push to v014

Author: bonagurol

CHANGELOG

@@ -36,4 +36,6 @@ v.014 -> Add ML classifier with CytoML
       -> Tested diffusion map and imporoved function
       -> Tested pseutodime and improved function
       -> Splittied functions in multiple files to make them easier to find
+      -> Improved package documentation
+      -> Improved package vignette
 

R/clinical_classifier.R

@@ -1,18 +1,18 @@
 #' Train Clinical Classifier
 #'
 #' @title train_classifier_model
-#' @description train_classifier_model
-#' @param fcd XX
-#' @param input_type XX
-#' @param data_slot XX
-#' @param sample_names XX
-#' @param classification_variable XX
-#' @param family XX
-#' @param type1 XX
-#' @param type2 XX
-#' @param parallelCore XX
-#' @param reg XX
-#' @param seed XX
+#' @description This function trains a classifier for a clinical feature of the data.
+#' @param fcd flowframe object.
+#' @param input_type data to use for the calculation, e.g. "pca" (suggested option).
+#' @param data_slot name to use. If no prefix was added the, *orig*.
+#' @param sample_names Column name of the metadata table containing the file names.
+#' @param classification_variable Vector (same length as number of cells) with the classes to classify (e.g. ctrl/dis).
+#' @param family Response type. Must be one of the following: "gaussian","binomial","poisson","multinomial","cox","mgaussian".
+#' @param type1 Type of first level prediction. Type of prediction required. Type "link" gives the linear predictors for "binomial", "multinomial", "poisson" or "cox" models; for "gaussian" models it gives the fitted values. Type "response" gives the fitted probabilities for "binomial" or "multinomial", fitted mean for "poisson" and the fitted relative-risk for "cox"; for "gaussian" type "response" is equivalent to type "link".
+#' @param type2 Type of second level prediction.
+#' @param parallelCore Number of cores to be used.
+#' @param reg If elestic net regularization will be used (Default: FALSE).
+#' @param seed seed to be used.
 #' @import CytoDx
 #' @return train_classifier_model
 #'
@@ -57,13 +57,13 @@ train_classifier_model <- function(fcd,
 #' Predict Clinical Classifier
 #'
 #' @title predict_classifier
-#' @description predict_classifier
-#' @param fcd XX
-#' @param input_type XX
-#' @param data_slot XX
-#' @param sample_names XX
-#' @param model_object XX
-#' @param seed XX
+#' @description This function uses the model trained with *train_classifier_model* to predict new samples.
+#' @param fcd flowframe object.
+#' @param input_type data to use.
+#' @param data_slot name of the data slot to use.
+#' @param sample_names Column name of the metadata table containing the file names.
+#' @param model_object flowframe object with the stored classifier model.
+#' @param seed seed to be used for the analysis.
 #' @import CytoDx
 #' @return predict_classifier
 #'

R/clustering.R

@@ -1,11 +1,11 @@
 #' metaclustering
 #'
 #' @title metaclustering
-#' @description Assignment of a metacluster.
+#' @description Assignment of a metaclusters name.
 #' @param fcd flow cytometry dataset.
 #' @param clustering Name of the clustering to match for the metaclustering.
-#' @param name_col Column containing the original cluster
-#' @param name_out Name of the output column
+#' @param name_col Column containing the original cluster.
+#' @param name_out Name of the output column.
 #' @param metaclusters Vector of the new clusters names, this should be of the same length of the levels of the original clustering.
 #' @return metaclustering
 #'
@@ -52,7 +52,7 @@ metaclustering <- function(fcd,
 #' @param k K value used for clustering.
 #' @param seed Seed used for the randomization steps.
 #' @param prefix Prefix for the output.
-#' @param top_PCA XX
+#' @param top_PCA Number of principal components to use for the analysis.
 #' @import Rphenograph
 #' @importFrom igraph membership
 #' @return runPhenograph
@@ -100,8 +100,8 @@ runPhenograph <- function(fcd,
 #' @param num_clusters number of final clusters.
 #' @param seed Seed used for the randomization steps.
 #' @param prefix Prefic for the output.
-#' @param ret_model XX
-#' @param top_PCA XX
+#' @param ret_model Logical: if the FlowSOM model should be kept for further visualization.
+#' @param top_PCA Number of principal components to use for the analysis.
 #' @return metaclustering
 #'
 #' @export

