Network-based patient classifier

Documentation for package ‘netDx’ version 1.14.0

Help Pages

-- A --

allowedSims	built-in similarity functions
avgNormDiff	takes average of normdiff of each row in x

-- B --

buildPredictor	Run nested cross-validation on data
buildPredictor_sparseGenetic	Performs feature selection using multiple resamplings of the data

-- C --

callFeatSel	Return feature selected nets based on given criteria
callOverallSelectedFeatures	Wrapper to call selected features
checkMakeNetFuncSims	internal test function to check validity of makeNetFunc and sims
checkSimValid	checks if provided similarity functions are valid. Returns error if not
cleanPathwayName	Clean pathway name so it can be a filename.
cnv_GR	CNV locations for breast cancer (subset)
cnv_netPass	Vector of pathways that pass class enrichment
cnv_netScores	List of pathway-level feature selection scores
cnv_patientNetCount	Binary matrix of patient occurrence in networks
cnv_pheno	data.frame of patient labels and status for CNV example
cnv_TTstatus	list of train/test statuses for CNV example
compareShortestPath	compare intra-cluster shortest distance to overall shortest distance of the network
compileFeatures	Create GeneMANIA database
compileFeatureScores	Tally the score of networks through cross-validation
confmat	Confusion matrix example
confusionMatrix	Make confusion matrix
convertProfileToNetworks	Convert profiles to interaction networks before integration
convertToMAE	Wrapper that converts an input list into a MultiAssayExperiment object
countIntType	Counts the number of (+,+) and (+,-) interactions in a single network
countIntType_batch	Counts number of (+,+) and (+,-) interactions in a set of networks
countPatientsInNet	Count number of patients in a network
createNetFuncFromSimList	Create PSN from provided similarities
createPSN_MultiData	Wrapper to create custom input features (patient similarity networks)

-- D --

dataList2List

Convert MultiAssayExperiment object to list and data.frame

-- E --

enrichLabelNets

Score networks based on their edge bias towards (+,+) interactions

-- F --

featScores	Demo feature-level scores from running feature selection on two-class problem
fetchPathwayDefinitions	fetch pathway definitions from downloads.baderlab.org

-- G --

genes	Table of gene definitions (small subsample of human genes)
getCorrType	Counts the relative correlation of (+,+) and (+,-)(-,-) interactions
getEMapInput	write enrichment map for consensus nets
getEMapInput_many	Wrapper to generate multiple EnrichmentMaps (perhaps one per class)
getEnr	Get ENR for all networks in a specified directory
getFeatureScores	Compile network scores into a matrix
getFileSep	platform-specific file separator
getGMjar_path	download and update GeneMANIA jar file
getNetConsensus	compile net score across a set of predictor results
getOR	Get relative proportion of patient classes that contribute to a set of networks
getPatientPredictions	Calculates patient-level classification accuracy across train/test splits
getPatientRankings	Process GM PRANK files to get the ROC curve for the query
getPerformance	performance metrics for model
getPSN	get the integrated patient similarity network made of selected features
getRegionOL	Returns overlapping named ranges for input ranges
getResults	Compiles performance and selected features for a trained model.
getSimilarity	Measures of patient similarity

-- M --

makeInputForEnrichmentMap	Wrapper to create input files for Enrichment Map
makePSN_NamedMatrix	Create patient networks from full matrix of named measurements
makePSN_RangeSets	Create patient similarity interaction networks based on range sets
makeQueries	Randomly select patients for queries for feature selection
makeSymmetric	Convert a network in source-target-weight format to symmetric matrix
mapNamedRangesToSets	Map named ranges to corresponding set of named ranges
matrix_getIJ	Converts matrix index (1 to m*n) to row (m) and column (n) number
MB.pheno	Sample metadata table for medulloblastoma dataset.
modelres	Sample output of getResults()
moveInteractionNets	moves interaction networks when compiling database for sparse genetic workflow

-- N --

normDiff	Similarity metric of normalized difference
npheno	Toy sample metadata table

-- P --

pathwayList	Sample list of pathways
pathway_GR	List of genomic ranges mapped to pathways
perfCalc	Computes variety of predictor evaluation measures based on the confusion matrix
pheno	Sample metadata table
pheno_full	Subsample of TCGA breast cancer data used for netDx function examples
plotEmap	Create EnrichmentMap in Cytoscape to visualize predictive pathways
plotIntegratedPatientNetwork	Visualize integrated patient similarity network based on selected features
plotPerf	Plots various measures of predictor performance for binary classifiers
plotPerf_multi	Plots a set of ROC/PR curves with average.
predict	predict patient labels
predictPatientLabels	assign patient class when ranked by multiple GM predictors
predRes	Example output of getPatientRankings, used to call labels for test patients.
pruneNet	Prune network by retaining strongest edges
pruneNets	Prune interaction networks to keep only the networks and patients requested
pruneNet_pctX	Prune network by retaining strongest edges
psn__builtIn	make PSN for built-in similarity functions
psn__corr	wrapper for PSNs using Pearson correlation
psn__custom	make PSN for custom similarity functions

-- R --

randAlphanumString	Generate random alphanumerical string of length 10
readPathways	Parse GMT file and return pathways as list
replacePattern	Replace pattern in all files in dir
RR_featureTally	Computes positive and negative calls upon changing stringency of feature selected networks (binary networks only)
runFeatureSelection	Run GeneMANIA cross-validation with a provided subset of networks
runQuery	Run a query

-- S --

setupFeatureDB	setup database of features for feature selection
silh	Toy network.
sim.eucscale	Similarity method. Euclidean distance followed by exponential scaling
sim.pearscale	various similarity functions Similarity function: Pearson correlation followed by exponential scaling
simpleCap	simple capitalization
smoothMutations_LabelProp	This function applies the random walk with restart propagation algorithm to a matrix of patients profiles
sparsify2	cleaner sparsification routine
sparsify3	cleaner sparsification routine - faster, matrix-based version
splitTestTrain	Split samples into train/test
splitTestTrain_resampling	Assign train/test labels over several resamplings of the data.
subsampleValidationData	Subsample a hold-out set from a larger patient dataset

-- T --

thresholdSmoothedMutations	Apply discretization to the matrix resulted from the propagation on the sparse patient matrix
toymodel	Example model returned by a buildPredictor() call.
tSNEPlotter	Plot tSNE

-- U --

updateNets

Synchronize patient set in sample table and network table.

-- W --

writeNetsSIF	write patient networks in Cytoscape's .sif format
writeQueryBatchFile	Write batch.txt file required to create GeneMANIA database
writeQueryFile	Wrapper to write GeneMANIA query file
writeWeightedNets	Write an integrated similarity network consisting of selected networks.

-- X --

xpr	Example expression matrix

-- misc --

.get_cache

wrapper function for getting BiocFileCache associated with netDx package