Main Functions

Functions that provide the main workflow of the package.

check.associations()

Check and visualize associations between features and classes

filter.features()

Perform unsupervised feature filtering.

create.data.split()

Split a dataset into training and a test sets.

normalize.features()

Perform feature normalization

train.model()

Model training

make.predictions()

Make predictions on a test set

evaluate.predictions()

Evaluate prediction results

Plots

Functions to produce the major visual output, i.e. the model evaluation and model interpretation plot

check.confounders()

Check for potential confounders in the metadata

model.evaluation.plot()

Model Evaluation Plot

model.interpretation.plot()

Model Interpretation Plot

Miscellaneous

Other functions for general data manipulation (some of them are probably mostly for internal use)

summarize.features()

Summarize features

filter.label()

Filter the label of a SIMACAT object

select.samples()

Select samples based on metadata

add.meta.pred()

Add metadata as predictors

create.label()

Create a label list

validate.data()

Validate samples in labels, features, and metadata

read.label()

Read label file

SIAMCAT class

The SIAMCAT class and the constructor function

siamcat-class

The S4 SIAMCAT class

siamcat()

SIAMCAT constructor function

SIAMCAT-package

SIAMCAT: Statistical Inference of Associations between Microbial Communities And host phenoTypes

Accessor functions

Functions to retrieve information out of the SIAMCAT object

label()

Retrieve the label from a SIAMCAT object

meta()

Retrieve the metadata from a SIAMCAT object

get.orig_feat.matrix()

Retrieve the original features from a SIAMCAT object

associations()

Retrieve the results of association testing from a SIAMCAT object

assoc_param()

Retrieve the list of parameters for association testing from a SIAMCAT object

filt_params()

Retrieve the list of parameters for feature filtering from a SIAMCAT object

get.filt_feat.matrix()

Retrieve the filtered features from a SIAMCAT object

data_split()

Retrieve the data split from a SIAMCAT object

norm_params()

Retrieve the list of parameters for feature normalization from a SIAMCAT object

get.norm_feat.matrix()

Retrieve the normalized features from a SIAMCAT object

models()

Retrieve list of trained models from a SIAMCAT object

model_type()

Retrieve the machine learning method from a SIAMCAT object

feature_type()

Retrieve the feature type used for model training from a SIAMCAT object

feature_weights()

Retrieve the matrix of feature weights from a SIAMCAT object

weight_matrix()

Retrieve the weight matrix from a SIAMCAT object

pred_matrix()

Retrieve the prediction matrix from a SIAMCAT object

eval_data()

Retrieve the evaluation metrics from a SIAMCAT object

Included data

Data included in the package

feat.crc.zeller

Example feature matrix

meta.crc.zeller

Example metadata matrix

siamcat_example

SIAMCAT example