Quantitative evaluation model of variable diagnosis for chest X-ray images using deep learning

The purpose of this study is to demonstrate the use of a deep learning model in quantitatively evaluating clinical findings typically subject to uncertain evaluations by physicians, using binary test results based on routine protocols. A chest X-ray is the most commonly used diagnostic tool for the detection of a wide range of diseases and is generally performed as a part of regular medical checkups. However, when it comes to findings that can be classified as within the normal range but are not considered disease-related, the thresholds of physicians' findings can vary to some extent, therefore it is necessary to define a new evaluation method and quantify it. The implementation of such methods is difficult and expensive in terms of time and labor. In this study, a total of 83,005 chest X-ray images were used to diagnose the common findings of pleural thickening and scoliosis. A novel method for quantitatively evaluating the probability that a physician would judge the images to have these findings was established. The proposed method successfully quantified the variation in physicians' findings using a deep learning model trained only on binary annotation data. It was also demonstrated that the developed method could be applied to both transfer learning using convolutional neural networks for general image analysis and a newly learned deep learning model based on vector quantization variational autoencoders with high correlations ranging from 0.89 to 0.97.

Small animal PET with spontaneous inhalation of 15O-labelled oxygen gases: Longitudinal assessment of cerebral oxygen metabolism in a rat model of neonatal hypoxic-ischaemic encephalopathy

Perinatal hypoxic-ischaemic encephalopathy (HIE) is the leading cause of irreversible brain damage resulting in serious neurological dysfunction among neonates. We evaluated the feasibility of positron emission tomography (PET) methodology with 15O-labelled gases without intravenous or tracheal cannulation for assessing temporal changes in cerebral blood flow (CBF) and cerebral metabolic rate for oxygen (CMRO2) in a neonatal HIE rat model. Sequential PET scans with spontaneous inhalation of 15O-gases mixed with isoflurane were performed over 14 days after the hypoxic-ischaemic insult in HIE pups and age-matched controls. CBF and CMRO2 in the injured hemispheres of HIE pups remarkably decreased 2 days after the insult, gradually recovering over 14 days in line with their increase found in healthy controls according to their natural maturation process. The magnitude of hemispheric tissue loss histologically measured after the last PET scan was significantly correlated with the decreases in CBF and CMRO2.This fully non-invasive imaging strategy may be useful for monitoring damage progression in neonatal HIE and for evaluating potential therapeutic outcomes.

Application of a Two-Dimensional Mapping-Based Visualization Technique: Nutrient-Value-Based Food Grouping

Worldwide, several food-based dietary guidelines, with diverse food-grouping methods in various countries, have been developed to maintain and promote public health. However, standardized international food-grouping methods are scarce. In this study, we used two-dimensional mapping to classify foods based on their nutrient composition. The Standard Tables of Food Composition in Japan were used for mapping with a novel technique-t-distributed stochastic neighbor embedding-to visualize high-dimensional data. The mapping results showed that most foods formed food group-based clusters in the Standard Tables of Food Composition in Japan. However, the beverages did not form large clusters and demonstrated scattered distribution on the map. Green tea, black tea, and coffee are located within or near the vegetable cluster whereas cocoa is near the pulse cluster. These results were ensured by the k-nearest neighbors. Thus, beverages made from natural materials can be categorized based on their origin. Visualization of food composition could enable an enhanced comprehensive understanding of the nutrients in foods, which could lead to novel aspects of nutrient-value-based food classifications.

Ensemble Machine Learning Approaches Based on Molecular Descriptors and Graph Convolutional Networks for Predicting the Efflux Activities of MDR1 and BCRP Transporters

Multidrug resistance (MDR1) and breast cancer resistance protein (BCRP) play important roles in drug absorption and distribution. Computational prediction of substrates for both transporters can help reduce time in drug discovery. This study aimed to predict the efflux activity of MDR1 and BCRP using multiple machine learning approaches with molecular descriptors and graph convolutional networks (GCNs). In vitro efflux activity was determined using MDR1- and BCRP-expressing cells. Predictive performance was assessed using an in-house dataset with a chronological split and an external dataset. CatBoost and support vector regression showed the best predictive performance for MDR1 and BCRP efflux activities, respectively, of the 25 descriptor-based machine learning methods based on the coefficient of determination (R2). The single-task GCN showed a slightly lower performance than descriptor-based prediction in the in-house dataset. In both approaches, the percentage of compounds predicted within twofold of the observed values in the external dataset was lower than that in the in-house dataset. Multi-task GCN did not show any improvements, whereas multimodal GCN increased the predictive performance of BCRP efflux activity compared with single-task GCN. Furthermore, the ensemble approach of descriptor-based machine learning and GCN achieved the highest predictive performance with R2 values of 0.706 and 0.587 in MDR1 and BCRP, respectively, in time-split test sets. This result suggests that two different approaches to represent molecular structures complement each other in terms of molecular characteristics. Our study demonstrated that predictive models using advanced machine learning approaches are beneficial for identifying potential substrate liability of both MDR1 and BCRP.

Learning vector quantized representation for cancer subtypes identification

BACKGROUND AND OBJECTIVE

Defining and separating cancer subtypes is essential for facilitating personalized therapy modality and prognosis of patients. The definition of subtypes has been constantly recalibrated as a result of our deepened understanding. During this recalibration, researchers often rely on clustering of cancer data to provide an intuitive visual reference that could reveal the intrinsic characteristics of subtypes. The data being clustered are often omics data such as transcriptomics that have strong correlations to the underlying biological mechanism. However, while existing studies have shown promising results, they suffer from issues associated with omics data: sample scarcity and high dimensionality while they impose unrealistic assumptions to extract useful features from the data while avoiding overfitting to spurious correlations.

METHODS

This paper proposes to leverage a recent strong generative model, Vector-Quantized Variational AutoEncoder, to tackle the data issues and extract discrete representations that are crucial to the quality of subsequent clustering by retaining only information relevant to reconstructing the input.

RESULTS

Extensive experiments and medical analysis on multiple datasets comprising 10 distinct cancers demonstrate the proposed clustering results can significantly and robustly improve prognosis over prevalent subtyping systems.

CONCLUSION

Our proposal does not impose strict assumptions on data distribution; while, its latent features are better representations of the transcriptomic data in different cancer subtypes, capable of yielding superior clustering performance with any mainstream clustering method.

On QSAR-based cardiotoxicity modeling with the expressiveness-enhanced graph learning model and dual-threshold scheme

Introduction: Given the direct association with malignant ventricular arrhythmias, cardiotoxicity is a major concern in drug design. In the past decades, computational models based on the quantitative structure-activity relationship have been proposed to screen out cardiotoxic compounds and have shown promising results. The combination of molecular fingerprint and the machine learning model shows stable performance for a wide spectrum of problems; however, not long after the advent of the graph neural network (GNN) deep learning model and its variant (e.g., graph transformer), it has become the principal way of quantitative structure-activity relationship-based modeling for its high flexibility in feature extraction and decision rule generation. Despite all these progresses, the expressiveness (the ability of a program to identify non-isomorphic graph structures) of the GNN model is bounded by the WL isomorphism test, and a suitable thresholding scheme that relates directly to the sensitivity and credibility of a model is still an open question. Methods: In this research, we further improved the expressiveness of the GNN model by introducing the substructure-aware bias by the graph subgraph transformer network model. Moreover, to propose the most appropriate thresholding scheme, a comprehensive comparison of the thresholding schemes was conducted. Results: Based on these improvements, the best model attains performance with 90.4% precision, 90.4% recall, and 90.5% F1-score with a dual-threshold scheme (active: < 1 μ M ; non-active: > 30 μ M ). The improved pipeline (graph subgraph transformer network model and thresholding scheme) also shows its advantages in terms of the activity cliff problem and model interpretability.

