Effect of femtosecond laser induced surface patterns on the flexural strength of monolithic zirconia.

To investigate how patterns generated by femtosecond (fs) laser and femtosecond laser power affect the surface roughness (Ra) and biaxial flexural strength (BFS) of monolithic zirconia. Eighty disk-shaped zirconia specimens were divided into eight subgroups (n = 10): Control (C), airborne-particle abrasion (APA), 400 mW fs laser (spiral [SP(400)], square [SQ(400)], circular [CI(400)]), and 700 mW fs laser ([SP(700)], [SQ(700)], [CI(700)]). Ra values were calculated by using a surface profilometer. One additional specimen per group was analyzed with scanning electron microscopy and x-ray diffractometry. BFS values were obtained by using the piston-on-3-ball test. One-way ANOVA and either Tukey's HSD (BFS) or Tamhane's T2 (Ra) tests were used to evaluate data (α = 0.05). Regardless of the pattern and power, fs laser groups had higher Ra than C and APA, while SP groups had lower Ra than CI and SQ groups (p ≤ 0.004). For each pattern, Ra increased with higher laser power (p < 0.001), while the laser power did not affect the BFS (p ≥ 0.793). CI and SQ groups had lower BFS than the other groups (p ≤ 0.040), whereas SP groups had similar BFS to C and APA (p ≥ 0.430). Fs laser microstructuring with spiral surface pattern increased the Ra without jeopardizing the BFS of zirconia. Thus, this treatment might be an option to roughen tested zirconia.

Classification of Influenza Hemagglutinin Protein Sequences using Convolutional Neural Networks.

The Influenza virus can be considered as one of the most severe viruses that can infect multiple species with often fatal consequences to the hosts. The Hemagglutinin (HA) gene of the virus can be a target for antiviral drug development realised through accurate identification of its sub-types and possible the targeted hosts. This paper focuses on accurately predicting if an Influenza type A virus can infect specific hosts, and more specifically, Human, Avian and Swine hosts, using only the protein sequence of the HA gene. In more detail, we propose encoding the protein sequences into numerical signals using the Hydrophobicity Index and subsequently utilising a Convolutional Neural Network-based predictive model. The Influenza HA protein sequences used in the proposed work are obtained from the Influenza Research Database (IRD). Specifically, complete and unique HA protein sequences were used for avian, human and swine hosts. The data obtained for this work was 17999 human-host proteins, 17667 avian-host proteins and 9278 swine-host proteins. Given this set of collected proteins, the proposed method yields as much as 10% higher accuracy for an individual class (namely, Avian) and 5% higher overall accuracy than in an earlier study. It is also observed that the accuracy for each class in this work is more balanced than what was presented in this earlier study. As the results show, the proposed model can distinguish HA protein sequences with high accuracy whenever the virus under investigation can infect Human, Avian or Swine hosts.

Investigation of the expression levels of CPEB4, APC, TRIP13, EIF2S3, EIF4A1, IFNg, PIK3CA and CTNNB1 genes in different stage colorectal tumors

Background/aim: The aim of the study is to assess expression levels of CPEB4, APC, TRIP13, EIF2S3, EIF4A1, IFNg, PIK3CA and CTNNB1 genes in tumors and peripheral bloods of colorectal cancer patients in stages I­IV. Materials and methods: The mRNA levels of the genes were determined in tumor tissues and peripheral blood samples of 45 colorectal cancer patients and colon tissues and peripheral blood samples of 5 healthy individuals. Real-time polymerase chain reaction method was used for the analysis. Results: The mRNA level of the CPEB4 gene was significantly downregulated in colorectal tumor tissues and was upregulated in the peripheral blood of colorectal cancer patients relative to the controls (P < 0.05). APC mRNA level was significantly downregulated in tissues and upregulated in the peripheral blood (P < 0.05). TRIP13 mRNA level was upregulated in peripheral blood and also significantly upregulated in colorectal tumor tissues (P < 0.05). EIF2S3 mRNA level was upregulated in tissues and also significantly upregulated in peripheral blood (P < 0.05). PIK3CA mRNA level was downregulated in tissues and upregulated in peripheral blood. EIF4A1 mRNA level was downregulated in tissues and significantly upregulated in peripheral blood (P < 0.05). CTNNB1 mRNA level was downregulated in tissues and upregulated in peripheral blood. IFNg mRNA level was upregulated in both colorectal cancer tumor tissues and peripheral blood. Conclusion: TRIP13 and CPEB4 mRNA up regulation in the peripheral blood of patients with colorectal cancer may be a potential target for early stage diagnosis. In addition to this evaluation, although there is not much study on EIF2S3 and EIF4A1 mRNA changes in cases with colorectal cancer, upregulation in peripheral blood draws attention in our study. These data will shed light on the new comprehensive studies.

