Heuristic Breadth-First Search Algorithm for Informative Gene Selection Based on Gene Expression Profiles

Motivation. Independent Components Analysis (ICA) maximizes the statistical independence of the representational components of a training gene expression profiles (GEP) ensemble, but it cannot distinguish relations between the different factors, or different modes, and it is not available to high-order GEP Data Mining. In order to generalize ICA, we introduce Multilinear-ICA and apply it to tumor classification using high order GEP. Firstly, we introduce the basis conceptions and operations of tensor and recommend Support Vector Machine (SVM) classifier and Multilinear-ICA. Secondly, the higher score genes of original high order GEP are selected by using t-statistics and tabulate tensors. Thirdly, the tensors are performed by Multilinear-ICA. Finally, the SVM is used to classify the tumor subtypes. Results. To show the validity of the proposed method, we apply it to tumor classification using high order GEP. Though we only use three datasets, the experimental results show that the method is effective and feasible. Through this survey, we hope to gain some insight into the problem of high order GEP tumor classification, in aid of further developing more effective tumor classification algorithms.

A combination of modified particle swarm optimization algorithm and support vector machine for gene selection and tumor classification

Gene Expression Analysis Uncovers Similarity and Differences Among Burkitt Lymphoma Subtypes

Feature extraction plays a key role in tumor classification based on gene expression profiles, which can improve the performance of classifier. We design two novel feature extraction methods to extract tumor-related features. One is combining gene ranking and discrete cosine transform (DCT) with principal component analysis (PCA), and another is combining gene ranking and discrete Fourier transform (DFT) with PCA. The proposed feature extraction methods are proved successfully and effectively to classify tumor dataset. Experiments show that the obtained classification performance are very steady, which are evaluated by support vector machines (SVM) and K-nearest neighbor (K-NN) classifier on two well-known tumor datasets. Experiment results also show that the 4-fold cross-validated accuracy rate of 100% is obtained for the leukemia dataset and 96.77% for the colon tumor dataset. Compared with other related works, the proposed method not only has higher classification accuracy rate but also is steadier in classification performance.

With the advancement of bioinformatics, the research on the gene chips has been paid more attention by the researchers in recent years. Applications of gene expression profiles on cancer diagnosis and classification have gradually become one of the hot topics in the field of bioinformatics. According to the gene expression profiles characteristics of high dimension and small sample set, we propose a classify method for cancer classification, which is based on neighborhood rough set theory and probabilistic neural network ensemble classification algorithm. Firstly, genes are sorted by using Relief algorithm. Then, classification informative genes are selected using the neighborhood rough set theory. At last, we do cancer classification with probabilistic neural networks ensemble classification model. The experimental results show that the proposed method can effectively select cancer genes, and can obtain better classification results.KeywordsGene Expression ProfilesNeighborhood Rough SetProbabilistic Neural Networks Ensemble Classification Algorithm

Support Vector Machine (SVM) has been applied in many classification systems successfully. However, it is restricted to work well on the small sample sets. This paper presents a novel parallel reduced support vector machine. The proposed algorithm consists of three parts: firstly dividing the training samples into some grids; then training sample subset through density clustering; and finally classifying the samples. After clustering the positive samples and negative samples, this algorithm picks out such samples that locate on the edge of clusters as reduced sample subset. Then, we sum up these reduced sample subsets as reduced sample set. These reduced samples are then used to find the support vectors and the optimal classifying hyperplane by support vector machine. Additionally, it also improves classification precision by reducing the percentage of counterexamples in kernel object e-area. Experiment results show that not only efficiency but also classification precision are improved, compared with other algorithms.

