Addressing data imbalance problems in ligand-binding site prediction using a variational autoencoder and a convolutional neural network.

Since 2015, a fast growing number of deep learning-based methods have been proposed for protein-ligand binding site prediction and many have achieved promising performance. These methods, however, neglect the imbalanced nature of binding site prediction problems. Traditional data-based approaches for handling data imbalance employ linear interpolation of minority class samples. Such approaches may not be fully exploited by deep neural networks on downstream tasks. We present a novel technique for balancing input classes by developing a deep neural network-based variational autoencoder (VAE) that aims to learn important attributes of the minority classes concerning nonlinear combinations. After learning, the trained VAE was used to generate new minority class samples that were later added to the original data to create a balanced dataset. Finally, a convolutional neural network was used for classification, for which we assumed that the nonlinearity could be fully integrated. As a case study, we applied our method to the identification of FAD- and FMN-binding sites of electron transport proteins. Compared with the best classifiers that use traditional machine learning algorithms, our models obtained a great improvement on sensitivity while maintaining similar or higher levels of accuracy and specificity. We also demonstrate that our method is better than other data imbalance handling techniques, such as SMOTE, ADASYN, and class weight adjustment. Additionally, our models also outperform existing predictors in predicting the same binding types. Our method is general and can be applied to other data types for prediction problems with moderate-to-heavy data imbalances.

An HPLC method with diode array detector for the simultaneous quantification of chloroquine and desethylchloroquine in plasma and whole blood samples from Plasmodium vivax patients in Vietnam, using quinine as an internal standard.

A sensitive, simple method for quantification of chloroquine (CQ) and desethylchloroquine (MCQ) in whole blood and plasma from Plasmodium vivax patients has been developed using HPLC with diode array detection (DAD). Solid-phase extraction on Isolute-96-CBA was employed to process 100 µL of plasma/whole blood samples. CQ, MCQ and quinine were separated using a mobile phase of phosphate buffer 25 mm, pH 2.60-acetonitrile (88:12, v/v) with 2 mm sodium perchlorate on a Zorbax SB-CN 150 × 4.6 mm, 5 µm column at a flow rate of 1.2 mL/min, at ambient temperature in 10 min, with the DAD wavelength of 343 nm. The method was linear over the range of 10-5000 ng/mL for both CQ and MCQ in plasma and whole blood. The limit of detection was 4 ng/mL and limit of quantification was 10 ng/mL in both plasma and blood for CQ and MCQ. The intra-, inter- and total assay precision were <10% for CQ and MCQ in plasma and whole blood. In plasma, the accuracies varied between 101 and 103%, whereas in whole blood, the accuracies ranged from 97.0 to 102% for CQ and MCQ. The method is an ideal technique with simple facilities and instruments, bringing about good separation in comparison with previous methods. © 2016 The Authors Biomedical Chromatography Published by John Wiley & Sons Ltd.

Decision support system for the differentiation of schizophrenia and mood disorders using multiple deep learning models on wearable devices data.

In the modern world, with so much inherent stress, mental health disorders (MHDs) are becoming more common in every country around the globe, causing a significant burden on society and patients' families. MHDs come in many forms with various severities of symptoms and differing periods of suffering, and as a result it is difficult to differentiate between them and simple to confuse them with each other. Therefore, we propose a support system that employs deep learning (DL) with wearable device data to provide physicians with an objective reference resource by which to make differential diagnoses and plan treatment. We conducted experiments on open datasets containing activity motion signal data from wearable devices to identify schizophrenia and mood disorders (bipolar and unipolar), the datasets being named Psykose and Depresjon. The results showed that, in both workflow approaches, the proposed framework performed well in comparison with the traditional machine learning (ML) and DL methods. We concluded that applying DL models using activity motion signal data from wearable devices represents a prospective objective support system for MHD differentiation with a good performance.

Deep Ensemble Learning Approaches in Healthcare to Enhance the Prediction and Diagnosing Performance: The Workflows, Deployments, and Surveys on the Statistical, Image-Based, and Sequential Datasets.

With the development of information and technology, especially with the boom in big data, healthcare support systems are becoming much better. Patient data can be collected, retrieved, and stored in real time. These data are valuable and meaningful for monitoring, diagnosing, and further applications in data analysis and decision-making. Essentially, the data can be divided into three types, namely, statistical, image-based, and sequential data. Each type has a different method of retrieval, processing, and deployment. Additionally, the application of machine learning (ML) and deep learning (DL) in healthcare support systems is growing more rapidly than ever. Numerous high-performance architectures are proposed to optimize decision-making. As reliability and stability are the most important factors in the healthcare support system, enhancing the predicted performance and maintaining the stability of the model are always the top priority. The main idea of our study comes from ensemble techniques. Numerous studies and data science competitions show that by combining several weak models into one, ensemble models can attain outstanding performance and reliability. We propose three deep ensemble learning (DEL) approaches, each with stable and reliable performance, that are workable on the above-mentioned data types. These are deep-stacked generalization ensemble learning, gradient deep learning boosting, and deep aggregation learning. The experiment results show that our proposed approaches achieve more vigorous and reliable performance than traditional ML and DL techniques on statistical, image-based, and sequential benchmark datasets. In particular, on the Heart Disease UCI dataset, representing the statistical type, the gradient deep learning boosting approach dominates the others with accuracy, recall, F1-score, Matthews correlation coefficient, and area under the curve values of 0.87, 0.81, 0.83, 0.73, and 0.91, respectively. On the X-ray dataset, representing the image-based type, the deep aggregation learning approach shows the highest performance with values of 0.91, 0.97, 0.93, 0.80, and 0.94, respectively. On the Depresjon dataset, representing the sequence type, the deep-stacked generalization ensemble learning approach outperforms the others with values of 0.91, 0.84, 0.86, 0.8, and 0.94, respectively. Overall, we conclude that applying DL models using our proposed approaches is a promising method for the healthcare support system to enhance prediction and diagnosis performance. Furthermore, our study reveals that these approaches are flexible and easy to apply to achieve optimal performance.

High-performance liquid chromatography with time-programmed fluorescence detection for the quantification of Levofloxacin in human plasma and cerebrospinal fluid in adults with tuberculous meningitis.

An accurate and reliable high-performance liquid chromatography with time-programmed fluorescence detection was developed and validated to measure levofloxacin in human plasma and cerebrospinal fluid (CSF). After solid phase extraction process using Evolute® ABN 96 fixed well plate; levofloxacin and internal standard-enoxacin were separated using a mobile phase consisting of phosphate buffer 10mM with 0.025% triethylamine pH 3.0 - acetonitrile (88:12, v/v) on a Purosphere RP-8e column (5µm, 125×4.0mm) at a flow rate of 1.2mL/min at 35°C. The excitation/emission wavelengths were set to 269/400nm and 294/500nm, for enoxacin and levofloxacin, respectively. The method was linear over the concentration range of 0.02 to 20.0µg/mL with a limit of detection of 0.01µg/mL. The relative standard deviation of intra-assay and inter-assay precision for levofloxacin at four quality controls concentrations (0.02, 0.06, 3.0 and 15.0µg/mL) were less than 7% and the accuracies ranged from 96.75% to 101.9% in plasma, and from 93.00% to 98.67% in CSF. The validated method was successfully applied to quantify levofloxacin in a considerable quantity of plasma (826) and CSF (477) samples collected from 232 tuberculous meningitis patients, and the preliminary intensive pharmacokinetics analysis from 14 tuberculous meningitis patients in Vietnam is described in this paper.