Deep learning in systems medicine.

Systems medicine (SM) has emerged as a powerful tool for studying the human body at the systems level with the aim of improving our understanding, prevention and treatment of complex diseases. Being able to automatically extract relevant features needed for a given task from high-dimensional, heterogeneous data, deep learning (DL) holds great promise in this endeavour. This review paper addresses the main developments of DL algorithms and a set of general topics where DL is decisive, namely, within the SM landscape. It discusses how DL can be applied to SM with an emphasis on the applications to predictive, preventive and precision medicine. Several key challenges have been highlighted including delivering clinical impact and improving interpretability. We used some prototypical examples to highlight the relevance and significance of the adoption of DL in SM, one of them is involving the creation of a model for personalized Parkinson's disease. The review offers valuable insights and informs the research in DL and SM.

Graph convolutional network approach to discovering disease-related circRNA-miRNA-mRNA axes.

Non-coding RNAs are gaining prominence in biology and medicine, as they play major roles in cellular homeostasis among which the circRNA-miRNA-mRNA axes are involved in a series of disease-related pathways, such as apoptosis, cell invasion and metastasis. Recently, many computational methods have been developed for the prediction of the relationship between ncRNAs and diseases, which can alleviate the time-consuming and labor-intensive exploration involved with biological experiments. However, these methods handle ncRNAs separately, ignoring the impact of the interactions among ncRNAs on the diseases. In this paper we present a novel approach to discovering disease-related circRNA-miRNA-mRNA axes from the disease-RNA information network. Our method, using graph convolutional network, learns the characteristic representation of each biological entity by propagating and aggregating local neighbor information based on the global structure of the network. The approach is evaluated using the real-world datasets and the results show that it outperforms other state-of-the-art baselines on most of the metrics.

A heat diffusion multilayer network approach for the identification of functional biomarkers in rumen methane emissions.

A better understanding of rumen microbial interactions is crucial for the study of rumen metabolism and methane emissions. Metagenomics-based methods can explore the relationship between microbial genes and metabolites to clarify the effect of microbial function on the host phenotype. This study investigated the rumen microbial mechanisms of methane metabolism in cattle by combining metagenomic data and network-based methods. Based on the relative abundance of 1461 rumen microbial genes and the main volatile fatty acids (VFAs), a multilayer heterogeneous network was constructed, and the functional modules associated with metabolite-microbial genes were obtained by heat diffusion algorithm. The PLS model by integrating data from VFAs and microbial genes explained 72.98% variation of methane emissions. Compared with single-layer networks, more previously reported biomarkers of methane prediction can be captured by the multilayer network. More biomarkers with the rank of top 20 topological centralities were from the PLS models of diffusion subsets. The heat diffusion algorithm is different from the strategy used by the microbial metabolic system to understand methane phenotype. It inferred 24 novel biomarkers that were preferentially affected by changes in specific VFAs. Results showed that the heat diffusion multilayer network approach improved the understanding of the microbial patterns of VFAs affecting methane emissions which represented by the functional microbial genes.

Upper Limb Position Tracking with a Single Inertial Sensor Using Dead Reckoning Method with Drift Correction Techniques.

Inertial sensors are widely used in human motion monitoring. Orientation and position are the two most widely used measurements for motion monitoring. Tracking with the use of multiple inertial sensors is based on kinematic modelling which achieves a good level of accuracy when biomechanical constraints are applied. More recently, there is growing interest in tracking motion with a single inertial sensor to simplify the measurement system. The dead reckoning method is commonly used for estimating position from inertial sensors. However, significant errors are generated after applying the dead reckoning method because of the presence of sensor offsets and drift. These errors limit the feasibility of monitoring upper limb motion via a single inertial sensing system. In this paper, error correction methods are evaluated to investigate the feasibility of using a single sensor to track the movement of one upper limb segment. These include zero velocity update, wavelet analysis and high-pass filtering. The experiments were carried out using the nine-hole peg test. The results show that zero velocity update is the most effective method to correct the drift from the dead reckoning-based position tracking. If this method is used, then the use of a single inertial sensor to track the movement of a single limb segment is feasible.

Review of applications of high-throughput sequencing in personalized medicine: barriers and facilitators of future progress in research and clinical application.