Automated lesion segmentation and dermoscopic feature segmentation for skin cancer analysis.

Segmentation is the first and most important task in computer-based diagnosis of skin cancer since other tasks are relied mainly on accurately segmented lesions. Recently, deep learning as a mainstream method in machine learning has shown promising results on semantic image segmentation. In this paper, we demonstrate applying deep convolutional networks to two main segmentation tasks in melanoma diagnosis, a lesion segmentation task followed by a lesion dermoscopic feature segmentation task. The proposed method is evaluated on a database from ISBI challenge 2016. By using a hybrid model, computation load for the second task decreases and masks provided by lesion segmentation have been used to enhance the results for the feature segmentation task as well. The results are close to the best results of ISBI challenge 2016. The proposed model yields quite promising results although it is based on very initial hybrid model without an aggressive fine-tuning that is heavily required in Deep Learning implementations. Therefore, there is a room for further improvements.

Prediction of Influenza A virus infections in humans using an Artificial Neural Network learning approach.

The Influenza type A virus can be considered as one of the most severe viruses that can infect multiple species with often fatal consequences to the hosts. The Haemagglutinin (HA) gene of the virus has the potential to be a target for antiviral drug development realised through accurate identification of its sub-types and possible the targeted hosts. In this paper, to accurately predict if an Influenza type A virus has the capability to infect human hosts, by using only the HA gene, is therefore developed and tested. The predictive model follows three main steps; (i) decoding the protein sequences into numerical signals using EIIP amino acid scale, (ii) analysing these sequences by using Discrete Fourier Transform (DFT) and extracting DFT-based features, (iii) using a predictive model, based on Artificial Neural Networks and using the features generated by DFT. In this analysis, from the Influenza Research Database, 30724, 18236 and 8157 HA protein sequences were collected for Human, Avian and Swine respectively. Given this set of the proteins, the proposed method yielded 97.36% (± 0.04%), 97.26% (± 0.26%), 0.978 (± 0.004), 0.963 (± 0.005) and 0.945 (±0.005) for the training accuracy validation accuracy, precision, recall and Mathews Correlation Coefficient (MCC) respectively, based on a 10-fold cross-validation. The classification model generated by using one of the largest dataset, if not the largest, yields promising results that could lead to early detection of such species and help develop precautionary measurements for possible human infections.

Recognition of protozoan parasites from microscopic images: Eimeria species in chickens and rabbits as a case study.

Automated diagnosis and identification of diseases and conditions such as parasites from microscopic images have been mainly carried out by utilizing the object morphological characteristics. The extraction of morphometric features needs the use of highly complex techniques that require computational power. Therefore, in order to reduce this complexity, this paper presents an automated identification based on analyzing three groups of pixel-based feature sets: column features (CF), row features (RF), and the third one (CRF) obtained by merging CF and RF together. For the classification task, K-Nearest Neighbor (KNN) and Artificial Neural Networks (ANN) have been applied. The classification results have been evaluated by adapting a 5-fold cross validation. Additionally, a robust sub-set of the features has been selected by Relieff feature selection method to prevent overfitting, which in turn has improved the final results. Two microscopic image slide databases of a type of protozoan parasites genus called Eimeria in fowls and rabbits have been examined in order to assess the robustness of the proposed methods. The highest accuracy rates obtained when the entire features were used are 85.55% (±0.39%) and 96.6% (±0.82%) from grey-scale level and color images, respectively. These results have been increased by 5% when the feature size is reduced by two thirds when Relieff was utilized. The feature sets have yielded highly accurate results and are expected to make the automatic identification simpler than the analysis of morphological features.

Exploration of unsupervised feature selection methods to predict chronological age of individuals by utilising CpG dinucleotics from whole blood.

Identification of the age of individuals from epigenetic biomarkers can reveal vital information for criminal investigation, disease prevention, and extension of life. DNA methylation changes are highly associated with chronological age and the process of disease development. Computational methods such as clustering, feature selection and regression can be utilised to construct quantitative model of aging. In this study, we utilised 473034 CpG biomarkers from whole blood of 656 individuals aged 19 to 101 to construct predictive models and we treat the development of this age predictive model as extremely high-dimensional regression problem that is relatively understudied. Unlike semi-supervised and supervised feature selection methods, unsupervised feature selection methods are generally good at removing irrelevant features that can act as noise. In this study, along with the entire feature set, four different unsupervised feature selection methods (USFSMs) are therefore considered for the quantitative prediction of human ages. Since USFSMs are independent of any predictive method, support vector regression is then used to evaluate the prediction performances of the unsupervised feature selection methods. We proposed a novel k-means based unsupervised feature selection method to predict human ages by utilising CpG dinucleotides. Experimental results have validated the effectiveness of the proposed method as the optimum number of the CpG dinucleotides is found to be only 41 that corresponds to only 0.0087% of the entire feature space. To the best of our knowledge, this is the first study that presents exploration and comprehensive comparison of USFSMs in very high dimensional regression problems, particularly in epigenetic biomedical domain for the prediction of chronological age from changes in DNA methylation.

Unsupervised selection of RV144 HIV vaccine-induced antibody features correlated to natural killer cell-mediated cytotoxic reactions.

HIV-1 vaccine injection has been shown less effective due to the diversity of antigens. Increasing the knowledge of the associations between immune system and virus would ultimately result in producing effective vaccines against HIV-1 virus. To increase the understanding of immunological information, computational models can be utilised to construct predictive models. The aim of this study is, therefore, to predict the effect of antibody features (IgGs) and primary Natural Killing (NK) cells' cytotoxic activities on RV144 vaccine recipients and to disclose the functional relationship between immune system and HIV virus. The RV144 vaccine data set contains 100 data samples in which 20 of them are the placebo samples and 80 of them are the vaccine injected samples. Each data sample has twenty antibody features that consist of features related to IgG subclass and antigen specificity. In this paper, five different unsupervised feature selection methods (USFSMs) are utilised in order to identify the discriminating antibody features as USFSMs are regarded as unbiased approach. Then, the support vector based methods are utilised to assess association between cellular cytotoxicity by Natural Killer (NK) cells and cells that release glycoprotein (gp)120 antibody. The results yield high correlation coefficient as much as 0.48 and 0.65 for classificationthe support vector regression (SVR) and classification (SVM) predictive models, respectively.

Structural classification of protein sequences based on signal processing and support vector machines.

The function of any protein depends directly on its secondary and tertiary structure. Proteins can fold into a three-dimensional shape, which is primarily depended on the arrangement of amino acids in the primary structure. In recent years, with the explosive sequencing of proteins, it is unfeasible to perform detailed experimental studies, as these methodologies are very expensive and time consuming. This leaves the structure of the majority of currently available protein sequences unknown. In this paper, a predictive model is therefore presented for the classification of protein sequence's secondary structures, namely alpha helix and beta sheet. The proteins used throughout this study were collected from the Structural Classification of Proteinsextended (SCOPe) database, which contains manually curated information from proteins with known structure. Two sets of proteins are used for all alpha and all beta protein sequences. The first set comprise of sequences with less than 40% identity, and the second set comprise of proteins with less than 95% identity. The analysis shows a strong connection between the amino acid indices used to convert protein sequences to numerical sequences and proteins' secondary structures. The total classification accuracy for the proposed classifier for the protein sequences with less than 40% identity for amino acid index BIOV880101 and BIOV880102 are 78.49% and 76.40%, respectively. The classification accuracy for sets of protein sequences with less than 95% identity for amino acid index BIOV880101 and BIOV880102 are 88.01% and 85.17%, respectively.

Binding affinity prediction of S. cerevisiae 14-3-3 and GYF peptide-recognition domains using support vector regression.

Proteins interact with other proteins and bio-molecules to carry out biological processes in a cell. Computational models help understanding complex biochemical processes that happens throughout the life of a cell. Domain-mediated protein interaction to peptides one such complex problem in bioinformatics that requires computational predictive models to identify meaningful bindings. In this study, domain-peptide binding affinity prediction models are proposed based on support vector regression. Proposed models are applied to yeast bmh 14-3-3 and syh GYF peptide-recognition domains. The cross validated results of the domain-peptide binding affinity data sets show that predictive performance of the support vector based models are efficient.

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.

CISAPS: Complex Informational Spectrum for the Analysis of Protein Sequences.

Complex informational spectrum analysis for protein sequences (CISAPS) and its web-based server are developed and presented. As recent studies show, only the use of the absolute spectrum in the analysis of protein sequences using the informational spectrum analysis is proven to be insufficient. Therefore, CISAPS is developed to consider and provide results in three forms including absolute, real, and imaginary spectrum. Biologically related features to the analysis of influenza A subtypes as presented as a case study in this study can also appear individually either in the real or imaginary spectrum. As the results presented, protein classes can present similarities or differences according to the features extracted from CISAPS web server. These associations are probable to be related with the protein feature that the specific amino acid index represents. In addition, various technical issues such as zero-padding and windowing that may affect the analysis are also addressed. CISAPS uses an expanded list of 611 unique amino acid indices where each one represents a different property to perform the analysis. This web-based server enables researchers with little knowledge of signal processing methods to apply and include complex informational spectrum analysis to their work.