R/data_load_and_transform.R

@@ -1,10 +1,10 @@
 #' nfTransform
 #'
 #' @title nfTransform
-#' @description Data transformation.
-#' @param transTypeTable Table with the transformation parameters
-#' @param dataA dataA
-#' @param dataB dataB
+#' @description Data transformation, this function run within the prep_fcd wrapper.
+#' @param transTypeTable Table with the transformation parameters.
+#' @param dataA dataA.
+#' @param dataB dataB, same as dataA.
 #' @return transformed flow cytometry dataset
 #'
 #' @export
@@ -90,11 +90,11 @@ nfTransform <- function(transTypeTable, dataA, dataB){
 #' prepFcsFolderData
 #'
 #' @title prepFcsFolderData
-#' @description Load the .fcs files into a dataframe
-#' @param LoaderPATH Path to the .fcs files
-#' @param ceil number of cells to subset
-#' @param useCSV Logical, if input is .csv and not .fcs
-#' @param separator Separato used the flow csv files (if loading from csv)
+#' @description Load .fcs or .csv files into a dataframe and prepare the condor object.
+#' @param LoaderPATH Path to the .fcs files.
+#' @param ceil number of cells to subset.
+#' @param useCSV Logical, if input is .csv and not .fcs.
+#' @param separator Separator used the flow csv files (if loading from csv).
 #' @import flowCore
 #' @import reshape2
 #' @import dplyr
@@ -172,17 +172,17 @@ prepFcsFolderData <- function(LoaderPATH, ceil, useCSV, separator){
 
 #' Read FlowJo workspace
 #'
-#' @title read_flowjo_workspace
-#' @description read_flowjo_workspace
-#' @param data_gs XX
-#' @param pop XX
-#' @param gate_list XX
-#' @param inverse.transform XX
-#' @param transformation XX
-#' @param remove_param XX
-#' @param merge_anno XX
-#' @param anno_table XX
-#' @param separator_anno XX
+#' @title Read FlowJo Workspace
+#' @description read_flowjo_workspace and prepare the condor object
+#' @param data_gs Gate Set object from flowWorkspace Package.
+#' @param pop Gate to keep for downstream analysis (default: 'root').
+#' @param gate_list Gate List of the FlowJo Workspace.
+#' @param inverse.transform Logical: if the data should be reverse transformed of kept with FlowJo transformation (default = FALSE).
+#' @param transformation If inverse.transform = TRUE, type of new transformation to perform (see nfTransform).
+#' @param remove_param Parameters to be removed from the condor object.
+#' @param merge_anno Logical: If sample anno should be merged to the condor object.
+#' @param anno_table Path to annotation table.
+#' @param separator_anno Separator of the .csv annotation table.
 #' @import flowWorkspace
 #' @import Biobase
 #' @import CytoML
@@ -294,15 +294,15 @@ prep_fjw <- function(data_gs,
 #' @title prep_fcd
 #' @description Wrapping function to prepare a flow cytometry dataset
 #' @param FCSpath Folder where the .fcs files are stored.
-#' @param ceil Number of cells to use for each file (set to a high number if you want to use all available events)
+#' @param ceil Number of cells to use for each file (set to a high number if you want to use all available events).
 #' @param useCSV Flag if the input are .csv files and not .fcs (experimental).
 #' @param transformation Transformation to perform.
-#' @param remove_param Parameters to remove from the trasfomration, "inTime" should be kept.
+#' @param remove_param Parameters to remove from the transformation, "inTime" should be kept.
 #' @param anno_table path to the annotation table file.
 #' @param filename_col Name of the column containing the filename matching with the .fcs files.
 #' @param seed seed to be used for the randomization of the events.
-#' @param separator_anno separator used in the annotation file
-#' @param separator_fc_csv separator used in the fc csv files
+#' @param separator_anno separator used in the annotation file.
+#' @param separator_fc_csv separator used in the fc csv files.
 #' @import readr
 #' @import readxl
 #' @import stringr

