ncRDeep: Non-coding RNA classification with convolutional neural network

A non-coding RNA (ncRNA) is a kind of RNA that is not converted into protein, however, it is involved in many biological processes, diseases, and cancers. Numerous ncRNAs have been identified and classified with high throughput sequencing technology. Hence, accurate ncRNAs class prediction is important and necessary for further study of their functions. Several computation techniques have been employed to predict the class of ncRNAs. Recent classification methods used the secondary structure as their primary input. However, the computational tools of RNA secondary structure are not accurate enough which affects the final performance of ncRNAs predictors. In this paper, we propose a simple yet efficient method, called ncRDeep, for ncRNAs prediction. It uses a simple convolutional neural network and RNA sequence information only. The ncRDeep was evaluated on benchmark datasets and the comparison results showed that the ncRDeep outperforms the state-of-the-art methods significantly. More specifically, the average accuracy was improved by 8.32%. Finally, we built a freely accessible web server for the developed tool ncRDeep at http://home.jbnu.ac.kr/NSCL/ncRDeep.htm     

A deep learning approach based on convolutional LSTM for detecting diabetes

Diabetes is a chronic disease that occurs when the pancreas does not generate sufficient insulin or the body cannot effectively utilize the produced insulin. If it remains unidentified and untreated, then it could be very deadliest. One can lead a healthy life with proper treatment if the presence of diabetes can be detected at an early stage. When the conventional process of detecting diabetes is tedious, there is a need of an automated system for identifying diabetes from the clinical and physical data. In this study, we developed a novel diabetes classifying model based on Convolutional Long Short-term Memory (Conv-LSTM) that was not applied yet in this regard. We applied another three popular models such as Convolutional Neural Network (CNN), Traditional LSTM (T-LSTM), and CNN-LSTM and compared the performance with our developed model over the Pima Indians Diabetes Database (PIDD). Significant features were extracted from the dataset using Boruta algorithm that returned glucose, BMI, insulin, blood pressure, and age as important features for classifying diabetes patients more accurately. We performed hyperparameter optimization using Grid Search algorithm in order to find the optimal parameters for the applied models. Initial experiment by splitting the dataset into separate training and testing sets, the Conv-LSTM-based model classified the diabetes patients with the highest accuracy of 91.38 %. In later, using cross-validation technique the Conv-LSTM model achieved the highest accuracy of 97.26 % and outperformed the other three models along with the state-of-the-art models.     

ECS: an automatic enzyme classifier based on functional domain composition

Classification for enzymes is a prerequisite for understanding their function. Here, an automatic enzyme identifier based on support vector machine (SVM) with feature vectors from protein functional domain composition was built to identify enzymes and further a classifier to classify enzymes into six different classes: oxidoreductase, transferase, hydrolase, lyase, isomerase and ligase. Jackknife cross-validation test was adopted to evaluate the performance of our classifier. The 86.03% success rate achieved for enzyme/non-enzyme identification and 91.32% for enzyme classification, which is much better than that of the BLAST and PSI-BLAST based method, also outperforms several existed works. The results indicate that protein functional domain composition is able to capture the major features which facilitate the identification/classification of proteins, thus demonstrating that our predictor could be a more effective and promising high-throughput method in enzyme research. Moreover, a web-based software Enzyme Classification System (ECS) for identification as well as classification of enzymes can be accessed at: http://pcal.biosino.org/.     

Protein secondary structure prediction using neural networks and deep learning: A review

Literature contains over fifty years of accumulated methods proposed by researchers for predicting the secondary structures of proteins in silico. A large part of this collection is comprised of artificial neural network-based approaches, a field of artificial intelligence and machine learning that is gaining increasing popularity in various application areas. The primary objective of this paper is to put together the summary of works that are important but sparse in time, to help new researchers have a clear view of the domain in a single place. An informative introduction to protein secondary structure and artificial neural networks is also included for context. This review will be valuable in designing future methods to improve protein secondary structure prediction accuracy. The various neural network methods found in this problem domain employ varying architectures and feature spaces, and a handful stand out due to significant improvements in prediction. Neural networks with larger feature scope and higher architecture complexity have been found to produce better protein secondary structure prediction. The current prediction accuracy lies around the 84% marks, leaving much room for further improvement in the prediction of secondary structures in silico. It was found that the estimated limit of 88% prediction accuracy has not been reached yet, hence further research is a timely demand.     

