A genetic algorithm–support vector machine method with parameter optimization for selecting the tag SNPs

Single Nucleotide Polymorphisms (SNPs) are common among human populations. SNPs that are proximally located within a small human chromosome region are generally strongly correlated that a subset of SNPs, termed tag SNPs, can provide enough information to infer neigh- boring SNPs. Such correlations are generally known as linkage disequilibrium (LD) and are measured either pair-wise, such as r2, or multi-to-one (multi-marker). For any given set of SNPs, a variety of algorithms have been proposed to identify a subset of tag SNPs by which the remaining SNPs can be inferred. This paper focuses on finding that number of tag SNPs from which remaining SNPs can be inferred through multi-allelic LD or pair-wise LD with a pre-defined r 2 threshold. We call this the optimal tag SNP selection problem. Although this problem is theoretically NP-hard, it can be formulated as an integer programming (IP) problem under a certain constraint, and the opti- mal solution can be efficiently found by our newly developed IPMarker program. In addition, the flexibility of the computational framework allows us to formulate and solve the problem of finding common tag SNPs for multiple populations that have different LD patterns. Various datasets, in- cluding ENCODE and the Major Histocompatiability Complex (MHC) region, were used to evaluate the performance of IPMarker. We also extended IPMarker to the whole genome HapMap Phase I data. Results showed that IPMarker significantly reduces the number of tag SNPs required when compared to the most widely used program, Haploview, although a significant longer running time is required. Thus, overall, genotyping a selected set of tag SNPs is the most cost-effective way to conduct large-scale genome-wide association studies.

The search for the association between complex diseases and single nucleotide polymorphisms (SNPs) or haplotypes has recently received great attention. For these studies, it is essential to use a small subset of informative SNPs, i.e., tag SNPs, accurately representing the rest of the SNPs. Tag SNP selection can achieve: 1) considerable budget savings by genotyping only a limited number of SNPs and computationally inferring all other SNPs or 2) necessary reduction of the huge SNP sets (obtained, e.g., from Affymetrix) for further fine haplotype analysis. In this paper, we show that the tag SNP selection strongly depends on how the chosen tags will be used-advantage of one tag set over another can only be considered with respect to a certain prediction method. We show how to separate tag selection from SNP prediction and propose greedy and local-minimization algorithms for tag SNP selection. We give two novel approaches to SNP prediction based on multiple linear regression (MLR) and support vector machines (SVMs). An extensive experimental study on various datasets including ten regions from hapMap project shows that the MLR prediction combined with stepwise tag selection uses fewer tags than the state-of-the-art method of Halperin et al. The MLR-based method also uses on average 30% fewer tags than IdSelect for statistical covering all SNPs. The tag selection based on SVM SNP prediction uses fewer tags to achieve the same prediction accuracy as the methods of Halldorsson et al.

The search for genetic regions associated with complex diseases, such as cancer or Alzheimer's disease, is an important challenge that may lead to better diagnosis and treatment. The existence of millions of DNA variations, primarily single nucleotide polymorphisms (SNPs), may allow the fine dissection of such associations. However, studies seeking disease association are limited by the cost of genotyping SNPs. Therefore, it is essential to find a small subset of informative SNPs (tag SNPs) that may be used as good representatives of the rest of the SNPs. We define a new natural measure for evaluating the prediction accuracy of a set of tag SNPs, and use it to develop a new method for tag SNPs selection. Our method is based on a novel algorithm that predicts the values of the rest of the SNPs given the tag SNPs. In contrast to most previous methods, our prediction algorithm uses the genotype information and not the haplotype information of the tag SNPs. Our method is very efficient, and it does not rely on having a block partition of the genomic region. We compared our method with two state-of-the-art tag SNP selection algorithms on 58 different genotype datasets from four different sources. Our method consistently found tag SNPs with considerably better prediction ability than the other methods. The software is available from the authors on request.