On Finding Natural Antibiotics based on TCM Formulae

CONTEXT

Novel kinds of antibiotics are needed to combat the emergence of antibacterial resistance. Natural products (NPs) have shown potential as antibiotic candidates. Current experimental methods are not yet capable of exploring the massive, redundant, and noise-involved chemical space of NPs. In silico approaches are needed to select NPs as antibiotic candidates.

OBJECTIVE

This study screens out NPs with antibacterial efficacy guided by both TCM and modern medicine and constructed a dataset aiming to serve the new antibiotic design.

METHOD

A knowledge-based network is proposed in this study involving NPs, herbs, the concepts of TCM, and the treatment protocols (or etiologies) of infectious in modern medicine. Using this network, the NPs candidates are screened out and compose the dataset. Feature selection of machine learning approaches is conducted to evaluate the constructed dataset and statistically validate the im- portance of all NPs candidates for different antibiotics by a classification task.

RESULTS

The extensive experiments prove the constructed dataset reaches a convincing classification performance with a 0.9421 weighted accuracy, 0.9324 recall, and 0.9409 precision. The further visu- alizations of sample importance prove the comprehensive evaluation for model interpretation based on medical value considerations.

A training pipeline of an arrhythmia classifier for atrial fibrillation detection using Photoplethysmography signal

Photoplethysmography (PPG) signal is potentially suitable in atrial fibrillation (AF) detection for its convenience in use and similarity in physiological origin to electrocardiogram (ECG). There are a few preceding studies that have shown the possibility of using the peak-to-peak interval of the PPG signal (PPIp) in AF detection. However, as a generalized model, the accuracy of an AF detector should be pursued on the one hand; on the other hand, its generalizability should be paid attention to in view of the individual differences in PPG manifestation of even the same arrhythmia and the existence of sub-types. Moreover, a binary classifier for atrial fibrillation and normal sinus rhythm is not convincing enough for the similarity between AF and ectopic beats. In this study, we project the atrial fibrillation detection as a multiple-class classification and try to propose a training pipeline that is advantageous both to the accuracy and generalizability of the classifier by designing and determining the configurable options of the pipeline, in terms of input format, deep learning model (with hyperparameter optimization), and scheme of transfer learning. With a rigorous comparison of the possible combinations of the configurable components in the pipeline, we confirmed that first-order difference of heartbeat sequence as the input format, a 2-layer CNN-1-layer Transformer hybrid^R model as the learning model and the whole model fine-tuning as the implementing scheme of transfer learning is the best combination for the pipeline (F1 value: 0.80, overall accuracy: 0.87)^R.

Automated Sleep Staging via Parallel Frequency-Cut Attention

Stage-based sleep screening is a widely-used tool in both healthcare and neuroscientific research, as it allows for the accurate assessment of sleep patterns and stages. In this paper, we propose a novel framework that is based on authoritative guidance in sleep medicine and is designed to automatically capture the time-frequency characteristics of sleep electroencephalogram (EEG) signals in order to make staging decisions. Our framework consists of two main phases: a feature extraction process that partitions the input EEG spectrograms into a sequence of time-frequency patches, and a staging phase that searches for correlations between the extracted features and the defining characteristics of sleep stages. To model the staging phase, we utilize a Transformer model with an attention-based module, which allows for the extraction of global contextual relevance among time-frequency patches and the use of this relevance for staging decisions. The proposed method is validated on the large-scale Sleep Heart Health Study dataset and achieves new state-of-the-art results for the wake, N2, and N3 stages, with respective F1 scores of 0.93, 0.88, and 0.87 using only EEG signals. Our method also demonstrates high inter-rater reliability, with a kappa score of 0.80. Moreover, we provide visualizations of the correspondence between sleep staging decisions and features extracted by our method, which enhances the interpretability of the proposal. Overall, our work represents a significant contribution to the field of automated sleep staging and has important implications for both healthcare and neuroscience research.

Sleep Staging Framework with Physiologically Harmonized Sub-Networks

Sleep screening is an important tool for both healthcare and neuroscientific research. Automatic sleep scoring is an alternative to the time-consuming gold-standard manual scoring procedure. Recently there have seen promising results on automatic stage scoring by extracting spatio-temporal features via deep neural networks from electroencephalogram (EEG). However, such methods fail to consistently yield good performance due to a missing piece in data representation: the medical criterion of the sleep scoring task on top of EEG features. We argue that capturing stage-specific features that satisfy the criterion of sleep medicine is non-trivial for automatic sleep scoring. This paper considers two criteria: Transient stage marker and Overall profile of EEG features, then we propose a physiologically meaningful framework for sleep stage scoring via mixed deep neural networks. The framework consists of two sub-networks: feature extraction networks, constructed in consideration of the physiological characteristics of sleep, and an attention-based scoring decision network. Moreover, we quantize the framework for potential use under an IoT setting. For proof-of-concept, the performance of the proposed framework is demonstrated by introducing multiple sleep datasets with the largest comprising 42,560 h recorded from 5,793 subjects. From the experiment results, the proposed method achieves a competitive stage scoring performance, especially for Wake, N2, and N3, with higher F1 scores of 0.92, 0.86, and 0.88, respectively. Moreover, the feasibility analysis of framework quantization provides a potential for future implementation in the edge computing field and clinical settings.

Chemoinformatics-driven classification of Angiosperms using sulfur-containing compounds and machine learning algorithm

BACKGROUND

Phytochemicals or secondary metabolites are low molecular weight organic compounds with little function in plant growth and development. Nevertheless, the metabolite diversity govern not only the phenetics of an organism but may also inform the evolutionary pattern and adaptation of green plants to the changing environment. Plant chemoinformatics analyzes the chemical system of natural products using computational tools and robust mathematical algorithms. It has been a powerful approach for species-level differentiation and is widely employed for species classifications and reinforcement of previous classifications.

RESULTS

This study attempts to classify Angiosperms using plant sulfur-containing compound (SCC) or sulphated compound information. The SCC dataset of 692 plant species were collected from the comprehensive species-metabolite relationship family (KNApSAck) database. The structural similarity score of metabolite pairs under all possible combinations (plant species-metabolite) were determined and metabolite pairs with a Tanimoto coefficient value > 0.85 were selected for clustering using machine learning algorithm. Metabolite clustering showed association between the similar structural metabolite clusters and metabolite content among the plant species. Phylogenetic tree construction of Angiosperms displayed three major clades, of which, clade 1 and clade 2 represented the eudicots only, and clade 3, a mixture of both eudicots and monocots. The SCC-based construction of Angiosperm phylogeny is a subset of the existing monocot-dicot classification. The majority of eudicots present in clade 1 and 2 were represented by glucosinolate compounds. These clades with SCC may have been a mixture of ancestral species whilst the combinatorial presence of monocot-dicot in clade 3 suggests sulphated-chemical structure diversification in the event of adaptation during evolutionary change.

CONCLUSIONS

Sulphated chemoinformatics informs classification of Angiosperms via machine learning technique.

Prediction of Potential Natural Antibiotics Plants Based on Jamu Formula Using Random Forest Classifier

Jamu is the traditional Indonesian herbal medicine system that is considered to have many benefits such as serving as a cure for diseases or maintaining sound health. A Jamu medicine is generally made from a mixture of several herbs. Natural antibiotics can provide a way to handle the problem of antibiotic resistance. This research aims to discover the potential of herbal plants as natural antibiotic candidates based on a machine learning approach. Our input data consists of a list of herbal formulas with plants as their constituents. The target class corresponds to bacterial diseases that can be cured by herbal formulas. The best model has been observed by implementing the Random Forest (RF) algorithm. For 10-fold cross-validations, the maximum accuracy, recall, and precision are 91.10%, 91.10%, and 90.54% with standard deviations 1.05, 1.05, and 1.48, respectively, which imply that the model obtained is good and robust. This study has shown that 14 plants can be potentially used as natural antibiotic candidates. Furthermore, according to scientific journals, 10 of the 14 selected plants have direct or indirect antibacterial activity.