The quantitative prediction of HLA-B*2705 peptide binding affinities using Support Vector Regression to gain insights into its role for the Spondyloarthropathies.

Computational methods are increasingly utilised in many immunoinformatics problems such as the prediction of binding affinity of peptides. The peptides could provide valuable insight into the drug design and development such as vaccines. Moreover, they can be used to diagnose diseases. The presence of human class I MHC allele HLA-B*2705 is one of the strong hypothesis that would lead spondyloarthropathies. In this paper, Support Vector Regression is used in order to predict binding affinity of peptides with the aid of experimentally determined peptide-MHC binding affinities of 222 peptides to HLA-B*2705 to get more insight into this problematic disease. The results yield a high correlation coefficient as much as 0.65 and the SVR-based predictive models can be considered as a useful tool in order to predict the binding affinities for newly discovered peptides.

Dynamic partial reconfiguration implementation of the SVM/KNN multi-classifier on FPGA for bioinformatics application.

Bioinformatics data tend to be highly dimensional in nature thus impose significant computational demands. To resolve limitations of conventional computing methods, several alternative high performance computing solutions have been proposed by scientists such as Graphical Processing Units (GPUs) and Field Programmable Gate Arrays (FPGAs). The latter have shown to be efficient and high in performance. In recent years, FPGAs have been benefiting from dynamic partial reconfiguration (DPR) feature for adding flexibility to alter specific regions within the chip. This work proposes combing the use of FPGAs and DPR to build a dynamic multi-classifier architecture that can be used in processing bioinformatics data. In bioinformatics, applying different classification algorithms to the same dataset is desirable in order to obtain comparable, more reliable and consensus decision, but it can consume long time when performed on conventional PC. The DPR implementation of two common classifiers, namely support vector machines (SVMs) and K-nearest neighbor (KNN) are combined together to form a multi-classifier FPGA architecture which can utilize specific region of the FPGA to work as either SVM or KNN classifier. This multi-classifier DPR implementation achieved at least ~8x reduction in reconfiguration time over the single non-DPR classifier implementation, and occupied less space and hardware resources than having both classifiers. The proposed architecture can be extended to work as an ensemble classifier.

Comparison of unsupervised feature selection methods for high-dimensional regression problems in prediction of peptide binding affinity.

Identification of robust set of predictive features is one of the most important steps in the construction of clustering, classification and regression models from many thousands of features. Although there have been various attempts to select predictive feature sets from high-dimensional data sets in classification and clustering, there is a limited attempt to study it in regression problems. As semi-supervised and supervised feature selection methods tend to identify noisy features in addition to discriminative variables, unsupervised feature selection methods (USFSMs) are generally regarded as more unbiased approach. Therefore, in this study, along with the entire feature set, four different USFSMs are considered for the quantitative prediction of peptide binding affinities being one of the most challenging post-genome regression problems of very high-dimension comparted to extremely small size of samples. As USFSMs are independent of any predictive method, support vector regression was then utilised to assess the quality of prediction. Given three different peptide binding affinity data sets, the results suggest that the regression performance of USFMs depends generally on the datasets. There is no particular method that yields the best performance compared to their performances in the classification problems. However, a closer investigation of the results appears to suggest that the spectral regression-based approach yields slightly better performance. To the best of our knowledge, this is the first study that presents comprehensive comparison of USFSMs in such high-dimensional regression problems, particularly in biological domain with an application in the prediction of peptide binding affinity, and provides a number of practical suggestions for future practitioners.

Inference of nonlinear gene regulatory networks through optimized ensemble of support vector regression and dynamic Bayesian networks.

Comprehensive understanding of gene regulatory networks (GRNs) is a major challenge in systems biology. Most methods for modeling and inferring the dynamics of GRNs, such as those based on state space models, vector autoregressive models and G1DBN algorithm, assume linear dependencies among genes. However, this strong assumption does not make for true representation of time-course relationships across the genes, which are inherently nonlinear. Nonlinear modeling methods such as the S-systems and causal structure identification (CSI) have been proposed, but are known to be statistically inefficient and analytically intractable in high dimensions. To overcome these limitations, we propose an optimized ensemble approach based on support vector regression (SVR) and dynamic Bayesian networks (DBNs). The method called SVR-DBN, uses nonlinear kernels of the SVR to infer the temporal relationships among genes within the DBN framework. The two-stage ensemble is further improved by SVR parameter optimization using Particle Swarm Optimization. Results on eight insilico-generated datasets, and two real world datasets of Drosophila Melanogaster and Escherichia Coli, show that our method outperformed the G1DBN algorithm by a total average accuracy of 12%. We further applied our method to model the time-course relationships of ovarian carcinoma. From our results, four hub genes were discovered. Stratified analysis further showed that the expression levels Prostrate differentiation factor and BTG family member 2 genes, were significantly increased by the cisplatin and oxaliplatin platinum drugs; while expression levels of Polo-like kinase and Cyclin B1 genes, were both decreased by the platinum drugs. These hub genes might be potential biomarkers for ovarian carcinoma.