Genetic changes that may be associated with complex diseases are tried to be determined by means of many genome-wide association studies. Single Nucleotide Polymorphisms (SNPs) are used primarily in these studies since they comprise a large part of these genetic changes. Statistical importance of the genome-wide association study is directly related to the number of individuals and SNPs. However, it is still very costly and time-consuming to genotype all SNPs inside the candidate area for many individuals in very large-scale association studies. For this reason, with a small error, it is necessary to select an appropriate subset of all SNPs that will represent the rest of SNPs. These selected SNPs are called tag SNPs or haplotype tag SNPs (tag SNPs or htSNPs). It is essential in tag SNP selection to determine minimum tag SNP set with very good prediction accuracy. In this study, while Clonal Selection Algorithm (CLONALG) was used as tag SNP selection method, a new method named CLONSim, in which similarity association between SNPs was used as the prediction method for the rest of SNPs was proposed. The proposed method was compared with BPSO (Binary Particle Swarm Optimization) and CLONTagger methods with parameter optimization using datasets of different sizes. Experiment results showed that the proposed method could identify tag SNPs significantly faster.

With the rapid development of high-throughput genotyping technologies, more and more attentions are paid to the disease association study identifying DNA variations that are highly associated with a specific disease. One main challenge for this study is to find the optimal subsets of Single Nucleotide Polymorphisms (SNPs) which are most tightly associated with diseases. Feature selection has become a necessity in many bioinformatics applications. In this paper, we propose a wrapper algorithm named USVM which combines Univariate Marginal Distribution Algorithm (UMDA) and Support Vector Machine (SVM) for disease association study. USVM not only eliminates the redundancy of feature, but also solves the problem of SVM's parameters selection. We use USVM to analyze the Crohn's disease (CD) dataset including 387 samples and each one has 103 SNPs. The experimental results show that our algorithm outperforms the current algorithms including DNF, CSP, ORF and so on.

As peer-to-peer (P2P) technology booms lots of problems arise such as rampant piracy, congestion, low quality etc. Thus, accurate identification of P2P traffic makes great sense for efficient network management. As one of the optimal classifiers, support vector machine (SVM) has been successfully used in P2P traffic identification. However, the performance of SVM is largely dependent on its parameters and the traditional tuning methods are inefficient. In the paper, a novel hybrid method to optimize parameters of SVM based on cuckoo search algorithm combined with particle swarm optimization algorithm is proposed. The first stage of the proposed approach is to tune the best parameters for SVM with training data. Subsequently, the SVM configured with the best parameters is employed to identify P2P traffic. In the end, we demonstrate the effectiveness of our approach on-campus traffic traces. Experimental results indicate that the proposed method outperforms SVM based on genetic algorithm, particle swarm optimization algorithm and cuckoo search algorithm.

Haplotype Block Structure and Its Applications to Association Studies: Power and Study Designs

Support Vector Machine (SVM) is a relatively novel classification technology, which has shown higher performance than traditional learning methods in many applications. Therefore, some security researchers have proposed an intrusion detection method based on SVM. However, the SVM algorithm is very sensitive to the choice of kernel function and parameter adjustment. Once the parameter selection is unscientific, it will lead to poor classification accuracy. To solve this problem, this paper presents a Grey Wolf Optimizer Algorithm based on Particle Swarm Optimization (PSOGWO) algorithm to improve the Intrusion Detection System (IDS) based on SVM. This method uses PSOGWO algorithm to optimize the parameters of SVM to improve the overall performance of intrusion detection based on SVM. The "optimal detection model" of SVM classifier is determined by the fusion of PSOGWO algorithm and SVM. The comparison experiments based on NSL-KDD dataset show that the intrusion detection method based on PSOGWO-SVM achieves the optimization of the parameters of SVM, and has improved significantly in terms of detection rate, convergence speed and model balance. This shows that the method has better performance for network intrusion detection.

