Search

Medical practitioners need to understand the critical features of ECG beats to diagnose and identify cardiovascular conditions accurately. This would be greatly facilitated by identifying the significant features of frequency components in temporal ECG wave-forms using computational methods. In this study, we have proposed a novel ECG beat classifier based on a customized VGG16-based Convolution Neural Network (CNN) that uses the time-frequency representation of temporal ECG, and a method to identify the contribution of interpretable ECG frequencies when classifying based on the SHapley Additive exPlanations (SHAP) values. We applied our model to the MIT-BIH arrhythmia dataset to classify the ECG beats and to characterise of the beats frequencies. This model was evaluated with two advanced time-frequency analysis methods. Our results indicated that for 2-4 classes our proposed model achieves a classification accuracy of 100% and for 5 classes it achieves a classification accuracy of 99.90%. We have also tested the proposed model using premature ventricular contraction beats from the American Heart Association (AHA) database and normal beats from Lobachevsky University Electrocardiography database (LUDB) and obtained a classification accuracy of 99.91% for the 5-classes case. In addition, SHAP value increased the interpretability of the ECG frequency features. Thus, this model could be applicable to the automation of the cardiovascular diagnosis system and could be used by clinicians.

Recently, electroencephalogram-based emotion recognition has become crucial in enabling the Human-Computer Interaction (HCI) system to become more intelligent. Due to the outstanding applications of emotion recognition, e.g., person-based decision making, mind-machine interfacing, cognitive interaction, affect detection, feeling detection, etc., emotion recognition has become successful in attracting the recent hype of AI-empowered research. Therefore, numerous studies have been conducted driven by a range of approaches, which demand a systematic review of methodologies used for this task with their feature sets and techniques. It will facilitate the beginners as guidance towards composing an effective emotion recognition system. In this article, we have conducted a rigorous review on the state-of-the-art emotion recognition systems, published in recent literature, and summarized some of the common emotion recognition steps with relevant definitions, theories, and analyses to provide key knowledge to develop a proper framework. Moreover, studies included here were dichotomized based on two categories: i) deep learning-based, and ii) shallow machine learning-based emotion recognition systems. The reviewed systems were compared based on methods, classifier, the number of classified emotions, accuracy, and dataset used. An informative comparison, recent research trends, and some recommendations are also provided for future research directions.

Influence map (IM) is often used as a decision supporting technology in game artificial intelligence (AI). However, the traditional influence map does not describe dynamic information. Some improved IM models can describe dynamic information, but not accurately enough. When an object moves, it would produce large influence in its moving direction than other directions. Therefore, the influence produce by the object to a location depends on the relation between the location and the object’s moving direction. This paper proposed a dynamic influence map model based on distance adjustment, DADIM. This model produces different influence values in different direction by adjusting the “distance” between two locations. This method can encode dynamic information into the influence map easily. Experiments show this model avoids the weakness of dynamic influence map with location prediction. Compared with other influence maps, this model could improve the performance of the game AI with time complexity being unchanged.

Using machine learning techniques to build representations from biomedical data can help us understand the latent biological mechanism of action and lead to important discoveries. Recent developments in single-cell RNA-sequencing protocols have allowed measuring gene expression for individual cells in a population, thus opening up the possibility of finding answers to biomedical questions about cell differentiation. In this paper, we explore unsupervised generative neural methods, based on the variational autoencoder, that can model cell differentiation by building meaningful representations from the high dimensional and complex gene expression data. We use disentanglement methods based on information theory to improve the data representation and achieve better separation of the biological factors of variation in the gene expression data. In addition, we use a graph autoencoder consisting of graph convolutional layers to predict relationships between single-cells. Based on these models, we develop a computational framework that consists of methods for identifying the cell types in the dataset, finding driver genes for the differentiation process and obtaining a better understanding of relationships between cells. We illustrate our methods on datasets from multiple species and also from different sequencing technologies.

Reinforcement Learning (RL) has achieved impressive performance in many complex environments due to the integration with Deep Neural Networks (DNNs). At the same time, Genetic Algorithms (GAs), often seen as a competing approach to RL, had limited success in scaling up to the DNNs required to solve challenging tasks. Contrary to this dichotomic view, in the physical world, evolution and learning are complementary processes that continuously interact. The recently proposed Evolutionary Reinforcement Learning (ERL) framework has demonstrated mutual benefits to performance when combining the two methods. However, ERL has not fully addressed the scalability problem of GAs. In this paper, we show that this problem is rooted in an unfortunate combination of a simple genetic encoding for DNNs and the use of traditional biologically-inspired variation operators. When applied to these encodings, the standard operators are destructive and cause catastrophic forgetting of the traits the networks acquired. We propose a novel algorithm called Proximal Distilled Evolutionary Reinforcement Learning (PDERL) that is characterised by a hierarchical integration between evolution and learning. The main innovation of PDERL is the use of learning-based variation operators that compensate for the simplicity of the genetic representation. Unlike traditional operators, our proposals meet the functional requirements of variation operators when applied on directly-encoded DNNs. We evaluate PDERL in five robot locomotion settings from the OpenAI gym. Our method outperforms ERL, as well as two state-of-the-art RL algorithms, PPO and TD3, in all tested environments., Comment: Camera-ready version for AAAI-20. Contains 10 pages, 11 figures

Topic detection technology can automatically discover new topics on the Internet. This paper investigates domain-oriented feature extraction methods, and proposes a keyword feature extraction method ITFIDF-LP, a subject word feature extraction method LDA-SLP and a topic clustering model based on vector product similarity. A novel Domain-oriented Topic Discovery based on Features Extraction and Topic Clustering (DTD-FETC) model is proposed to analyze open source web of a domain and identify emerging topics in the domain in real time. This article describes a DTD-FETC system built for cyber security domain. It filters and aggregates web for specical security threat topics such as vulnerability and malware, and helps security staff respond quickly and defends against the emerging cyber threats as early as possible. The recall rate, accuracy and F1 value results of the DTD-FETC method applied to the cyber security dataset are all above 0.99.

ObjectiveModern medicine needs to shift from a wait and react, curative discipline to a preventative, interdisciplinary science aiming at providing personalised, systemic and precise treatment plans to patients. The aim of this work is to present how the integration of machine learning approaches with mechanistic computational modelling could yield a reliable infrastructure to run probabilistic simulations where the entire organism is considered as a whole.MethodsWe propose a general framework that composes advanced AI approaches and integrates mathematical modelling in order to provide a panoramic view over current and future physiological conditions. The proposed architecture is based on a graph neural network (GNNs) forecasting clinically relevant endpoints (such as blood pressure) and a generative adversarial network (GANs) providing a proof of concept of transcriptomic integrability.ResultsWe show the results of the investigation of pathological effects of overexpression of ACE2 across different signalling pathways in multiple tissues on cardiovascular functions. We provide a proof of concept of integrating a large set of composable clinical models using molecular data to drive local and global clinical parameters and derive future trajectories representing the evolution of the physiological state of the patient.SignificanceWe argue that the graph representation of a computational patient has potential to solve important technological challenges in integrating multiscale computational modelling with AI. We believe that this work represents a step forward towards a healthcare digital twin.

