Package 'omics'

Cross Phenotype Meta-Analysis

Description

Performs (signed) cross phenotype meta-analysis.

Usage

cpma(ps)

Arguments

ps	a (non-empty) numeric vector of $p$-values.

Value

A list with class htest containing the following components:

statistic	the value of the $\chi^2$ test statistic.
parameter	the estimated rate $\lambda$.
p.value	the $p$-value for the test.
method	a character string indicating the type of test performed.
data.name	a character string giving the name of the data.

References

Cotsapas, C., et al. 2011 Pervasive Sharing of Genetic Effects in Autoimmune Disease. PLOS Genetics 7(8):e1002254.

---

Multiple Linear Models

Description

Fits multiple linear models.

Usage

mlm(formula, data, vars, save.residuals=FALSE)

Arguments

formula	an object of class formula (or one that can be coerced to that class): a symbolic description of the models to be fitted.
data	an optional data frame, list or environment (or object coercible by as.data.frame to a data frame) containing the variables in the model.
vars	a character vector of variables of interest.
save.residuals	whether model residuals should be stored and returned.

Value

A list with elements:

coefficients	if 'vars' is missing or non-empty, an array (or data frame, if vars contains a single element) of regression coefficient estimates (coef), standard errors (coef.se), and corresponding $p$-values (pval).
residuals	if save.residuals is TRUE, a matrix of model residuals.

See Also

lm

Examples

coefs <- matrix(runif(6*10), 6, 10)
    X <- matrix(rnorm(100*5), 100, 5)
    Y <- cbind(1, X) 

    models <- mlm(Y ~ X)
    str(models)

---

Multiple Linear Mixed-Effects Models

Description

Fits multiple linear mixed-effects models.

Usage

mlmer(formula, data, vars, lrt=TRUE, save.residuals=FALSE, save.ranks=TRUE)

Arguments

formula	an object of class formula (or one that can be coerced to that class): a symbolic description of the models to be fitted.
data	an optional data frame, list or environment (or object coercible by as.data.frame to a data frame) containing the variables in the model.
vars	a character vector of variables of interest.
lrt	whether $p$-values should be computed using likelihood-ratio tests.
save.residuals	whether model residuals should be stored and returned.
save.ranks	whether random effect ranks should be stored and returned.

Value

A list with elements:

coefficients	if 'vars' is missing or non-empty, an array (or data frame, if vars contains a single element) of regression coefficient estimates (coef), standard errors (coef.se), and corresponding $p$-values (pval).
residuals	if save.residuals is TRUE, a matrix of model residuals.
ranef.ranks	if save.ranks is TRUE (default), a list of rank matrices (one per random effect) that can be visualized using ranks.heatmap.

See Also

lmer and mlm

---

Count Missing Values

Description

Counts the number of missing values.

Usage

na.count(X, margin, fraction=TRUE)

Arguments

X	an array, including a matrix.
margin	a vector giving the subscripts to count over.
fraction	whether to return the fraction of missing values.

Value

The number (or fraction) of missing values.

---

Quantile-Quantile Plot for $p$-values

Description

Computes value to produce a quantile-quantile plot in $-log_10$ scale of the given $p$-values.

Usage

pqq(ps)

    pqq.ci(n, level=0.95)

Arguments

ps	a (non-empty) numeric vector of $p$-values.
n	number of $p$-values.
level	significance level.

Value

For pqq, a list containing the following components (all in $-log_10$ scale):

x	a vector of (sorted) expected $p$-values.
y	a vector of (sorted) observed $p$-values.

For pqq.ci, a matrix with the lower and upper bounds for the confidence interval at the given significance level.

---

Extract Random Effect Rank Distributions

Description

Extracts random effect rank distributions from a linear mixed-effects model.

Usage

## S3 method for class 'merMod'
ranef.ranks(model, groups)

Arguments

model	a linear mixed-effects model estimated using lmer.
groups	a character vector of random effects of interest.

Value

If which is missing, a list of rank distribution vectors for all random intercepts in the model. Otherwise, a list of rank distribution vectors for random intercepts specified by which.

See Also

mlmer

---

Plot Random Effect Rank Distributions

Description

Plots the rank distribution matrix for a random effect generated by mlmer.

Usage

ranks.heatmap(x, col="red")

Arguments

x	a matrix with the rank distribution for a random effect generated by mlmer.
col	the color corresponding to "higher-than-expected" counts.

Side Effects

Generates a new plot.

See Also

mlmer

---

Pattern Matching and Extraction

Description

Matches and extracts substrings using regular expressions.

Usage

re.match(pattern, x, ...)

Arguments

pattern	character string containing a regular expression.
x	a character vector where matches are sought, or an object which can be coerced by as.character to a character vector.
...	further arguments to be passed to regexec.

Details

This function is a wrapper for consecutive calls to regexec and regmatches.

Value

A matrix of matched substrings.

See Also

regexec and regmatches

---

Set Operations on Multiple Vectors

Description

Performs set operations on multiple vectors.

Usage

mintersect(..., sorted=FALSE)

    munion(..., sorted=FALSE)

Arguments

...	input vectors
sorted	whether the result should be sorted

Value

Set intersection or union of the given vectors

See Also

intersect and union

---

Extract Variance Components

Description

Extracts variance components from a linear mixed-effects model.

Usage

## S3 method for class 'merMod'
var.components(model)

Arguments

model

a linear mixed-effects model estimated using lmer.

Value

A data frame with elements:

group	the name of the random effect.
var.name	the name of the variable.
var	the estimated variance.
var.prop	the estimated proportion of variance.

See Also

mlmer

---