Cancers classification based on deep neural networks and emotional learning approach

In the present era, enormous factors contribute to causing cancer. So cancer classification cannot rely only on doctor''s thoughts. As a result, intelligent algorithms concerning doctor''s help are inevitable. Therefore, the authors are motivated to suggest a novel algorithm to classify three cancer datasets; colon, ALL‐AML, and leukaemia cancers. Their proposed algorithm is based on the deep neural network and emotional learning process. First of all, by applying the principal component analysis, they had a feature reduction. Then, they used deep neural as a feature extraction. Then, they implemented different classifiers; multi‐layer perceptron, support vector machine (SVM), decision tree, and Gaussian mixture model. In the end, because in the real world, especially when working on systems biology, unpredictable events, and uncertainties are undeniable, the robustness of their model against uncertainties is important. So they added Gaussian noise to the input features of the first encoder in each dataset, then, they applied the stacked denoising method. Experimental results disclosed that, generally, using emotional learning increased the accuracy. In addition, the highest accuracy was gained by SVM, 91.66, 92.27, and 96.56% for colon, ALL‐AML, and leukaemia, respectively. However, GMM led to the lowest accuracy. The best accuracy gained by GMM was 60%.Inspec keywords: cancer, learning (artificial intelligence), principal component analysis, multilayer perceptrons, feature extraction, support vector machines, pattern classification, Gaussian processes, decision trees, Gaussian noise, medical computingOther keywords: colon cancer, Gaussian noise, stacked denoising method, SVM, support vector machine, emotional learning process, cancer datasets, intelligent algorithms, cancer classification, ALL‐AML, input features, Gaussian mixture model, decision tree, multilayer perceptron, feature extraction, feature reduction, principal component analysis, deep neural network, leukaemia cancers     

Prediction of NSCLC recurrence from microarray data with GEP

Lung cancer is one of the deadliest diseases in the world. Non‐small cell lung cancer (NSCLC) is the most common and dangerous type of lung cancer. Despite the fact that NSCLC is preventable and curable for some cases if diagnosed at early stages, the vast majority of patients are diagnosed very late. Furthermore, NSCLC usually recurs sometime after treatment. Therefore, it is of paramount importance to predict NSCLC recurrence, so that specific and suitable treatments can be sought. Nonetheless, conventional methods of predicting cancer recurrence rely solely on histopathology data and predictions are not reliable in many cases. The microarray gene expression (GE) technology provides a promising and reliable way to predict NSCLC recurrence by analysing the GE of sample cells. This study proposes a new model from GE programming to use microarray datasets for NSCLC recurrence prediction. To this end, the authors also propose a hybrid method to rank and select relevant prognostic genes that are related to NSCLC recurrence prediction. The proposed model was evaluated on real NSCLC microarray datasets and compared with other representational models. The results demonstrated the effectiveness of the proposed model.Inspec keywords: lung, cancer, lab‐on‐a‐chip, genetics, patient diagnosisOther keywords: NSCLC recurrence prediction, microarray data, GE programming, nonsmall cell lung cancer, cancer recurrence, histopathology data, microarray gene expression, prognostic genes     

In silico identification of potential targets and drugs for non‐small cell lung cancer

Lung cancer is one of the leading causes of death in both the USA and Taiwan, and it is thought that the cause of cancer could be because of the gain of function of an oncoprotein or the loss of function of a tumour suppressor protein. Consequently, these proteins are potential targets for drugs. In this study, differentially expressed genes are identified, via an expression dataset generated from lung adenocarcinoma tumour and adjacent non‐tumour tissues. This study has integrated many complementary resources, that is, microarray, protein‐protein interaction and protein complex. After constructing the lung cancer protein‐protein interaction network (PPIN), the authors performed graph theory analysis of PPIN. Highly dense modules are identified, which are potential cancer‐associated protein complexes. Up‐ and down‐regulated communities were used as queries to perform functional enrichment analysis. Enriched biological processes and pathways are determined. These sets of up‐ and down‐regulated genes were submitted to the Connectivity Map web resource to identify potential drugs. The authors'' findings suggested that eight drugs from DrugBank and three drugs from NCBI can potentially reverse certain up‐ and down‐regulated genes'' expression. In conclusion, this study provides a systematic strategy to discover potential drugs and target genes for lung cancer.Inspec keywords: cellular biophysics, lung, cancer, drugs, genetics, tumours, lab‐on‐a‐chip, proteins, molecular biophysics, graph theory, query processing, medical computingOther keywords: down‐regulated gene expression, up‐regulated gene expression, potential target genes, DrugBank, potential drugs, connectivity map Web resource, biological processes, functional enrichment analysis, up‐regulated communities, down‐regulated communities, cancer‐associated protein complexes, k‐communities, highly‐dense modules, PPIN, graph theory analysis, lung cancer protein‐protein interaction network, MIPS, BioGrid, ArrayExpress, microarray, nontumour tissues, human lung adenocarcinoma tumour, bioconductor package, tumour suppressor protein, oncoprotein, nonsmall cell lung cancer, in silico identification     