Cancer Subtyping via Embedded Unsupervised Learning on Transcriptomics Data

Cancer is one of the deadliest diseases worldwide. Accurate diagnosis and classification of cancer subtypes are indispensable for effective clinical treatment. Promising results on automatic cancer subtyping systems have been published recently with the emergence of various deep learning methods. However, such automatic systems often overfit the data due to the high dimensionality and scarcity. In this paper, we propose to investigate automatic subtyping from an unsupervised learning perspective by directly constructing the underlying data distribution itself, hence sufficient data can be generated to alleviate the issue of overfitting. Specifically, we bypass the strong Gaussianity assumption that typically exists but fails in the unsupervised learning subtyping literature due to small-sized samples by vector quantization. Our proposed method better captures the latent space features and models the cancer subtype manifestation on a molecular basis, as demonstrated by the extensive experimental results.

Very short-term beat-by-beat blood pressure variability in the supine position at rest correlates well with the nocturnal blood pressure variability assessed by ambulatory blood pressure monitoring

Blood pressure variability (BPV) is an important indicator in risk stratification for hypertension. Among the daily BPVs assessed using a 24-h ambulatory blood pressure (BP) monitor nocturnal systolic BPV has been suggested to predict cardiovascular risks. We hypothesized that very short-term BPV at rest would correlate with nocturnal BPV because of the shared autonomic BP regulatory system under no daily exertion. Thirty untreated normotensive and hypertensive adults underwent 30-min continuous beat-by-beat BP recordings in the supine position, followed by 24-h ambulatory blood pressure monitoring (ABPM). The relationship between very short-term BPV (standard deviation (SD), coefficient of variation (CV)) and daytime and nocturnal BPV (SD, CV, average real variability (ARV), and standardized ARV (CV-ARV)) was assessed with Pearson's correlation coefficients. Very short-term BPV correlated significantly with nocturnal BPV (ARV, r = 0.604, p < 0.001) but not with daytime BPV. These trends were more pronounced with the increasing data length of continuous beat-by-beat BP recording. Using a data segment from the last 10 min of a 30-min continuous beat-by-beat BP recording resulted in a stronger correlation between very short-term BPV and nocturnal BPV than using earlier segments. The findings of this study suggest that very short-term BPV in the supine position at rest may predict nocturnal BPV. Since the burden of ABPM for patients has hindered clinical dissemination, very short-term BPV has the potential to develop a novel index of BPV.

Evaluation of [18F]F-DPA PET for Detecting Microglial Activation in the Spinal Cord of a Rat Model of Neuropathic Pain

Purpose

Recent studies have linked activated spinal glia to neuropathic pain. Here, using a positron emission tomography (PET) scanner with high spatial resolution and sensitivity, we evaluated the feasibility and sensitivity of N,N-diethyl-2-(2-(4-([¹⁸F]fluoro)phenyl)-5,7-dimethylpyrazolo[1,5-a] pyrimidin-3-yl)acetamide ([¹⁸F]F-DPA) imaging for detecting spinal cord microglial activation after partial sciatic nerve ligation (PSNL) in rats.

Procedures

Neuropathic pain was induced in rats (n = 20) by PSNL, and pain sensation tests were conducted before surgery and 3 and 7 days post-injury. On day 7, in vivo PET imaging and ex vivo autoradiography were performed using [¹⁸F]F-DPA or [¹¹C]PK11195. Ex vivo biodistribution and PET imaging of the removed spinal cord were carried out with [¹⁸F]F-DPA. Sham-operated and PK11195-pretreated animals were also examined.

Results

Mechanical allodynia was confirmed in the PSNL rats from day 3 through day 7. Ex vivo autoradiography showed a higher lesion-to-background uptake with [¹⁸F]F-DPA compared with [¹¹C]PK11195. Ex vivo PET imaging of the removed spinal cord showed [¹⁸F]F-DPA accumulation in the inflammation site, which was immunohistochemically confirmed to coincide with microglia activation. Pretreatment with PK11195 eliminated the uptake. The SUV values of in vivo [¹⁸F]F-DPA and [¹¹C]PK11195 PET were not significantly increased in the lesion compared with the reference region, and were fivefold higher than the values obtained from the ex vivo data. Ex vivo biodistribution revealed a twofold higher [¹⁸F]F-DPA uptake in the vertebral body compared to that seen in the bone from the skull.

Conclusions

[¹⁸F]F-DPA aided visualization of the spinal cord inflammation site in PSNL rats on ex vivo autoradiography and was superior to [¹¹C]PK11195. In vivo [¹⁸F]F-DPA PET did not allow for visualization of tracer accumulation even using a high-spatial-resolution PET scanner. The main reason for this result was due to insufficient SUVs in the spinal cord region as compared with the background noise, in addition to a spillover from the vertebral body.

Classification of ischemia from myocardial polar maps in 15O-H2O cardiac perfusion imaging using a convolutional neural network

We implemented a two-dimensional convolutional neural network (CNN) for classification of polar maps extracted from Carimas (Turku PET Centre, Finland) software used for myocardial perfusion analysis. 138 polar maps from ¹⁵O–H₂O stress perfusion study in JPEG format from patients classified as ischemic or non-ischemic based on finding obstructive coronary artery disease (CAD) on invasive coronary artery angiography were used. The CNN was evaluated against the clinical interpretation. The classification accuracy was evaluated with: accuracy (ACC), area under the receiver operating characteristic curve (AUC), F1 score (F1S), sensitivity (SEN), specificity (SPE) and precision (PRE). The CNN had a median ACC of 0.8261, AUC of 0.8058, F1S of 0.7647, SEN of 0.6500, SPE of 0.9615 and PRE of 0.9286. In comparison, clinical interpretation had ACC of 0.8696, AUC of 0.8558, F1S of 0.8333, SEN of 0.7500, SPE of 0.9615 and PRE of 0.9375. The CNN classified only 2 cases differently than the clinical interpretation. The clinical interpretation and CNN had similar accuracy in classifying false positives and true negatives. Classification of ischemia is feasible in ¹⁵O–H₂O stress perfusion imaging using JPEG polar maps alone with a custom CNN and may be useful for the detection of obstructive CAD.

Antibacterial Activity Prediction of Plant Secondary Metabolites Based on a Combined Approach of Graph Clustering and Deep Neural Network

The plants produce numerous types of secondary metabolites which have pharmacological importance in drug development for different diseases. Computational methods widely use the fingerprints of the metabolites to understand different properties and similarities among metabolites and for the prediction of chemical reactions etc. In this work, we developed three different deep neural network models (DNN) to predict the antibacterial property of plant metabolites. We developed the first DNN model using the fingerprint set of metabolites as features. In the second DNN model, we searched the similarities among fingerprints using correlation and used one representative feature from each group of highly correlated fingerprints. In the third model, the fingerprints of metabolites were used to find structurally similar chemical compound clusters. Form each cluster a representative metabolite is selected and made part of the training dataset. The second model reduced the number of features where the third model achieved better classification results for test data. In both cases, we applied the simple graph clustering method to cluster the corresponding network. The correlation‐based DNN model reduced some features while retaining an almost similar performance compared to the first DNN model. The third model improves classification results for test data by capturing wider variance within training data using graph clustering method. This third model is somewhat novel approach and can be applied to build DNN models for other purposes.

Recent Trends in Computational Biomedical Research

Recent advances in information technology have brought forth a paradigm shift in science, especially in the biology and medical fields [...].

Discussion of Cuffless Blood Pressure Prediction Using Plethysmograph Based on a Longitudinal Experiment: Is the Individual Model Necessary?

