Addressing nurses' prolonged grief due to the COVID-19 pandemic.

ABSTRACT: The COVID-19 pandemic resulted in physical and emotional tolls on healthcare workers and caregivers, which have caused prolonged grief disorder and persistent complex bereavement disorder. Highlighting key learnings from healthcare workers' experiences during the pandemic, this article outlines self-care strategies to help nurses better prepare for future healthcare emergencies.

Helping children and adolescents who lost a caregiver during the COVID-19 pandemic.

ABSTRACT: Between March 2020 and June of 2021, 140,000 children under 18 in the US lost a caregiver. Due to this sudden loss, their lives have been drastically impacted. This article presents interventions for this population's unique and stressful emotional trauma.

Systemic delivery of antagomirs during blood-brain barrier disruption is disease-modifying in experimental epilepsy.

Oligonucleotide therapies offer precision treatments for a variety of neurological diseases, including epilepsy, but their deployment is hampered by the blood-brain barrier (BBB). Previous studies showed that intracerebroventricular injection of an antisense oligonucleotide (antagomir) targeting microRNA-134 (Ant-134) reduced evoked and spontaneous seizures in animal models of epilepsy. In this study, we used assays of serum protein and tracer extravasation to determine that BBB disruption occurring after status epilepticus in mice was sufficient to permit passage of systemically injected Ant-134 into the brain parenchyma. Intraperitoneal and intravenous injection of Ant-134 reached the hippocampus and blocked seizure-induced upregulation of miR-134. A single intraperitoneal injection of Ant-134 at 2 h after status epilepticus in mice resulted in potent suppression of spontaneous recurrent seizures, reaching a 99.5% reduction during recordings at 3 months. The duration of spontaneous seizures, when they occurred, was also reduced in Ant-134-treated mice. In vivo knockdown of LIM kinase-1 (Limk-1) increased seizure frequency in Ant-134-treated mice, implicating de-repression of Limk-1 in the antagomir mechanism. These studies indicate that systemic delivery of Ant-134 reaches the brain and produces long-lasting seizure-suppressive effects after systemic injection in mice when timed with BBB disruption and may be a clinically viable approach for this and other disease-modifying microRNA therapies.

SCLpred-MEM: Subcellular localization prediction of membrane proteins by deep N-to-1 convolutional neural networks.

The knowledge of the subcellular location of a protein is a valuable source of information in genomics, drug design, and various other theoretical and analytical perspectives of bioinformatics. Due to the expensive and time-consuming nature of experimental methods of protein subcellular location determination, various computational methods have been developed for subcellular localization prediction. We introduce "SCLpred-MEM," an ab initio protein subcellular localization predictor, powered by an ensemble of Deep N-to-1 Convolutional Neural Networks (N1-NN) trained and tested on strict redundancy reduced datasets. SCLpred-MEM is available as a web-server predicting query proteins into two classes, membrane and non-membrane proteins. SCLpred-MEM achieves a Matthews correlation coefficient of 0.52 on a strictly homology-reduced independent test set and 0.62 on a less strict homology reduced independent test set, surpassing or matching other state-of-the-art subcellular localization predictors.

SCLpred-EMS: subcellular localization prediction of endomembrane system and secretory pathway proteins by Deep N-to-1 Convolutional Neural Networks.

MOTIVATION: The subcellular location of a protein can provide useful information for protein function prediction and drug design. Experimentally determining the subcellular location of a protein is an expensive and time-consuming task. Therefore, various computer-based tools have been developed, mostly using machine learning algorithms, to predict the subcellular location of proteins. RESULTS: Here, we present a neural network-based algorithm for protein subcellular location prediction. We introduce SCLpred-EMS a subcellular localization predictor powered by an ensemble of Deep N-to-1 Convolutional Neural Networks. SCLpred-EMS predicts the subcellular location of a protein into two classes, the endomembrane system and secretory pathway versus all others, with a Matthews correlation coefficient of 0.75-0.86 outperforming the other state-of-the-art web servers we tested. AVAILABILITY AND IMPLEMENTATION: SCLpred-EMS is freely available for academic users at http://distilldeep.ucd.ie/SCLpred2/. CONTACT: catherine.mooney@ucd.ie.

Genome-wide microRNA profiling of plasma from three different animal models identifies biomarkers of temporal lobe epilepsy.

