Bayesian Lasso and multinomial logistic regression on GPU.
Ontology highlight
ABSTRACT:
SUBMITTER: Cesnovar R
PROVIDER: S-EPMC5489220 | biostudies-literature | 2017
REPOSITORIES: biostudies-literature
Publications
Bayesian Lasso and multinomial logistic regression on GPU.
Češnovar Rok R Štrumbelj Erik E
PloS one 20170628 6
We describe an efficient Bayesian parallel GPU implementation of two classic statistical models-the Lasso and multinomial logistic regression. We focus on parallelizing the key components: matrix multiplication, matrix inversion, and sampling from the full conditionals. Our GPU implementations of Bayesian Lasso and multinomial logistic regression achieve 100-fold speedups on mid-level and high-end GPUs. Substantial speedups of 25 fold can also be achieved on older and lower end GPUs. Samplers ar ...[more]
Similar Datasets
Project description:BackgroundComplex binary traits are influenced by many factors including the main effects of many quantitative trait loci (QTLs), the epistatic effects involving more than one QTLs, environmental effects and the effects of gene-environment interactions. Although a number of QTL mapping methods for binary traits have been developed, there still lacks an efficient and powerful method that can handle both main and epistatic effects of a relatively large number of possible QTLs.ResultsIn this paper, we use a Bayesian logistic regression model as the QTL model for binary traits that includes both main and epistatic effects. Our logistic regression model employs hierarchical priors for regression coefficients similar to the ones used in the Bayesian LASSO linear model for multiple QTL mapping for continuous traits. We develop efficient empirical Bayesian algorithms to infer the logistic regression model. Our simulation study shows that our algorithms can easily handle a QTL model with a large number of main and epistatic effects on a personal computer, and outperform five other methods examined including the LASSO, HyperLasso, BhGLM, RVM and the single-QTL mapping method based on logistic regression in terms of power of detection and false positive rate. The utility of our algorithms is also demonstrated through analysis of a real data set. A software package implementing the empirical Bayesian algorithms in this paper is freely available upon request.ConclusionsThe EBLASSO logistic regression method can handle a large number of effects possibly including the main and epistatic QTL effects, environmental effects and the effects of gene-environment interactions. It will be a very useful tool for multiple QTLs mapping for complex binary traits.
| S-EPMC3771412 | biostudies-literature
Project description:MotivationFor many classes of disease the same genetic risk variants underly many related phenotypes or disease subtypes. Multinomial logistic regression provides an attractive framework to analyze multi-category phenotypes, and explore the genetic relationships between these phenotype categories. We introduce Trinculo, a program that implements a wide range of multinomial analyses in a single fast package that is designed to be easy to use by users of standard genome-wide association study software.Availability and implementationAn open source C implementation, with code and binaries for Linux and Mac OSX, is available for download at http://sourceforge.net/projects/trinculoSupplementary informationSupplementary data are available at Bioinformatics online.Contactlj4@well.ox.ac.uk.
| S-EPMC4908321 | biostudies-literature
Project description:MOTIVATION:In ordinary regression, imposition of a lasso penalty makes continuous model selection straightforward. Lasso penalized regression is particularly advantageous when the number of predictors far exceeds the number of observations. METHOD:The present article evaluates the performance of lasso penalized logistic regression in case-control disease gene mapping with a large number of SNPs (single nucleotide polymorphisms) predictors. The strength of the lasso penalty can be tuned to select a predetermined number of the most relevant SNPs and other predictors. For a given value of the tuning constant, the penalized likelihood is quickly maximized by cyclic coordinate ascent. Once the most potent marginal predictors are identified, their two-way and higher order interactions can also be examined by lasso penalized logistic regression. RESULTS:This strategy is tested on both simulated and real data. Our findings on coeliac disease replicate the previous SNP results and shed light on possible interactions among the SNPs. AVAILABILITY:The software discussed is available in Mendel 9.0 at the UCLA Human Genetics web site. SUPPLEMENTARY INFORMATION:Supplementary data are available at Bioinformatics online.
| S-EPMC2732298 | biostudies-literature
Project description:Two important contributors to missing heritability are believed to be rare variants and gene-environment interaction (GXE). Thus, detecting GXE where G is a rare haplotype variant (rHTV) is a pressing problem. Haplotype analysis is usually the natural second step to follow up on a genomic region that is implicated to be associated through single nucleotide variants (SNV) analysis. Further, rHTV can tag associated rare SNV and provide greater power to detect them than popular collapsing methods. Recently we proposed Logistic Bayesian LASSO (LBL) for detecting rHTV association with case-control data. LBL shrinks the unassociated (especially common) haplotypes toward zero so that an associated rHTV can be identified with greater power. Here, we incorporate environmental factors and their interactions with haplotypes in LBL. As LBL is based on retrospective likelihood, this extension is not trivial. We model the joint distribution of haplotypes and covariates given the case-control status. We apply the approach (LBL-GXE) to the Michigan, Mayo, AREDS, Pennsylvania Cohort Study on Age-related Macular Degeneration (AMD). LBL-GXE detects interaction of a specific rHTV in CFH gene with smoking. To the best of our knowledge, this is the first time in the AMD literature that an interaction of smoking with a specific (rather than pooled) rHTV has been implicated. We also carry out simulations and find that LBL-GXE has reasonably good powers for detecting interactions with rHTV while keeping the type I error rates well controlled. Thus, we conclude that LBL-GXE is a useful tool for uncovering missing heritability.