Using the Plethysmograph (PPG) signal to estimate blood pressure (BP) is attractive given the convenience and possibility of continuous measurement. However, due to the personal differences and the insufficiency of data, the dilemma between the accuracy for a small dataset and the robustness as a general method remains. To this end, we scrutinized the whole pipeline from the feature selection to regression model construction based on a one-month experiment with 11 subjects. By constructing the explanatory features consisting of five general PPG waveform features that do not require the identification of dicrotic notch and diastolic peak and the heart rate, three regression models, which are partial least square, local weighted partial least square, and Gaussian Process model, were built to reflect the underlying assumption about the nature of the fitting problem. By comparing the regression models, it can be confirmed that an individual Gaussian Process model attains the best results with 5.1 mmHg and 4.6 mmHg mean absolute error for SBP and DBP and 6.2 mmHg and 5.4 mmHg standard deviation for SBP and DBP. Moreover, the results of the individual models are significantly better than the generalized model built with the data of all subjects.

Exploration and characterization of chemical stimulators to maximize the wax ester production by Euglena gracilis

Euglena gracilis, a phototrophic protist, is a valuable biomass producer that is often employed in sustainable development efforts. E. gracilis accumulates wax esters as byproducts during anaerobic ATP production via the reductive tricarboxylic acid cycle, utilizing the storage carbohydrate β-1,3-glucan paramylon as the carbon source. Here, we report a library screening for chemical stimulators that accelerate both wax ester production and paramylon consumption. Among the 115 compounds tested, we identified nine compounds that increased wax ester production by more than 2.0-fold relative to the solvent control. In the presence of these nine compounds, the paramylon content decreased compared with the control experiment, and the residual paramylon content varied between 7% and 26% of the initial level. The most active compound, 1,4-diaminoanthracene-9,10-dione (OATQ008), stimulated wax ester production up to 2.7-fold within 24 h, and 93% of the cellular paramylon was consumed. In terms of the structural features of the chemical stimulators, we discuss the potential target sites to stimulate wax ester production in mitochondria under anaerobic conditions.

Evaluating cepharanthine analogues as natural drugs against SARS-CoV-2

Cepharanthine (CEP) is a natural biscoclaurine alkaloid of plant origin and was recently demonstrated to have anti‐severe acute respiratory syndrome coronavirus 2 (anti‐SARS‐CoV‐2) activity. In this study, we evaluated whether natural analogues of CEP may act as potential anti‐coronavirus disease 2019 drugs. A total of 24 compounds resembling CEP were extracted from the KNApSAcK database, and their binding affinities to target proteins, including the spike protein and main protease of SARS‐CoV‐2, NPC1 and TPC2 in humans, were predicted via molecular docking simulations. Selected analogues were further evaluated by a cell‐based SARS‐CoV‐2 infection assay. In addition, the efficacies of CEP and its analogue tetrandrine were assessed. A comparison of the docking conformations of these compounds suggested that the diphenyl ester moiety of the molecules was a putative pharmacophore of the CEP analogues.

Evaluation of intercellular lipid lamellae in the stratum corneum by polarized microscopy

BACKGROUND

Intercellular lipids contain a lamellar structure that glows in polarized images. It could be expected that the intercellular lipid content be estimated from the luminance values calculated from polarized images of stratum corneum strips. Therefore, we attempted to develop a method for simple and rapid evaluation of the intercellular lipid content through a procedure. Herein, we demonstrated a relationship between the luminance value and the amount of ceramides, one of the main components of intercellular lipids.

MATERIALS AND METHODS

The stratum corneum was collected from the forearm using slides with a pure rubber-based adhesive, which did not produce unnecessary luminescence under polarizing conditions. Images were analyzed using luminance indices. The positive secondary ion peak images were obtained using the time of flight-secondary ion mass spectrometry; the polarized and brightfield images were obtained using a polarized microscope. The ceramide and protein amount was measured by high-performance liquid chromatography and bicinchoninic acid protein assay after microscope imaging. Images and quantitative values were used to construct evaluation models based on a convolutional neural network (CNN).

RESULTS

There was a correlation between the highlighted areas of the polarized image to overlap with the area where ceramide-derived peak was detected. Evaluation of the CNN-based model of the polarized images predicted the amount of ceramides per unit of stratum corneum.

CONCLUSION

The method proposed in the study enabled a large number of specimens to provide a simple, rapid, and efficient evaluation of the intercellular lipid content.

Feasibility Analysis of Symbolic Representation for Single-Channel EEG-Based Sleep Stages

Sleep screening based on the construction of sleep stages is one of the major tool for the assessment of sleep quality and early detection of sleep-related disorders. Due to the inherent variability such as inter-users anatomical variability and the inter-systems differences, representation learning of sleep stages in order to obtain the stable and reliable characteristics is runoff for downstream tasks in sleep science. In this paper, we investigated feasibility of the EEG-based symbolic representation for sleep stages. By combining the Latent Dirichlet Allocation topic model and comparing with different feature extraction methods, the work proved the feasibility of multi-topics representation for sleep stages and physiological signals.

A Real-Time Portable IoT System for Telework Tracking

Telework has become a universal working style under the background of COVID-19. With the increased time of working at home, problems, such as lack of physical activities and prolonged sedentary behavior become more prominent. In this situation, a self-managing working pattern regulation may be the most practical way to maintain worker's well-being. To this end, this paper validated the idea of using an Internet of Things (IoT) system (a smartphone and the accompanying smartwatch) to monitor the working status in real-time so as to record the working pattern and nudge the user to have a behavior change. By using the accelerometer and gyroscope enclosed in the smartwatch worn on the right wrist, nine-channel data streams of the two sensors were sent to the paired smartphone for data preprocessing, and action recognition in real time. By considering the cooperativity and orthogonality of the data streams, a shallow convolutional neural network (CNN) model was constructed to recognize the working status from a common working routine. As preliminary research, the results of the CNN model show accurate performance [5-fold cross-validation: 0.97 recall and 0.98 precision; leave-one-out validation: 0.95 recall and 0.94 precision; (support vector machine (SVM): 0.89 recall and 0.90 precision; random forest: 0.95 recall and 0.93 precision)] for the recognition of working status, suggesting the feasibility of this fully online method. Although further validation in a more realistic working scenario should be conducted for this method, this proof-of-concept study clarifies the prospect of a user-friendly online working tracking system. With a tailored working pattern guidance, this method is expected to contribute to the workers' wellness not only during the COVID-19 pandemic but also take effect in the post-COVID-19 era.

Cheminformatics modeling of the correlation between Bupleurum Root-formula medicines and Excess and Deficiency pattern in the diagnostic criteria of Sho in Kampo (traditional Japanese medicine) by non-targeted direct infusion mass spectrometry with machine learning

Kampo is a form of traditional Japanese medicine, and its therapeutic strategy has been validated empirically over millennia, mainly in Asia. Kampo therapy aims to holistically prevent and treat disease based on the specific diagnosis Sho (in Japanese), in contrast with modern medical treatment which focuses on a patient's affected parts and local conditions. The medicines formulated using crude drugs derived from natural sources (Kampo formulas) are prescribed for patients according to their specific Sho, and thus the Kampo medication system is very complex. However, our previous study strongly suggested that Kampo medication theory could be explained by chemometrics and informatic approaches [Okada et al. in J Nat Med 70:107-114, 2016]. Here, we studied a group of seven formulas with Bupleurum Root and Scutellaria Root as the principal crude drugs. First, decoctions of the formulas were prepared and their supernatants were analyzed by non-targeted direct infusion mass spectrometry (MS) and principal component analysis, which is a type of unsupervised machine learning. Next, supervised machine learning was used to perform partial least squares modeling of the MS data matrix trained on the patients' constitution of Excess, Deficiency, or Medium between these two states (EDM) in Sho. The results showed that the correlation between the chemical fingerprints obtained by MS analysis and EDM could be modeled well using this approach. This cheminformatics modeling approach successfully interpreted part of the complex Kampo medication system studied using the fingerprints of formulas obtained by MS analysis and was consistent with the predicted Sho.