Funder: Chiang Mai University, Funder: College of Arts, Media and Technology, Chiang Mai University, Funder: Mahidol University, Accurate identification of bitter peptides is of great importance for better understanding their biochemical and biophysical properties. To date, machine learning-based methods have become effective approaches for providing a good avenue for identifying potential bitter peptides from large-scale protein datasets. Although few machine learning-based predictors have been developed for identifying the bitterness of peptides, their prediction performances could be improved. In this study, we developed a new predictor (named iBitter-Fuse) for achieving more accurate identification of bitter peptides. In the proposed iBitter-Fuse, we have integrated a variety of feature encoding schemes for providing sufficient information from different aspects, namely consisting of compositional information and physicochemical properties. To enhance the predictive performance, the customized genetic algorithm utilizing self-assessment-report (GA-SAR) was employed for identifying informative features followed by inputting optimal ones into a support vector machine (SVM)-based classifier for developing the final model (iBitter-Fuse). Benchmarking experiments based on both 10-fold cross-validation and independent tests indicated that the iBitter-Fuse was able to achieve more accurate performance as compared to state-of-the-art methods. To facilitate the high-throughput identification of bitter peptides, the iBitter-Fuse web server was established and made freely available online. It is anticipated that the iBitter-Fuse will be a useful tool for aiding the discovery and de novo design of bitter peptides.

Recent advancements in graph representation learning have led to the emergence of condensed encodings that capture the main properties of a graph. However, even though these abstract representations are powerful for downstream tasks, they are not equally suitable for visualisation purposes. In this work, we merge Mapper, an algorithm from the field of Topological Data Analysis (TDA), with the expressive power of Graph Neural Networks (GNNs) to produce hierarchical, topologically-grounded visualisations of graphs. These visualisations do not only help discern the structure of complex graphs but also provide a means of understanding the models applied to them for solving various tasks. We further demonstrate the suitability of Mapper as a topological framework for graph pooling by mathematically proving an equivalence with Min-Cut and Diff Pool. Building upon this framework, we introduce a novel pooling algorithm based on PageRank, which obtains competitive results with state of the art methods on graph classification benchmarks., 13 pages, 10 figures

Background Single-cell RNA sequencing (scRNA-Seq) experiments are gaining ground to study the molecular processes that drive normal development as well as the onset of different pathologies. Finding an effective and efficient low-dimensional representation of the data is one of the most important steps in the downstream analysis of scRNA-Seq data, as it could provide a better identification of known or putatively novel cell-types. Another step that still poses a challenge is the integration of different scRNA-Seq datasets. Though standard computational pipelines to gain knowledge from scRNA-Seq data exist, a further improvement could be achieved by means of machine learning approaches. Results Autoencoders (AEs) have been effectively used to capture the non-linearities among gene interactions of scRNA-Seq data, so that the deployment of AE-based tools might represent the way forward in this context. We introduce here scAEspy, a unifying tool that embodies: (1) four of the most advanced AEs, (2) two novel AEs that we developed on purpose, (3) different loss functions. We show that scAEspy can be coupled with various batch-effect removal tools to integrate data by different scRNA-Seq platforms, in order to better identify the cell-types. We benchmarked scAEspy against the most used batch-effect removal tools, showing that our AE-based strategies outperform the existing solutions. Conclusions scAEspy is a user-friendly tool that enables using the most recent and promising AEs to analyse scRNA-Seq data by only setting up two user-defined parameters. Thanks to its modularity, scAEspy can be easily extended to accommodate new AEs to further improve the downstream analysis of scRNA-Seq data. Considering the relevant results we achieved, scAEspy can be considered as a starting point to build a more comprehensive toolkit designed to integrate multi single-cell omics.

In this paper, a new deep learning and machine learning combined model is proposed for malware behavior analysis. One part of it analyzes the dependency relation in API (Application Programming Interface) call sequence at the functional level, and extracts features for random forest to learn and classify. The other part employs a bidirectional residual neural network to study the API sequence and discover malware with redundant information preprocessing. In the API call sequence, future information is much more important for conjecturing the semantic of the current API call. We conducted experiments on a malware dataset. The experiment results show that both methods can effectively detect malwares. However, the combined framework has better classification performance. The classification accuracy of the combined malware detection architecture is 0.967.

BackgroundThe welding process releases potentially hazardous gases and fumes, mainly composed of metallic oxides, fluorides and silicates. Long term welding fume (WF) inhalation is a recognized health issue that carries a risk of developing chronic health problems, particularly respiratory system diseases (RSDs). Aside from general airway irritation, WF exposure may drive direct cellular responses in the respiratory system which increase risk of RSD, but these are not well understood.MethodsWe developed a quantitative framework to identify gene expression effects of WF exposure that may affect RSD development. We analyzed gene expression microarray data from WF-exposed tissues and RSD-affected tissues, including chronic bronchitis (CB), asthma (AS), pulmonary edema (PE), lung cancer (LC) datasets. We built disease-gene (diseasome) association networks and identified dysregulated signaling and ontological pathways, and protein-protein interaction sub-network using neighborhood-based benchmarking and multilayer network topology.ResultsWe observed many genes with altered expression in WF-exposed tissues were also among differentially expressed genes (DEGs) in RSD tissues; for CB, AS, PE and LC there were 34, 27, 50 and 26 genes respectively. DEG analysis, using disease association networks, pathways, ontological analysis and protein-protein interaction sub-network suggest significant links between WF exposure and the development of CB, AS, PE and LC.ConclusionsOur network-based analysis and investigation of the genetic links of WFs and RSDs confirm a number of genes and gene products are plausible participants in RSD development. Our results are a significant resource to identify causal influences on the development of RSDs, particularly in the context of WF exposure.

Autism Spectrum Disorder (ASD) is a group of neurodevelopmental disabilities that are not curable but may be ameliorated by early interventions. We gathered early-detected ASD datasets relating to toddlers, children, adolescents and adults, and applied several feature transformation methods, including log, Z-score and sine functions to these datasets. Various classification techniques were then implemented with these transformed ASD datasets and assessed for their performance. We found SVM showed the best performance for the toddler dataset, while Adaboost gave the best results for the children dataset, Glmboost for the adolescent and Adaboost for the adult datasets. The feature transformations resulting in the best classifications was sine function for toddler and Z-score for children and adolescent datasets. After these analyses, several feature selection techniques were used with these Z-score-transformed datasets to identify the significant ASD risk factors for the toddler, child, adolescent and adult subjects. The results of these analytical approaches indicate that, when appropriately optimised, machine learning methods can provide good predictions of ASD status. This suggests that it may possible to apply these models for the detection of ASD in its early stages.