Epilepsy diagnosis is complex, requires a team of specialists and relies on in-depth patient and family history, MRI-imaging and EEG monitoring. There is therefore an unmet clinical need for a non-invasive, molecular-based, biomarker to either predict the development of epilepsy or diagnose a patient with epilepsy who may not have had a witnessed seizure. Recent studies have demonstrated a role for microRNAs in the pathogenesis of epilepsy. MicroRNAs are short non-coding RNA molecules which negatively regulate gene expression, exerting profound influence on target pathways and cellular processes. The presence of microRNAs in biofluids, ease of detection, resistance to degradation and functional role in epilepsy render them excellent candidate biomarkers. Here we performed the first multi-model, genome-wide profiling of plasma microRNAs during epileptogenesis and in chronic temporal lobe epilepsy animals. From video-EEG monitored rats and mice we serially sampled blood samples and identified a set of dysregulated microRNAs comprising increased miR-93-5p, miR-142-5p, miR-182-5p, miR-199a-3p and decreased miR-574-3p during one or both phases. Validation studies found miR-93-5p, miR-199a-3p and miR-574-3p were also dysregulated in plasma from patients with intractable temporal lobe epilepsy. Treatment of mice with common anti-epileptic drugs did not alter the expression levels of any of the five miRNAs identified, however administration of an anti-epileptogenic microRNA treatment prevented dysregulation of several of these miRNAs. The miRNAs were detected within the Argonuate2-RISC complex from both neurons and microglia indicating these miRNA biomarker candidates can likely be traced back to specific brain cell types. The current studies identify additional circulating microRNA biomarkers of experimental and human epilepsy which may support diagnosis of temporal lobe epilepsy via a quick, cost-effective rapid molecular-based test.

Obesity in children and adolescents: An overview.

Childhood obesity is an epidemic in the US. This article discusses the evolution, prevention, and associated physical and psychosocial consequences of and interventions for obesity in the pediatric population.

PaleAle 5.0: prediction of protein relative solvent accessibility by deep learning.

Predicting the three-dimensional structure of proteins is a long-standing challenge of computational biology, as the structure (or lack of a rigid structure) is well known to determine a protein's function. Predicting relative solvent accessibility (RSA) of amino acids within a protein is a significant step towards resolving the protein structure prediction challenge especially in cases in which structural information about a protein is not available by homology transfer. Today, arguably the core of the most powerful prediction methods for predicting RSA and other structural features of proteins is some form of deep learning, and all the state-of-the-art protein structure prediction tools rely on some machine learning algorithm. In this article we present a deep neural network architecture composed of stacks of bidirectional recurrent neural networks and convolutional layers which is capable of mining information from long-range interactions within a protein sequence and apply it to the prediction of protein RSA using a novel encoding method that we shall call "clipped". The final system we present, PaleAle 5.0, which is available as a public server, predicts RSA into two, three and four classes at an accuracy exceeding 80% in two classes, surpassing the performances of all the other predictors we have benchmarked.

EpimiRBase: a comprehensive database of microRNA-epilepsy associations.

UNLABELLED: MicroRNAs are short non-coding RNA which function to fine-tune protein levels in all cells. This is achieved mainly by sequence-specific binding to 3' untranslated regions of target mRNA. The result is post-transcriptional interference in gene expression which reduces protein levels either by promoting destabilisation of mRNA or translational repression. Research published since 2010 shows that microRNAs are important regulators of gene expression in epilepsy. A series of microRNA profiling studies in rodent and human tissue has revealed that epilepsy is associated with wide ranging changes to microRNA levels in the brain. These are thought to influence processes including cell death, inflammation and re-wiring of neuronal networks. MicroRNAs have also been identified in the blood after injury to the brain and therefore may serve as biomarkers of epilepsy. EpimiRBase is a manually curated database for researchers interested in the role of microRNAs in epilepsy. The fully searchable database includes information on up- and down-regulated microRNAs in the brain and blood, as well as functional studies, and covers both rodent models and human epilepsy. AVAILABILITY AND IMPLEMENTATION: EpimiRBase is available at http://www.epimirbase.eu CONTACT: catherinemooney@rcsi.ie.

Eosinophil peroxidase activates cells by HER2 receptor engagement and ß1-integrin clustering with downstream MAPK cell signaling.