R/data_projection.R

@@ -1,15 +1,15 @@
 #' learnUMAP
 #'
 #' @title learnUMAP
-#' @description learnUMAP
-#' @param fcd XX
-#' @param input_type XX
-#' @param data_slot XX
-#' @param model XX
-#' @param n_epochs XX
-#' @param prefix XX
-#' @param n_threads XX
-#' @param seed XX
+#' @description Uses the model calculated with *runUMAP* to project new samples
+#' @param fcd flow cytometry dataset.
+#' @param input_type data to use for the calculation of the UMAP, e.g. "expr" or "pca".
+#' @param data_slot name of the PCA data slot to use to harmonize. If no prefix was added the, *orig*.
+#' @param model Data associated with an existing embedding.
+#' @param n_epochs Number of epochs to use during the optimization of the embedded coordinates. A value between 30 - 100 is a reasonable trade off between speed and thoroughness. By default, this value is set to one third the number of epochs used to build the model.
+#' @param prefix Prefix for the name of the dimensionality reduction.
+#' @param n_threads Number of threads to use, (except during stochastic gradient descent). Default is half the number of concurrent threads supported by the system.
+#' @param seed Seed to be used.
 #' @return learnUMAP
 #'
 #' @export
@@ -42,15 +42,15 @@ learnUMAP <- function(fcd,
 #' train_transfer_model
 #'
 #' @title train_transfer_model
-#' @description train_transfer_model
-#' @param fcd XX
-#' @param input_type XX
-#' @param data_slot XX
-#' @param label XX
-#' @param method XX
-#' @param tuneLength XX
-#' @param trControl XX
-#' @param seed XX
+#' @description Train a machine learning model to transfer cell label (this function implement the *caret* workflow)
+#' @param fcd flow cytometry dataset.
+#' @param input_type data to use for the calculation of the UMAP, e.g. "expr" or "pca".
+#' @param data_slot name of the PCA data slot to use to harmonize. If no prefix was added the, *orig*.
+#' @param label Vector with the labels to be used for the label transfer.
+#' @param method A string specifying which classification or regression model to use. Possible values are found using names(getModelInfo()). See http://topepo.github.io/caret/train-models-by-tag.html. A list of functions can also be passed for a custom model function. See http://topepo.github.io/caret/using-your-own-model-in-train.html for details.
+#' @param tuneLength An integer denoting the amount of granularity in the tuning parameter grid. By default, this argument is the number of levels for each tuning parameters that should be generated by train. If trainControl has the option search = "random", this is the maximum number of tuning parameter combinations that will be generated by the random search. (NOTE: If given, this argument must be named.)
+#' @param trControl A list of values that define how this function acts. See trainControl and http://topepo.github.io/caret/using-your-own-model-in-train.html. (NOTE: If given, this argument must be named.)
+#' @param seed Seed to be used.
 #' @import caret
 #' @import randomForest
 #' @return train_transfer_model
@@ -93,13 +93,13 @@ train_transfer_model <- function(fcd,
 #' predict_labels
 #'
 #' @title predict_labels
-#' @description predict_labels
-#' @param fcd XX
-#' @param input_type XX
-#' @param data_slot XX
-#' @param model_object XX
-#' @param label XX
-#' @param seed XX
+#' @description Uses the model generated with *train_transfer_model* to predict the labels of new samples
+#' @param fcd flow cytometry dataset.
+#' @param input_type data to use for the calculation of the UMAP, e.g. "expr" or "pca".
+#' @param data_slot name of the PCA data slot to use to harmonize. If no prefix was added the, *orig*.
+#' @param model_object Caret model to the used for the label transfer.
+#' @param label Label for the output column of the condor object.
+#' @param seed Seed to be used.
 #' @return predict_labels
 #'
 #' @export