There has been an exponential growth in the performance and output of sequencing technologies (omics data) with full genome sequencing now producing gigabases of reads on a daily basis. These data may hold the promise of personalized medicine, leading to routinely available sequencing tests that can guide patient treatment decisions. In the era of high-throughput sequencing (HTS), computational considerations, data governance and clinical translation are the greatest rate-limiting steps. To ensure that the analysis, management and interpretation of such extensive omics data is exploited to its full potential, key factors, including sample sourcing, technology selection and computational expertise and resources, need to be considered, leading to an integrated set of high-performance tools and systems. This article provides an up-to-date overview of the evolution of HTS and the accompanying tools, infrastructure and data management approaches that are emerging in this space, which, if used within in a multidisciplinary context, may ultimately facilitate the development of personalized medicine.

Community effort endorsing multiscale modelling, multiscale data science and multiscale computing for systems medicine.

Systems medicine holds many promises, but has so far provided only a limited number of proofs of principle. To address this road block, possible barriers and challenges of translating systems medicine into clinical practice need to be identified and addressed. The members of the European Cooperation in Science and Technology (COST) Action CA15120 Open Multiscale Systems Medicine (OpenMultiMed) wish to engage the scientific community of systems medicine and multiscale modelling, data science and computing, to provide their feedback in a structured manner. This will result in follow-up white papers and open access resources to accelerate the clinical translation of systems medicine.

Two-Dimensional Porous Molybdenum Phosphide/Nitride Heterojunction Nanosheets for pH-Universal Hydrogen Evolution Reaction.

Herein, we present a new strategy for the synthesis of 2D porous MoP/Mo2 N heterojunction nanosheets based on the pyrolysis of 2D [PMo12 O40 ]3- -melamine (PMo12 -MA) nanosheet precursor from a polyethylene glycol (PEG)-mediated assembly route. The heterostructure nanosheets are ca. 20 nm thick and have plentiful pores (<5 nm). These structure features offer advantages to promote the HER activity, including the favorable water dissociation kinetics around heterojunction as confirmed by theoretical calculations, large accessible surface of 2D nanosheets, and enhanced mass-transport ability by pores. Consequently, the 2D porous MoP/Mo2 N heterojunction nanosheets exhibit excellent HER activity with low overpotentials of 89, 91 and 89 mV to achieve a current density of 10 mA cm-2 in alkaline, neutral and acidic electrolytes, respectively. The HER performance is superior to the commercial Pt/C at a current density >55 mA cm-2 in neutral medium and >190 mA cm-2 in alkaline medium.

Developing the novel bioinformatics algorithms to systematically investigate the connections among survival time, key genes and proteins for Glioblastoma multiforme.

BACKGROUND: Glioblastoma multiforme (GBM) is one of the most common malignant brain tumors and its average survival time is less than 1 year after diagnosis. RESULTS: Firstly, this study aims to develop the novel survival analysis algorithms to explore the key genes and proteins related to GBM. Then, we explore the significant correlation between AEBP1 upregulation and increased EGFR expression in primary glioma, and employ a glioma cell line LN229 to identify relevant proteins and molecular pathways through protein network analysis. Finally, we identify that AEBP1 exerts its tumor-promoting effects by mainly activating mTOR pathway in Glioma. CONCLUSIONS: We summarize the whole process of the experiment and discuss how to expand our experiment in the future.

Impact of digital technologies for communicating messages on weight loss maintenance: a systematic literature review.

BACKGROUND: Research into the use of digital technology for weight loss maintenance (intentionally losing at least 10% of initial body weight and actively maintaining it) is limited. The aim of this article was to systematically review randomized controlled trials (RCTs) reporting on the use of digital technologies for communicating on weight loss maintenance to determine its' effectiveness, and identify gaps and areas for further research. METHODS: A systematic literature review was conducted by searching electronic databases to locate publications dated between 2006 and February 2018. Criteria were applied, and RCTs using digital technologies for weight loss maintenance were selected. RESULTS: Seven RCTs were selected from a total of 6541 hits after de-duplication and criteria applied. Three trials used text messaging, one used e-mail, one used a web-based system and two compared such a system with face-to-face contact. From the seven RCTs, one included children (n = 141) and reported no difference in BMI Standard Deviation between groups. From the seven trials, four reported that technology is effective for significantly aiding weight loss maintenance compared with control (no contact) or face-to face-contact in the short term (between 3 and 24 months). CONCLUSIONS: It was concluded that digital technologies have the potential to be effective communication tools for significantly aiding weight loss maintenance, especially in the short term (from 3 to 24 months). Further research is required into the long-term effectiveness of contemporary technologies.