| S-EPMC4174302 | biostudies-literature
Project description:Many diseases such as cancer and heart diseases are heterogeneous and it is of great interest to study the disease risk specific to the subtypes in relation to genetic and environmental risk factors. However, due to logistic and cost reasons, the subtype information for the disease is missing for some subjects. In this article, we investigate methods for multinomial logistic regression with missing outcome data, including a bootstrap hot deck multiple imputation (BHMI), simple inverse probability weighted (SIPW), augmented inverse probability weighted (AIPW), and expected estimating equation (EEE) estimators. These methods are important approaches for missing data regression. The BHMI modifies the standard hot deck multiple imputation method such that it can provide valid confidence interval estimation. Under the situation when the covariates are discrete, the SIPW, AIPW, and EEE estimators are numerically identical. When the covariates are continuous, nonparametric smoothers can be applied to estimate the selection probabilities and the estimating scores. These methods perform similarly. Extensive simulations show that all of these methods yield unbiased estimators while the complete-case (CC) analysis can be biased if the missingness depends on the observed data. Our simulations also demonstrate that these methods can gain substantial efficiency compared with the CC analysis. The methods are applied to a colorectal cancer study in which cancer subtype data are missing among some study individuals.
| S-EPMC7736568 | biostudies-literature
Project description:In countries with a high incidence of tuberculosis, the typical clinical features of Crohn's disease (CD) may be covered up after tuberculosis infection, and the identification of atypical Crohn's disease and intestinal tuberculosis (ITB) is still a dilemma for clinicians. Least absolute shrinkage and selection operator (LASSO) regression has been applied to select variables in disease diagnosis. However, its value in discriminating ITB and atypical Crohn's disease remains unknown. A total of 400 patients were enrolled from January 2014 to January 2019 in second Xiangya hospital Central South University.Among them, 57 indicators including clinical manifestations, laboratory results, endoscopic findings, computed tomography enterography features were collected for further analysis. R software version 3.6.1 (glmnet package) was used to perform the LASSO logistic regression analysis. SPSS 20.0 was used to perform Pearson chi-square test and binary logistic regression analysis. In the variable selection step, LASSO regression and Pearson chi-square test were applied to select the most valuable variables as candidates for further logistic regression analysis. Secondly, variables identified from step 1 were applied to construct binary logistic regression analysis. Receiver operating characteristic (ROC) curve analysis was performed on these models to assess the ability and the optimal cutoff value for diagnosis. The area under the ROC curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy rate, together with their 95% confidence and intervals (CIs) were calculated. MedCalc software (Version 16.8) was applied to analyze the ROC curves of models. 332 patients were eventually enrolled to build a binary logistic regression model to discriminate CD (including comprehensive CD and tuberculosis infected CD) and ITB. However, we did not get a satisfactory diagnostic value via applying the binary logistic regression model of comprehensive CD and ITB to predict tuberculosis infected CD and ITB (accuracy rate:79.2%VS 65.1%). Therefore, we further established a binary logistic regression model to discriminate atypical CD from ITB, based on Pearsonchi-square test (model1) and LASSO regression (model 2). Model 1 showed 89.9% specificity, 65.9% sensitivity, 88.5% PPV, 68.9% NPV, 76.9% diagnostic accuracy, and an AUC value of 0.811, and model 2 showed 80.6% specificity, 84.4% sensitivity, 82.3% PPV, 82.9% NPV, 82.6% diagnostic accuracy, and an AUC value of 0.887. The comparison of AUCs between model1 and model2 was statistically different (P < 0.05). Tuberculosis infection increases the difficulty of discriminating CD from ITB. LASSO regression showed a more efficient ability than Pearson chi-square test based logistic regression on differential diagnosing atypical CD and ITB.