Cancer adjuvant chemotherapy prediction model for non‐small cell lung cancer

Non‐small cell lung cancer (NSCLC) is the most popular and dangerous type of lung cancer. Adjuvant chemotherapy (ACT) is the main treatment after surgery resection to prevent the patient from cancer recurrence. However, ACT could be toxic and unhelpful in some cases. Therefore, it is highly desired in clinical applications to predict the treatment outcomes of chemotherapy. Conventional methods of predicting cancer treatment rely solely on histopathology and the results are not reliable in some cases. This study aims at building a predictive model to identify who needs ACT treatment and who should avoid it. To this end, the authors propose an innovative method to identify NSCLC‐related prognostic genes from microarray gene‐expression datasets. They also propose a new model using gene‐expression programming algorithm for ACT classification. The proposed model was evaluated on integrated microarray datasets from four institutes and compared with four representative methods: general regression neural network, decision tree, support vector machine and naive Bayes. Evaluation results demonstrated the effectiveness of the proposed model with accuracy 89.8% which is higher than other representative models. They obtained four probes (four genes) that can get good prediction results. These genes are 204891_s_at (LCK), 208893_s_at (DUSP6), 202454_s_at (ERBB3) and 201076_at (MMD).Inspec keywords: neural nets, regression analysis, decision trees, surgery, medical computing, cancer, cellular biophysics, lung, genetics, support vector machines, Bayes methods, biochemistryOther keywords: cancer ACT prediction model, nonsmall cell lung cancer, adjuvant chemotherapy, surgery resection, cancer recurrence, conventional methods, cancer treatment, microarray gene‐expression technology, NSCLC treatment, ACT treatment, NSCLC‐related prognostic genes, microarray gene‐expression datasets, gene‐expression programming algorithm, ACT classification, ACT information, integrated microarray datasets, representative models, survival time, general regression neural network, decision tree, support vector machine, naive Bayes     

In silico discovery of significant pathways in colorectal cancer metastasis using a two‐stage optimisation approach

Accurate and reliable modelling of protein–protein interaction networks for complex diseases such as colorectal cancer can help better understand mechanism of diseases and potentially discover new drugs. Different machine learning methods such as empirical mode decomposition combined with least square support vector machine, and discrete Fourier transform have been widely utilised as a classifier and for automatic discovery of biomarkers for the diagnosis of the disease. The existing methods are, however, less efficient as they tend to ignore interaction with the classifier. In this study, the authors propose a two‐stage optimisation approach to effectively select biomarkers and discover interactions among them. At the first stage, particle swarm optimisation (PSO) and differential evolution (DE) are used to optimise parameters of support vector machine recursive feature elimination algorithm, and dynamic Bayesian network is then used to predict temporal relationship between biomarkers across two time points. Results show that 18 and 25 biomarkers selected by PSO and DE‐based approach, respectively, yields the same accuracy of 97.3% and F1‐score of 97.7 and 97.6%, respectively. The stratified analysis reveals that Alpha‐2‐HS‐glycoprotein was a dominant hub gene with multiple interactions to other genes including Fibrinogen alpha chain, which is also a potential biomarker for colorectal cancer.Inspec keywords: cancer, proteins, particle swarm optimisation, evolutionary computation, support vector machines, recursive functions, Bayes methods, genetics, molecular biophysics, medical computingOther keywords: colorectal cancer metastasis, two‐stage optimisation approach, protein–protein interaction networks, biomarkers, particle swarm optimisation, differential evolution, support vector machine recursive feature elimination, dynamic Bayesian network, stratified analysis, Alpha‐2‐HS‐glycoprotein, hub gene, Fibrinogen alpha chain     