Eosinophils account for 1-3% of peripheral blood leukocytes and accumulate at sites of allergic inflammation, where they play a pathogenic role. Studies have shown that treatment with mepolizumab (an anti-IL-5 monoclonal antibody) is beneficial to patients with severe eosinophilic asthma, however, the mechanism of precisely how eosinophils mediate these pathogenic effects is uncertain. Eosinophils contain several cationic granule proteins, including Eosinophil Peroxidase (EPO). The main significance of this work is the discovery of EPO as a novel ligand for the HER2 receptor. Following HER2 activation, EPO induces activation of FAK and subsequent activation of ß1-integrin, via inside-out signaling. This complex results in downstream activation of ERK1/2 and a sustained up regulation of both MUC4 and the HER2 receptor. These data identify a receptor for one of the eosinophil granule proteins and demonstrate a potential explanation of the proliferative effects of eosinophils.

PeptideLocator: prediction of bioactive peptides in protein sequences.

MOTIVATION: Peptides play important roles in signalling, regulation and immunity within an organism. Many have successfully been used as therapeutic products often mimicking naturally occurring peptides. Here we present PeptideLocator for the automated prediction of functional peptides in a protein sequence. RESULTS: We have trained a machine learning algorithm to predict bioactive peptides within protein sequences. PeptideLocator performs well on training data achieving an area under the curve of 0.92 when tested in 5-fold cross-validation on a set of 2202 redundancy reduced peptide containing protein sequences. It has predictive power when applied to antimicrobial peptides, cytokines, growth factors, peptide hormones, toxins, venoms and other peptides. It can be applied to refine the choice of experimental investigations in functional studies of proteins. AVAILABILITY AND IMPLEMENTATION: PeptideLocator is freely available for academic users at http://bioware.ucd.ie/.

CPPpred: prediction of cell penetrating peptides.

Cell penetrating peptides (CPPs) are attracting much attention as a means of overcoming the inherently poor cellular uptake of various bioactive molecules. Here, we introduce CPPpred, a web server for the prediction of CPPs using a N-to-1 neural network. The server takes one or more peptide sequences, between 5 and 30 amino acids in length, as input and returns a prediction of how likely each peptide is to be cell penetrating. CPPpred was developed with redundancy reduced training and test sets, offering an advantage over the only other currently available CPP prediction method.

Mutations in γ adducin are associated with inherited cerebral palsy.

OBJECTIVE: Cerebral palsy is estimated to affect nearly 1 in 500 children, and although prenatal and perinatal contributors have been well characterized, at least 20% of cases are believed to be inherited. Previous studies have identified mutations in the actin-capping protein KANK1 and the adaptor protein-4 complex in forms of inherited cerebral palsy, suggesting a role for components of the dynamic cytoskeleton in the genesis of the disease. METHODS: We studied a multiplex consanguineous Jordanian family by homozygosity mapping and exome sequencing, then used patient-derived fibroblasts to examine functional consequences of the mutation we identified in vitro. We subsequently studied the effects of adducin loss of function in Drosophila. RESULTS: We identified a homozygous c.1100G>A (p.G367D) mutation in ADD3, encoding gamma adducin in all affected members of the index family. Follow-up experiments in patient fibroblasts found that the p.G367D mutation, which occurs within the putative oligomerization critical region, impairs the ability of gamma adducin to associate with the alpha subunit. This mutation impairs the normal actin-capping function of adducin, leading to both abnormal proliferation and migration in cultured patient fibroblasts. Loss of function studies of the Drosophila adducin ortholog hts confirmed a critical role for adducin in locomotion. INTERPRETATION: Although likely a rare cause of cerebral palsy, our findings indicate a critical role for adducins in regulating the activity of the actin cytoskeleton, suggesting that impaired adducin function may lead to neuromotor impairment and further implicating abnormalities of the dynamic cytoskeleton as a pathogenic mechanism contributing to cerebral palsy.

SCL-Epred: a generalised de novo eukaryotic protein subcellular localisation predictor.