The development of targeted assays that monitor biomedically relevant proteins is an important step in bridging discovery experiments to large scale clinical studies. Targeted assays are currently unable to scale to hundreds or thousands of targets. We demonstrate the generation of large-scale assays using a novel hybrid nominal mass instrument. The scale of these assays is achievable with the Stellar mass spectrometer through the accommodation of shifting retention times by real-time alignment, while being sensitive and fast enough to handle many concurrent targets. Assays were constructed using precursor information from gas-phase fractionation data-independent acquisition (DIA). We demonstrate the ability to schedule methods from orbitrap and linear ion trap acquired gas-phase fractionation DIA library, and compare the quantification of a matrix-matched calibration curve from orbitrap DIA and linear ion trap parallel reaction monitoring (PRM). Two applications of these proposed workflows are shown with a cerebrospinal fluid neurodegenerative disease protein PRM assay and with a Mag-Net enriched plasma extracellular vesicle protein survey PRM assay. In cerebrospinal fluid, our assay targets proteins discovered previously to be associated with Alzheimer's disease in a small independent sample set. For the Mag-Net enriched plasma survey assay, we observe that proteins selected based on their measurement robustness are still able to capture differences in abundance across disease groups in a small sample set. These highlight the application of highly multiplex, targeted protein assays in clinical research.

A heuristic search algorithm is given that determines and resolves the Hamiltonian circuit problem in directed graphs. The heuristic information of each vertex is a set composed of its possible path length values from the starting vertex, which is obtained by the path length extension algorithm. A detailed analysis of algorithm examples shows that the heuristic algorithm can greatly reduce the number of processing nodes compared to the backtracking algorithm without information; meanwhile, the algorithm’s time complexity is related to the number of loops in the directed graph. If a directed graph G(V, E) only contains loops that contain the starting point, then the Hamiltonian problem of G can be determined in polynomial time. The algorithm is implemented using C++ and Python programming, and all of the test graphs are generated by the random graph algorithm. The experiments show that the heuristic algorithm can reduce the number of extended nodes by at least 10% in directed random graphs with no or only a few loops. This heuristic algorithm can save time in applications that perform tasks while extending nodes because it reduce the number of extended nodes.

Molecular omics (genomics, transcriptomics, proteomics, metabolomics, etc.) analysis is now playing the significant rule for cancer prediction, where gene expression profile is one of the most popular omicss. Kernel based Support Vector Machines (SVMs) are now widely using for cancer prediction based on the profiles of gene expression. However, the kernel based SVM's performance depends on both kernel and feature selection. Here, in this paper, we would like propose a way for both important kernel and features (important genes) selection for SVM to predict the colon cancer based on gene expression profile. Features (genes) selection has been done by t-statistic. Then a comparative study of cancer prediction accuracy of the proposed kernel based SVM with some popular predictors (Naive Bayes (NB), linear discriminate analysis (LDA) and quadratic linear discriminate analysis (QDA)) had been performed using the selected top 3 genes which are ranked with the help of the t-statistic. The proposed SVM-radial basis is found to be the better colon cancer predictor based on area under the curve (AUC) of the receiver operating characteristics and total accuracy. Thus we may reach to a conclusion that SVM-radial basis and t-statistic based feature selection altogether is an effective and feasible substitute to common techniques.

Co-ABC: Correlation artificial bee colony algorithm for biomarker gene discovery using gene expression profile.

Microarray analysis and gene expression profile have been widely used in tumor classification, survival analysis and ER statues of breast cancer. Sample discrimination as well as identification of significant genes have been the focus of most previous studies. The aim of this research is to propose a fuzzy model to predict the relapse time of breast cancer by using breast cancer dataset published by van't Veer. Fuzzy rule mining based on support vector machine has been used in a hybrid method with rule pruning and shown its ability to divide the samples in many subgroups. To handle the existence of uncertainties in linguistic variables and fuzzy sets, the TSK model of Interval type-2 fuzzy logic system has been used and a new simple method is also developed to consider the uncertainties of the rules which have been optimized by genetic algorithm. B632 validation method is applied to estimate the error of the model. The results with 95 % confidence interval show a reasonable accuracy in prediction.

MDS and AML Are Closely Related Diseases: Gene Expression Patterns Reveal Clear Similarities with Respect to Karyotypes and Are Less Related to the Bone Marrow Blast Percentages.