Motivation Single-cell RNA sequencing allows high-resolution views of individual cells for libraries of up to millions of samples, thus motivating the use of deep learning for analysis. In this study, we introduce the use of graph neural networks for the unsupervised exploration of scRNA-seq data by developing a variational graph autoencoder architecture with graph attention layers that operates directly on the connectivity between cells, focusing on dimensionality reduction and clustering. With the help of several case studies, we show that our model, named CellVGAE, can be effectively used for exploratory analysis even on challenging datasets, by extracting meaningful features from the data and providing the means to visualize and interpret different aspects of the model. Results We show that CellVGAE is more interpretable than existing scRNA-seq variational architectures by analysing the graph attention coefficients. By drawing parallels with other scRNA-seq studies on interpretability, we assess the validity of the relationships modelled by attention, and furthermore, we show that CellVGAE can intrinsically capture information such as pseudotime and NF-ĸB activation dynamics, the latter being a property that is not generally shared by existing neural alternatives. We then evaluate the dimensionality reduction and clustering performance on 9 difficult and well-annotated datasets by comparing with three leading neural and non-neural techniques, concluding that CellVGAE outperforms competing methods. Finally, we report a decrease in training times of up to × 20 on a dataset of 1.3 million cells compared to existing deep learning architectures. Availabilityand implementation The CellVGAE code is available at https://github.com/davidbuterez/CellVGAE. Supplementary information Supplementary data are available at Bioinformatics online.

Background High-throughput sequencing Chromosome Conformation Capture (Hi-C) allows the study of DNA interactions and 3D chromosome folding at the genome-wide scale. Usually, these data are represented as matrices describing the binary contacts among the different chromosome regions. On the other hand, a graph-based representation can be advantageous to describe the complex topology achieved by the DNA in the nucleus of eukaryotic cells. Methods Here we discuss the use of a graph database for storing and analysing data achieved by performing Hi-C experiments. The main issue is the size of the produced data and, working with a graph-based representation, the consequent necessity of adequately managing a large number of edges (contacts) connecting nodes (genes), which represents the sources of information. For this, currently available graph visualisation tools and libraries fall short with Hi-C data. The use of graph databases, instead, supports both the analysis and the visualisation of the spatial pattern present in Hi-C data, in particular for comparing different experiments or for re-mapping omics data in a space-aware context efficiently. In particular, the possibility of describing graphs through statistical indicators and, even more, the capability of correlating them through statistical distributions allows highlighting similarities and differences among different Hi-C experiments, in different cell conditions or different cell types. Results These concepts have been implemented in NeoHiC, an open-source and user-friendly web application for the progressive visualisation and analysis of Hi-C networks based on the use of the Neo4j graph database (version 3.5). Conclusion With the accumulation of more experiments, the tool will provide invaluable support to compare neighbours of genes across experiments and conditions, helping in highlighting changes in functional domains and identifying new co-organised genomic compartments.

Background: Machine learning (ML), one aspect of artificial intelligence (AI), involves computer algorithms that train themselves. They have been widely applied in the healthcare domain. However, many trained ML algorithms operate as “black boxes”, producing a prediction from input data without a clear explanation of their workings. Non-transparent predictions are of limited utility in many clinical domains, where decisions must be justifiable. Methods: Here, we apply class-contrastive counterfactual reasoning to ML to demonstrate how specific changes in inputs lead to different predictions of mortality in people with severe mental illness (SMI), a major public health challenge. We produce predictions accompanied by visual and textual explanations as to how the prediction would have differed given specific changes to the input. We apply it to routinely collected data from a mental health secondary care provider in patients with schizophrenia. Using a data structuring framework informed by clinical knowledge, we captured information on physical health, mental health, and social predisposing factors. We then trained an ML algorithm to predict the risk of death. Results: The ML algorithm predicted mortality with an area under receiver operating characteristic curve (AUROC) of 0.8 (compared to an AUROC of 0.67 from a logistic regression model), and produced class-contrastive explanations for its predictions. Conclusions: In patients with schizophrenia, our work suggests that use of medications like second generation antipsychotics and antidepressants was associated with lower risk of death. Abuse of alcohol/drugs and a diagnosis of delirium were associated with higher risk of death. Our ML models highlight the role of co-morbidities in determining mortality in patients with SMI and the need to manage them. We hope that some of these bio-social factors can be targeted therapeutically by either patient-level or service-level interventions. This approach combines clinical knowledge, health data, and statistical learning, to make predictions interpretable to clinicians using class-contrastive reasoning. This is a step towards interpretable AI in the management of patients with SMI and potentially other diseases. Funding: UK Medical Research Council. Declaration of Interest: RNC consults for Campden Instruments Ltd and receives royalties from Cambridge University Press, Cambridge Enterprise, and Routledge. SB, PL and PJ declare they have no conflicts of interest to disclose. Ethical Approval: The CPFT Research Database operates under UK NHS Research Ethics approvals (REC references 12/EE/0407, 17/EE/0442; IRAS project ID 237953).

Recently, it has become progressively more evident that classic diagnostic labels are unable to accurately and reliably describe the complexity and variability of several clinical phenotypes. This is particularly true for a broad range of neuropsychiatric illnesses such as depression and anxiety disorders or behavioural phenotypes such as aggression and antisocial personality. Patient heterogeneity can be better described and conceptualized by grouping individuals into novel categories, which are based on empirically-derived sections of intersecting continua that span both across and beyond traditional categorical borders. In this context, neuroimaging data carry a wealth of spatiotemporally resolved information about each patient’s brain. However, they are usually heavily collapsed a priori through procedures which are not learned as part of model training, and consequently not optimized for the downstream prediction task. This is due to the fact that every individual participant usually comes with multiple whole-brain 3D imaging modalities often accompanied by a deep genotypic and phenotypic characterization, hence posing formidable computational challenges.In this paper we design and validate a deep learning architecture based on generative models rooted in a modular approach and separable convolutional blocks (which result in a 20-fold decrease in parameter utilization) in order to a) fuse multiple 3D neuroimaging modalities on a voxel-wise level, b) efficiently convert them into informative latent embeddings through heavy dimensionality reduction, c) maintain excellent generalizability and minimal information loss. As proof of concept, we test our architecture on the well characterized Human Connectome Project database (n=974 healthy subjects), demonstrating that our latent embeddings can be clustered into easily separable subject strata which, in turn, map to extremely different phenotypical information (including organic, neuropsychological, personality variables) which was not included in the embedding creation process.The ability to extract meaningful and separable phenotypic information from brain images alone can aid in creating multi-dimensional biomarkers able to chart spatio-temporal trajectories which may correspond to different pathophysiological mechanisms unidentifiable to traditional data analysis approaches. In turn, this may be of aid in predicting disease evolution as well as drug response, hence supporting mechanistic disease understanding and also empowering clinical trials.