| S-EPMC9256608 | biostudies-literature
Project description:It has been hypothesized that rare variants may hold the key to unraveling the genetic transmission mechanism of many common complex traits. Currently, there is a dearth of statistical methods that are powerful enough to detect association with rare haplotypes. One of the recently proposed methods is logistic Bayesian LASSO for case-control data. By penalizing the regression coefficients through appropriate priors, logistic Bayesian LASSO weeds out the unassociated haplotypes, making it possible for the associated rare haplotypes to be detected with higher powers. We used the Genetic Analysis Workshop 18 simulated data to evaluate the behavior of logistic Bayesian LASSO in terms of its power and type I error under a complex disease model. We obtained knowledge of the simulation model, including the locations of the functional variants, and we chose to focus on two genomic regions in the MAP4 gene on chromosome 3. The sample size was 142 individuals and there were 200 replicates. Despite the small sample size, logistic Bayesian LASSO showed high power to detect two haplotypes containing functional variants in these regions while maintaining low type I errors. At the same time, a commonly used approach for haplotype association implemented in the software hapassoc failed to converge because of the presence of rare haplotypes. Thus, we conclude that logistic Bayesian LASSO can play an important role in the search for rare haplotypes.
| S-EPMC4144467 | biostudies-literature
Project description:Genetic variants in genome-wide association studies (GWAS) are tested for disease association mostly using simple regression, one variant at a time. Standard approaches to improve power in detecting disease-associated SNPs use multiple regression with Bayesian variable selection in which a sparsity-enforcing prior on effect sizes is used to avoid overtraining and all effect sizes are integrated out for posterior inference. For binary traits, the logistic model has not yielded clear improvements over the linear model. For multi-SNP analysis, the logistic model required costly and technically challenging MCMC sampling to perform the integration. Here, we introduce the quasi-Laplace approximation to solve the integral and avoid MCMC sampling. We expect the logistic model to perform much better than multiple linear regression except when predicted disease risks are spread closely around 0.5, because only close to its inflection point can the logistic function be well approximated by a linear function. Indeed, in extensive benchmarks with simulated phenotypes and real genotypes, our Bayesian multiple LOgistic REgression method (B-LORE) showed considerable improvements (1) when regressing on many variants in multiple loci at heritabilities ≥ 0.4 and (2) for unbalanced case-control ratios. B-LORE also enables meta-analysis by approximating the likelihood functions of individual studies by multivariate normal distributions, using their means and covariance matrices as summary statistics. Our work should make sparse multiple logistic regression attractive also for other applications with binary target variables. B-LORE is freely available from: https://github.com/soedinglab/b-lore.
| S-EPMC6329526 | biostudies-literature
Project description:BackgroundBreast cancer is one of the most common cancers in women. It is necessary to classify breast cancer subtypes because different subtypes need specific treatment. Identifying biomarkers and classifying breast cancer subtypes is essential for developing appropriate treatment methods for patients. MiRNAs can be easily detected in tumor biopsy and play an inhibitory or promoting role in breast cancer, which are considered promising biomarkers for distinguishing subtypes.ResultsA new method combing ensemble regularized multinomial logistic regression and Cox regression was proposed for identifying miRNA biomarkers in breast cancer. After adopting stratified sampling and bootstrap sampling, the most suitable sample subset for miRNA feature screening was determined via ensemble 100 regularized multinomial logistic regression models. 124 miRNAs that participated in the classification of at least 3 subtypes and appeared at least 50 times in 100 integrations were screened as features. 22 miRNAs from the proposed feature set were further identified as the biomarkers for breast cancer by using Cox regression based on survival analysis. The accuracy of 5 methods on the proposed feature set was significantly higher than on the other two feature sets. The results of 7 biological analyses illustrated the rationality of the identified biomarkers.ConclusionsThe screened features can better distinguish breast cancer subtypes. Notably, the genes and proteins related to the proposed 22 miRNAs were considered oncogenes or inhibitors of breast cancer. 9 of the 22 miRNAs have been proved to be markers of breast cancer. Therefore, our results can be considered in future related research.
| S-EPMC9580207 | biostudies-literature
Project description:Because of the limited information from the GAW20 samples when only case-control or trio data are considered, we propose eLBL, an extension of the Logistic Bayesian LASSO (least absolute shrinkage and selection operator) methodology so that both types of data can be analyzed jointly in the hope of obtaining an increased statistical power, especially for detecting association between rare haplotypes and complex diseases. The methodology is further extended to account for familial correlation among the case-control individuals and the trios. A 2-step analysis strategy was taken to first perform a genome-wise single single-nucleotide polymorphism (SNP) search using the Monte Carlo pedigree disequilibrium test (MCPDT) to determine interesting regions for the Adult Treatment Panel (ATP) binary trait. Then eLBL was applied to haplotype blocks covering the flagged SNPs in Step 1. Several significantly associated haplotypes were identified; most are in blocks contained in protein coding genes that appear to be relevant for metabolic syndrome. The results are further substantiated with a Type I error study and by an additional analysis using the triglyceride measurements directly as a quantitative trait.
| S-EPMC6156907 | biostudies-literature