Classification of drug molecules for oxidative stress signalling pathway

In humans, oxidative stress is involved in the development of diabetes, cancer, hypertension, Alzheimers’ disease, and heart failure. One of the mechanisms in the cellular defence against oxidative stress is the activation of the Nrf2‐antioxidant response element (ARE) signalling pathway. Computation of activity, efficacy, and potency score of ARE signalling pathway and to propose a multi‐level prediction scheme for the same is the main aim of the study as it contributes in a big amount to the improvement of oxidative stress in humans. Applying the process of knowledge discovery from data, required knowledge is gathered and then machine learning techniques are applied to propose a multi‐level scheme. The validation of the proposed scheme is done using the K‐fold cross‐validation method and an accuracy of 90% is achieved for prediction of activity score for ARE molecules which determine their power to refine oxidative stress.Inspec keywords: cancer, cellular biophysics, biochemistry, drugs, molecular biophysics, proteins, learning (artificial intelligence), medical computingOther keywords: oxidative stress, Nrf2‐antioxidant response element signalling pathway, ARE signalling pathway, diabetes, cancer, hypertension, Alzheimers’ disease, heart failure, machine learning techniques, K‐fold cross‐validation method, ARE molecules     

Prediction of drug synergy score using ensemble based differential evolution

Prediction of drug synergy score is an ill‐posed problem. It plays an efficient role in the medical field for inhibiting specific cancer agents. An efficient regression‐based machine learning technique has an ability to minimise the drug synergy prediction errors. Therefore, in this study, an efficient machine learning technique for drug synergy prediction technique is designed by using ensemble based differential evolution (DE) for optimising the support vector machine (SVM). Because the tuning of the attributes of SVM kernel regulates the prediction precision. The ensemble based DE employs two trial vector generation techniques and two control attributes settings. The initial generation technique has the best solution and the other is without the best solution. The proposed and existing competitive machine learning techniques are applied to drug synergy data. The extensive analysis demonstrates that the proposed technique outperforms others in terms of accuracy, root mean square error and coefficient of correlation.Inspec keywords: cancer, evolutionary computation, support vector machines, regression analysis, drugs, learning (artificial intelligence), medical computingOther keywords: ensemble based differential evolution, specific cancer agents, efficient regression‐based machine learning technique, drug synergy prediction errors, efficient machine learning technique, drug synergy prediction technique, support vector machine, prediction precision, trial vector generation techniques, initial generation technique, drug synergy data, drug synergy score prediction, medical field, SVM kernel attributes, ensemble based DE, control attribute settings, competitive machine learning techniques, root mean square error     

Signalling pathway impact analysis based on the strength of interaction between genes

Signalling pathway analysis is a popular approach that is used to identify significant cancer‐related pathways based on differentially expressed genes (DEGs) from biological experiments. The main advantage of signalling pathway analysis lies in the fact that it assesses both the number of DEGs and the propagation of signal perturbation in signalling pathways. However, this method simplifies the interactions between genes by categorising them only as activation (+1) and suppression (−1), which does not encompass the range of interactions in real pathways, where interaction strength between genes may vary. In this study, the authors used newly developed signalling pathway impact analysis (SPIA) methods, SPIA based on Pearson correlation coefficient (PSPIA), and mutual information (MSPIA), to measure the interaction strength between pairs of genes. In analyses of a colorectal cancer dataset, a lung cancer dataset, and a pancreatic cancer dataset, PSPIA and MSPIA identified more candidate cancer‐related pathways than were identified by SPIA. Generally, MSPIA performed better than PSPIA.Inspec keywords: genetics, cancer, biology computing, perturbation theory, biological organs, data analysisOther keywords: gene interaction strength, cancer‐related pathways, differentially expressed genes, biological experiments, signal perturbation propagation, signalling pathway impact analysis methods, Pearson correlation coefficient, mutual information, colorectal cancer dataset analysis, pancreatic cancer dataset, PSPIA, MSPIA     

Chaotic emperor penguin optimised extreme learning machine for microarray cancer classification

Microarray technology plays a significant role in cancer classification, where a large number of genes and samples are simultaneously analysed. For the efficient analysis of the microarray data, there is a great demand for the development of intelligent techniques. In this article, the authors propose a novel hybrid technique employing Fisher criterion, ReliefF, and extreme learning machine (ELM) based on the principle of chaotic emperor penguin optimisation algorithm (CEPO). EPO is a recently developed metaheuristic method. In the proposed method, initially, Fisher score and ReliefF are independently used as filters for relevant gene selection. Further, a novel population‐based metaheuristic, namely, CEPO was proposed to pre‐train the ELM by selecting the optimal input weights and hidden biases. The authors have successfully conducted experiments on seven well‐known data sets. To evaluate the effectiveness, the proposed method is compared with original EPO, genetic algorithm, and particle swarm optimisation‐based ELM along with other state‐of‐the‐art techniques. The experimental results show that the proposed framework achieves better accuracy as compared to the state‐of‐the‐art schemes. The efficacy of the proposed method is demonstrated in terms of accuracy, sensitivity, specificity, and F‐measure.Inspec keywords: genetic algorithms, pattern classification, biology computing, cancer, learning (artificial intelligence), search problems, particle swarm optimisationOther keywords: optimal input weights, data sets, original EPO, genetic algorithm, particle swarm optimisation‐based ELM, microarray cancer classification, microarray technology, microarray data, intelligent techniques, Fisher criterion, ReliefF, chaotic emperor penguin optimisation algorithm, CEPO, recently developed metaheuristic method, Fisher score, relevant gene selection, population‐based, chaotic penguin optimised extreme learning machine, F     

