Package 'PhyloProfile'

Description

Add colors to features/domains of 2 domain dataframes. Users can choose to color only the shared features, unique features, all features (default) or based on feature types. Default color pallete is "Paired", but it can be changed.

Usage

addFeatureColors(
  seedDf = NULL,
  orthoDf = NULL,
  colorType = "all",
  colorPalette = "Paired",
  ignoreInstanceNo = FALSE
)

Arguments

Value

2 dataframes (seedDf and orthoDf) with an additional column for the assigned color to each feature instance

Author(s)

Vinh Tran [email protected]

Examples

# get domain data
seedID <- "101621at6656"
domainFile <- system.file(
    "extdata", "domainFiles/101621at6656.domains",
    package = "PhyloProfile", mustWork = TRUE
)
domainDf <- parseDomainInput(seedID, domainFile, "file")
# get seedDf and orthoDf
subDf <- domainDf[
    domainDf$seedID ==
    "101621at6656#101621at6656:AGRPL@224129@0:224129_0:001955:1",]
orthoDf <- subDf[subDf$orthoID == "101621at6656:DROME@7227@1:Q9VG04",]
seedDf <- subDf[subDf$orthoID != "101621at6656:DROME@7227@1:Q9VG04",]
# add colors to features
PhyloProfile:::addFeatureColors(seedDf, orthoDf)

Description

Add taxonomy rank division lines to the heatmap plot

Usage

addRankDivisionPlot(profilePlot = NULL, plotDf = NULL,
    taxDB = NULL, workingRank = NULL, superRank = NULL, xAxis = "taxa",
    font = "Arial", groupLabelSize = 14, groupLabelDist = 2,
    groupLabelAngle = 90, refLine = TRUE)

Arguments

Value

A profile heatmap plot with highlighted gene and/or taxon of interest as ggplot object.

Author(s)

Vinh Tran [email protected]

See Also

heatmapPlotting, highlightProfilePlot, getTaxonomyMatrix

Examples

data("finalProcessedProfile", package="PhyloProfile")
plotDf <- dataMainPlot(finalProcessedProfile)
plotParameter <- list(
    "xAxis" = "taxa",
    "geneIdType" = "geneID",
    "var1ID" = "FAS_FW",
    "var2ID"  = "FAS_BW",
    "midVar1" = 0.5,
    "midColorVar1" =  "#FFFFFF",
    "lowColorVar1" =  "#FF8C00",
    "highColorVar1" = "#4682B4",
    "midVar2" = 1,
    "midColorVar2" =  "#FFFFFF",
    "lowColorVar2" = "#CB4C4E",
    "highColorVar2" = "#3E436F",
    "paraColor" = "#07D000",
    "xSize" = 8,
    "ySize" = 8,
    "legendSize" = 8,
    "mainLegend" = "top",
    "dotZoom" = 0,
    "xAngle" = 60,
    "guideline" = 0,
    "colorByGroup" = FALSE,
    "colorByOrthoID" = FALSE
)
profilePlot <- heatmapPlotting(plotDf, plotParameter)
workingRank <- "class"
superRank <- "superkingdom"
addRankDivisionPlot(
    profilePlot, plotDf, NULL, workingRank, superRank, "taxa", font = "sans"
)

Description

Add colors for taxa in UMAP plot

Usage

addUmapTaxaColors(plotDf = NULL, colorPalette = "Set2", 
    highlightTaxa = NULL)

Arguments

Value

A dataframe for UMAP plot with an additional column for the assigned color to each taxon

Author(s)

Vinh Tran [email protected]

See Also

prepareUmapData, umapClustering, createUmapPlotData

Examples

rawInput <- system.file(
   "extdata", "test.main.long", package = "PhyloProfile", mustWork = TRUE
)
longDf <- createLongMatrix(rawInput)
umapData <- prepareUmapData(longDf, "phylum")
data.umap <- umapClustering(umapData)
plotDf <- createUmapPlotData(data.umap, umapData)
PhyloProfile:::addUmapTaxaColors(plotDf, colorPalette = "Set2")

Description

Calculate percentage of present species in each super taxon

Usage

calcPresSpec(profileWithTax, taxaCount)

Arguments

Value

A data frame with

Author(s)