Automatic recognition of skin symptom plays an importance role in the skin diagnosis and treatment. Feature selection is to increase the classification performance of skin symptom. In this paper, the effects of feature selection on the classification of 4-class skin symptoms (chloasma, blackhead, freckled and comedone) are analyzed. Support vector machine (SVM) is employed to construct classifier, the parameters setting is very crucial to the learning results and generalization ability of SVM, and many irrelevant and redundant features degrade the performance of classification, furthermore, the choice of SVM parameters is influenced by the feature subset taken into account and vice versa. So a joint optimization method for selecting features and SVM parameters is proposed. Genetic algorithms, which have a lot of improvements about fitness, crossover and mutation in comparison with simple genetic algorithms, is to achieve a balance between the classification accuracy and the size of the feature subsets selected and have a fast convergence rate. Furthermore, ‘one-against-one’ approach is used to solve multi-class classification problems and a comparison of the model performances is made among the results of the joint optimization and the single optimization of features or SVM parameters in the experiments. The simulation result shows that our approach can find subsets of features for 4-class skin symptoms classification with higher average cross validation accuracy and a higher rate of convergence compared with single optimization of features or SVM parameters.

Recent studies have shown that a small subset of Single Nucleotide Polymorphisms (SNPs) (called tag SNPs) is sufficient to capture the haplotype patterns in a high linkage disequilibrium region. To find the minimum set of tag SNPs, exact algorithms for finding the optimal solution could take exponential time. On the other hand, approximation algorithms are more efficient but may fail to find the optimal solution. We propose a hybrid method that combines the ideas of the branch-and-bound method and the greedy algorithm. This method explores larger solution space to obtain a better solution than a traditional greedy algorithm. It also allows the user to adjust the efficiency of the program and quality of solutions. This algorithm has been implemented and tested on a variety of simulated and biological data. The experimental results indicate that our program can find better solutions than previous methods. This approach is quite general since it can be used to adapt other greedy algorithms to solve their corresponding problems. The program is available upon request.

Introduction: Since the delay or mistake in the diagnosis of mood disorders due to the similarity of their symptoms hinders effective treatment, this study aimed to accurately diagnose mood disorders including psychosis, autism, personality disorder, bipolar, depression, and schizophrenia, through modeling and analyzing patients' data . Method : Data collected in this applied developmental research included 996 records with 130 features obtained by interviewing and completing questionnaires in a mental hospital in the city of Sari, Iran in 2021. After preprocessing, the number of features was reduced to 91, and then through Principal Component Analysis (PCA) reduced to 35 factors. Modeling was done in Python software with K -Nearest Neighbor (KNN), Naive Bayes (NB), Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), and Support Vector Machine (SVM) algorithms. The models were evaluated to select algorithms with higher accuracy. Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) were applied to determine the optimal parameters of the selected algorithms . Results: Among the machine learning algorithms, random forest with 91% accuracy and support vector machine with 90% accuracy showed better performance. The genetic algorithms did not make any notable increase in prediction accuracy. Whereas considering N=30, T=150, W=0.9, c1=2, and c2=2 in the particle swarm optimization algorithm increased the prediction accuracy up to 3.3 %. Conclusion : With less classification error compared to similar studies, the PSO -SVM model designed in this study can be used in patient data monitoring with acceptable accuracy and can be used in intelligent systems in psychiatric centers.

The goal of genome-wide association studies (GWAS) is to identify the best subset of single-nucleotide polymorphisms (SNPs) that strongly influence a certain trait. State of the art GWAS comprise several thousand or even millions of SNPs, scored on a substantially lower number of individuals. Hence, the number of variables greatly exceeds the number of observations, which also is known as the p≫n problem. This problem has been tackled by using Bayesian variable selection methods, for example stochastic search variable selection (SSVS) and Bayesian penalized regression methods (Bayesian lasso; BLA and Bayesian ridge regression; BRR). Even though the above mentioned approaches are capable of dealing with situations where p≫n, it is also known that these methods experience problems when the predictor variables are correlated. The potential problem that linkage disequilibrium (LD) between SNPs can introduce is often ignored. The main contribution of this study is to assess the performance of SSVS, BLA, BRR and a recently introduced method denoted hybrid correlation based search (hCBS) with respect to their ability to identify quantitative trait loci, where SNPs are partially highly correlated. Furthermore, each method’s capability to predict phenotypes based on the selected SNPs and their computational demands are studied. Comparison is based upon three simulated datasets where the simulated phenotypes are assumed to be normally distributed. Results indicate that all methods perform reasonably well with respect to true positive detections but often detect too many false positives on all datasets. As the heritability decreases, the Bayesian penalized regression methods are no longer able to detect any predictors because of shrinkage. Overall, BLA slightly outperformed the other methods and provided superior results in terms of highest true positive/ false positive ratio, but SSVS achieved the best properties on the real LD data.

