A hybrid metaheuristic-deep learning technique for the pan-classification of cancer based on DNA methylation.

BACKGROUND: DNA Methylation is one of the most important epigenetic processes that are crucial to regulating the functioning of the human genome without altering the DNA sequence. DNA Methylation data for cancer patients are becoming more accessible than ever, which is attributed to newer DNA sequencing technologies, notably, the relatively low-cost DNA microarray technology by Illumina Infinium. This technology makes it possible to study DNA methylation at hundreds of thousands of different loci. Currently, most of the research found in the literature focuses on the discovery of DNA methylation markers for specific cancer types. A relatively small number of studies have attempted to find unified DNA methylation biomarkers that can diagnose different types of cancer (pan-cancer classification). RESULTS: In this study, the aim is to conduct a pan-classification of cancer disease. We retrieved individual data for different types of cancer patients from The Cancer Genome Atlas (TCGA) portal. We selected data for many cancer types: Breast Cancer (BRCA), Ovary Cancer (OV), Stomach Cancer (STOMACH), Colon Cancer (COAD), Kidney Cancer (KIRC), Liver Cancer (LIHC), Lung Cancer (LUSC), Prostate Cancer (PRAD) and Thyroid cancer (THCA). The data was pre-processed and later used to build the required dataset. The system that we developed consists of two main stages. The purpose of the first stage is to perform feature selection and, therefore, decrease the dimensionality of the DNA methylation loci (features). This is accomplished using an unsupervised metaheuristic technique. As for the second stage, we used supervised machine learning and developed deep neural network (DNN) models to help classify the samples' malignancy status and cancer type. Experimental results showed that compared to recently published methods, our proposed system achieved better classification results in terms of recall, and similar and higher results in terms of precision and accuracy. The proposed system also achieved an excellent receiver operating characteristic area under the curve (ROC AUC) values varying from 0.85 to 0.89. CONCLUSIONS: This research presented an effective new approach to classify different cancer types based on DNA methylation data retrieved from TCGA. The performance of the proposed system was compared to recently published works, using different performance metrics. It provided better results, confirming the effectiveness of the proposed method for classifying different cancer types based on DNA methylation data.

Novel trajectory clustering method based on distance dependent Chinese restaurant process.

Trajectory clustering and path modelling are two core tasks in intelligent transport systems with a wide range of applications, from modeling drivers' behavior to traffic monitoring of road intersections. Traditional trajectory analysis considers them as separate tasks, where the system first clusters the trajectories into a known number of clusters and then the path taken in each cluster is modelled. However, such a hierarchy does not allow the knowledge of the path model to be used to improve the performance of trajectory clustering. Based on the distance dependent Chinese restaurant process (DDCRP), a trajectory analysis system that simultaneously performs trajectory clustering and path modelling was proposed. Unlike most traditional approaches where the number of clusters should be known, the proposed method decides the number of clusters automatically. The proposed algorithm was tested on two publicly available trajectory datasets, and the experimental results recorded better performance and considerable improvement in both datasets for the task of trajectory clustering compared to traditional approaches. The study proved that the proposed method is an appropriate candidate to be used for trajectory clustering and path modelling.

Automatic Region-Based Brain Classification of MRI-T1 Data.

Image segmentation of medical images is a challenging problem with several still not totally solved issues, such as noise interference and image artifacts. Region-based and histogram-based segmentation methods have been widely used in image segmentation. Problems arise when we use these methods, such as the selection of a suitable threshold value for the histogram-based method and the over-segmentation followed by the time-consuming merge processing in the region-based algorithm. To provide an efficient approach that not only produce better results, but also maintain low computational complexity, a new region dividing based technique is developed for image segmentation, which combines the advantages of both regions-based and histogram-based methods. The proposed method is applied to the challenging applications: Gray matter (GM), White matter (WM) and cerebro-spinal fluid (CSF) segmentation in brain MR Images. The method is evaluated on both simulated and real data, and compared with other segmentation techniques. The obtained results have demonstrated its improved performance and robustness.

An Efficient Optimization Method for Solving Unsupervised Data Classification Problems.

