Saras Saraswathi

ICGA-PSO-ELM Approach for Accurate Multiclass Cancer Classification Resulting in Reduced Gene Sets in Which Genes Encoding Secreted Proteins Are Highly Represented

A combination of Integer-Coded Genetic Algorithm (ICGA) and Particle Swarm Optimization (PSO), coupled with the neural-network-based Extreme Learning Machine (ELM), is used for gene selection and cancer classification. ICGA is used with PSO-ELM to select an optimal set of genes, which is then used to build a classifier to develop an algorithm (ICGA_PSO_ELM) that can handle sparse data and sample imbalance. We evaluate the performance of ICGA-PSO-ELM and compare our results with existing methods in the literature. An investigation into the functions of the selected genes, using a systems biology approach, revealed that many of the identified genes are involved in cell signaling and proliferation. An analysis of these gene sets shows a larger representation of genes that encode secreted proteins than found in randomly selected gene sets. Secreted proteins constitute a major means by which cells interact with their surroundings. Mounting biological evidence has identified the tumor microenvironment as a critical factor that determines tumor survival and growth. Thus, the genes identified by this study that encode secreted proteins might provide important insights to the nature of the critical biological features in the microenvironment of each tumor type that allow these cells to thrive and proliferate.

The importance of slow motions for protein functional loops

Loops in proteins that connect secondary structures such as alpha-helix and beta-sheet, are often on the surface and may play a critical role in some functions of a protein. The mobility of loops is central for the motional freedom and flexibility requirements of active-site loops and may play a critical role for some functions. The structures and behaviors of loops have not been studied much in the context of the whole structure and its overall motions, especially how these might be coupled. Here we investigate loop motions by using coarse-grained structures (C(α) atoms only) to solve the motions of the system by applying Lagrange equations with elastic network models to learn about which loops move in an independent fashion and which move in coordination with domain motions, faster and slower, respectively. The normal modes of the system are calculated using eigen-decomposition of the stiffness matrix. The contribution of individual modes and groups of modes is investigated for their effects on all residues in each loop by using Fourier analyses. Our results indicate overall that the motions of functional sets of loops behave in similar ways as the whole structure. But overall only a relatively few loops move in coordination with the dominant slow modes of motion, and these are often closely related to function.

Protein secondary structure prediction using a small training set (compact model) combined with a Complex-valued neural network approach

BackgroundProtein secondary structure prediction (SSP) has been an area of intense research interest. Despite advances in recent methods conducted on large datasets, the estimated upper limit accuracy is yet to be reached. Since the predictions of SSP methods are applied as input to higher-level structure prediction pipelines, even small errors may have large perturbations in final models. Previous works relied on cross validation as an estimate of classifier accuracy. However, training on large numbers of protein chains compromises the classifier ability to generalize to new sequences. This prompts a novel approach to training and an investigation into the possible structural factors that lead to poor predictions.Here, a small group of 55 proteins termed the compact model is selected from the CB513 dataset using a heuristics-based approach. In a prior work, all sequences were represented as probability matrices of residues adopting each of Helix, Sheet and Coil states, based on energy calculations using the C-Alpha, C-Beta, Side-chain (CABS) algorithm. The functional relationship between the conformational energies computed with CABS force-field and residue states is approximated using a classifier termed the Fully Complex-valued Relaxation Network (FCRN). The FCRN is trained with the compact model proteins.ResultsThe performance of the compact model is compared with traditional cross-validated accuracies and blind-tested on a dataset of G Switch proteins, obtaining accuracies of ∼81 %. The model demonstrates better results when compared to several techniques in the literature. A comparative case study of the worst performing chain identifies hydrogen bond contacts that lead to Coil ⇔ Sheet misclassifications. Overall, mispredicted Coil residues have a higher propensity to participate in backbone hydrogen bonding than correctly predicted Coils.ConclusionsThe implications of these findings are: (i) the choice of training proteins is important in preserving the generalization of a classifier to predict new sequences accurately and (ii) SSP techniques sensitive in distinguishing between backbone hydrogen bonding and side-chain or water-mediated hydrogen bonding might be needed in the reduction of Coil ⇔ Sheet misclassifications.