Recognition of big data mixed Raman spectra based on deep learning with smartphone as Raman analyzer

Raman spectral detection has emerged as a powerful analytical technique due to the advantages of fast acquisition, non-invasion, and low cost. The on-site application is highly dependent on Raman automatic analysis algorithm. However, current Raman algorithm research mainly focuses on small sample Raman spectroscopy (RS) identification with defects of low accuracy and detection rate. It is also difficult to realize rapid RS measurement under big data. In this paper, rapid recognition of mixtures in complex environments was realized by establishing a fast Raman analysis model based on deep learning through data training, self-learning, and parameter optimization. The cloud network architecture was proposed to apply deep learning to real-time detection using Smartphone-based Raman devices. This research solves the technical problems about mixture recognition under big data and thus could be used as a new method for fast and field RS detection in complex environments.     

Phosphate-sensitive enzyme electrode: a potential sensor for environment control

A highly sensitive enzyme electrode was designed for the assay of phosphate ions. For this purpose, a bienzyme membrane with co-immobilized nucleoside phosphorylase and xanthine oxidase was used with a platinum amperometric electrode for the detection of enzymatically generated hydrogen peroxide. A detection limit of 10^?7 M was obtained and phosphate assays could be easily performed in the range 0.1–10 μM, which is of interest in the control of water pollution.     

Incorporating deep learning and multi-omics autoencoding for analysis of lung adenocarcinoma prognostication

Lung cancer is the most occurring cancer type, and its mortality rate is also the highest, among them lung adenocarcinoma (LUAD) accounts for about 40 % of lung cancer. There is an urgent need to develop a prognosis prediction model for lung adenocarcinoma. Previous LUAD prognosis studies only took single-omics data, such as mRNA or miRNA, into consideration. To this end, we proposed a deep learning-based autoencoding approach for combination of four-omics data, mRNA, miRNA, DNA methylation and copy number variations, to construct an autoencoder model, which learned representative features to differentiate the two optimal patient subgroups with a significant difference in survival (P = 4.08e-09) and good consistency index (C-index = 0.65). The multi-omics model was validated though four independent datasets, i.e. GSE81089 for mRNA (n = 198, P = 0.0083), GSE63805 for miRNA (n = 32, P = 0.018), GSE63384 for DNA methylation (n = 35, P = 0.009), and TCGA independent samples for copy number variations (n = 94, P = 0.0052). Finally, a functional analysis was performed on two survival subgroups to discover genes involved in biological processes and pathways. This is the first study incorporating deep autoencoding and four-omics data to construct a robust survival prediction model, and results show the approach is useful at predicting LUAD prognostication.     

diSBPred: A machine learning based approach for disulfide bond prediction

The protein disulfide bond is a covalent bond that forms during post-translational modification by the oxidation of a pair of cysteines. In protein, the disulfide bond is the most frequent covalent link between amino acids after the peptide bond. It plays a significant role in three-dimensional (3D) ab initio protein structure prediction (aiPSP), stabilizing protein conformation, post-translational modification, and protein folding. In aiPSP, the location of disulfide bonds can strongly reduce the conformational space searching by imposing geometrical constraints. Existing experimental techniques for the determination of disulfide bonds are time-consuming and expensive. Thus, developing sequence-based computational methods for disulfide bond prediction becomes indispensable. This study proposed a stacking-based machine learning approach for disulfide bond prediction (diSBPred). Various useful sequence and structure-based features are extracted for effective training, including conservation profile, residue solvent accessibility, torsion angle flexibility, disorder probability, a sequential distance between cysteines, and more. The prediction of disulfide bonds is carried out in two stages: first, individual cysteines are predicted as either bonding or non-bonding; second, the cysteine-pairs are predicted as either bonding or non-bonding by including the results from cysteine bonding prediction as a feature.The examination of the relevance of the features employed in this study and the features utilized in the existing nearest neighbor algorithm (NNA) method shows that the features used in this study improve about 7.39 % in jackknife validation balanced accuracy. Moreover, for individual cysteine bonding prediction and cysteine-pair bonding prediction, diSBPred provides a 10-fold cross-validation balanced accuracy of 82.29 % and 94.20 %, respectively. Altogether, our predictor achieves an improvement of 43.25 % based on balanced accuracy compared to the existing NNA based approach. Thus, diSBPred can be utilized to annotate the cysteine bonding residues of protein sequences whose structures are unknown as well as improve the accuracy of the aiPSP method, which can further aid in experimental studies of the disulfide bond and structure determination.     

Recognition of protein allosteric states and residues: Machine learning approaches

Allostery is a process by which proteins transmit the effect of perturbation at one site to a distal functional site upon certain perturbation. As an intrinsically global effect of protein dynamics, it is difficult to associate protein allostery with individual residues, hindering effective selection of key residues for mutagenesis studies. The machine learning models including decision tree (DT) and artificial neural network (ANN) models were applied to develop classification model for a cell signaling allosteric protein with two states showing extremely similar tertiary structures in both crystallographic structures and molecular dynamics simulations. Both DT and ANN models were developed with 75% and 80% of predicting accuracy, respectively. Good agreement between machine learning models and previous experimental as well as computational studies of the same protein validates this approach as an alternative way to analyze protein dynamics simulations and allostery. In addition, the difference of distributions of key features in two allosteric states also underlies the population shift hypothesis of dynamics‐driven allostery model. © 2018 Wiley Periodicals, Inc.     