Unsupervised data classification (or clustering) analysis is one of the most useful tools and a descriptive task in data mining that seeks to classify homogeneous groups of objects based on similarity and is used in many medical disciplines and various applications. In general, there is no single algorithm that is suitable for all types of data, conditions, and applications. Each algorithm has its own advantages, limitations, and deficiencies. Hence, research for novel and effective approaches for unsupervised data classification is still active. In this paper a heuristic algorithm, Biogeography-Based Optimization (BBO) algorithm, was adapted for data clustering problems by modifying the main operators of BBO algorithm, which is inspired from the natural biogeography distribution of different species. Similar to other population-based algorithms, BBO algorithm starts with an initial population of candidate solutions to an optimization problem and an objective function that is calculated for them. To evaluate the performance of the proposed algorithm assessment was carried on six medical and real life datasets and was compared with eight well known and recent unsupervised data classification algorithms. Numerical results demonstrate that the proposed evolutionary optimization algorithm is efficient for unsupervised data classification.

Magnetic resonance image tissue classification using an automatic method.

BACKGROUND: Brain segmentation in magnetic resonance images (MRI) is an important stage in clinical studies for different issues such as diagnosis, analysis, 3-D visualizations for treatment and surgical planning. MR Image segmentation remains a challenging problem in spite of different existing artifacts such as noise, bias field, partial volume effects and complexity of the images. Some of the automatic brain segmentation techniques are complex and some of them are not sufficiently accurate for certain applications. The goal of this paper is proposing an algorithm that is more accurate and less complex). METHODS: In this paper we present a simple and more accurate automated technique for brain segmentation into White Matter, Gray Matter and Cerebrospinal fluid (CSF) in three-dimensional MR images. The algorithm's three steps are histogram based segmentation, feature extraction and final classification using SVM. The integrated algorithm has more accurate results than what can be obtained with its individual components. To produce much more efficient segmentation method our framework captures different types of features in each step that are of special importance for MRI, i.e., distributions of tissue intensities, textural features, and relationship with neighboring voxels or spatial features. RESULTS: Our method has been validated on real images and simulated data, with desirable performance in the presence of noise and intensity inhomogeneities. CONCLUSIONS: The experimental results demonstrate that our proposed method is a simple and accurate technique to define brain tissues with high reproducibility in comparison with other techniques. VIRTUAL SLIDES: The virtual slide(s) for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/13000_2014_207.

An analytical approach to evaluate the performance of graphene and carbon nanotubes for NH3 gas sensor applications.

Carbon, in its variety of allotropes, especially graphene and carbon nanotubes (CNTs), holds great potential for applications in variety of sensors because of dangling π-bonds that can react with chemical elements. In spite of their excellent features, carbon nanotubes (CNTs) and graphene have not been fully exploited in the development of the nanoelectronic industry mainly because of poor understanding of the band structure of these allotropes. A mathematical model is proposed with a clear purpose to acquire an analytical understanding of the field-effect-transistor (FET) based gas detection mechanism. The conductance change in the CNT/graphene channel resulting from the chemical reaction between the gas and channel surface molecules is emphasized. NH3 has been used as the prototype gas to be detected by the nanosensor and the corresponding current-voltage (I-V) characteristics of the FET-based sensor are studied. A graphene-based gas sensor model is also developed. The results from graphene and CNT models are compared with the experimental data. A satisfactory agreement, within the uncertainties of the experiments, is obtained. Graphene-based gas sensor exhibits higher conductivity compared to that of CNT-based counterpart for similar ambient conditions.

Development of solution-gated graphene transistor model for biosensors.

: The distinctive properties of graphene, characterized by its high carrier mobility and biocompatibility, have stimulated extreme scientific interest as a promising nanomaterial for future nanoelectronic applications. In particular, graphene-based transistors have been developed rapidly and are considered as an option for DNA sensing applications. Recent findings in the field of DNA biosensors have led to a renewed interest in the identification of genetic risk factors associated with complex human diseases for diagnosis of cancers or hereditary diseases. In this paper, an analytical model of graphene-based solution gated field effect transistors (SGFET) is proposed to constitute an important step towards development of DNA biosensors with high sensitivity and selectivity. Inspired by this fact, a novel strategy for a DNA sensor model with capability of single-nucleotide polymorphism detection is proposed and extensively explained. First of all, graphene-based DNA sensor model is optimized using particle swarm optimization algorithm. Based on the sensing mechanism of DNA sensors, detective parameters (Ids and Vgmin) are suggested to facilitate the decision making process. Finally, the behaviour of graphene-based SGFET is predicted in the presence of single-nucleotide polymorphism with an accuracy of more than 98% which guarantees the reliability of the optimized model for any application of the graphene-based DNA sensor. It is expected to achieve the rapid, quick and economical detection of DNA hybridization which could speed up the realization of the next generation of the homecare sensor system.