Pedestrian Dead Reckoning-Assisted Visual Inertial Odometry Integrity Monitoring.

Visual inertial odometers (VIOs) have received increasing attention in the area of indoor positioning due to the universality and convenience of the camera. However, the visual observation of VIO is more susceptible to the environment, and the error of observation affects the final positioning accuracy. To address this issue, we analyzed the causes of visual observation error that occur under different scenarios and their impact on positioning accuracy. We propose a new method of using the short-time reliability of pedestrian dead reckoning (PDR) to aid in visual integrity monitoring and to reduce positioning error. The proposed method selects optimized positioning by automatically switching between outputs from VIO and PDR. Experiments were carried out to test and evaluate the proposed PDR-assisted visual integrity monitoring. The sensor suite of experiments consisted of a stereo camera and an inertial measurement unit (IMU). Results were analyzed in detailed and indicated that the proposed system performs better for indoor positioning within an environment that contains low illumination, little background texture information, or few moving objects.

Integrated metagenomic analysis of the rumen microbiome of cattle reveals key biological mechanisms associated with methane traits.

Methane is one of the major contributors to global warming. The rumen microbiota is directly involved in methane production in cattle. The link between variation in rumen microbial communities and host genetics has important applications and implications in bioscience. Having the potential to reveal the full extent of microbial gene diversity and complex microbial interactions, integrated metagenomics and network analysis holds great promise in this endeavour. This study investigates the rumen microbial community in cattle through the integration of metagenomic and network-based approaches. Based on the relative abundance of 1570 microbial genes identified in a metagenomics analysis, the co-abundance network was constructed and functional modules of microbial genes were identified. One of the main contributions is to develop a random matrix theory-based approach to automatically determining the correlation threshold used to construct the co-abundance network. The resulting network, consisting of 549 microbial genes and 3349 connections, exhibits a clear modular structure with certain trait-specific genes highly over-represented in modules. More specifically, all the 20 genes previously identified to be associated with methane emissions are found in a module (hypergeometric test, p<10-11). One third of genes are involved in methane metabolism pathways. The further examination of abundance profiles across 8 samples of genes highlights that the revealed pattern of metagenomics abundance has a strong association with methane emissions. Furthermore, the module is significantly enriched with microbial genes encoding enzymes that are directly involved in methanogenesis (hypergeometric test, p<10-9).

A Novel Energy-Efficient Approach for Human Activity Recognition.

In this paper, we propose a novel energy-efficient approach for mobile activity recognition system (ARS) to detect human activities. The proposed energy-efficient ARS, using low sampling rates, can achieve high recognition accuracy and low energy consumption. A novel classifier that integrates hierarchical support vector machine and context-based classification (HSVMCC) is presented to achieve a high accuracy of activity recognition when the sampling rate is less than the activity frequency, i.e., the Nyquist sampling theorem is not satisfied. We tested the proposed energy-efficient approach with the data collected from 20 volunteers (14 males and six females) and the average recognition accuracy of around 96.0% was achieved. Results show that using a low sampling rate of 1Hz can save 17.3% and 59.6% of energy compared with the sampling rates of 5 Hz and 50 Hz. The proposed low sampling rate approach can greatly reduce the power consumption while maintaining high activity recognition accuracy. The composition of power consumption in online ARS is also investigated in this paper.

A computational framework for the prioritization of disease-gene candidates.