Objective. Intracortical brain–machine interfaces (iBMIs) aim to restore efficient communication and movement ability for paralyzed patients. However, frequent recalibration is required for consistency and reliability, and every recalibration will require relatively large most current sample set. The aim in this study is to develop an effective decoder calibration method that can achieve good performance while minimizing recalibration time. Approach. Two rhesus macaques implanted with intracortical microelectrode arrays were trained separately on movement and sensory paradigm. Neural signals were recorded to decode reaching positions or grasping postures. A novel principal component analysis-based domain adaptation (PDA) method was proposed to recalibrate the decoder with only ultra small current sample set by taking advantage of large historical data, and the decoding performance was compared with other three calibration methods for evaluation. Main results. The PDA method closed the gap between historical and current data effectively, and made it possible to take advantage of large historical data for decoder recalibration in current data decoding. Using only ultra small current sample set (five trials of each category), the decoder calibrated using the PDA method could achieve much better and more robust performance in all sessions than using other three calibration methods in both monkeys. Significance. (1) By this study, transfer learning theory was brought into iBMIs decoder calibration for the first time. (2) Different from most transfer learning studies, the target data in this study were ultra small sample set and were transferred to the source data. (3) By taking advantage of historical data, the PDA method was demonstrated to be effective in reducing recalibration time for both movement paradigm and sensory paradigm, indicating a viable generalization. By reducing the demand for large current training data, this new method may facilitate the application of intracortical brain–machine interfaces in clinical practice.

Among the large number of gene selection algorithms available in literature, the rough set based maximum relevance-maximum significance (RSMRMS) algorithm has been shown to be successful for selecting a set of relevant and significant genes from microarray data. However, the analysis of functional diversity of a gene set is essential to understand the role of genes in a particular disease as well as to evaluate the effectiveness of a gene selection algorithm. In this regard, a gene ontology based quantitative index, termed as degree of functional diversity (DoFD), is proposed to quantify the functional diversity of a set of genes selected by any gene selection algorithm. Moreover, a new gene selection algorithm is presented, integrating judiciously the merits of both DoFD and RSMRMS, to select relevant and significant genes those are also functionally diverse. The performance of the proposed gene selection algorithm, along with a comparison with other gene selection methods, is studied using the proposed DoFD and predictive accuracy of K-nearest neighbor rule and support vector machine on six cancer and one arthritis microarray data sets. An important finding is that the proposed gene ontology based quantitative index can accurately evaluate functional diversity of a set of genes. Also, the proposed gene selection algorithm is shown to be effective for selecting relevant, significant, and functionally diverse genes from microarray data.

BackgroundMicroarray techniques provide promising tools for cancer diagnosis using gene expression profiles. However, molecular diagnosis based on high-throughput platforms presents great challenges due to the overwhelming number of variables versus the small sample size and the complex nature of multi-type tumors. Support vector machines (SVMs) have shown superior performance in cancer classification due to their ability to handle high dimensional low sample size data. The multi-class SVM algorithm of Crammer and Singer provides a natural framework for multi-class learning. Despite its effective performance, the procedure utilizes all variables without selection. In this paper, we propose to improve the procedure by imposing shrinkage penalties in learning to enforce solution sparsity.ResultsThe original multi-class SVM of Crammer and Singer is effective for multi-class classification but does not conduct variable selection. We improved the method by introducing soft-thresholding type penalties to incorporate variable selection into multi-class classification for high dimensional data. The new methods were applied to simulated data and two cancer gene expression data sets. The results demonstrate that the new methods can select a small number of genes for building accurate multi-class classification rules. Furthermore, the important genes selected by the methods overlap significantly, suggesting general agreement among different variable selection schemes.ConclusionsHigh accuracy and sparsity make the new methods attractive for cancer diagnostics with gene expression data and defining targets of therapeutic intervention.Availability: The source MATLAB code are available from http://math.arizona.edu/~hzhang/software.html.