Short Course on Graphical Models

Event
Monday, June 19, 2017 - 8:30am to Friday, June 23, 2017 - 12:00pm
Event Type: 

Instructors:     Dr. Guilherme J. M. Rosa           University of Wisconsin-Madison      (http://www.ansci.wisc.edu/Facultypages/rosa.html)


Dr. Francisco Peñagaricano    University of Florida-Gainesville            (http://animal.ifas.ufl.edu/faculty/penagaricano/index.shtml)


 


Registration for this course is now open at:   https://registration.extension.iastate.edu/emc00/register.aspx?OrgCode=10&EvtID=8416&AppCode=REG&CC=117020764527 .   Space is limited, so register early (by May 31).


Limited shared on-campus housing is available on a first-come basis at $125 per week (book through the registration website by May 15). 


A room block is available at the Best Western Plus University Park Inn & Suites at $109 /$119 single/double/day.; book directly with hotel at (515) 296-2500. Be sure to mention you are with the Animal Breeding & Genetics Short Course.


For transportation to and from the Des Moines airport, see: http://www.executiveexpress.biz/shuttle-service 


 


Course Content


The course will provide an introduction to graphical models, including correlation networks, structural equation models, and Bayesian networks. Topics to be discussed include the concept of d-separation, causal sufficiency, and Markov blanket. The material will be illustrated with applications in quantitative genetics and genomics, including the prediction of phenotypes using earlier expressed traits, and genome-enabled prediction. Other examples of application of graphical modeling will include genome-wide association analysis (GWAS) and quantitative trait loci (QTL) mapping for multiple traits, structural equation models with latent variables, and the combination of multiple layers of omics information. Additional topics will include the concept of Mendelian randomization, direct and indirect genetic effects, and the analysis of field data in livestock production.


 


Target audience and prerequisites


The course targets graduate students and researchers interested on the analysis of genetics and genomics data, including complex traits, molecular markers and gene expression. Some basic knowledge of quantitative and molecular genetics, linear mixed models, and elementary probability and statistics is expected. However, a brief overview of matrix algebra, probability distributions, and statistical inference will be provided at the beginning of the course. In addition, a working knowledge of R is desirable but an introduction will be offered prior to the use of specific R packages for graphical modeling.


 


COURSE OUTLINE


 


Correlation and Causation


Sewall Wright and path analysis


Observational and experimental data


Confounding and selection bias


Randomization


 


Basics of Matrix Algebra


Definitions and matrix operations


Systems of equations


Linear regression and least squares


 


Aspects of Multivariate Distributions


Density function or mass function


Marginal and conditional distributions


Expectation and variance


Covariance and independence


The multivariate normal distribution


 


Inference with Multivariate Models


Likelihood principle


Parameter estimation, Hypothesis test


Independence tests (Discrete, Continuous, and Mixed cases)


 


Introduction to Graphical Models


Basic concepts; network topology features


Correlation networks


Marginal and partial correlations


Conditional independence and the concept of d-separation


 


Structural Equation Models in Quantitative Genetics


Traditional multi-trait mixed effects model (MTM)


Genetic and phenotypic correlation


Basics of structural equation models (SEM)


SEM with latent variables


SEM embedded in MTM; direct and indirect genetic effects


 


Bayesian Networks


Introduction


Structure learning (constraint- and score-based algorithms)


Parameter learning


The concept of Markov blanket


Causal inference


 


Applications in Genetics and Genomics


Building parsimonious models


Genome-enabled prediction


Instrumental variable and Mendelian randomization


Multiple-trait QTL mapping


Combining multiple layers of omics information


 


R packages: Rgraphviz, pcalg, bnlearn, qtlnet, sem, lavaan, among others


 


Dr. Jack C. M. Dekkers

C.F. Curtiss Distinguished Professor

Section Leader of Animal Breeding and Genetics

239D Kildee Hall

Department of Animal Science

Iowa State University

Ames, IA, 50011

515-294-7509  Fax: 515-294-9150  
jdekkers@iastate.edu http://www.ans.iastate.edu/people/jack-c-dekkers 

Category: