The Experts below are selected from a list of 294 Experts worldwide ranked by ideXlab platform

Mingyuan Zhou - One of the best experts on this subject based on the ideXlab platform.

  • bnp seq bayesian nonparametric differential expression analysis of sequencing count data
    Journal of the American Statistical Association, 2018
    Co-Authors: Siamak Zamani Dadaneh, Xiaoning Qian, Mingyuan Zhou
    Abstract:

    ABSTRACTWe perform differential expression analysis of high-throughput sequencing count data under a Bayesian nonparametric framework, removing sophisticated ad hoc pre-processing steps commonly required in existing algorithms. We propose to use the gamma (beta) negative Binomial process, which takes into account different sequencing depths using sample-specific negative Binomial Probability (dispersion) parameters, to detect differentially expressed genes by comparing the posterior distributions of gene-specific negative Binomial dispersion (Probability) parameters. These model parameters are inferred by borrowing statistical strength across both the genes and samples. Extensive experiments on both simulated and real-world RNA sequencing count data show that the proposed differential expression analysis algorithms clearly outperform previously proposed ones in terms of the areas under both the receiver operating characteristic and precision-recall curves. Supplementary materials for this article are avai...

  • bnp seq bayesian nonparametric differential expression analysis of sequencing count data
    arXiv: Applications, 2016
    Co-Authors: Siamak Zamani Dadaneh, Xiaoning Qian, Mingyuan Zhou
    Abstract:

    We perform differential expression analysis of high-throughput sequencing count data under a Bayesian nonparametric framework, removing sophisticated ad-hoc pre-processing steps commonly required in existing algorithms. We propose to use the gamma (beta) negative Binomial process, which takes into account different sequencing depths using sample-specific negative Binomial Probability (dispersion) parameters, to detect differentially expressed genes by comparing the posterior distributions of gene-specific negative Binomial dispersion (Probability) parameters. These model parameters are inferred by borrowing statistical strength across both the genes and samples. Extensive experiments on both simulated and real-world RNA sequencing count data show that the proposed differential expression analysis algorithms clearly outperform previously proposed ones in terms of the areas under both the receiver operating characteristic and precision-recall curves.

Siamak Zamani Dadaneh - One of the best experts on this subject based on the ideXlab platform.

  • bnp seq bayesian nonparametric differential expression analysis of sequencing count data
    Journal of the American Statistical Association, 2018
    Co-Authors: Siamak Zamani Dadaneh, Xiaoning Qian, Mingyuan Zhou
    Abstract:

    ABSTRACTWe perform differential expression analysis of high-throughput sequencing count data under a Bayesian nonparametric framework, removing sophisticated ad hoc pre-processing steps commonly required in existing algorithms. We propose to use the gamma (beta) negative Binomial process, which takes into account different sequencing depths using sample-specific negative Binomial Probability (dispersion) parameters, to detect differentially expressed genes by comparing the posterior distributions of gene-specific negative Binomial dispersion (Probability) parameters. These model parameters are inferred by borrowing statistical strength across both the genes and samples. Extensive experiments on both simulated and real-world RNA sequencing count data show that the proposed differential expression analysis algorithms clearly outperform previously proposed ones in terms of the areas under both the receiver operating characteristic and precision-recall curves. Supplementary materials for this article are avai...

  • bnp seq bayesian nonparametric differential expression analysis of sequencing count data
    arXiv: Applications, 2016
    Co-Authors: Siamak Zamani Dadaneh, Xiaoning Qian, Mingyuan Zhou
    Abstract:

    We perform differential expression analysis of high-throughput sequencing count data under a Bayesian nonparametric framework, removing sophisticated ad-hoc pre-processing steps commonly required in existing algorithms. We propose to use the gamma (beta) negative Binomial process, which takes into account different sequencing depths using sample-specific negative Binomial Probability (dispersion) parameters, to detect differentially expressed genes by comparing the posterior distributions of gene-specific negative Binomial dispersion (Probability) parameters. These model parameters are inferred by borrowing statistical strength across both the genes and samples. Extensive experiments on both simulated and real-world RNA sequencing count data show that the proposed differential expression analysis algorithms clearly outperform previously proposed ones in terms of the areas under both the receiver operating characteristic and precision-recall curves.

Xiaoning Qian - One of the best experts on this subject based on the ideXlab platform.