Deep learning models are receiving increasing attention in clinical decision-making, however the lack of interpretability and explainability impedes their deployment in day-to-day clinical practice. We propose REM, an interpretable and explainable methodology for extracting rules from deep neural networks and combining them with other data-driven and knowledge-driven rules. This allows integrating ma- chine learning and reasoning for investigating applied and basic biological research questions. We evaluate the utility of REM on the predictive tasks of classifying histological and immunohistochemical breast cancer subtypes from genotype and phenotype data. We demonstrate that REM efficiently extracts accurate, compre- hensible and, biologically relevant rulesets from deep neural networks that can be readily integrated with rulesets obtained from tree-based approaches. REM provides explanation facilities for predictions and enables the clinicians to vali- date and calibrate the extracted rulesets with their domain knowledge. With these functionalities, REM caters for a novel and direct human-in-the-loop approach in clinical decision making.

Motivation High-throughput gene expression can be used to address a wide range of fundamental biological problems, but datasets of an appropriate size are often unavailable. Moreover, existing transcriptomics simulators have been criticized because they fail to emulate key properties of gene expression data. In this article, we develop a method based on a conditional generative adversarial network to generate realistic transcriptomics data for Escherichia coli and humans. We assess the performance of our approach across several tissues and cancer-types. Results We show that our model preserves several gene expression properties significantly better than widely used simulators, such as SynTReN or GeneNetWeaver. The synthetic data preserve tissue- and cancer-specific properties of transcriptomics data. Moreover, it exhibits real gene clusters and ontologies both at local and global scales, suggesting that the model learns to approximate the gene expression manifold in a biologically meaningful way. Availability and implementation Code is available at: https://github.com/rvinas/adversarial-gene-expression. Supplementary information Supplementary data are available at Bioinformatics online.

Although chemotherapy is the first-line treatment for ovarian cancer (OCa) patients, chemoresistance (CR) decreases their progression-free survival. This paper investigates the genetic interaction (GI) related to OCa-CR. To decrease the complexity of establishing gene networks, individual signature genes related to OCa-CR are identified using a gradient boosting decision tree algorithm. Additionally, the genetic interaction coefficient (GIC) is proposed to measure the correlation of two signature genes quantitatively and explain their joint influence on OCa-CR. Gene pair that possesses high GIC is identified as signature pair. A total of 24 signature gene pairs are selected that include 10 individual signature genes and the influence of signature gene pairs on OCa-CR is explored. Finally, a signature gene pair-based prediction of OCa-CR is identified. The area under curve (AUC) is a widely used performance measure for machine learning prediction. The AUC of signature gene pair reaches 0.9658, whereas the AUC of individual signature gene-based prediction is 0.6823 only. The identified signature gene pairs not only build an efficient GI network of OCa-CR but also provide an interesting way for OCa-CR prediction. This improvement shows that our proposed method is a useful tool to investigate GI related to OCa-CR.

Objective: Modern medicine needs to shift from a wait and react, curative discipline to a preventative, interdisciplinary science aiming at providing personalized, systemic, and precise treatment plans to patients. To this purpose, we propose a “digital twin” of patients modeling the human body as a whole and providing a panoramic view over individuals' conditions.Methods: We propose a general framework that composes advanced artificial intelligence (AI) approaches and integrates mathematical modeling in order to provide a panoramic view over current and future pathophysiological conditions. Our modular architecture is based on a graph neural network (GNN) forecasting clinically relevant endpoints (such as blood pressure) and a generative adversarial network (GAN) providing a proof of concept of transcriptomic integrability.Results: We tested our digital twin model on two simulated clinical case studies combining information at organ, tissue, and cellular level. We provided a panoramic overview over current and future patient's conditions by monitoring and forecasting clinically relevant endpoints representing the evolution of patient's vital parameters using the GNN model. We showed how to use the GAN to generate multi-tissue expression data for blood and lung to find associations between cytokines conditioned on the expression of genes in the renin–angiotensin pathway. Our approach was to detect inflammatory cytokines, which are known to have effects on blood pressure and have previously been associated with SARS-CoV-2 infection (e.g., CXCR6, XCL1, and others).Significance: The graph representation of a computational patient has potential to solve important technological challenges in integrating multiscale computational modeling with AI. We believe that this work represents a step forward toward next-generation devices for precision and predictive medicine.

Protein–protein interactions (PPIs) are central to cellular functions. Experimental methods for predicting PPIs are well developed but are time and resource expensive and suffer from high false-positive error rates at scale. Computational prediction of PPIs is highly desirable for a mechanistic understanding of cellular processes and offers the potential to identify highly selective drug targets. In this chapter, details of developing a deep learning approach to predicting which residues in a protein are involved in forming a PPI—a task known as PPI site prediction—are outlined. The key decisions to be made in defining a supervised machine learning project in this domain are here highlighted. Alternative training regimes for deep learning models to address shortcomings in existing approaches and provide starting points for further research are discussed. This chapter is written to serve as a companion to developing deep learning approaches to protein–protein interaction site prediction, and an introduction to developing geometric deep learning projects operating on protein structure graphs.

Human-Cyber-Physical-Systems (HPCS), such as critical infrastructures in modern society, are subject to several systemic threats due to their complex interconnections and interdependencies. Management of systemic threats requires a paradigm shift from static risk assessment to holistic resilience modeling and evaluation using intelligent, data-driven and run-time approaches. In fact, the complexity and criticality of HCPS requires timely decisions considering many parameters and implications, which in turn require the adoption of advanced monitoring frameworks and evaluation tools. In order to tackle such challenge, we introduce those new paradigms in a framework named RESILTRON, envisioning Digital Twins (DT) to support decision making and improve resilience in HCPS under systemic stress. In order to represent possibly complex and heterogeneous HCPS, together with their environment and stressors, we leverage on multi-simulation approaches, combining multiple formalisms, data-driven approaches and Artificial Intelligence (AI) modelling paradigms, through a structured, modular and compositional framework. DT are used to provide an adaptive abstract representation of the system in terms of multi-layered spatially-embedded dynamic networks, and to apply self-adaptation to time-warped What-If analyses, in order to find the best sequence of decisions to ensure resilience under uncertainty and continuous HPCS evolution.

