Modeling of Cancer Classifier to Predict Site of Origin

Identification of Homo sapiens cancer classes based on fusion of hidden gene features

Classification of Homo sapiens cancer genes in molecular level is a challenging research issue as they are extremely pseudo random in nature. Signature gene features need to be exposed to distinctly identify the gene class. Tree-structured filter bank is chosen to perform feature extraction and dimension reduction of the genes. Extracted gene features are fused using Gaussian mixture probability distribution function and identify different cancer classes depending on amount of correlation and exploiting maximum likelihood function. The algorithm is tested on 161 sample gene data of 7 different cancer classes. Sensitivity, specificity, accuracy, precision and F-score are used as metrics to judge the performance of the system and ROC is plotted in comparison with existing electrical network model based classifier. The proposed classifier can identify more than stated number of cancer classes which is a major limitation of the existing electrical network based method. The proposed algorithm is validated by comparing the results with other seven existing image processing based methods.

Performance analysis of melanoma classifier using electrical modeling technique

An efficient and novel modeling approach is proposed in this paper for identifying proteins or genes involved in melanoma skin cancer. Two types of classifiers are modeled, based on the chemical structure and hydropathy property of amino acids. These classifiers are further implemented using NI LabVIEW-based hardware kit to observe the real-time response for proper diagnosis. The phase responses, pole-zero diagrams, and transient responses are examined to screen out the genes related to melanoma from healthy genes. The performance of the proposed classifier is measured using various performance measurement metrics in terms of accuracy, sensitivity, specificity, etc. The classifier is experimented along with a color code scheme on skin genes and illustrates the superiority in comparison with traditional methods by achieving 94% of classification accuracy with 96% of sensitivity.Graphical abstract An equivalent electrical model is developed for designing melanoma classifier. Initially, each amino acid is modeled using the RC passive circuit depending on their physicochemical structure and hydropathy nature, to form a gene structure model. The melanoma-related genes are detected by phase, transient, and color code analysis.

Hereditary disease prediction in eukaryotic DNA: an adaptive signal processing approach

Hereditary disease prediction in eukaryotic DNA using signal processing approaches is an incredible work in bioinformatics. Researchers of various fields are trying to put forth a noninvasive approach to forecast the disease-related genes. As diseased genes are more random than the healthy ones, in this work, a comparison of the diseased gene is made against the healthy ones. An adaptive signal processing method like functional link artificial neural network-based Levenberg-Marquardt filter has been proposed in this regard. For parameter upgradation, the algorithm is modified using particle swarm optimization. Here, disease genes are discriminated from healthy ones based on the magnitude of mean square error (MSE), which is calculated through the adaptive filter. The performance of the algorithm is inspected by computing some evaluation parameters. Since accuracy is the prime concern, authors in this work have taken an attempt to improve the accuracy level compared to the existing methods. Taking the reference gene as healthy, the overall process is accomplished by categorizing the diseased and healthy targets with MSE value at a threshold of 0.012. The proposed technique predicts the test gene sets successfully.

A Markov chain-based feature extraction method for classification and identification of cancerous DNA sequences

Introduction: In recent decades, the growing rate of cancer incidence is a big concern for most societies. Due to the genetic origins of cancer disease, its internal structure is necessary for the study of this disease.

Methods: In this research, cancer data are analyzed based on DNA sequences. The transition probability of occurring two pairs of nucleotides in DNA sequences has Markovian property. This property inspires the idea of feature dimension reduction of DNA sequence for overcoming the high computational overhead of genes analysis. This idea is utilized in this research based on the Markovian property of DNA sequences. This mapping decreases feature dimensions and conserves basic properties for discrimination of cancerous and non-cancerous genes.

Results: The results showed that a non-linear support vector machine (SVM) classifier with RBF and polynomial kernel functions can discriminate selected cancerous samples from non-cancerous ones. Experimental results based on the 10-fold cross-validation and accuracy metrics verified that the proposed method has low computational overhead and high accuracy.

Conclusion: The proposed algorithm was successfully tested on related research case studies. In general, a combination of proposed Markovian-based feature reduction and non-linear SVM classifier can be considered as one of the best methods for discrimination of cancerous and non-cancerous genes.