In Silico Modeling of Human α2C-Adrenoreceptor Interaction with Filamin-2

Vascular smooth muscle α2C-adrenoceptors (α2C-ARs) mediate vasoconstriction of small blood vessels, especially arterioles. Studies of endogenous receptors in human arteriolar smooth muscle cells (referred to as microVSM) and transiently transfected receptors in heterologous HEK293 cells show that the α2C-ARs are perinuclear receptors that translocate to the cell surface under cellular stress and elicit a biological response. Recent studies in microVSM unraveled a crucial role of Rap1A-Rho-ROCK-F-actin pathways in receptor translocation, and identified protein-protein interaction of α2C-ARs with the actin binding protein filamin-2 as an essential step in the process. To better understand the molecular nature and specificity of this interaction, in this study, we constructed comparative models of human α2C-AR and human filamin-2 proteins. Finally, we performed in silico protein-protein docking to provide a structural platform for the investigation of human α2C-AR and filamin-2 interactions. We found that electrostatic interactions seem to play a key role in this complex formation which manifests in interactions between the C-terminal arginines of α2C-ARs (particularly R454 and R456) and negatively charged residues from filamin-2 region between residues 1979 and 2206. Phylogenetic and sequence analysis showed that these interactions have evolved in warm-blooded animals.

Detection of onset of Alzheimer's disease from MRI images using a GA-ELM-PSO classifier

In this paper, a novel method for detecting the onset of Alzheimers disease (AD) from Magnetic Resonance Imaging (MRI) scans is presented. It uses a combination of three different machine learning algorithms in order to get improved results and is based on a three-class classification problem. The three classes for classification considered in this study are normal, very mild AD and mild and moderate AD subjects. The machine learning algorithms used are: the Extreme Learning Machine (ELM) for classification, with its performance optimized by a Particle Swarm Optimization (PSO) and a Genetic algorithm (GA) used for feature selection. A Voxel-Based Morphometry (VBM) approach is used for feature extraction from the MRI images and GA is used to reduce the high dimensional features needed for classification. The GA-ELM-PSO classifier yields an average training accuracy of 94.57 % and a testing accuracy of 87.23 %, averaged across the three classes, over ten random trials. The results clearly indicate that the proposed approach can differentiate between very mild AD and normal cases more accurately, indicating its usefulness in detecting the onset of AD.

Multi-class BCGA-ELM based classifier that identifies biomarkers associated with hallmarks of cancer

BackgroundTraditional cancer treatments have centered on cytotoxic drugs and general purpose chemotherapy that may not be tailored to treat specific cancers. Identification of molecular markers that are related to different types of cancers might lead to discovery of drugs that are patient and disease specific. This study aims to use microarray gene expression cancer data to identify biomarkers that are indicative of different types of cancers. Our aim is to provide a multi-class cancer classifier that can simultaneously differentiate between cancers and identify type-specific biomarkers, through the application of the Binary Coded Genetic Algorithm (BCGA) and a neural network based Extreme Learning Machine (ELM) algorithm.ResultsBCGA and ELM are combined and used to select a subset of genes that are present in the Global Cancer Mapping (GCM) data set. This set of candidate genes contains over 52 biomarkers that are related to multiple cancers, according to the literature. They include APOA1, VEGFC, YWHAZ, B2M, EIF2S1, CCR9 and many other genes that have been associated with the hallmarks of cancer. BCGA-ELM is tested on several cancer data sets and the results are compared to other classification methods. BCGA-ELM compares or exceeds other algorithms in terms of accuracy. We were also able to show that over 50% of genes selected by BCGA-ELM on GCM data are cancer related biomarkers.ConclusionsWe were able to simultaneously differentiate between 14 different types of cancers, using only 92 genes, to achieve a multi-class classification accuracy of 95.4% which is between 21.6% and 38% higher than other results in the literature for multi-class cancer classification. Our findings suggest that computational algorithms such as BCGA-ELM can facilitate biomarker-driven integrated cancer research that can lead to a detailed understanding of the complexities of cancer.