Funder: University of Cambridge, The COVID-19 global pandemic is a threat not only to the health of millions of individuals, but also to the stability of infrastructure and economies around the world. The disease will inevitably place an overwhelming burden on healthcare systems that cannot be effectively dealt with by existing facilities or responses based on conventional approaches. We believe that a rigorous clinical and societal response can only be mounted by using intelligence derived from a variety of data sources to better utilize scarce healthcare resources, provide personalized patient management plans, inform policy, and expedite clinical trials. In this paper, we introduce five of the most important challenges in responding to COVID-19 and show how each of them can be addressed by recent developments in machine learning (ML) and artificial intelligence (AI). We argue that the integration of these techniques into local, national, and international healthcare systems will save lives, and propose specific methods by which implementation can happen swiftly and efficiently. We offer to extend these resources and knowledge to assist policymakers seeking to implement these techniques.

OBJECTIVE: In a previous study, we observed the presence of simultaneous increases in intracranial pressure (ICP) and the heart rate (HR), which we denominated cardio-cerebral crosstalk (CC), and we related the number of such events to patient outcomes in a paediatric cohort. In this chapter, we present an extension of this work to an adult cohort from the Collaborative European NeuroTrauma Effectiveness Research in TBI (CENTER-TBI) study. METHODS: We implemented a sliding window algorithm to detect CC events. We considered subwindows of 10-min observations. If simultaneous increases of at least 20% in ICP and HR occurred with respect to the minimum ICP and HR values in the time windows, a CC event was detected. Correlation between the number of CC events and mortality was then obtained. RESULTS: The cohort consisted of 226 adults (aged 16-85 years). The number of CC events that were detected varied (mean 50, standard deviation 58). A point biserial correlation coefficient of -0.13 between mortality and CC was found. Although the correlation was weaker than that seen in the paediatric cohort (-0.30), the negative direction was replicated. CONCLUSION: In this work, we first extracted CC events from ICP and HR observations of adult patients with traumatic brain injury and related the number of CC events to patient outcomes. Consistency with the previous results in the paediatric cohort was observed. The more crosstalk events occurred, the better the patient outcome was.

Purpose Approaches to solving sustainability problems require a specific problem-solving mode, encompassing the complexity, fuzziness and interdisciplinary nature of the problem. This paper aims to promote a complex systems’ view of addressing sustainability problems, in particular through the tool of network science, and provides an outline of an interdisciplinary training workshop. Design/methodology/approach The topic of the workshop is the analysis of the Sustainable Development Goals (SDGs) as a political action plan. The authors are interested in the synergies and trade-offs between the goals, which are investigated through the structure of the underlying network. The authors use a teaching approach aligned with sustainable education and transformative learning. Findings Methodologies from network science are experienced as valuable tools to familiarise students with complexity and to handle the proposed case study. Originality/value To the best of the authors’ knowledge, this is the first work which uses network terminology and approaches to teach sustainability problems. This work highlights the potential of network science in sustainability education and contributes to accessible material.

Funder: Medical Research Council; doi: http://dx.doi.org/10.13039/501100000265, Extensive monitoring in intensive care units (ICUs) generates large quantities of data which contain numerous trends that are difficult for clinicians to systematically evaluate. Current approaches to such heterogeneity in electronic health records (EHRs) discard pertinent information. We present a deep learning pipeline that uses all uncurated chart, lab, and output events for prediction of in-hospital mortality without variable selection. Over 21,000 ICU patients and tens of thousands of variables derived from the MIMIC-III database were used to train and validate our model. Recordings in the first few hours of a patient's stay were found to be strongly predictive of mortality, outperforming models using SAPS II and OASIS scores, AUROC 0.72 and 0.76 at 24 h respectively, within just 12 h of ICU admission. Our model achieves a very strong predictive performance of AUROC 0.85 (95% CI 0.83-0.86) after 48 h. Predictive performance increases over the first 48 h, but suffers from diminishing returns, providing rationale for time-limited trials of critical care and suggesting that the timing of decision making can be optimised and individualised.

Funder: Università degli Studi di Siena, BACKGROUND: Traumatic brain injury (TBI) is an extremely heterogeneous and complex pathology that requires the integration of different physiological measurements for the optimal understanding and clinical management of patients. Information derived from intracranial pressure (ICP) monitoring can be coupled with information obtained from heart rate (HR) monitoring to assess the interplay between brain and heart. The goal of our study is to investigate events of simultaneous increases in HR and ICP and their relationship with patient mortality.. METHODS: In our previous work, we introduced a novel measure of brain-heart interaction termed brain-heart crosstalks (ctnp), as well as two additional brain-heart crosstalks indicators [mutual information ([Formula: see text]) and average edge overlap (ωct)] obtained through a complex network modeling of the brain-heart system. These measures are based on identification of simultaneous increase of HR and ICP. In this article, we investigated the relationship of these novel indicators with respect to mortality in a multicenter TBI cohort, as part of the Collaborative European Neurotrauma Effectiveness Research in TBI high-resolution work package. RESULTS: A total of 226 patients with TBI were included in this cohort. The data set included monitored parameters (ICP and HR), as well as laboratory, demographics, and clinical information. The number of detected brain-heart crosstalks varied (mean 58, standard deviation 57). The Kruskal-Wallis test comparing brain-heart crosstalks measures of survivors and nonsurvivors showed statistically significant differences between the two distributions (p values: 0.02 for [Formula: see text], 0.005 for ctnp and 0.006 for ωct). An inverse correlation was found, computed using the point biserial correlation technique, between the three new measures and mortality: - 0.13 for ctnp (p value 0.04), - 0.19 for ωct (p value 0.002969) and - 0.09 for [Formula: see text] (p value 0.1396). The measures were then introduced into the logistic regression framework, along with a set of input predictors made of clinical, demographic, computed tomography (CT), and lab variables. The prediction models were obtained by dividing the original cohort into four age groups (16-29, 30-49, 50-65, and 65-85 years of age) to properly treat with the age confounding factor. The best performing models were for age groups 16-29, 50-65, and 65-85, with the deviance of ratio explaining more than 80% in all the three cases. The presence of an inverse relationship between brain-heart crosstalks and mortality was also confirmed. CONCLUSIONS: The presence of a negative relationship between mortality and brain-heart crosstalks indicators suggests that a healthy brain-cardiovascular interaction plays a role in TBI.