Current status of structure-based drug repurposing against COVID-19 by targeting SARS-CoV-2 proteins

More than one and half years have passed, as of August 2021, since the COVID-19 caused by the novel coronavirus named SARS-CoV-2 emerged in 2019. While the recent success of vaccine developments likely reduces the severe cases, there is still a strong requirement of safety and effective therapeutic drugs for overcoming the unprecedented situation. Here we review the recent progress and the status of the drug discovery against COVID-19 with emphasizing a structure-based perspective. Structural data regarding the SARS-CoV-2 proteome has been rapidly accumulated in the Protein Data Bank, and up to 68% of the total amino acid residues encoded in the genome were covered by the structural data. Despite a global effort of in silico and in vitro screenings for drug repurposing, there is only a limited number of drugs had been successfully authorized by drug regulation organizations. Although many approved drugs and natural compounds, which exhibited antiviral activity in vitro, were considered potential drugs against COVID-19, a further multidisciplinary investigation is required for understanding the mechanisms underlying the antiviral effects of the drugs.

Potential Arabidopsis thaliana glucosinolate genes identified from the co-expression modules using graph clustering approach

Background

Glucosinolates (GSLs) are plant secondary metabolites that contain nitrogen-containing compounds. They are important in the plant defense system and known to provide protection against cancer in humans. Currently, increasing the amount of data generated from various omics technologies serves as a hotspot for new gene discovery. However, sometimes sequence similarity searching approach is not sufficiently effective to find these genes; hence, we adapted a network clustering approach to search for potential GSLs genes from the Arabidopsis thaliana co-expression dataset.

Methods

We used known GSL genes to construct a comprehensive GSL co-expression network. This network was analyzed with the DPClusOST algorithm using a density of 0.5. 0.6. 0.7, 0.8, and 0.9. Generating clusters were evaluated using Fisher’s exact test to identify GSL gene co-expression clusters. A significance score (SScore) was calculated for each gene based on the generated p-value of Fisher’s exact test. SScore was used to perform a receiver operating characteristic (ROC) study to classify possible GSL genes using the ROCR package. ROCR was used in determining the AUC that measured the suitable density value of the cluster for further analysis. Finally, pathway enrichment analysis was conducted using ClueGO to identify significant pathways associated with the GSL clusters.

Results

The density value of 0.8 showed the highest area under the curve (AUC) leading to the selection of thirteen potential GSL genes from the top six significant clusters that include IMDH3, MVP1, T19K24.17, MRSA2, SIR, ASP4, MTO1, At1g21440, HMT3, At3g47420, PS1, SAL1, and At3g14220. A total of Four potential genes (MTO1, SIR, SAL1, and IMDH3) were identified from the pathway enrichment analysis on the significant clusters. These genes are directly related to GSL-associated pathways such as sulfur metabolism and valine, leucine, and isoleucine biosynthesis. This approach demonstrates the ability of the network clustering approach in identifying potential GSL genes which cannot be found from the standard similarity search.

Identification of Targeted Proteins by Jamu Formulas for Different Efficacies Using Machine Learning Approach

BACKGROUND

We performed in silico prediction of the interactions between compounds of Jamu herbs and human proteins by utilizing data-intensive science and machine learning methods. Verifying the proteins that are targeted by compounds of natural herbs will be helpful to select natural herb-based drug candidates.

METHODS

Initially, data related to compounds, target proteins, and interactions between them were collected from open access databases. Compounds are represented by molecular fingerprints, whereas amino acid sequences are represented by numerical protein descriptors. Then, prediction models that predict the interactions between compounds and target proteins were constructed using support vector machine and random forest.

RESULTS

A random forest model constructed based on MACCS fingerprint and amino acid composition obtained the highest accuracy. We used the best model to predict target proteins for 94 important Jamu compounds and assessed the results by supporting evidence from published literature and other sources. There are 27 compounds that can be validated by professional doctors, and those compounds belong to seven efficacy groups.

CONCLUSION

By comparing the efficacy of predicted compounds and the relations of the targeted proteins with diseases, we found that some compounds might be considered as drug candidates.

A system biology approach based on metabolic biomarkers and protein-protein interactions for identifying pathways underlying schizophrenia and bipolar disorder

Mental disorders (MDs), including schizophrenia (SCZ) and bipolar disorder (BD), have attracted special attention from scientists due to their high prevalence and significantly debilitating clinical features. The diagnosis of MDs is still essentially based on clinical interviews, and intensive efforts to introduce biochemical based diagnostic methods have faced several difficulties for implementation in clinics, due to the complexity and still limited knowledge in MDs. In this context, aiming for improving the knowledge in etiology and pathophysiology, many authors have reported several alterations in metabolites in MDs and other brain diseases. After potentially fishing all metabolite biomarkers reported up to now for SCZ and BD, we investigated here the proteins related to these metabolites in order to construct a protein-protein interaction (PPI) network associated with these diseases. We determined the statistically significant clusters in this PPI network and, based on these clusters, we identified 28 significant pathways for SCZ and BDs that essentially compose three groups representing three major systems, namely stress response, energy and neuron systems. By characterizing new pathways with potential to innovate the diagnosis and treatment of psychiatric diseases, the present data may also contribute to the proposal of new intervention for the treatment of still unmet aspects in MDs.

The feasibility of predicting impending malignant ventricular arrhythmias by using nonlinear features of short heartbeat intervals

BACKGROUND AND OBJECTIVE

Malignant ventricular arrhythmias (MAs) occur unpredictably and lead to emergencies. A new approach that uses a timely tracking device e.g., photoplethysmogram (PPG) solely to predict MAs would be irreplaceably valuable and it is natural to expect the approach can predict the occurrence as early as possible.

METHOD

We assumed that with an appropriate metric based on signal complexity, the heartbeat interval time series (HbIs) can be used to manifest the intrinsic characteristics of the period immediately precedes the MAs (preMAs). The approach first characterizes the patterns of preMAs by a new complexity metric (the refined composite multi-scale entropy). The MAs detector is then constructed by checking the discriminability of the MAs against the sinus rhythm and other prevalent arrhythmias (atrial fibrillation and premature ventricular contraction) of three machine-learning models (SVM, Random Forest, and XGboost).

RESULTS

Two specifications are of interest: the length of the HbIs needed to delineate the preMAs patterns sufficiently (l_spec) and how long before the occurrence of MAs will the HbIs manifest specific patterns that are distinct enough to predict the impending MAs (t_spec). Our experimental results confirmed the best performance came from a Random-Forest model with an average precision of 99.99% and recall of 88.98% using a HbIs of 800 heartbeats (the l_spec), 108 seconds (the t_spec) before the occurrence of MAs.

CONCLUSION

By experimental validation of the unique pattern of the preMAs in HbIs and using it in the machine learning model, we showed the high possibility of MAs prediction in a broader circumstance, which may cover daily healthcare using the alternative sensor in HbIs monitoring. Therefore, this research is theoretically and practically significant in cardiac arrest prevention.

Kinematics approach with neural networks for early detection of sepsis (KANNEDS)

BACKGROUND

Sepsis is a severe illness that affects millions of people worldwide, and its early detection is critical for effective treatment outcomes. In recent years, researchers have used models to classify positive patients or identify the probability for sepsis using vital signs and other time-series variables as input.

METHODS

In our study, we analyzed patients' conditions by their kinematics position, velocity, and acceleration, in a six-dimensional space defined by six vital signs. The patient is affected by the disease after a period if the position gets "near" to a calculated sepsis position in space. We imputed these kinematics features as explanatory variables of long short-term memory (LSTM), convolutional neural network (CNN) and linear neural network (LNN) and compared the prediction accuracies with only the vital signs as input. The dataset used contained information of approximately 4800 patients, each with 48 hourly registers.