Improvement in prediction of antigenic epitopes using stacked generalisation: an ensemble approach

The major intent of peptide vaccine designs, immunodiagnosis and antibody productions is to accurately identify linear B‐cell epitopes. The determination of epitopes through experimental analysis is highly expensive. Therefore, it is desirable to develop a reliable model with significant improvement in prediction models. In this study, a hybrid model has been designed by using stacked generalisation ensemble technique for prediction of linear B‐cell epitopes. The goal of using stacked generalisation ensemble approach is to refine predictions of base classifiers and to get rid of the worse predictions. In this study, six machine learning models are fused to predict variable length epitopes (6–49 mers). The proposed ensemble model achieves 76.6% accuracy and average accuracy of repeated 10‐fold cross‐validation is 73.14%. The trained ensemble model has been tested on the benchmark dataset and compared with existing sequential B‐cell epitope prediction techniques including APCpred, ABCpred, BCpred and AAPBCPred.Inspec keywords: generalisation (artificial intelligence), support vector machines, cellular biophysics, pattern classification, proteins, learning (artificial intelligence), bioinformaticsOther keywords: antigenic epitopes, stacked generalisation, peptide vaccine designs, immunodiagnosis, antibody productions, linear B‐cell epitopes, generalisation ensemble technique, generalisation ensemble approach, machine learning models, base classifiers     

Prediction of human disease‐associated phosphorylation sites with combined feature selection approach and support vector machine

Phosphorylation is a crucial post‐translational modification, which regulates almost all cellular processes in life. It has long been recognised that protein phosphorylation has close relationship with diseases, and therefore many researches are undertaken to predict phosphorylation sites for disease treatment and drug design. However, despite the success achieved by these approaches, no method focuses on disease‐associated phosphorylation sites prediction. Herein, for the first time the authors propose a novel approach that is specially designed to identify associations between phosphorylation sites and human diseases. To take full advantage of local sequence information, a combined feature selection method‐based support vector machine (CFS‐SVM) that incorporates minimum‐redundancy‐maximum‐relevance filtering process and forward feature selection process is developed. Performance evaluation shows that CFS‐SVM is significantly better than the widely used classifiers including Bayesian decision theory, k nearest neighbour and random forest. With the extremely high specificity of 99%, CFS‐SVM can still achieve a high sensitivity. Besides, tests on extra data confirm the effectiveness and general applicability of CFS‐SVM approach on a variety of diseases. Finally, the analysis of selected features and corresponding kinases also help the understanding of the potential mechanism of disease‐phosphorylation relationships and guide further experimental validations.Inspec keywords: proteins, cellular biophysics, diseases, support vector machines, feature selection, filtering theory, medical computing, bioinformaticsOther keywords: forward feature selection process, minimum‐redundancy‐maximum‐relevance filtering process, cellular process, post‐translational modification, support vector machine, human disease‐associated phosphorylation sites     

Fold change based approach for identification of significant network markers in breast,lung and prostate cancer

Cancer belongs to a class of highly aggressive diseases and a leading cause of death in the world. With more than 100 types of cancers, breast, lung and prostate cancer remain to be the most common types. To identify essential network markers (NMs) and therapeutic targets in these cancers, the authors present a novel approach which uses gene expression data from microarray and RNA‐seq platforms and utilises the results from this data to evaluate protein–protein interaction (PPI) network. Differentially expressed genes (DEGs) are extracted from microarray data using three different statistical methods in R, to produce a consistent set of genes. Also, DEGs are extracted from RNA‐seq data for the same three cancer types. DEG sets found to be common in both platforms are obtained at three fold change (FC) cut‐off levels to accurately identify the level of change in expression of these genes in all three cancers. A cancer network is built using PPI data characterising gene sets at log‐FC (LFC)>1, LFC>1.5 and LFC>2, and interconnection between principal hub nodes of these networks is observed. Resulting network of hubs at three FC levels highlights prime NMs with high confidence in multiple cancers as validated by Gene Ontology functional enrichment and maximal complete subgraphs from CFinder.Inspec keywords: cancer, proteins, RNA, bioinformatics, statistical analysis, genetics, molecular biophysics, ontologies (artificial intelligence), lungOther keywords: cancer network, PPI data, gene sets, multiple cancers, Gene Ontology functional enrichment, prostate cancer, gene expression data, RNA‐seq platforms, protein–protein interaction network, DEG, microarray data, RNA‐seq data, cancer types, lung cancer, diseases, breast cancer, network markers, differentially expressed genes, fold change based approach, CFinder, statistical methods     