Structured illumination microscopy (SIM) has become an important technique for optical super-resolution imaging because it allows a doubling of image resolution at speeds compatible with live-cell imaging. However, the reconstruction of SIM images is often slow, prone to artefacts, and requires multiple parameter adjustments to reflect different hardware or experimental conditions. Here, we introduce a versatile reconstruction method, ML-SIM, which makes use of transfer learning to obtain a parameter-free model that generalises beyond the task of reconstructing data recorded by a specific imaging system for a specific sample type. We demonstrate the generality of the model and the high quality of the obtained reconstructions by application of ML-SIM on raw data obtained for multiple sample types acquired on distinct SIM microscopes. ML-SIM is an end-to-end deep residual neural network that is trained on an auxiliary domain consisting of simulated images, but is transferable to the target task of reconstructing experimental SIM images. By generating the training data to reflect challenging imaging conditions encountered in real systems, ML-SIM becomes robust to noise and irregularities in the illumination patterns of the raw SIM input frames. Since ML-SIM does not require the acquisition of experimental training data, the method can be efficiently adapted to any specific experimental SIM implementation. We compare the reconstruction quality enabled by ML-SIM with current state-of-the-art SIM reconstruction methods and demonstrate advantages in terms of generality and robustness to noise for both simulated and experimental inputs, thus making ML-SIM a useful alternative to traditional methods for challenging imaging conditions. Additionally, reconstruction of a SIM stack is accomplished in less than 200 ms on a modern graphics processing unit, enabling future applications for real-time imaging. Source code and ready-to-use software for the method are available at http://ML-SIM.github.io.

Resting-state functional magnetic resonance imaging (rs-fMRI) has been successfully employed to understand the organisation of the human brain. For rs-fMRI analysis, the brain is typically parcellated into regions of interest (ROIs) and modelled as a graph where each ROI is a node and pairwise correlation between ROI blood-oxygen-level-dependent (BOLD) time series are edges. Recently, graph neural networks (GNNs) have seen a surge in popularity due to their successes in modelling unstructured relational data. The latest developments with GNNs, however, have not yet been fully exploited for the analysis of rs-fMRI data, particularly with regards to its spatio-temporal dynamics. Herein we present a novel deep neural network architecture, combining both GNNs and temporal convolutional networks (TCNs), which is able to learn from the spatial and temporal components of rs-fMRI data in an end-to-end fashion. In particular, this corresponds to intra-feature learning (i.e., learning temporal dynamics with TCNs) as well as inter-feature learning (i.e., leveraging spatial interactions between ROIs with GNNs). We evaluate our model with an ablation study using 35,159 samples from the UK Biobank rs-fMRI database. We also demonstrate explainability features of our architecture which map to realistic neurobiological insights. We hope our model could lay the groundwork for future deep learning architectures focused on leveraging the inherently and inextricably spatio-temporal nature of rs-fMRI data.

A question of fundamental biological significance is to what extent the expression of a subset of genes can be used to recover the full transcriptome, with important implications for biological discovery and clinical application. To address this challenge, we propose two novel deep learning methods, PMI and GAIN-GTEx, for gene expression imputation. In order to increase the applicability of our approach, we leverage data from GTEx v8, a reference resource that has generated a comprehensive collection of transcriptomes from a diverse set of human tissues. We show that our approaches compare favorably to several standard and state-of-the-art imputation methods in terms of predictive performance and runtime in two case studies and two imputation scenarios. In comparison conducted on the protein-coding genes, PMI attains the highest performance in inductive imputation whereas GAIN-GTEx outperforms the other methods in in-place imputation. Furthermore, our results indicate strong generalization on RNA-Seq data from 3 cancer types across varying levels of missingness. Our work can facilitate a cost-effective integration of large-scale RNA biorepositories into genomic studies of disease, with high applicability across diverse tissue types.

A significant seasonal variation in tuberculosis (TB) is observed in north India during 2006-2011, particularly in states like Himachal Pradesh, Haryana and Rajasthan. To quantify the seasonal variation, we measure average amplitude (peak to trough distance) across seasons in smear positive cases of TB and observe that it is maximum for Himachal Pradesh (40.01%) and minimum for Maharashtra (3.87%). In north India, smear positive cases peak in second quarter (April-June) and reach a trough in fourth quarter (October-December), however low seasonal variation is observed in southern region of the country. The significant correlations as 0.64 (p-value

Cellular network data traffic can be offload onto opportunistic networks. This paper proposes a Distance-based Opportunistic Publish/Subscribe (DOPS) content dissemination model, which is composed of three layers: application layer, decision-making layer and network layer. When a user wants new content, he/she subscribes on a subscribing server. Users having the contents decide whether to deliver the contents to the subscriber based on the distance information. If in the meantime a content owner has traveled further in the immediate past time than the distance between the owner and the subscriber, the content owner will send the content to the subscriber through opportunistic routing. Simulations provide an evaluation of the data traffic offloading efficiency of DOPS.

Advanced age is the major risk factor for idiopathic Parkinson's disease (PD), but to date the biological relationship between PD and ageing remains elusive. Here we describe the rationale and the design of the H2020 funded project "PROPAG-AGEING", whose aim is to characterize the contribution of the ageing process to PD development. We summarize current evidences that support the existence of a continuum between ageing and PD and justify the use of a Geroscience approach to study PD. We focus in particular on the role of inflammaging, the chronic, low-grade inflammation characteristic of elderly physiology, which can propagate and transmit both locally and systemically. We then describe PROPAG-AGEING design, which is based on the multi-omic characterization of peripheral samples from clinically characterized drug-naive and advanced PD, PD discordant twins, healthy controls and "super-controls", i.e. centenarians, who never showed clinical signs of motor disability, and their offspring. Omic results are then validated in a large number of samples, including in vitro models of dopaminergic neurons and healthy siblings of PD patients, who are at higher risk of developing PD, with the final aim of identifying the molecular perturbations that can deviate the trajectories of healthy ageing towards PD development.

Multi-Agent Reinforcement Learning (MARL) encompasses a powerful class of methodologies that have been applied in a wide range of fields. An effective way to further empower these methodologies is to develop libraries and tools that could expand their interpretability and explainability. In this work, we introduce MARLeME: a MARL model extraction library, designed to improve explainability of MARL systems by approximating them with symbolic models. Symbolic models offer a high degree of interpretability, well-defined properties, and verifiable behaviour. Consequently, they can be used to inspect and better understand the underlying MARL system and corresponding MARL agents, as well as to replace all/some of the agents that are particularly safety and security critical., Presented at the KR2ML workshop at the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada

While Deep Learning methods have been successfully applied to tackle a wide variety of prediction problems, their application has been mostly limited to data structured in a grid-like fashion. However, the study of the human brain "connectome" involves the representation of the brain as a graph with interacting nodes. In this paper, we extend the Graph Attention Network (GAT), a novel neural network (NN) architecture acting on the features of the nodes of a binary graph, to handle a set of graphs provided with node features and non-binary edge weights. We demonstrate the effectiveness of our architecture by training it multimodal data collected from a large homogeneous fMRI dataset (n=1003 individuals with multiple fMRI sessions per subject) made publicly available by the Human Connectome Project (HCP), demonstrating good performance and seamless integration of multimodal neuroimaging data. Our adaptation provides a powerful and flexible deep learning tool to integrate multimodal neuroimaging connectomics data in a predictive context.