Vinh Tran [email protected]

See Also

profileWithTaxonomy for a demo input data

Examples

# NOTE: for internal testing only
library(dplyr)
data("profileWithTaxonomy", package="PhyloProfile")
taxaCount <- profileWithTaxonomy %>% dplyr::count(supertaxon)
taxaCount$n <- 1
calcPresSpec(profileWithTaxonomy, taxaCount)

Description

Check if a color pallete has enough colors for a list of items

Usage

checkColorPalette(items, pallete = "Paired")

Arguments

Value

TRUE if color pallete has enough colors, otherwise FALSE

Author(s)

Vinh Tran [email protected]

Examples

myItems <- rep("a",3)
checkColorPalette(myItems, "Set1")

Description

Check if input file has one of the following format: orthoXML, multiple FASTA, tab-delimited matrix (wide or long), or list of OMA IDs.

Usage

checkInputValidity(filein)

Arguments

Value

The format of the input file format, or type of error

Author(s)

Vinh Tran [email protected]

See Also

checkOmaID

Examples

filein <- system.file(
    "extdata", "test.main.wide", package = "PhyloProfile", mustWork = TRUE
)
checkInputValidity(filein)

Description

Check the validity of input newick tree

Usage

checkNewick(tree, inputTaxonID = NULL)

Arguments

Value

Possible formatting error of input tree. 0 = suitable tree for using with PhyloProfile, 1 = missing parenthesis; 2 = missing comma; 3 = tree has singleton; or a list of taxa that do not exist in the input phylogenetic profile.

Author(s)

Vinh Tran [email protected]

See Also

getInputTaxaID for getting input taxon IDs, ppTree for an example of input tree

Examples

data("ppTree", package="PhyloProfile")
checkNewick(ppTree, c("ncbi3702", "ncbi3711", "ncbi7029"))

Description

Check if input IDs are valid OMA IDs for OMA Browser

Usage

checkOmaID(ids)

Arguments

Value

List of invalid IDs (not readable for OMA)

Author(s)

Vinh Tran [email protected]

Examples

### Uncomment the following line to run the function
# checkOmaID("HUMAN29398")

Description

Identify feature type(s) containing overlapped domains/features

Usage

checkOverlapDomains(domainDf)

Arguments

Value

List of feature types that have overlapped domains

Author(s)

Vinh Tran [email protected]

Examples

# get domain data
seedID <- "101621at6656"
domainFile <- system.file(
    "extdata", "domainFiles/101621at6656.domains",
    package = "PhyloProfile", mustWork = TRUE
)
domainDf <- parseDomainInput(seedID, domainFile, "file")
# get seedDf and orthoDf
subDf <- domainDf[
    domainDf$seedID ==
    "101621at6656#101621at6656:AGRPL@224129@0:224129_0:001955:1",]
orthoDf <- subDf[subDf$orthoID == "101621at6656:DROME@7227@1:Q9VG04",]
# check overlap features
PhyloProfile:::checkOverlapDomains(orthoDf)

Description

Create a hclust object from the distance matrix

Usage

clusterDataDend(distanceMatrix = NULL, clusterMethod = "complete")

Arguments

Value

An object class hclust generated based on input distance matrix and a selected clustering method.

Author(s)

Vinh Tran [email protected]

See Also

getDataClustering, getDistanceMatrix, hclust

Examples

data("finalProcessedProfile", package="PhyloProfile")
data <- finalProcessedProfile
profileType <- "binary"
profiles <- getDataClustering(
    data, profileType, var1AggregateBy, var2AggregateBy)
distMethod <- "mutualInformation"
distanceMatrix <- getDistanceMatrix(profiles, distMethod)
clusterMethod <- "complete"
clusterDataDend(distanceMatrix, clusterMethod)

Description

Given the phylogenetic profiles that contains up to 2 additional variables besides the presence/absence information of the orthologous proteins. This function will compare the median scores of those variables between 2 different taxon groups (e.g. parasitic species vs non-parasitic species), which are defined as in-group and out-group. In-group is identified by the user. Out-group contains all taxa in the input phylogenetic profiles that are not part of the in-group.