BACKGROUND: The identification of genes and uncovering the role they play in diseases is an important and complex challenge. Genome-wide linkage and association studies have made advancements in identifying genetic variants that underpin human disease. An important challenge now is to identify meaningful disease-associated genes from a long list of candidate genes implicated by these analyses. The application of gene prioritization can enhance our understanding of disease mechanisms and aid in the discovery of drug targets. The integration of protein-protein interaction networks along with disease datasets and contextual information is an important tool in unraveling the molecular basis of diseases. RESULTS: In this paper we propose a computational pipeline for the prioritization of disease-gene candidates. Diverse heterogeneous data including: gene-expression, protein-protein interaction network, ontology-based similarity and topological measures and tissue-specific are integrated. The pipeline was applied to prioritize Alzheimer's Disease (AD) genes, whereby a list of 32 prioritized genes was generated. This approach correctly identified key AD susceptible genes: PSEN1 and TRAF1. Biological process enrichment analysis revealed the prioritized genes are modulated in AD pathogenesis including: regulation of neurogenesis and generation of neurons. Relatively high predictive performance (AUC: 0.70) was observed when classifying AD and normal gene expression profiles from individuals using leave-one-out cross validation. CONCLUSIONS: This work provides a foundation for future investigation of diverse heterogeneous data integration for disease-gene prioritization.

Cloud computing-based TagSNP selection algorithm for human genome data.

Single nucleotide polymorphisms (SNPs) play a fundamental role in human genetic variation and are used in medical diagnostics, phylogeny construction, and drug design. They provide the highest-resolution genetic fingerprint for identifying disease associations and human features. Haplotypes are regions of linked genetic variants that are closely spaced on the genome and tend to be inherited together. Genetics research has revealed SNPs within certain haplotype blocks that introduce few distinct common haplotypes into most of the population. Haplotype block structures are used in association-based methods to map disease genes. In this paper, we propose an efficient algorithm for identifying haplotype blocks in the genome. In chromosomal haplotype data retrieved from the HapMap project website, the proposed algorithm identified longer haplotype blocks than an existing algorithm. To enhance its performance, we extended the proposed algorithm into a parallel algorithm that copies data in parallel via the Hadoop MapReduce framework. The proposed MapReduce-paralleled combinatorial algorithm performed well on real-world data obtained from the HapMap dataset; the improvement in computational efficiency was proportional to the number of processors used.

Stroke patients' utilisation of extrinsic feedback from computer-based technology in the home: a multiple case study realistic evaluation.

BACKGROUND: Evidence indicates that post-stroke rehabilitation improves function, independence and quality of life. A key aspect of rehabilitation is the provision of appropriate information and feedback to the learner.Advances in information and communications technology (ICT) have allowed for the development of various systems to complement stroke rehabilitation that could be used in the home setting. These systems may increase the provision of rehabilitation a stroke survivor receives and carries out, as well as providing a learning platform that facilitates long-term self-managed rehabilitation and behaviour change. This paper describes the application of an innovative evaluative methodology to explore the utilisation of feedback for post-stroke upper-limb rehabilitation in the home. METHODS: Using the principles of realistic evaluation, this study aimed to test and refine intervention theories by exploring the complex interactions of contexts, mechanisms and outcomes that arise from technology deployment in the home. Methods included focus groups followed by multi-method case studies (n = 5) before, during and after the use of computer-based equipment. Data were analysed in relation to the context-mechanism-outcome hypotheses case by case. This was followed by a synthesis of the findings to answer the question, 'what works for whom and in what circumstances and respects?' RESULTS: Data analysis reveals that to achieve desired outcomes through the use of ICT, key elements of computer feedback, such as accuracy, measurability, rewarding feedback, adaptability, and knowledge of results feedback, are required to trigger the theory-driven mechanisms underpinning the intervention. In addition, the pre-existing context and the personal and environmental contexts, such as previous experience of service delivery, personal goals, trust in the technology, and social circumstances may also enable or constrain the underpinning theory-driven mechanisms. CONCLUSIONS: Findings suggest that the theory-driven mechanisms underpinning the utilisation of feedback from computer-based technology for home-based upper-limb post-stroke rehabilitation are dependent on key elements of computer feedback and the personal and environmental context. The identification of these elements may therefore inform the development of technology; therapy education and the subsequent adoption of technology and a self-management paradigm; long-term self-managed rehabilitation; and importantly, improvements in the physical and psychosocial aspects of recovery.

