctor's office. Although the digital insoles will require further analytical and clinical study before they can be widely used, Wipperman et al. hope they will eventually make monitoring muscle and joint conditions easier and more affordable.

magpie: A power evaluation method for differential RNA methylation analysis in N6-methyladenosine sequencing.

Recently, novel biotechnologies to quantify RNA modifications became an increasingly popular choice for researchers who study epitranscriptome. When studying RNA methylations such as N6-methyladenosine (m6A), researchers need to make several decisions in its experimental design, especially the sample size and a proper statistical power. Due to the complexity and high-throughput nature of m6A sequencing measurements, methods for power calculation and study design are still currently unavailable. In this work, we propose a statistical power assessment tool, magpie, for power calculation and experimental design for epitranscriptome studies using m6A sequencing data. Our simulation-based power assessment tool will borrow information from real pilot data, and inspect various influential factors including sample size, sequencing depth, effect size, and basal expression ranges. We integrate two modules in magpie: (i) a flexible and realistic simulator module to synthesize m6A sequencing data based on real data; and (ii) a power assessment module to examine a set of comprehensive evaluation metrics.

Evaluation of epitranscriptome-wide N6-methyladenosine differential analysis methods.

RNA methylation has emerged recently as an active research domain to study post-transcriptional alteration in gene expression regulation. Various types of RNA methylation, including N6-methyladenosine (m6A), are involved in human disease development. As a newly developed sequencing biotechnology to quantify the m6A level on a transcriptome-wide scale, MeRIP-seq expands RNA epigenetics study in both basic and clinical applications, with an upward trend. One of the fundamental questions in RNA methylation data analysis is to identify the Differentially Methylated Regions (DMRs), by contrasting cases and controls. Multiple statistical approaches have been recently developed for DMR detection, but there is a lack of a comprehensive evaluation for these analytical methods. Here, we thoroughly assess all eight existing methods for DMR calling, using both synthetic and real data. Our simulation adopts a Gamma-Poisson model and logit linear framework, and accommodates various sample sizes and DMR proportions for benchmarking. For all methods, low sensitivities are observed among regions with low input levels, but they can be drastically boosted by an increase in sample size. TRESS and exomePeak2 perform the best using metrics of detection precision, FDR, type I error control and runtime, though hampered by low sensitivity. DRME and exomePeak obtain high sensitivities, at the expense of inflated FDR and type I error. Analyses on three real datasets suggest differential preference on identified DMR length and uniquely discovered regions, between these methods.

NeuCA web server: a neural network-based cell annotation tool with web-app and GUI.

SUMMARY: Correctly annotating individual cell's type is an important initial step in single-cell RNA sequencing (scRNA-seq) data analysis. Here, we present NeuCA web server, a neural network-based scRNA-seq cell annotation tool with web-app portal and graphical user interface, for automatically assigning cell labels. NeuCA algorithm is accurate and exhaustive, maximizing the usage of measured cells for downstream analysis. NeuCA web server provides over 20 ready-to-use pre-trained classifiers for commonly used tissue types. As the first web-app tool with neural-network infrastructure implemented, NeuCA web will facilitate the research community in analyzing and annotating scRNA-seq data. AVAILABILITY AND IMPLEMENTATION: NeuCA web server is implemented with R Shiny application online at https://statbioinfo.shinyapps.io/NeuCA/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Considerations for Soluble Protein Biomarker Blood Sample Matrix Selection.

Blood-based soluble protein biomarkers provide invaluable clinical information about patients and are used as diagnostic, prognostic, and pharmacodynamic markers. The most commonly used blood sample matrices are serum and different types of plasma. In drug development research, the impact of sample matrix selection on successful protein biomarker quantification is sometimes overlooked. The sample matrix for a specific analyte is often chosen based on prior experience or literature searches, without good understanding of the possible effects on analyte quantification. Using a data set of 32 different soluble protein markers measured in matched serum and plasma samples, we examined the differences between serum and plasma and discussed how platelet or immune cell activation can change the quantified concentration of the analyte. We have also reviewed the effect of anticoagulant on analyte quantification. Finally, we provide specific recommendations for biomarker sample matrix selection and propose a systematic and data-driven approach for sample matrix selection. This review is intended to raise awareness of the impact and considerations of sample matrix selection on biomarker quantification.