Usage

compareMedianTaxonGroups(data, inGroup, useCommonAncestor, variable,
    taxDB)

Arguments

Value

List of genes that have a difference in the variable's median scores between the in-group and out-group taxa and their corresponding delta-median.

Author(s)

Vinh Tran ([email protected])

Examples

data("mainLongRaw", package="PhyloProfile")
data <- mainLongRaw
inGroup <- c("ncbi9606", "ncbi10116")
variable <- colnames(data)[4]
compareMedianTaxonGroups(data, inGroup, TRUE, variable)

Description

Given the phylogenetic profiles that contains up to 2 additional variables besides the presence/absence information of the orthologous proteins. This function will compare the distribution of those variables between 2 different taxon groups (e.g. parasitic species vs non-parasitic species), which are defined as in-group and out-group. In-group is identified by the user. Out-group contains all taxa in the input phylogenetic profiles that are not part of the in-group.

Usage

compareTaxonGroups(data, inGroup, useCommonAncestor, variable,
    significanceLevel, taxDB)

Arguments

Value

list of genes that have a significant difference in the variable distributions between the in-group and out-group taxa and their corresponding p-values.

Author(s)

Vinh Tran ([email protected])

Examples

data("mainLongRaw", package="PhyloProfile")
data <- mainLongRaw
inGroup <- c("ncbi9606", "ncbi10116")
variable <- colnames(data)[4]
compareTaxonGroups(data, inGroup, TRUE, variable, 0.05)

Description

Create architecture plot for both seed and orthologous protein. If domains of ortholog are missing, only architecture of seed protein will be plotted. NOTE: seed protein ID is the one being shown in the profile plot, which normally is also the orthologous group ID.

Usage

createArchiPlot(info, domainDf, labelArchiSize, titleArchiSize,
    showScore, showWeight, namePosition, firstDist, nameType, nameSize,
    segmentSize, nameColor, labelPos, colorType, ignoreInstanceNo,
    currentNCBIinfo, featureClassSort, featureClassOrder, colorPalette,
    resolveOverlap, font)

Arguments

Value

A domain plot as arrangeGrob object. Use grid::grid.draw(plot) to render.

Author(s)

Vinh Tran [email protected]

See Also

singleDomainPlotting,pairDomainPlotting, sortDomains, parseDomainInput

Examples

seedID <- "101621at6656"
orthoID <- "101621at6656|AGRPL@224129@0|224129_0:001955|1"
info <- c(seedID, orthoID)
domainFile <- system.file(
    "extdata", "domainFiles/101621at6656.domains",
    package = "PhyloProfile", mustWork = TRUE
)
domainDf <- parseDomainInput(seedID, domainFile, "file")
domainDf$feature_id_mod <- domainDf$feature_id
domainDf$feature_id_mod <- gsub("SINGLE", "LCR", domainDf$feature_id_mod)
domainDf$feature_id_mod[domainDf$feature_type == "coils"] <- "Coils"
domainDf$feature_id_mod[domainDf$feature_type == "seg"] <- "LCR"
domainDf$feature_id_mod[domainDf$feature_type == "tmhmm"] <- "TM"
plot <- createArchiPlot(info, domainDf, font = "sans")
grid::grid.draw(plot)

Description

Create gene age plot

Usage

createGeneAgePlot(geneAgePlotDf, textFactor = 1, font = "Arial")

Arguments

Value

A gene age distribution plot as a ggplot2 object

Author(s)

Vinh Tran [email protected]

See Also

estimateGeneAge and geneAgePlotDf

Examples

geneAgePlotDf <- data.frame(
    name = c("Streptophyta (Phylum)", "Bikonta", "Eukaryota (Superkingdom)"),
    count = c(7, 1, 30),
    percentage = c(18, 3, 79)
)
createGeneAgePlot(geneAgePlotDf, 1, "sans")

Description

Create a long matrix format for all kinds of input phylogenetic profiles

Usage

createLongMatrix(inputFile = NULL)

Arguments

Value

A data frame of input data in long-format containing seed gene IDs ( or orthologous group IDs), their orthologous proteins together with the corresponding taxonomy IDs and values of (up to) two additional variables.

