Improved Classification of Lung Cancer Using Radial Basis Function Neural Network with Affine Transforms of Voss Representation

Lung cancer is one of the diseases responsible for a large number of cancer related death cases worldwide. The recommended standard for screening and early detection of lung cancer is the low dose computed tomography. However, many patients diagnosed die within one year, which makes it essential to find alternative approaches for screening and early detection of lung cancer. We present computational methods that can be implemented in a functional multi-genomic system for classification, screening and early detection of lung cancer victims. Samples of top ten biomarker genes previously reported to have the highest frequency of lung cancer mutations and sequences of normal biomarker genes were respectively collected from the COSMIC and NCBI databases to validate the computational methods. Experiments were performed based on the combinations of Z-curve and tetrahedron affine transforms, Histogram of Oriented Gradient (HOG), Multilayer perceptron and Gaussian Radial Basis Function (RBF) neural networks to obtain an appropriate combination of computational methods to achieve improved classification of lung cancer biomarker genes. Results show that a combination of affine transforms of Voss representation, HOG genomic features and Gaussian RBF neural network perceptibly improves classification accuracy, specificity and sensitivity of lung cancer biomarker genes as well as achieving low mean square error.     

Preparation of Monodomain Liquid Crystal Elastomers and Liquid Crystal Elastomer Nanocomposites

LCEs are shape-responsive materials with fully reversible shape change and potential applications in medicine, tissue engineering, artificial muscles, and as soft robots. Here, we demonstrate the preparation of shape-responsive liquid crystal elastomers (LCEs) and LCE nanocomposites along with characterization of their shape-responsiveness, mechanical properties, and microstructure. Two types of LCEs — polysiloxane-based and epoxy-based — are synthesized, aligned, and characterized. Polysiloxane-based LCEs are prepared through two crosslinking steps, the second under an applied load, resulting in monodomain LCEs. Polysiloxane LCE nanocomposites are prepared through the addition of conductive carbon black nanoparticles, both throughout the bulk of the LCE and to the LCE surface. Epoxy-based LCEs are prepared through a reversible esterification reaction. Epoxy-based LCEs are aligned through the application of a uniaxial load at elevated (160 °C) temperatures. Aligned LCEs and LCE nanocomposites are characterized with respect to reversible strain, mechanical stiffness, and liquid crystal ordering using a combination of imaging, two-dimensional X-ray diffraction measurements, differential scanning calorimetry, and dynamic mechanical analysis. LCEs and LCE nanocomposites can be stimulated with heat and/or electrical potential to controllably generate strains in cell culture media, and we demonstrate the application of LCEs as shape-responsive substrates for cell culture using a custom-made apparatus.