A5070991337- Genetic Associations and Epidemiology
- Genetic Mapping and Diversity in Plants and Animals
- Statistical Methods in Clinical Trials
- Gene expression and cancer classification
- Spectroscopy and Chemometric Analyses
- Statistical Methods and Inference
- Genetic and phenotypic traits in livestock
- Matrix Theory and Algorithms
- Blind Source Separation Techniques
- Molecular spectroscopy and chirality
- Sex and Gender in Healthcare
- Statistical and numerical algorithms
- Cystic Fibrosis Research Advances
- Bioinformatics and Genomic Networks
- VLSI and Analog Circuit Testing
- Stress Responses and Cortisol
- Islamic Studies and History
- Genomics and Rare Diseases
- Genetic and Clinical Aspects of Sex Determination and Chromosomal Abnormalities
- Statistical Methods and Bayesian Inference
- Archaeology and Historical Studies
- Health, Environment, Cognitive Aging
- Middle East and Rwanda Conflicts
- Biomedical Text Mining and Ontologies
- Advanced Control Systems Optimization
Communities In Schools of Orange County
2024
Statistical and Applied Mathematical Sciences Institute
2016
University of North Carolina at Chapel Hill
2011-2015
Genomes of men and women differ in only a limited number genes located on the sex chromosomes, whereas transcriptome is far more sex-specific. Identification sex-biased gene expression will contribute to understanding molecular basis sex-differences complex traits common diseases. Sex differences human peripheral blood were characterized using microarrays 5,241 subjects, accounting for menopause status hormonal contraceptive use. Sex-specific was observed 582 autosomal genes, which 57.7%...
Abstract Summary: seeQTL is a comprehensive and versatile eQTL database, including various studies meta-analysis of HapMap information. The database presents association results in convenient browser, using both segmented local-association plots genome-wide Manhattan plots. Availability implementation: freely available for non-commercial use at http://www.bios.unc.edu/research/genomic_software/seeQTL/. Contact: fred_wright@unc.edu; kxia@bios.unc.edu Supplementary information: data are...
We address a common problem in large-scale data analysis, and especially the field of genetics, huge-scale testing problem, where millions to billions hypotheses are tested together creating computational challenge control inflation false discovery rate. As solution we propose an alternative algorithm for famous Linear Step Up procedure Benjamini Hochberg.Our requires linear time does not require any P-value ordering. It permits separating problems arbitrarily into computationally feasible...
Abstract Purpose Epistasis, the interaction between two or more genes, is integral to study of genetics and present throughout nature. Yet, it seldom fully explored as most approaches primarily focus on single-locus effects, partly because analyzing all pairwise higher-order interactions requires significant computational resources. Furthermore, existing methods for epistasis detection only consider a Cartesian (multiplicative) model terms. This likely limiting epistatic can evolve produce...
By connecting the LU factorization and Gram-Schmidt orthogonalization without any normalization, closed-forms for coefficients of ordinary least squares solution are presented. Each is expressed computed directly as a linear combination vectors from single nonnormalized process. The may be separately or altogether using closed-form given. As immediate consequences, we also obtain closed form generalized inverse, each weighted regression, simplification computation Frisch-Waugh-Lovell Theorem.
Abstract Statistical epistasis has been studied extensively because of its potential to provide evidence for genetic interactions phenotypes, but there have methodological limitations exhaustive, widespread application. We present new algorithms the interaction coefficients standard regression models that permit many varied encodings terms loci and efficient memory usage. The are given two-way three-way may be generalized higher order epistasis. tests also provided. an matrix based algorithm...
Many studies draw inferences about multiple endpoints but ignore the statistical implications of multiplicity. Effects inferred to be positive when there is no adjustment for multiplicity can lose their significance taken into account, perhaps explaining why such adjustments are so often omitted. We develop new simultaneous confidence intervals that mitigate this problem; these uniformly more likely determine signs than standard intervals. When one or parameter estimates small, sacrifice...
We address a common problem in large-scale data analysis, and especially the field of genetics, huge-scale testing problem, where millions to billions hypotheses are tested together creating computational challenge perform multiple procedures. As solution we propose an alternative algorithm well used Linear Step Up procedure Benjamini Hochberg (1995). Our requires linear time does not require any p-value ordering. It permits separating problems arbitrarily into computationally feasible sets...
We present two novel, explicit representations of Cholesky factor a nonsingular correlation matrix. The first representation uses semi-partial coefficients as its entries. second, an equivalent form the square roots differences between ratios successive determinants. Each new forms enjoys parsimony notations and offers simpler alternative to both spherical factorization multiplicative partial matrix (Cooke et al 2011). Two relevant applications are offered for each form: simple $t$-test...
By connecting the LU factorization and Gram-Schmidt orthogonalization without any normalization, closed-forms for coefficients of ordinary least squares estimates are presented. Instead using matrix inversion explicitly, each is expressed computed directly as a linear combination non-normalized vectors original data also in terms upper triangular factor from factorization. The may iteratively backward or forward algorithms given.