Fuzzy cognitive map based approach for determining the risk of ischemic stroke

Stroke is the third major cause of mortality in the world. The diagnosis of stroke is a very complex issue considering controllable and uncontrollable factors. These factors include age, sex, blood pressure, diabetes, obesity, heart disease, smoking, and so on, having a considerable influence on the diagnosis of stroke. Hence, designing an intelligent system leading to immediate and effective treatment is essential. In this study, the soft computing method known as fuzzy cognitive mapping was proposed for diagnosis of the risk of ischemic stroke. Non‐linear Hebbian learning method was used for fuzzy cognitive maps training. In the proposed method, the risk rate for each person was determined based on the opinions of the neurologists. The accuracy of the proposed model was tested using 10‐fold cross‐validation, for 110 real cases, and the results were compared with those of support vector machine and K ‐nearest neighbours. The proposed system showed a superior performance with a total accuracy of (93.6 ± 4.5)%. The data used in this study is available by emailing the first author for academic and non‐commercial purposes.Inspec keywords: patient diagnosis, fuzzy logic, diseases, medical computing, cognition, learning (artificial intelligence), fuzzy set theory, Hebbian learning, neural nets, support vector machinesOther keywords: ischemic stroke, controllable factors, uncontrollable factors, blood pressure, heart disease, intelligent system, immediate treatment, soft computing method, fuzzy cognitive mapping, nonlinear Hebbian learning method, fuzzy cognitive maps training, risk rate     

Construction and investigation of breast‐cancer‐specific ceRNA network based on the mRNA and miRNA expression data

It has been proved and widely acknowledged that messenger RNAs can talk to each other by competing for a limited pool of miRNAs. The competing endogenous RNAs are called as ceRNAs. Although some researchers have recently used ceRNAs to do biological function annotations, few of them have investigated the ceRNA network on specific disease systematically. In this work, using both miRNA expression data and mRNA expression data of breast cancer patient as well as the miRNA target relations, the authors proposed a computational method to construct a breast‐cancer‐specific ceRNA network by checking whether the shared miRNA sponges between the gene pairs are significant. The ceRNA network is shown to be scale‐free, thus the topological characters such as hub nodes and communities may provide important clues for the biological mechanism. Through investigation on the communities (the dense clusters) in the network, it was found that they are related to cancer hallmarks. In addition, through function annotation of the hub genes in the network, it was found that they are related to breast cancer. Moreover, classifiers based on the discriminative hubs can significantly distinguish breast cancer patients’ risks of distant metastasis in all the three independent data sets.Inspec keywords: cancer, genetics, medical computing, molecular biophysics, RNAOther keywords: breast‐cancer specific ceRNA network construction, miRNA expression data, mRNA expression data, gene pairs, computational method, dense clusters, cancer hallmarks, biological mechanism, discriminative hub genes     

Biclustering‐based association rule mining approach for predicting cancer‐associated protein interactions

Protein–protein interactions (PPIs) have been widely used to understand different biological processes and cellular functions associated with several diseases like cancer. Although some cancer‐related protein interaction databases are available, lack of experimental data and conflicting PPI data among different available databases have slowed down the cancer research. Therefore, in this study, the authors have focused on various proteins that are directly related to different types of cancer disease. They have prepared a PPI database between cancer‐associated proteins with the rest of the human proteins. They have also incorporated the annotation type and direction of each interaction. Subsequently, a biclustering‐based association rule mining algorithm is applied to predict new interactions with type and direction. This study shows the prediction power of association rule mining algorithm over the traditional classifier model without choosing a negative data set. The time complexity of the biclustering‐based association rule mining is also analysed and compared to traditional association rule mining. The authors are able to discover 38 new PPIs which are not present in the cancer database. The biological relevance of these newly predicted interactions is analysed by published literature. Recognition of such interactions may accelerate a way of developing new drugs to prevent different cancer‐related diseases.Inspec keywords: cancer, medical computing, data mining, proteins, genetics, pattern clusteringOther keywords: biological processes, cancer‐related diseases, cancer research, cancer‐related protein interaction databases, protein–protein interactions, cancer‐associated protein interactions, biclustering‐based association rule mining approach, negative data set, annotation type, human proteins, cancer‐associated proteins, PPI database, cancer disease