Biosensors based on enzyme field-effect transistors for determination of some substrates and inhibitors

This paper is a review of the authors' publications concerning the development of biosensors based on enzyme field-effect transistors (ENFETs) for direct substrates or inhibitors analysis. Such biosensors were designed by using immobilised enzymes and ion-selective field-effect transistors (ISFETs). Highly specific, sensitive, simple, fast and cheap determination of different substances renders them as promising tools in medicine, biotechnology, environmental control, agriculture and the food industry.The biosensors based on ENFETs and direct enzyme analysis for determination of concentrations of different substrates (glucose, urea, penicillin, formaldehyde, creatinine, etc.) have been developed and their laboratory prototypes were fabricated. Improvement of the analytical characteristics of such biosensors may be achieved by using a differential mode of measurement, working solutions with different buffer concentrations and specific agents, negatively or positively charged additional membranes, or genetically modified enzymes. These approaches allow one to decrease the effect of the buffer capacity influence on the sensor response in an aim to increase the sensitivity of the biosensors and to extend their dynamic ranges.Biosensors for the determination of concentrations of different toxic substances (organophosphorous pesticides, heavy metal ions, hypochlorite, glycoalkaloids, etc.) were designed on the basis of reversible and/or irreversible enzyme inhibition effect(s). The conception of an enzymatic multibiosensor for the determination of different toxic substances based on the enzyme inhibition effect is also described.We will discuss the respective advantages and disadvantages of biosensors based on the ENFETs developed and also demonstrate their practical application.     

An inhibition type amperometric biosensor based on tyrosinase enzyme for fluoride determination

In this study, a new biosensor based on the inhibition of tyrosinase for the determination of fluoride is described. To construct the biosensor tyrosinase was immobilized by using gelatine and cross-linking agent glutaraldehyde on a Clark type dissolved oxygen (DO) probe covered with a teflon membrane which is sensitive for oxygen. The phosphate buffer (50 mM, pH 7.0) at 30 °C were established as providing the optimum working conditions. The method is based on the measurement of the decreasing of dissolved oxygen level of the interval surface that related to fluoride concentration added into reaction medium in the presence of catechol. Inhibitor effect of fluoride results in decrease in dissolved oxygen concentration. The biosensor response depends linearly on fluoride concentration between 1.0 and 20 μM with a response time of 3 min.In the characterization studies of the biosensor some parameters such as reproducibility, substrate specificity and storage stability were carried out. From the experiments, the average value (x), Standard deviation (S.D) and coefficient of variation (C.V %) were found as 10.5 μM, ± 0.57 μM, 5.43%, respectively for 10 μM fluoride standard.     

Metal-metal oxide enzyme electrodes for the determination of urea

Enzyme electrodes for urea assay based on metal-metal oxide (Sb, Bi, W, Ti + RuO₂) with urease immobilized in gelatin gel were examined. It was shown that the best electrodes were obtained for tungsten. The urea response of the electrodes was influenced by the pH and concentration of the buffer used. Increasing additions of inert salt (potassium chloride) change the pH characteristic of the tungsten electrode and buffer capacity, thus influencing the urea response of the electrode.     

Sparse Representation Classification of Tobacco Leaves Using Near-Infrared Spectroscopy and a Deep Learning Algorithm

A spare representation classification method for tobacco leaves based on near-infrared spectroscopy and deep learning algorithm is reported in this paper. All training samples were used to make up a data dictionary of the sparse representation and the test samples were represented by the sparsest linear combinations of the dictionary by sparse coding. The regression residual of the test sample to each class was computed and finally assigned to the class with the minimum residual. The effectiveness of spare representation classification method was compared with K-nearest neighbor and particle swarm optimization–support vector machine algorithms. The results show that the classification accuracy of the proposed method is higher and it is more efficient. The results suggest that near-infrared spectroscopy with spare representation classification algorithm may be an alternative method to traditional methods for discriminating classes of tobacco leaves.     

A Machine Learning Model to Classify Dynamic Processes in Liquid Water

The front cover artwork is provided by the groups of Prof. Shiben Li (Wenzhou University, P.R. China) as well as Dr. Gang Huang (Institute of Theoretical Physics, Chinese Academy of Sciences, P.R. China). The image shows that characteristics of dynamic processes of water molecules in liquid water can be recognized and classified by a machine learning-based model if a graph representation is used to describe the hydrogen bond network. Read the full text of the Article at 10.1002/cphc.202100599 .     