Protein secondary structure prediction using a fully complex-valued relaxation network

Knowledge of the various protein functions is essential to understand the manifestation of diseases and develop suitable drugs to alleviate them. As proteins form conformational patterns like α-helix and β-strands that eventually fold up into 3-D structure, prediction of the secondary structure of proteins is an important intermediate step in understanding the final structure of proteins that are vital for performing biological functions. Thus, there is a need to predict the secondary structure of proteins accurately and efficiently. Recent studies in machine learning have shown that complex-valued neural networks have better decision making ability than real-valued networks. Therefore, we use a Fully Complex-valued Relaxation Network (FCRN) classifier to predict the secondary structure of proteins in this paper. FCRN classifier is a single hidden layer neural network classifier with nonlinear input, hidden and output layers. The neurons in the input layer convert the real-valued input features to the Complex domain using a circular transformation. The neurons in the hidden layer employ a fully complex-valued sech activation function and those in the output layer employ the fully complex-valued exp activation function. For constant random input parameters, FCRN estimates the output weights corresponding to the minimum energy point of a logarithmic error function that represents both the magnitude and phase error explicitly. The prediction performance of FCRN is compared against the best results available in the literature for this problem. Our results show that FCRN presents higher or comparable prediction accuracy than other classifiers available in the literature.

PLoS Computational Biology conference postcards from ISMB 2010.

The annual international conference on Intelligent Systems for Molecular Biology (ISMB) is the largest meeting of the International Society for Computational Biology (ISCB). In 2010 it was held in Boston, United States, July 11–13. What follows are four conference postcards that reflect different activities considered exciting and important by younger attendees. Postcards, as the name suggests, are brief reports on the talks and other events that interested attendees. You can read more about the idea of conference postcards at http://www.ploscompbiol.org/doi/pcbi.1000746, and if you are a graduate student or postdoctoral fellow, please consider contributing postcards at any future meetings of interest to the PLoS Computational Biology readership. We want to hear your view of the science being presented.

Immunoglobulin functional motions and their effects on the complementarity determining regions

Motions of the IgG structure are evaluated using normal mode analysis and a new time dependent form of the elastic network model, to detect hinges, the dominance of low frequency modes, and the most important internal motions. We also evaluate the protein crystal and its packing effects on the experimental temperature factors and disorder prediction. We find that the effects of the protein environment on the crystallographic temperature factors may be misleading for evaluating specific functional motions of IgG. The extent of motion of the antigen binding domains is computed to show their large spatial sampling. We conclude that the IgG structure is specifically designed to facilitate large excursions of the antigen binding domains. Normal modes are shown as capable of computationally evaluating the hinge motions and the spatial sampling of domains of the structure. The antigen binding loops and the major hinge appear to behave similarly to the rest of the structure when we consider the dominance of the low frequency modes and the extent of internal motion.

Immunological implications of a structural analysis of two different porcine IL1β proteins expressed in macrophages and embryos

IL1β is an important protein in vertebrates. It is a member of the cytokine protein family and is involved in generating an inflammatory response to infections. Researchers have found that there are two porcine IL1β proteins expressed - one in embryos and the other in macrophage and endometrial tissues. These two proteins have about 86% sequence identity. In this paper, we attempt to describe how these two proteins might differ structurally and functionally. We find that 1) A predicted binding site appears to have different side chain arrangements that might lead to different binding efficiencies for the same protein or even to different partners. 2) The Caspase 1 cleavage site in the precursor proteins differs in a way that has previously been experimentally determined to reduce the cleavage activity by one order of magnitude for the embryonic IL1β, conferring a significant advantage to the protein (embryonic IL1β).