Software defect prediction could improve the reliability of software and reduce development costs. Traditional prediction models usually have a lower prediction accuracy. In order to solve this problem, a new model for software defect prediction using Particle Swarm Optimization (PSO) and Support Vector Machine (SVM) named P-SVM model is proposed in this paper, which takes advantage of non-linear computing capability of SVM and parameters optimization capability of PSO. Firstly, P-SVM model uses PSO algorithm to calculate the best parameters of SVM, and then it adopts the optimized SVM model to predict software defect. P-SVM model and other three different prediction models are used to predict the software defects in JM1 data set as an experiment, the results show that P-SVM model has a higher prediction accuracy than BP Neural Network model, SVM model, GA-SVM model.

Transport management is a system that allows travelers to plan, schedule and manage their journey from takeoff till arrival. Passengers involved in the journey either use private or public vehicles and they always estimate their arrival-time. As the total vehicles on the road increases, the possibility of traffic congestion would also increase which is becoming a major problem for traffic planning and scheduling. To address the issue of congestion, many scholars’ opted for solutions such as building a proper infrastructure and developing an accurate travel time prediction models such as historical datasets and statistical models. However, these solutions are not efficient from an economic perspective. Therefore, the key goal of this research paper is to propose a new robust model that could forecast the arrival-time of buses by using support vector machine and Kalman filtering algorithm. The experimental results showed that the prediction model produced an outstanding performance in terms of prediction accuracy over the available historical traffic data (achieved) models using Genetic Algorithm – Support Vector machine (GA-SVM) and Artificial - Neural - Networks (ANN). Based on the analysis, the performance of this prediction model is 87.63% better than ANN which was 83.5%. The proposed model has contributed to the field of study by introducing an integrated process for estimation bus arrival-time prediction in Artificial, data mining and Transportation Engineering field.

BackgroundStructural variants (SV) are causative for some prominent phenotypic traits of livestock as different comb types in chickens or color patterns in pigs. Their effects on production traits are also increasingly studied. Nevertheless, accurately calling SV remains challenging. It is therefore of interest, whether close-by single nucleotide polymorphisms (SNPs) are in strong linkage disequilibrium (LD) with SVs and can serve as markers. Literature comes to different conclusions on whether SVs are in LD to SNPs on the same level as SNPs to other SNPs. The present study aimed to generate a precise SV callset from whole-genome short-read sequencing (WGS) data for three commercial chicken populations and to evaluate LD patterns between the called SVs and surrounding SNPs. It is thereby the first study that assessed LD between SVs and SNPs in chickens.ResultsThe final callset consisted of 12,294,329 bivariate SNPs, 4,301 deletions (DEL), 224 duplications (DUP), 218 inversions (INV) and 117 translocation breakpoints (BND). While average LD between DELs and SNPs was at the same level as between SNPs and SNPs, LD between other SVs and SNPs was strongly reduced (DUP: 40%, INV: 27%, BND: 19% of between-SNP LD). A main factor for the reduced LD was the presence of local minor allele frequency differences, which accounted for 50% of the difference between SNP – SNP and DUP – SNP LD. This was potentially accompanied by lower genotyping accuracies for DUP, INV and BND compared with SNPs and DELs. An evaluation of the presence of tag SNPs (SNP in highest LD to the variant of interest) further revealed DELs to be slightly less tagged by WGS SNPs than WGS SNPs by other SNPs. This difference, however, was no longer present when reducing the pool of potential tag SNPs to SNPs located on four different chicken genotyping arrays.ConclusionsThe results implied that genomic variance due to DELs in the chicken populations studied can be captured by different SNP marker sets as good as variance from WGS SNPs, whereas separate SV calling might be advisable for DUP, INV, and BND effects.