  • bnp seq bayesian nonparametric differential expression analysis of sequencing count data
    Journal of the American Statistical Association, 2018
    Co-Authors: Siamak Zamani Dadaneh, Xiaoning Qian, Mingyuan Zhou
    Abstract:

    ABSTRACTWe perform differential expression analysis of high-throughput sequencing count data under a Bayesian nonparametric framework, removing sophisticated ad hoc pre-processing steps commonly required in existing algorithms. We propose to use the gamma (beta) negative Binomial process, which takes into account different sequencing depths using sample-specific negative Binomial Probability (dispersion) parameters, to detect differentially expressed genes by comparing the posterior distributions of gene-specific negative Binomial dispersion (Probability) parameters. These model parameters are inferred by borrowing statistical strength across both the genes and samples. Extensive experiments on both simulated and real-world RNA sequencing count data show that the proposed differential expression analysis algorithms clearly outperform previously proposed ones in terms of the areas under both the receiver operating characteristic and precision-recall curves. Supplementary materials for this article are avai...

  • bnp seq bayesian nonparametric differential expression analysis of sequencing count data
    arXiv: Applications, 2016
    Co-Authors: Siamak Zamani Dadaneh, Xiaoning Qian, Mingyuan Zhou
    Abstract:

    We perform differential expression analysis of high-throughput sequencing count data under a Bayesian nonparametric framework, removing sophisticated ad-hoc pre-processing steps commonly required in existing algorithms. We propose to use the gamma (beta) negative Binomial process, which takes into account different sequencing depths using sample-specific negative Binomial Probability (dispersion) parameters, to detect differentially expressed genes by comparing the posterior distributions of gene-specific negative Binomial dispersion (Probability) parameters. These model parameters are inferred by borrowing statistical strength across both the genes and samples. Extensive experiments on both simulated and real-world RNA sequencing count data show that the proposed differential expression analysis algorithms clearly outperform previously proposed ones in terms of the areas under both the receiver operating characteristic and precision-recall curves.

Paul I Louangrath - One of the best experts on this subject based on the ideXlab platform.

  • bayesian inference for Binomial Probability and psychometrics techniques
    Social Science Research Network, 2013
    Co-Authors: Paul I Louangrath
    Abstract:

    This paper introduces a new concept of distribution called circular distribution. The total area of the circle is defined as the distribution density of the Binomial Probability which consists of . This probabilistic sum is assumed to be equal to , the area of a unit circle. In a Binomial distribution where the Probability of success is equal to one minus the Probability of failure: , the Probability of failure sector may be further sectioned in parts (sections) as required by the Probability of failure subspace. Using the Laplace Rule of Success as the basis for deriving the prior for Probability of success, the Probability distribution density for success, failure and subspace of failure in a successive Binomial partition may be accomplished. This circular distribution differs from the Gaussian distribution in that the graphical representation is a circle, not a bell shape curve. The bell shape curved may also be used to express the Normality of the distribution in the long run. However, for purposes of determining prior for Bayesian inference, the circular distribution may be used for visual aid and convenience in calculating Binomial Probability. There are several theories used in this paper. Primus, the Bayesian Probability is a Binomial Probability. A Binomial Probability is defined by the Probability with two categories of answer. Secundus, the Laplace Rule of Succession is a definitional rule of Binomial Probability. The two category answer choice is defined by two choices: success and failure. The LaPlace Rule of Success expresses the ratio of observed success to the total number of observation. Tertius, the Buddha’s psychometric technique is explained and used as an illustrative model for generating Bayesian prior.

Shanshan Gao - One of the best experts on this subject based on the ideXlab platform.

  • defining a minimum number of examined lymph nodes improves the prognostic value of lymphadenectomy in pancreas ductal adenocarcinoma
    Hpb, 2020
    Co-Authors: Shanshan Gao, Ross Beckman, Ding Ding, Michael J Wright, Zhiyao Chen, Yayun Zhu, Lingdi Yin, Michael Beckman, Elizabeth D Thompson
    Abstract:

    Abstract Background Lymph node (LN) metastasis is associated with decreased survival following resection for pancreatic ductal adenocarcinoma (PDAC). In N0 disease, increasing total evaluated LN (ELN) correlates with improved outcomes suggesting patients may be understaged when LNs are undersampled. We aim to assess the optimal number of examined lymph nodes (ELN) following pancreatectomy. Methods Data from 1837 patients undergoing surgery were prospectively collected. The Binomial Probability law was utilized to analyze the minimum number of examined LNs (minELN) and accurately characterize each histopathologic stage. LN ratio (LNR) was compared to American Joint Committee on Cancer (AJCC) guidelines. Results As ELN total increased, the likelihood of finding node positive disease increased. An evaluation based upon the Binomial Probability law suggested an optimal minELN of 12 for accurate AJCC N staging. As the number of ELNs increased, the discriminatory capacity of alternative strategies to characterize LN disease exceeded that offered by AJCC N stage. Conclusion This is the first study dedicated to optimizing histopathologic staging in PDAC using models of minELN informed by the Binomial Probability law. This study highlights two separate cutoffs for ELNs depending upon prognostic goal and validates that 12 LNs are adequate to determine AJCC N stage for the majority of patients.