Novel protein weight matrix generated from amino acid indices.

In recent years, numerous protein weight matrices have been developed that include physical characteristics of proteins, such as local sequence-structure information, alpha-helix information, secondary structure information and solvent accessibility states. These protein weight matrices are shown to have generally improved protein sequence alignments over classical protein weight matrices, like Point Accepted Mutation (PAM), Blocks of Amino Acid Substitution (BLOSUM), and GONNET matrices, where important limitations have been observe in recent works. In this paper, a novel protein weight matrix is constructed and presented. This protein weight matrix is not considered based on the mutation rate, like PAM or BLOSUM matrices, but on the physicochemical properties of each amino acid. In the literature, over 500 amino acid indices exist, each one representing a unique biological protein feature. For this study, 25 amino acid indices were selected. These amino acid indices represent general and widely accepted features of the amino acids. By using the proposed protein weight matrix the following advantages can be obtained compared to the classical protein weight matrices. The proposed protein weight matrix is not biased to specific groups of protein sequences as the values are calculated from the amino acid indices, and not from the protein sequences. Additionally, for the proposed protein weight matrix, the same matrix can be considered regardless of the protein sequence's homology to be aligned or the mutation rate presented. A correlation to the physical characterisations of the amino acids that the protein weight matrix derived from can be achieved. Different similarity matrices can be generated when different physical characterisations of amino acids are considered.

Pigment network-based skin cancer detection.

Diagnosing skin cancer in its early stages is a challenging task for dermatologists given the fact that the chance for a patient's survival is higher and hence the process of analyzing skin images and making decisions should be time efficient. Therefore, diagnosing the disease using automated and computerized systems has nowadays become essential. This paper proposes an efficient system for skin cancer detection on dermoscopic images. It has been shown that the statistical characteristics of the pigment network, extracted from the dermoscopic image, could be used as efficient discriminating features for cancer detection. The proposed system has been assessed on a dataset of 200 dermoscopic images of the `Hospital Pedro Hispano' [1] and the results of cross-validation have shown high detection accuracy.

Combining multiple clusterings for protein structure prediction.

Computational annotation and prediction of protein structure is very important in the post-genome era due to existence of many different proteins, most of which are yet to be verified. Mutual information based feature selection methods can be used in selecting such minimal yet predictive subsets of features. However, as protein features are organised into natural partitions, individual feature selection that ignores the presence of these views, dismantles them, and treats their variables intermixed along with those of others at best results in a complex un-interpretable predictive system for such multi-view datasets. In this paper, instead of selecting a subset of individual features, each feature subset is passed through a clustering step so that it is represented in discrete form using the cluster indices; this makes mutual information based methods applicable to view-selection. We present our experimental results on a multi-view protein dataset that are used to predict protein structure.

A hybrid dynamic Bayesian network approach for modelling temporal associations of gene expressions for hypertension diagnosis.

Computational and machine learning techniques have been applied in identifying biomarkers and constructing predictive models for diagnosis of hypertension. Strategies such as improved classification rules based on decision trees have been proposed. Other techniques such as Fuzzy Expert Systems (FES) and Neuro-Fuzzy Systems (NFS) have recently been applied. However, these methods lack the ability to detect temporal relationships among biomarker genes that will aid better understanding of the mechanism of hypertension disease. In this paper we apply a proposed two-stage bio-network construction approach that combines the power and computational efficiency of classification methods with the well-established predictive ability of Dynamic Bayesian Network. We demonstrate our method using the analysis of male young-onset hypertension microarray dataset. Four key genes were identified by the Least Angle Shrinkage and Selection Operator (LASSO) and three Support Vector Machine Recursive Feature Elimination (SVM-RFE) methods. Results show that cell regulation FOXQ1 may inhibit the expression of focusyltransferase-6 (FUT6) and that ABCG1 ATP-binding cassette sub-family G may also play inhibitory role against NR2E3 nuclear receptor sub-family 2 and CGB2 Chromatin Gonadotrophin.