Gene selection from microarray data for cancer classification--a machine learning approach

A DNA microarray can track the expression levels of thousands of genes simultaneously. Previous research has demonstrated that this technology can be useful in the classification of cancers. Cancer microarray data normally contains a small number of samples which have a large number of gene expression levels as features. To select relevant genes involved in different types of cancer remains a challenge. In order to extract useful gene information from cancer microarray data and reduce dimensionality, feature selection algorithms were systematically investigated in this study. Using a correlation-based feature selector combined with machine learning algorithms such as decision trees, nave Bayes and support vector machines, we show that classification performance at least as good as published results can be obtained on acute leukemia and diffuse large B-cell lymphoma microarray data sets. We also demonstrate that a combined use of different classification and feature selection approaches makes it possible to select relevant genes with high confidence. This is also the first paper which discusses both computational and biological evidence for the involvement of zyxin in leukaemogenesis.     

Amperometric enzyme sensor for glucose based on graphite paste-modified electrodes

Amperometric enzyme electrode for glucose is described based on the incorporation of glucose oxidase (GOD) into graphite paste modified with tetracyanoquinodimethane (TCNQ). The incorporated enzyme exhibits high activity and long-term stability over the earlier TCNQ-based glucose sensor (1). The sensor provides a linear response to glucose over a wide concentration range. The response time of the sensor is 15-50 sec, and the detection limit is 0.5 mM. Stable response to the substrate was obtained during a period of 35 d. Application of the sensor in the plasma analysis is reported.     

Deep_CNN_LSTM_GO: Protein function prediction from amino-acid sequences

Protein amino acid sequences can be used to determine the functions of the protein. However, determining the function of a single protein requires many resources and a tremendous amount of time. Computational Intelligence methods such as Deep learning have been shown to predict the proteins' functions. This paper proposes a hybrid deep neural network model to predict an unknown protein's functions from sequences. The proposed model is named Deep_CNN_LSTM_GO. Deep_CNN_LSTM_GO is an Integration between Convolutional Neural network (CNN) and Long Short-Term Memory (LSTM) Neural Network to learn features from amino acid sequences and outputs the three different Gene Ontology (GO). The gene ontology represents the protein functions in the three sub-ontologies: Molecular Functions (MF), Biological Process (BP), and Cellular Component (CC). The proposed model has been trained and tested using UniProt-SwissProt's dataset. Another test has been done using Computational Assessment of Function Annotation (CAFA) on the three sub-ontologies. The proposed model outperforms different methods proposed in the field with better performance using three different evaluation metrics (Fmax, Smin, and AUPR) in the three sub-ontologies (MF, BP, CC).     

Development and evaluation of electrochemical glucose enzyme biosensors based on carbon film electrodes

Electrochemical glucose enzyme biosensors have been prepared on carbon film electrodes made from carbon film electrical resistors. Evaluation and characterisation of these electrodes in phosphate buffer saline solution has been carried out with and without pretreatment by cycling in perchloric acid or at fixed applied potential. Both pretreatments led to a reduction in the carbon surface oxidation peak and enabled better detection of hydrogen peroxide in the pH range of 5-7. Glucose oxidase enzyme was immobilised on the carbon surface by mixing with glutaraldehyde, bovine serum albumin and with and without Nafion. The performance of these two types of electrode was similar, that containing Nafion being more physically robust. Linear ranges were up to around 1.5 mM, with detection limits 60 μM, and pretreatment of the carbon film electrode at a fixed potential of +0.9 V versus SCE for 5 min was found to be the most beneficial. Michaelis-Menten constants between 5 mM and 10 mM were found under the different experimental conditions. Coating the immobilised enzyme layer with a thin layer of Nafion was found to give similar results in the determination of glucose to mixing it but with benefits against interferences for the analysis of complex matrices, such as wine. Potentialities, for a short-term-use or disposable sensors, are indicated.     

Theoretical investigation of the peroxidase-oxidase chemical oscillator for quantitative enzyme analysis

The theoretical basis for quantitative enzyme determinations by using the features of chemical oscillations is developed. An existing model of the peroxidase-oxidase chemical oscillator, consisting of the enzyme horseradish peroxidase, oxygen and reduced nicotinamide adenine dinucleotide (NADH), is modified to include a competing (analyte) reaction. The competitive effect between the analyte and the peroxidase on the observed periodic and chaotic oscillations forms the basis of the modified model. Corresponding differential equations are numerically integrated to produce plots of dissolved oxygen concentration vs. time. The calculated oscillatory oxygen transient shows a sensitive dependence on the analyte concentration. Utilizing the property of period doubling, a theoretical calibration graph can be generated for the determination of an analyte enzyme concentration. Special properties of the technique offer a potential combination of wide dynamic range and selectable precision. This demonstrates that the oscillator should prove experimentally useful for quantitative analysis.