Neurodegenerative diseases such as Alzheimer's and Parkinson's impact millions of people worldwide. Early diagnosis has proven to greatly increase the chances of slowing down the diseases' progression. Correct diagnosis often relies on the analysis of large amounts of patient data, and thus lends itself well to support from machine learning algorithms, which are able to learn from past diagnosis and see clearly through the complex interactions of a patient's symptoms and data. Unfortunately, many contemporary machine learning techniques fail to reveal details about how they reach their conclusions, a property considered fundamental when providing a diagnosis. Here we introduce our Personalisable Clinical Decision Support System (PECLIDES), an algorithmic process formulated to address this specific fault in diagnosis detection. PECLIDES provides a clear insight into the decision-making process leading to a diagnosis, making it a gray box model. Our algorithm enriches the fundamental work of Masheyekhi and Gras in data integration, personal medicine, usability, visualization, and interactivity. Our decision support system is an operation of translational medicine. It is based on random forests, is personalisable and allows a clear insight into the decision-making process. A well-structured rule set is created and every rule of the decision-making process can be observed by the user (physician). Furthermore, the user has an impact on the creation of the final rule set and the algorithm allows the comparison of different diseases as well as regional differences in the same disease. The algorithm is applicable to various decision problems. In this paper we will evaluate it on diagnosing neurological diseases and therefore refer to the algorithm as PECLIDES Neuro1.

The COVID-19 pandemic has led to unprecedented strain on intensive care unit (ICU) admission in parts of the world. Strategies to create surge ICU capacity require complex local and national service reconfiguration and reduction or cancellation of elective activity. These measures have an inevitable lag-time before additional capacity comes on-line. An accurate short-range forecast would be helpful in guiding such difficult, costly, and ethically challenging decisions.At the time this work began, cases in England were starting to increase. If this represents a true spread in disease then ICU demand could increase rapidly. Here we present a short-range forecast based on published real-time COVID-19 case data from the seven National Health Service (NHS) commissioning regions in England (East of England, London, Midlands, North East and Yorkshire, North West, South East and South West). We use a Monte Carlo approach to model the likely impact of current diagnoses on regional ICU capacity over a 14-day horizon under the assumption that the increase in cases represents the start of an exponential growth in infections. Our model is designed to be parsimonious and based on available epidemiological data from the literature at the moment.On the basis of the modelling assumptions made, ICU occupancy is likely to increase dramatically in the days following the time of modelling. If the current exponential growth continues, case numbers will be comparable to current ICU bed numbers within weeks. Despite variable growth in absolute patients, all commissioning regions are forecast to be heavily burdened under the assumptions used.Whilst, like any forecast model, there remain uncertainties both in terms of model specification and robust epidemiological data in this early prospective phase, it would seem that surge capacity will be required in the very near future. Our findings should be interpreted with caution, but we hope that our model will help policy decision makers with their preparations. The uncertainties in the data highlight the urgent need for ongoing real-time surveillance to allow forecasts to be constantly updated using high quality local patient-facing data as it emerges.

International initiatives such as the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC), Cancer Genome Atlas (TCGA), and the International Cancer Genome Consortium (ICGC) are collecting multiple data sets at different genome-scales with the aim to identify novel cancer bio-markers and predict patient survival. To analyse such data, several machine learning, bioinformatics and statistical methods have been applied, among them neural networks such as autoencoders. Although these models provide a good statistical learning framework to analyse multi-omic and/or clinical data, there is a distinct lack of work on how to integrate diverse patient data and identify the optimal design best suited to the available data. In this paper, we investigate several autoencoder architectures that integrate a variety of cancer patient data types (e.g., multi-omics and clinical data). We perform extensive analyses of these approaches and provide a clear methodological and computational framework for designing systems that enable clinicians to investigate cancer traits and translate the results into clinical applications. We demonstrate how these networks can be designed, built and, in particular, applied to tasks of integrative analyses of heterogeneous breast cancer data. The results show that these approaches yield relevant data representations that, in turn, lead to accurate and stable diagnosis.

The pressure of ever-increasing patient demand and budget restrictions make hospital bed management a daily challenge for clinical staff. Most critical is the efficient allocation of resource-heavy Intensive Care Unit (ICU) beds to the patients who need life support. Central to solving this problem is knowing for how long the current set of ICU patients are likely to stay in the unit. In this work, we propose a new deep learning model based on the combination of temporal convolution and pointwise (1x1) convolution, to solve the length of stay prediction task on the eICU and MIMIC-IV critical care datasets. The model - which we refer to as Temporal Pointwise Convolution (TPC) - is specifically designed to mitigate common challenges with Electronic Health Records, such as skewness, irregular sampling and missing data. In doing so, we have achieved significant performance benefits of 18-68% (metric and dataset dependent) over the commonly used Long-Short Term Memory (LSTM) network, and the multi-head self-attention network known as the Transformer. By adding mortality prediction as a side-task, we can improve performance further still, resulting in a mean absolute deviation of 1.55 days (eICU) and 2.28 days (MIMIC-IV) on predicting remaining length of stay., Comment: ACM CHIL 2021 Proceedings. arXiv admin note: substantial text overlap with arXiv:2006.16109

In recent years, the conceptualisation of the brain as a "connectome" as summary measures derived from graph theory analyses, has become increasingly popular. Still, such approaches are inherently limited by the need to condense and simplify temporal fMRI dynamics and architecture into a purely spatial representation. We formulate a novel architecture based on Geometric Deep Learning which is specifically tailored to the one-step integration of spatial relationship between nodes and single-node temporal dynamics. We compare different spatiotemporal modelling mechanisms and demonstrate the effectiveness of our architecture in a binary prediction task based on a large homogeneous fMRI dataset made publicly available by the Human Connectome Project (HCP). As the idea of e.g. a dynamical network connectivity is beginning to make its way into the more mainstream toolset which neuroscientists commonly employ with neuroimaging data, our model can contribute to laying the groundwork for explicitly incorporating spatiotemporal information into every association and prediction problem in neuroscience.