RESULTS

We demonstrated that the kinematics features models had an improved performance compared with vital signs models. The kinematics features model of LSTM achieved the best accuracy, 0.803, which was nine points higher than the vital signs model. Although with lesser accuracies, the kinematics features models of the CNN and LNN showed better performances than vital signs models.

CONCLUSION

Applying our novel approach for early detection of sepsis using neural networks will prove to be an invaluable, more accurate method than considering only simple vital signs as input variables. We expect that other researchers with similar objectives can use the model presented in this innovative approach to improve their results.

Potential anti-COVID-19 agents, cepharanthine and nelfinavir, and their usage for combination treatment

Antiviral treatments targeting the coronavirus disease 2019 are urgently required. We screened a panel of already approved drugs in a cell culture model of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and identified two new agents having higher antiviral potentials than the drug candidates such as remdesivir and chroloquine in VeroE6/TMPRSS2 cells: the anti-inflammatory drug cepharanthine and human immunodeficiency virus protease inhibitor nelfinavir. Cepharanthine inhibited SARS-CoV-2 entry through the blocking of viral binding to target cells, while nelfinavir suppressed viral replication partly by protease inhibition. Consistent with their different modes of action, synergistic effect of this combined treatment to limit SARS-CoV-2 proliferation was highlighted. Mathematical modeling in vitro antiviral activity coupled with the calculated total drug concentrations in the lung predicts that nelfinavir will shorten the period until viral clearance by 4.9 days and the combining cepharanthine/nelfinavir enhanced their predicted efficacy. These results warrant further evaluation of the potential anti-SARS-CoV-2 activity of cepharanthine and nelfinavir.

Potential anti-COVID-19 agents, cepharanthine and nelfinavir, and their usage for combination treatment

Antiviral treatments targeting the coronavirus disease 2019 are urgently required. We screened a panel of already approved drugs in a cell culture model of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and identified two new agents having higher antiviral potentials than the drug candidates such as remdesivir and chroloquine in VeroE6/TMPRSS2 cells: the anti-inflammatory drug cepharanthine and human immunodeficiency virus protease inhibitor nelfinavir. Cepharanthine inhibited SARS-CoV-2 entry through the blocking of viral binding to target cells, while nelfinavir suppressed viral replication partly by protease inhibition. Consistent with their different modes of action, synergistic effect of this combined treatment to limit SARS-CoV-2 proliferation was highlighted. Mathematical modeling in vitro antiviral activity coupled with the calculated total drug concentrations in the lung predicts that nelfinavir will shorten the period until viral clearance by 4.9 days and the combining cepharanthine/nelfinavir enhanced their predicted efficacy. These results warrant further evaluation of the potential anti-SARS-CoV-2 activity of cepharanthine and nelfinavir.

Aging steepens the slope of power spectrum density of 30-minute continuous blood pressure recording in healthy human subjects

BACKGROUND

The increase of blood pressure (BP) variability (BPV) is recognized as an important additional cardiovascular risk factor in both normotensive subjects and hypertensive patients. Aging-induced atherosclerosis and autonomic dysfunction impair the baroreflex and, in turn, augment 24-hour BPV. In small and large animal experiments, impaired baroreflex steepens the slope of the power spectrum density (PSD) of continuous BP in the frequency range of 0.01 to 0.1 Hz. Although the repeated oscillometric BP recording over 24 hours or longer is a prerequisite to quantify BPV in humans, how the very short-term continuous BP recording reflects BPV remains unknown. This study aimed to evaluate the impact of aging on the very short-term (30-min) BPV in healthy human subjects by frequency analysis.

METHODS

We recorded continuous BP tonometrically for 30 min in 56 healthy subjects aged between 28 and 85 years. Considering the frequency-dependence of the baroreflex dynamic function, we estimated the PSD of BP in the frequency range of 0.01 to 0.1 Hz, and compared the characteristics of PSD among four age groups (26-40, 41-55, 56-70 and 71-85 years).

RESULTS

Aging did not significantly alter mean and standard deviation (SD) of BP among four age groups. PSD was nearly flat around 0.01 Hz and decreased gradually as the frequency increased. The slope of PSD between 0.01 and 0.1 Hz was steeper in older subjects (71 years or older) than in younger subjects (55 years or younger) (p < 0.05).

CONCLUSIONS

Aging steepened the slope of PSD of BP between 0.01 and 0.1 Hz. This phenomenon may partly be related to the deterioration of the baroreflex in older subjects. Our proposed method to evaluate very short-term continuous BP recordings may contribute to the stratification of BPV.

Development of a biomarker database toward performing disease classification and finding disease interrelations

A biomarker is a measurable indicator of a disease or abnormal state of a body that plays an important role in disease diagnosis, prognosis and treatment. The biomarker has become a significant topic due to its versatile usage in the medical field and in rapid detection of the presence or severity of some diseases. The volume of biomarker data is rapidly increasing and the identified data are scattered. To provide comprehensive information, the explosively growing data need to be recorded in a single platform. There is no open-source freely available comprehensive online biomarker database. To fulfill this purpose, we have developed a human biomarker database as part of the KNApSAcK family databases which contain a vast quantity of information on the relationships between biomarkers and diseases. We have classified the diseases into 18 disease classes, mostly according to the National Center for Biotechnology Information definitions. Apart from this database development, we also have performed disease classification by separately using protein and metabolite biomarkers based on the network clustering algorithm DPClusO and hierarchical clustering. Finally, we reached a conclusion about the relationships among the disease classes. The human biomarker database can be accessed online and the inter-disease relationships may be helpful in understanding the molecular mechanisms of diseases. To our knowledge, this is one of the first approaches to classify diseases based on biomarkers. Database URL:  http://www.knapsackfamily.com/Biomarker/top.php.

Embedding of Molecular Structure Using Molecular Hypergraph Variational Autoencoder with Metric Learning

Deep learning approaches are widely used to search molecular structures for a candidate drug/material. The basic approach in drug/material candidate structure discovery is to embed a relationship that holds between a molecular structure and the physical property into a low-dimensional vector space (chemical space) and search for a candidate molecular structure in that space based on a desired physical property value. Deep learning simplifies the structure search by efficiently modeling the structure of the chemical space with greater detail and lower dimensions than the original input space. In our research, we propose an effective method for molecular embedding learning that combines variational autoencoders (VAEs) and metric learning using any physical property. Our method enables molecular structures and physical properties to be embedded locally and continuously into VAEs' latent space while maintaining the consistency of the relationship between the structural features and the physical properties of molecules to yield better predictions.

Examination of the regression model to quantify the degree of low back pain and lower limb symptoms in patients with lumbar disc herniation by the Japanese Orthopaedic Association Back Pain Evaluation Questionnaire (JOABPEQ)

The Japanese Orthopedic Association Back Pain Evaluation Questionnaire (JOABPEQ) was created to evaluate specific treatment outcomes in terms of physical functioning, social ability, and mental health in patients with back pain-related diseases. In this study, we investigated whether the JOABPEQ could be used to construct a regression model to quantify low back pain and lower limb symptoms in patients with lumbar disc herniation (LDH). We reviewed 114 patients with LDH scheduled to undergo surgery at our hospital. We measured the degrees of 1) lower back pain, 2) lower limb pain, and 3) lower limb numbness using the visual analog scale before the surgery. All answers and physical function data were subjected to partial least squares regression analysis. The degrees of lower back and lower limb pain could be used as a regression model from the JOABPEQ and had a significant causal relationship with them. However, the degree of lower limb numbness could not be used for the same. Based on our results, the questions of the JOABPEQ can be used to multilaterally understand the degree of lower back pain and lower limb pain in patients with LDH. However, the degree of lower limb numbness has no causal relationship, so actual measurement is essential.