Knowledge of the subcellular location of a protein provides valuable information about its function, possible interaction with other proteins and drug targetability, among other things. The experimental determination of a protein's location in the cell is expensive, time consuming and open to human error. Fast and accurate predictors of subcellular location have an important role to play if the abundance of sequence data which is now available is to be fully exploited. In the post-genomic era, genomes in many diverse organisms are available. Many of these organisms are important in human and veterinary disease and fall outside of the well-studied plant, animal and fungi groups. We have developed a general eukaryotic subcellular localisation predictor (SCL-Epred) which predicts the location of eukaryotic proteins into three classes which are important, in particular, for determining the drug targetability of a protein-secreted proteins, membrane proteins and proteins that are neither secreted nor membrane. The algorithm powering SCL-Epred is a N-to-1 neural network and is trained on very large non-redundant sets of protein sequences. SCL-Epred performs well on training data achieving a Q of 86 % and a generalised correlation of 0.75 when tested in tenfold cross-validation on a set of 15,202 redundancy reduced protein sequences. The three class accuracy of SCL-Epred and LocTree2, and in particular a consensus predictor comprising both methods, surpasses that of other widely used predictors when benchmarked using a large redundancy reduced independent test set of 562 proteins. SCL-Epred is publicly available at http://distillf.ucd.ie/distill/ .

Transfer Learning-based Seizure Detection on Multiple Channels of Paediatric EEGs.

Epilepsy is a common neurological disease characterised by recurring seizures that affect up to 70 million people worldwide. During the first ten years of life, approximately one in every 150 children is diagnosed with epilepsy. EEG is an important tool for diagnosing seizures and other brain disorders. However, expert visual analysis of EEGs is time-consuming. In addition to reducing expert annotation time, the automatic seizure detection method is a powerful tool for assisting experts with the analysis of EEGs. Research on the automated detection of seizures in pediatric EEG has been limited. Deep learning algorithms are typically used in paediatric seizure detection methods; however, they are computationally expensive and take a long time to develop. This problem can be solved using transfer learning. In this study, we developed a transfer learning-based seizure detection method on multiple channels of paediatric EEGs. The publicly available CHB-MIT EEG dataset was used to build our method. The dataset was split into training (n=14), validation (n=4), and testing (n=6). Spectrograms generated from 10 s EEG signals with 5 s overlap were used as the input into three pre-trained transfer learning models (ResNet50, VGG16 and InceptionV3). We took care to separate the children into either the training or test set to ensure that the test set was independent. Based on the EEG test set, the method has 85.41% accuracy, 85.94% recall, and 85.49% precision. This method has the potential to assist researchers and clinicians in the automated analysis of seizures in paediatric EEGs.

A Machine Learning Approach for Sex and Age Classification of Paediatric EEGs.

Electroencephalography (EEG) is an important investigation of childhood seizures and other brain disorders. Expert visual analysis of EEGs can estimate subjects' age based on the presence of particular maturational features. The sex of a child, however, cannot be determined by visual inspection. In this study, we explored sex and age differences in the EEGs of 351 healthy male and female children aged between 6 and 10 years. We developed machine learning-based methods to classify the sex and age of healthy children from their EEGs. This preliminary study based on small EEG numbers demonstrates the potential for machine learning in helping with age determination in healthy children. This may be useful in distinguishing developmentally normal from developmentally delayed children. The model performed poorly for estimation of biological sex. However, we achieved 66.67% accuracy in age prediction allowing a 1 year error, on the test set.

Towards an explainable clinical decision support system for large-for-gestational-age births.

A myriad of maternal and neonatal complications can result from delivery of a large-for-gestational-age (LGA) infant. LGA birth rates have increased in many countries since the late 20th century, partially due to a rise in maternal body mass index, which is associated with LGA risk. The objective of the current study was to develop LGA prediction models for women with overweight and obesity for the purpose of clinical decision support in a clinical setting. Maternal characteristics, serum biomarkers and fetal anatomy scan measurements for 465 pregnant women with overweight and obesity before and at approximately 21 weeks gestation were obtained from the PEARS (Pregnancy Exercise and Nutrition with smart phone application support) study data. Random forest, support vector machine, adaptive boosting and extreme gradient boosting algorithms were applied with synthetic minority over-sampling technique to develop probabilistic prediction models. Two models were developed for use in different settings: a clinical setting for white women (AUC-ROC of 0.75); and a clinical setting for women of all ethnicity and regions (AUC-ROC of 0.57). Maternal age, mid upper arm circumference, white cell count at the first antenatal visit, fetal biometry and gestational age at fetal anatomy scan were found to be important predictors of LGA. Pobal HP deprivation index and fetal biometry centiles, which are population-specific, are also important. Moreover, we explained our models with Local Interpretable Model-agnostic Explanations (LIME) to improve explainability, which was proven effective by case studies. Our explainable models can effectively predict the probability of an LGA birth for women with overweight and obesity, and are anticipated to be useful to support clinical decision-making and for the development of early pregnancy intervention strategies to reduce pregnancy complications related to LGA.

