predict.codacore

In the context of high-throughput genetic data,
CoDaCoRe identifies a set of sparse biomarkers that are
predictive of a response variable of interest (Gordon-Rodriguez
et al., 2021) <doi:10.1093/bioinformatics/btab645>. More
generally, CoDaCoRe can be applied to any regression problem
where the independent variable is Compositional (CoDa), to
derive a set of scale-invariant log-ratios (ILR or SLR) that
are maximally associated to a dependent variable.

Elliott Gordon-Rodriguez

codacore

Learning Sparse Log-Ratios for Compositional Data

Thomas Quinn

predict.codacore function

<dl><dt>object</dt>
<dd>A codacore object.</dd>
<dt>newx</dt>
<dd>A set of inputs to our model.</dd>
<dt>asLogits</dt>
<dd>Whether to return outputs in logit space
(as opposed to probability space). Should always be set
to TRUE for regression with continuous outputs, but can
be toggled for classification problems.</dd>
<dt>numLogRatios</dt>
<dd>How many predictive log-ratios to 
include in the prediction. By default, includes the
effects of all log-ratios that were obtained during
training. Setting this parameter to an integer k will
restrict to using only the top k log-ratios in the model.</dd>
<dt>...</dt>
<dd>Not used.</dd></dl>

Arguments

predict — predict.codacore

<dl>

<dt>object</dt>
<dd>A codacore object.</dd>


<dt>newx</dt>
<dd>A set of inputs to our model.</dd>


<dt>asLogits</dt>
<dd>Whether to return outputs in logit space
(as opposed to probability space). Should always be set
to TRUE for regression with continuous outputs, but can
be toggled for classification problems.</dd>


<dt>numLogRatios</dt>
<dd>How many predictive log-ratios to 
include in the prediction. By default, includes the
effects of all log-ratios that were obtained during
training. Setting this parameter to an integer k will
restrict to using only the top k log-ratios in the model.</dd>


<dt>...</dt>
<dd>Not used.</dd>

</dl>

predict.codacore: predict

Description

Usage

Arguments