BiClusO: A Novel Biclustering Approach and Its Application to Species-VOC Relational Data

In this paper, we propose a novel biclustering approach called BiClusO. Biclustering can be applied to various types of bipartite data such as gene-condition or gene-disease relations. For example, we applied BiClusO to bipartite relations between species and volatile organic compounds (VOCs). VOCs, which are emitted by different species, have huge environmental and ecological impacts. The biosynthesis of VOCs depends on different metabolic pathways which can be used to categorize the species. A previous study related to the KNApSAcK VOC database classified microorganisms based on their VOC profiles, which confirmed the consistency between VOC-based and pathogenicity-based classifications. However, due to limited data, classification of all species in terms of VOC profiles was not performed. In this study, we enriched our database with additional data collected from different online sources and journals. Then, by applying BiClusO to species-VOC relational data, we determined that VOC-based classification is consistent with taxonomy-based classification of the species. We also assessed the diversity of VOC pathways across different kingdoms of species.

Divergence of metabolites in three phylogenetically close Monascus species (M. pilosus, M. ruber, and M. purpureus) based on secondary metabolite biosynthetic gene clusters

BACKGROUND

Species of the genus Monascus are considered to be economically important and have been widely used in the production of yellow and red food colorants. In particular, three Monascus species, namely, M. pilosus, M. purpureus, and M. ruber, are used for food fermentation in the cuisine of East Asian countries such as China, Japan, and Korea. These species have also been utilized in the production of various kinds of natural pigments. However, there is a paucity of information on the genomes and secondary metabolites of these strains. Here, we report the genomic analysis and secondary metabolites produced by M. pilosus NBRC4520, M. purpureus NBRC4478 and M. ruber NBRC4483, which are NBRC standard strains. We believe that this report will lead to a better understanding of red yeast rice food.

RESULTS

We examined the diversity of secondary metabolite production in three Monascus species (M. pilosus, M. purpureus, and M. ruber) at both the metabolome level by LCMS analysis and at the genome level. Specifically, M. pilosus NBRC4520, M. purpureus NBRC4478 and M. ruber NBRC4483 strains were used in this study. Illumina MiSeq 300 bp paired-end sequencing generated 17 million high-quality short reads in each species, corresponding to 200 times the genome size. We measured the pigments and their related metabolites using LCMS analysis. The colors in the liquid media corresponding to the pigments and their related metabolites produced by the three species were very different from each other. The gene clusters for secondary metabolite biosynthesis of the three Monascus species also diverged, confirming that M. pilosus and M. purpureus are chemotaxonomically different. M. ruber has similar biosynthetic and secondary metabolite gene clusters to M. pilosus. The comparison of secondary metabolites produced also revealed divergence in the three species.

CONCLUSIONS

Our findings are important for improving the utilization of Monascus species in the food industry and industrial field. However, in view of food safety, we need to determine if the toxins produced by some Monascus strains exist in the genome or in the metabolome.

Knowledge-based structural models of SARS-CoV-2 proteins and their complexes with potential drugs

The World Health Organization (WHO) has declared the coronavirus disease 2019 (COVID‐19) caused by the novel coronavirus SARS‐CoV‐2 a pandemic. There is, however, no confirmed anti‐COVID‐19 therapeutic currently. In order to assist structure‐based discovery efforts for repurposing drugs against this disease, we constructed knowledge‐based models of SARS‐CoV‐2 proteins and compared the ligand molecules in the template structures with approved/experimental drugs and components of natural medicines. Our theoretical models suggest several drugs, such as carfilzomib, sinefungin, tecadenoson, and trabodenoson, that could be further investigated for their potential for treating COVID‐19.

Discovery of inflammatory bowel disease-associated miRNAs using a novel bipartite clustering approach

BACKGROUND

Multidimensional data mining from an integrated environment of different data sources is frequently performed in computational system biology. The molecular mechanism from the analysis of a complex network of gene-miRNA can aid to diagnosis and treatment of associated diseases.

METHODS

In this work, we mainly focus on finding inflammatory bowel disease (IBD) associated microRNAs (miRNAs) by biclustering the miRNA-target interactions aided by known IBD risk genes and their associated miRNAs collected from several sources. We rank different miRNAs by attributing to the dataset size and connectivity of IBD associated genes in the miRNA regulatory modules from biclusters. We search the association of some top-ranking miRNAs to IBD related diseases. We also search the network of discovered miRNAs to different diseases and evaluate the similarity of those diseases to IBD.

RESULTS

According to different literature, our results show the significance of top-ranking miRNA to IBD or related diseases. The ratio analysis supports our ranking method where the top 20 miRNA has approximately tenfold attachment to IBD genes. From disease-associated miRNA network analysis we found that 71% of different diseases attached to those miRNAs show more than 0.75 similarity scores to IBD.

CONCLUSION

We successfully identify some miRNAs related to IBD where the scoring formula and disease-associated network analysis show the significance of our method. This method can be a promising approach for isolating miRNAs for similar types of diseases.

The Feasibility of Arrhythmias Detection from A Capacitive ECG Measurement Using Convolutional Neural Network

Capacitive ECG (cECG) can measure the cardiac electrical signal via capacitive coupling between electrodes and skin. This unconstrained measurement is suitable for personal heart monitoring; however, the instability in the quality of the signal hinders a further use of the signal. To use the cECG for heart monitoring, an adapted framework that could automatically classify the signal into clear cECG, arrhythmias and noise signal is a prerequisite. In view of this problem, the conventional quality estimation method using predefined features based on R-peak detection is not suitable for this unconstrained measurement of cECG. In this study, we examine the feasibility of arrhythmias detection from the cECG measurement using a convolutional neural network (CNN) model. The malignant ventricular tachycardia (VT) and ventricular fibrillation (VF) do not have the Q-R-S waveforms and therefore may be easily classified as the noise. Hence, in this study, we used the cECG signals that have 3 classes in quality (C1: clear signal; C2: blurry signal with significant R peak and N: noise) and the arrhythmias signals (VT, VF, and atrial fibrillation) from open databases to train the classification model. 13 subjects were recruited in an experiment for the cECG data collection in the Nara Institute of Science and Technology. As a result, the CNN model could recognize C1 and AF signal with over 0.98 recalls and precisions; whereas the recall and precision of VT and VF are lower scores and the lower scores were caused mainly by the similarity between VT and VF. Given the results of the CNN model, this CNN-based framework can accurately label the C1, AF, and malignant ventricular arrhythmias (VT and VF) signals. Further stratification of the C2, VT, and VF will further enhance the use of the cECG measurement.

Comprehensive Exploration of Target-specific Ligands Using a Graph Convolution Neural Network

Machine learning approaches are widely used to evaluate ligand activities of chemical compounds toward potential target proteins. Especially, exploration of highly selective ligands is important for the development of new drugs with higher safety. One difficulty in constructing well-performing model predicting such a ligand activity is the absence of data on true negative ligand-protein interactions. In other words, in many cases we can access to plenty of information on ligands that bind to specific protein, but less or almost no information showing that compounds don't bind to proteins of interest. In this paper, we suggested an approach to comprehensively explore candidates for ligands specifically targeting toward proteins without using information on the true negative interaction. The approach consists of 4 steps: 1) constructing a model that distinguishes ligands for the target proteins of interest from those targeting proteins that cause off-target effects, by using graph convolution neural network (GCNN); 2) extracting feature vectors after convolution/pooling processes and mapping their principal components in two dimensions; 3) specifying regions with higher density for two ligand groups through kernel density estimation; and 4) investigating the distribution of compounds for exploration on the density map using the same classifier and decomposer. If compounds for exploration are located in higher-density regions of ligand compounds, these compounds can be regarded as having relatively high binding affinity to the major target or off-target proteins compared with other compounds. We applied the approach to the exploration of ligands for β-site amyloid precursor protein [APP]-cleaving enzyme 1 (BACE1), a major target for Alzheimer Disease (AD), with less off-target effect toward cathepsin D. We demonstrated that the density region of BACE1 and cathepsin D ligands are well-divided, and a group of natural compounds as a target for exploration of new drug candidates also has significantly different distribution on the density map.

Graph cluster approach in identifying novel proteins and significant pathways involved in polycystic ovary syndrome

RESEARCH QUESTION

Polycystic ovary syndrome (PCOS) is a complex endocrine disorder with diverse clinical implications, such as infertility, metabolic disorders, cardiovascular diseases and psychological problems among others. The heterogeneity of conditions found in PCOS contribute to its various phenotypes, leading to difficulties in identifying proteins involved in this abnormality. Several studies, however, have shown the feasibility in identifying molecular evidence underlying other diseases using graph cluster analysis. Therefore, is it possible to identify proteins and pathways related to PCOS using the same approach?

METHODS

Known PCOS-related proteins (PCOSrp) from PCOSBase and DisGeNET were integrated with protein-protein interactions (PPI) information from Human Integrated Protein-Protein Interaction reference to construct a PCOS PPI network. The network was clustered with DPClusO algorithm to generate clusters, which were evaluated using Fisher's exact test. Pathway enrichment analysis using gProfileR was conducted to identify significant pathways.

RESULTS

The statistical significance of the identified clusters has successfully predicted 138 novel PCOSrp with 61.5% reliability and, based on Cronbach's alpha, this prediction is acceptable. Androgen signalling pathway and leptin signalling pathway were among the significant PCOS-related pathways corroborating the information obtained from the clinical observation, where androgen signalling pathway is responsible in producing male hormones in women with PCOS, whereas leptin signalling pathway is involved in insulin sensitivity.

CONCLUSIONS

These results show that graph cluster analysis can provide additional insight into the pathobiology of PCOS, as the pathways identified as statistically significant correspond to earlier biological studies. Therefore, integrative analysis can reveal unknown mechanisms, which may enable the development of accurate diagnosis and effective treatment in PCOS.

Power Spectral Analysis of Short-Term Blood Pressure Recordings for Assessing Daily Variations of Blood Pressure in Human

Although daily variations of blood pressure (BP) predict cardiovascular event risk, their assessment requires ambulatory BP monitoring which hinders the clinical application of this approach. Since the baroreflex is a major determinant of BP variations, especially in the frequency range of 0.01-0.1 Hz (baro-frequency), we hypothesized that the power spectral density (PSD) of short-term BP recordings in the baro-frequency range may predict daily variations of BP. In nine-week-old Wister-Kyoto male rats (N =5) with or without baroreflex dysfunction, we telemetrically recorded continuous BP for 24 hours and estimated PSD using Welch's periodogram for the recordings during the 12-hour light period. We compared the reference PSD of 12-hour recording with the PSDs obtained from shorter data lengths ranging from 5 to 240 minutes. The 30-minute BP recordings reproduced PSD of 12-hour recordingswell, and PSD in the baro-frequency range paralleled the standard deviation of 12-hour BP. Thus, the PSD of 30-minute BP reflects the daily BP variability in rats. In human subjects, we estimated PSD from 30-minute noninvasive continuous BP recordings. The rat and human PSDs shared remarkably similar characteristics. Furthermore, comparison of PSD between elderly and young subjects suggested that the baro-frequency range in humans overlapped with that in rats. In conclusion, PSD derived from 30-minute BP recordings is capable of predicting daily BP variations. Our proposed method may serve as a simple, noninvasive and practical tool for predicting cardiovascular events in the clinical setting.

Classification of alkaloids according to the starting substances of their biosynthetic pathways using graph convolutional neural networks

BACKGROUND

Alkaloids, a class of organic compounds that contain nitrogen bases, are mainly synthesized as secondary metabolites in plants and fungi, and they have a wide range of bioactivities. Although there are thousands of compounds in this class, few of their biosynthesis pathways are fully identified. In this study, we constructed a model to predict their precursors based on a novel kind of neural network called the molecular graph convolutional neural network. Molecular similarity is a crucial metric in the analysis of qualitative structure-activity relationships. However, it is sometimes difficult for current fingerprint representations to emphasize specific features for the target problems efficiently. It is advantageous to allow the model to select the appropriate features according to data-driven decisions for extracting more useful information, which influences a classification or regression problem substantially.

RESULTS

In this study, we applied a neural network architecture for undirected graph representation of molecules. By encoding a molecule as an abstract graph and applying "convolution" on the graph and training the weight of the neural network framework, the neural network can optimize feature selection for the training problem. By incorporating the effects from adjacent atoms recursively, graph convolutional neural networks can extract the features of latent atoms that represent chemical features of a molecule efficiently. In order to investigate alkaloid biosynthesis, we trained the network to distinguish the precursors of 566 alkaloids, which are almost all of the alkaloids whose biosynthesis pathways are known, and showed that the model could predict starting substances with an averaged accuracy of 97.5%.

CONCLUSION

We have showed that our model can predict more accurately compared to the random forest and general neural network when the variables and fingerprints are not selected, while the performance is comparable when we carefully select 507 variables from 18000 dimensions of descriptors. The prediction of pathways contributes to understanding of alkaloid synthesis mechanisms and the application of graph based neural network models to similar problems in bioinformatics would therefore be beneficial. We applied our model to evaluate the precursors of biosynthesis of 12000 alkaloids found in various organisms and found power-low-like distribution.

Evaluation of microbial communities in peels of Brazilian tropical fruits by amplicon sequence analysis

Elucidation of the distinctive microbial taxonomic profiles of tropical fruit peels is the indispensable component of investigations aimed at the detection of microorganisms responsible for the post-harvest loss. The objective of the present work was to dissect the bacterial and fungal community of five tropical fruit peels (banana, guava, mango, papaya, and passion fruit) in wild (non-cultivated) and conventionally produced samples from Brazil. To that end, 16S rRNA-encoding gene and ITS rDNA amplicon analysis of the five tropical fruit peels were performed to discriminate the bacterial and fungal communities, respectively. The result showed that bacterial communities of the five types of fruit peels were by far more diversified than that of fungal communities, independent of the type of production system involved. Among the investigated fruits, non-cultivated papaya peels hosted the most diversified bacterial community while the least bacterial community diversity was found in the conventionally produced papaya fruit peels. The gene amplicon analysis clearly discriminated the bacterial community into their respective classes, while fungal communities were better classified in their phyla, yet with clearer component discrimination of fungal community based on the type of cultivation system practiced. Conventionally produced banana and non-cultivated passion fruit peels were characteristically dominated by fungal and bacterial groups, respectively. Overall, in conventionally produced fruit peels, bacterial community was mainly composed of Proteobacteria, Actinobacteria, and Bacilli. The result provided a broad microbial diversity profile that could be used as an important input for seeking alternative fruit spoilage control and post-harvest treatments.

A Novel CNN-Based Framework for Classification of Signal Quality and Sleep Position from a Capacitive ECG Measurement

The further exploration of the capacitive ECG (cECG) is hindered by frequent fluctuations in signal quality from body movement and changes in sleep position. The processing framework must be fundamentally adapted to make full use of this signal. Therefore, we propose a new signal-processing framework that determines the signal quality for short signal segments (2 and 4 seconds) using a multi-class classification model (qua_model) based on a convolutional neural network (CNN). We built another independent deep CNN classifier (pos_model) to classify the sleep position. In the validation, 12 subjects were recruited for a 30-minute experiment, which required the subjects to lie on a bed in different sleeping positions. The short segments, classified as clear (C1 class) by the qua_model, were used to determine sleep positions with the pos_model. In 10-fold cross-validation, the qua_model for signals of 4-second length could recognize the signal of the C1 class at a 0.99 precision and a 0.99 recall; the pos_model could recognize the supine sleep position, the left, and right lateral sleep positions at a 0.99 averaged precision and a 0.99 averaged recall. Given the amount of data accumulated per night and the instability in the signal quality, this fully automatic processing framework is indispensable for a personal healthcare system. Therefore, this study could serve as an important step for cECG technique trying to explore the cECG for unconstrained heart monitoring.