A novel fluorescence sensor based on Al3+-mediated aggregation of gold nanoclusters for determination of citric acid in beverages.

This paper revealed a new strategy for citric acid (CA) detection using aggregation-induced emission (AIE)-based fluorescent gold nanoclusters (AuNCs). AuNCs was synthesized using glutathione (GSH) as the template and reducing agent and used as the fluorescent probe to detect CA under aluminum ion (Al3+) mediation. The fluorescence intensity of AuNCs increased about 4 times with the addition of Al3+, but the enhanced fluorescence was quenched after the addition of CA. Based on this fluorescence phenomenon, an "on-off" fluorescence strategy was designed for the sensitive determination of CA and a linear detection range for CA was achieved within 0-80.0 µM. In addition, the developed probe exhibited high selectivity and accuracy for determination of CA. The mechanism of fluorescence enhancement and quenching of AuNCs was explored in detail. The established probe was used successfully for CA detection in beverages. The spiked recoveries from 97.50% to 103.67% were gratifying, which indicated the probe had potential prospects for detecting CA in food.

Integrating domain similarity to improve protein complexes identification in TAP-MS data.

BACKGROUND: Detecting protein complexes in protein-protein interaction (PPI) networks plays an important role in improving our understanding of the dynamic of cellular organisation. However, protein interaction data generated by high-throughput experiments such as yeast-two-hybrid (Y2H) and tandem affinity-purification/mass-spectrometry (TAP-MS) are characterised by the presence of a significant number of false positives and false negatives. In recent years there has been a growing trend to incorporate diverse domain knowledge to support large-scale analysis of PPI networks. METHODS: This paper presents a new algorithm, by incorporating Gene Ontology (GO) based semantic similarities, to detect protein complexes from PPI networks generated by TAP-MS. By taking co-complex relations in TAP-MS data into account, TAP-MS PPI networks are modelled as bipartite graph, where bait proteins consist of one set of nodes and prey proteins are on the other. Similarities between pairs of bait proteins are computed by considering both the topological features and GO-driven semantic similarities. Bait proteins are then grouped in to sets of clusters based on their pair-wise similarities to produce a set of 'seed' clusters. An expansion process is applied to each 'seed' cluster to recruit prey proteins which are significantly associated with the same set of bait proteins. Thus, completely identified protein complexes are then obtained. RESULTS: The proposed algorithm has been applied to real TAP-MS PPI networks. Fifteen quality measures have been employed to evaluate the quality of generated protein complexes. Experimental results show that the proposed algorithm has greatly improved the accuracy of identifying complexes and outperformed several state-of-the-art clustering algorithms. Moreover, by incorporating semantic similarity, the proposed algorithm is more robust to noises in the networks.

Developing a New Phylogeny-Driven Random Forest Model for Functional Metagenomics.

Metagenomics is an unobtrusive science linking microbial genes to biological functions or environmental states. Classifying microbial genes into their functional repertoire is an important task in the downstream analysis of Metagenomic studies. The task involves Machine Learning (ML) based supervised methods to achieve good classification performance. Random Forest (RF) has been applied rigorously to microbial gene abundance profiles, mapping them to functional phenotypes. The current research targets tuning RF by the evolutionary ancestry of microbial phylogeny, developing a Phylogeny-RF model for functional classification of metagenomes. This method facilitates capturing the effects of phylogenetic relatedness in an ML classifier itself rather than just applying a supervised classifier over the raw abundances of microbial genes. The idea is rooted in the fact that closely related microbes by phylogeny are highly correlated and tend to have similar genetic and phenotypic traits. Such microbes behave similarly; and hence tend to be selected together, or one of these could be dropped from the analysis, to improve the ML process. The proposed Phylogeny-RF algorithm has been compared with state-of-the-art classification methods including RF and the phylogeny-aware methods of MetaPhyl and PhILR, using three real-world 16S rRNA metagenomic datasets. It has been observed that the proposed method not only achieved significantly better performance than the traditional RF model but also performed better than the other phylogeny-driven benchmarks (p < 0.05). For example, Phylogeny-RF attained a highest AUC of 0.949 and Kappa of 0.891 over soil microbiomes in comparison to other benchmarks.