All perception is a construction of the brain from sensory input. Our first perceptions begin during gestation, making fetal brain development fundamental to how we experience a diverse world. Hallucinations are percepts without origin in physical reality that occur in health and disease. Despite longstanding research on the brain structures supporting hallucinations and on perinatal contributions to the pathophysiology of schizophrenia, what links these two distinct lines of research remains unclear. Sulcal patterns derived from structural magnetic resonance (MR) images can provide a proxy in adulthood for early brain development. We studied two independent datasets of patients with schizophrenia who underwent clinical assessment and 3T MR imaging from the United Kingdom and Shanghai, China (n = 181 combined) and 63 healthy controls from Shanghai. Participants were stratified into those with (n = 79 UK; n = 22 Shanghai) and without (n = 43 UK; n = 37 Shanghai) hallucinations from the PANSS P3 scores for hallucinatory behaviour. We quantified the length, depth, and asymmetry indices of the paracingulate and superior temporal sulci (PCS, STS), which have previously been associated with hallucinations in schizophrenia, and constructed cortical folding covariance matrices organized by large-scale functional networks. In both ethnic groups, we demonstrated a significantly shorter left PCS in patients with hallucinations compared to those without, and to healthy controls. Reduced PCS length and STS depth corresponded to focal deviations in their geometry and to significantly increased covariance within and between areas of the salience and auditory networks. The discovery of neurodevelopmental alterations contributing to hallucinations establishes testable models for these enigmatic, sometimes highly distressing, perceptions and provides mechanistic insight into the pathological consequences of prenatal origins.

Functional MRI (fMRI) attracts huge interest for the machine learning community nowadays. In this work we propose a novel data augmentation procedure through analysing the inherent noise in fMRI. We then use the novel augmented dataset for the classification of subjects by age and gender, showing a significant improvement in the accuracy performance of Recurrent Neural Networks. We test the new data augmentation procedure in the fMRI dataset belonging to one international consortium of neuroimaging data for healthy controls: the Human Connectome Projects (HCP).

High-throughput sequencing Chromosome Conformation Capture (Hi-C) allows the study of chromatin interactions and 3D chromosome folding on a larger scale. A graph-based multi-level representation of Hi-C data is essential for proper visualisation of the spatial pattern they represent, in particular for comparing different experiments or for re-mapping omics-data in a space-aware context. The size of the HiC data hampers the straightforward use of currently available graph visualisation tools and libraries. In this paper, we present the first version of NeoHiC, a user-friendly web application for the progressive graph visualisation of Hi-C data based on the use of the Neo4j graph database. The user could select the richness of the environment of the query gene by choosing among a large number of proximity and distance metrics.

We present here a novel measure called brain-heart crosstalks. The measure captured events of simultaneous increase of intracranial pressure (ICP) and heart rate (HR), and showed a relationship with mortality. We therefore propose in the present work an extension of the code, to allow for the implementation and insertion of the above measure into ICM+, a software for online bedside management and analysis of traumatic brain injury (TBI) patients.

Recent attempts at Super-Resolution for medical images used deep learning techniques such as Generative Adversarial Networks (GANs) to achieve perceptually realistic single image Super-Resolution. Yet, they are constrained by their inability to generalise to different scale factors. This involves high storage and energy costs as every integer scale factor involves a separate neural network. A recent paper has proposed a novel meta-learning technique that uses a Weight Prediction Network to enable Super-Resolution on arbitrary scale factors using only a single neural network. In this paper, we propose a new network that combines that technique with SRGAN, a state-of-the-art GAN-based architecture, to achieve arbitrary scale, high fidelity Super-Resolution for medical images. By using this network to perform arbitrary scale magnifications on images from the Multimodal Brain Tumor Segmentation Challenge (BraTS) dataset, we demonstrate that it is able to outperform traditional interpolation methods by up to 20\(\%\) on SSIM scores whilst retaining generalisability on brain MRI images. We show that performance across scales is not compromised, and that it is able to achieve competitive results with other state-of-the-art methods such as EDSR whilst being fifty times smaller than them. Combining efficiency, performance, and generalisability, this can hopefully become a new foundation for tackling Super-Resolution on medical images.

Mitochondrial-dysfunction is linked to various neurological diseases. To understand these complications we developed a quantitative framework to explore how mitochondrial-dysfunction influences the progression of Alzheimer’s, Parkin-son’s, Huntington’s, Amyotrophic Lateral Sclerosis and Cerebral Palsy. We sought insights from the gene profiles of mitochondrial and associated neurological disorders by constructing gene-disease networks. We also employed KEGG pathways and Gene Ontology to explore functional enrichment, and protein-protein interaction networks to identify the protein groups shared between these diseases. These identified potential biomarkers were verified using gold-benchmark databases. Our identified signature genes and pathways are useful to identify co-morbidity outcomes for the mitochondrial dysfunction.

This letter investigates the impact of noise on the functionality of channel switches in molecular communication networks. The channel switches considered in this letter are designed based on a set of biological cells that propagate frequency-encoded Ca2+ signals through gap junction channels. First, we develop a stochastic and generalized model of Ca2+ signaling considering three types of noise, such as internal noise, external noise, and gating noise of gap junction channels. Second, we develop a method based on spectral analysis to determine whether cells extract information from frequency-encoded Ca2+ signals. Third, we examine numerically whether channel switches propagate Ca2+ signals to selected cells in the presence of noise, and show how noise degrades the performance of channel switches.

Single image super-resolution (SISR) aims to obtain a high-resolution output from one low-resolution image. Currently, deep learning-based SISR approaches have been widely discussed in medical image processing, because of their potential to achieve high-quality, high spatial resolution images without the cost of additional scans. However, most existing methods are designed for scale-specific SR tasks and are unable to generalize over magnification scales. In this paper, we propose an approach for medical image arbitrary-scale super-resolution (MIASSR), in which we couple meta-learning with generative adversarial networks (GANs) to super-resolve medical images at any scale of magnification in [Formula: see text]. Compared to state-of-the-art SISR algorithms on single-modal magnetic resonance (MR) brain images (OASIS-brains) and multi-modal MR brain images (BraTS), MIASSR achieves comparable fidelity performance and the best perceptual quality with the smallest model size. We also employ transfer learning to enable MIASSR to tackle SR tasks of new medical modalities, such as cardiac MR images (ACDC) and chest computed tomography images (COVID-CT). The source code of our work is also public. Thus, MIASSR has the potential to become a new foundational pre-/post-processing step in clinical image analysis tasks such as reconstruction, image quality enhancement, and segmentation.

Background Tuberculosis (TB) is one of the main causes of mortality on the globe. Besides the full implementation of Revised National Tuberculosis Control Programme (RNTCP), TB continues to be a major public health problem in India. Methods In the present study, parameters of a TB model are estimated using Ensemble Kalman filter (EnKf) approach. Infection rate and fraction of smear positive cases of TB are estimated in context of India. Results and Conclusions Results reveal that the infection rate is highest in Manipur and the ratio of smear positive cases is highest in Pondicherry. The infection rate of TB in Manipur is found to be 2.57 per quarter for the period 2006–2011.