Machine learning-based clinical decision support systems for pregnancy care: A systematic review.

BACKGROUND: Clinical decision support systems (CDSSs) can provide various functions and advantages to healthcare delivery. Quality healthcare during pregnancy and childbirth is of vital importance, and machine learning-based CDSSs have shown positive impact on pregnancy care. OBJECTIVE: This paper aims to investigate what has been done in CDSSs in the context of pregnancy care using machine learning, and what aspects require attention from future researchers. METHODS: We conducted a systematic review of existing literature following a structured process of literature search, paper selection and filtering, and data extraction and synthesis. RESULTS: 17 research papers were identified on the topic of CDSS development for different aspects of pregnancy care using various machine learning algorithms. We discovered an overall lack of explainability in the proposed models. We also observed a lack of experimentation, external validation and discussion around culture, ethnicity and race from the source data, with most studies using data from a single centre or country, and an overall lack of awareness of applicability and generalisability of the CDSSs regarding different populations. Finally, we found a gap between machine learning practices and CDSS implementation, and an overall lack of user testing. CONCLUSION: Machine learning-based CDSSs are still under-explored in the context of pregnancy care. Despite the open problems that remain, the few studies that tested a CDSS for pregnancy care reported positive effects, reinforcing the potential of such systems to improve clinical practice. We encourage future researchers to take into consideration the aspects we identified in order for their work to translate into clinical use.

Brain cell-specific origin of circulating microRNA biomarkers in experimental temporal lobe epilepsy.

The diagnosis of epilepsy is complex and challenging and would benefit from the availability of molecular biomarkers, ideally measurable in a biofluid such as blood. Experimental and human epilepsy are associated with altered brain and blood levels of various microRNAs (miRNAs). Evidence is lacking, however, as to whether any of the circulating pool of miRNAs originates from the brain. To explore the link between circulating miRNAs and the pathophysiology of epilepsy, we first sequenced argonaute 2 (Ago2)-bound miRNAs in plasma samples collected from mice subject to status epilepticus induced by intraamygdala microinjection of kainic acid. This identified time-dependent changes in plasma levels of miRNAs with known neuronal and microglial-cell origins. To explore whether the circulating miRNAs had originated from the brain, we generated mice expressing FLAG-Ago2 in neurons or microglia using tamoxifen-inducible Thy1 or Cx3cr1 promoters, respectively. FLAG immunoprecipitates from the plasma of these mice after seizures contained miRNAs, including let-7i-5p and miR-19b-3p. Taken together, these studies confirm that a portion of the circulating pool of miRNAs in experimental epilepsy originates from the brain, increasing support for miRNAs as mechanistic biomarkers of epilepsy.

SCLpred: protein subcellular localization prediction by N-to-1 neural networks.

SUMMARY: Knowledge of the subcellular location of a protein provides valuable information about its function and possible interaction with other proteins. In the post-genomic era, fast and accurate predictors of subcellular location are required if this abundance of sequence data is to be fully exploited. We have developed a subcellular localization predictor (SCLpred), which predicts the location of a protein into four classes for animals and fungi and five classes for plants (secreted, cytoplasm, nucleus, mitochondrion and chloroplast) using machine learning models trained on large non-redundant sets of protein sequences. The algorithm powering SCLpred is a novel Neural Network (N-to-1 Neural Network, or N1-NN) we have developed, which is capable of mapping whole sequences into single properties (a functional class, in this work) without resorting to predefined transformations, but rather by adaptively compressing the sequence into a hidden feature vector. We benchmark SCLpred against other publicly available predictors using two benchmarks including a new subset of Swiss-Prot Release 2010_06. We show that SCLpred surpasses the state of the art. The N1-NN algorithm is fully general and may be applied to a host of problems of similar shape, that is, in which a whole sequence needs to be mapped into a fixed-size array of properties, and the adaptive compression it operates may shed light on the space of protein sequences. AVAILABILITY: The predictive systems described in this article are publicly available as a web server at http://distill.ucd.ie/distill/. CONTACT: gianluca.pollastri@ucd.ie.