Author(s)

Vinh Tran [email protected]

See Also

xmlParser, fastaParser, wideToLong

Examples

inputFile <- system.file(
    "extdata", "test.main.wide", package = "PhyloProfile", mustWork = TRUE
)
createLongMatrix(inputFile)

Description

Create data for percentage present taxa distribution

Usage

createPercentageDistributionData(inputData = NULL, rankName = NULL,
    taxDB = NULL)

Arguments

Value

A dataframe for analysing the distribution of the percentage of species in the selected supertaxa, containing the seed protein IDs, percentage of their orthologs in each supertaxon and the corresponding supertaxon names.

Author(s)

Vinh Tran [email protected]

See Also

mainLongRaw

Examples

data("mainLongRaw", package="PhyloProfile")
createPercentageDistributionData(mainLongRaw, "class")

Description

Create a phylogenetic profile from a raw OMA dataframe

Usage

createProfileFromOma(finalOmaDf = NULL)

Arguments

Value

Dataframe of the phylogenetic profiles in long format, which contains the seed protein IDs, their orthologous proteins and the corresponding taxononmy IDs of the orthologs.

Author(s)

Vinh Tran [email protected]

See Also

getDataForOneOma

Examples

### Uncomment the following lines to run the function
# omaData <- getDataForOneOma("HUMAN29397", "OG")
# createProfileFromOma(omaData)

Description

Create UMAP cluster plot

Usage

createUmapPlotData(umapData = NULL, data4umap = NULL, 
    freqCutoff = c(0,200), excludeTaxa = "None", currentNCBIinfo = NULL)

Arguments

Value

A plot as ggplot object

Author(s)

Vinh Tran [email protected]

See Also

prepareUmapData, umapClustering

Examples

rawInput <- system.file(
   "extdata", "test.main.long", package = "PhyloProfile", mustWork = TRUE
)
longDf <- createLongMatrix(rawInput)
data4umap <- prepareUmapData(longDf, "phylum")
umapData <- umapClustering(data4umap)
createUmapPlotData(umapData, data4umap)

Description

Create unrooted tree from a taxonomy matrix

Usage

createUnrootedTree(df)

Arguments

Value

A unrooted taxonomy tree as an object of class "phylo".

Author(s)

Vinh Tran [email protected]

See Also

taxa2dist for distance matrix generation from a taxonomy matrix, getTaxonomyMatrix for getting taxonomy matrix, ppTaxonomyMatrix for a demo taxonomy matrix data

Examples

data("ppTaxonomyMatrix", package = "PhyloProfile")
createUnrootedTree(ppTaxonomyMatrix)

Description

Create distribution plot for one of the additional variable or the percentage of the species present in the supertaxa.

Usage

createVarDistPlot(data, varName = "var", varType = "var1",
    percent = c(0, 1), textSize = 12)

Arguments

Value

A distribution plot for the selected variable as a ggplot object

Author(s)

Vinh Tran [email protected]

See Also

mainLongRaw, createVariableDistributionData, createVariableDistributionDataSubset, createPercentageDistributionData

Examples

data("mainLongRaw", package="PhyloProfile")
data <- createVariableDistributionData(
    mainLongRaw, c(0, 1), c(0.5, 1)
)
varName <- "Variable abc"
varType <- "var1"
percent <- c(0,1)
textSize <- 12
createVarDistPlot(
    data,
    varName,
    varType,
    percent,
    textSize
)

Description

Create data for additional variable distribution

Usage

createVariableDistributionData(inputData, var1Cutoff = c(0 ,1),
    var2Cutoff = c(0, 1))

Arguments

Value

A dataframe for analysing the distribution of the additional variable(s) containing the protein (ortholog) IDs and the values of their variables (var1 and var2).

Author(s)

Vinh Tran [email protected]

See Also

mainLongRaw

Examples

data("mainLongRaw", package="PhyloProfile")
createVariableDistributionData(
    mainLongRaw, c(0, 1), c(0.5, 1)
)

Description

Create data for additional variable distribution (for a subset data)

Usage

createVariableDistributionDataSubset(fullProfileData,
    distributionData, selectedGenes, selectedTaxa)

Arguments

Value

A dataframe for analysing the distribution of the additional variable(s) for a subset of genes and/or taxa containing the protein (ortholog) IDs and the values of their variables (var1 and var2).

Author(s)

Vinh Tran [email protected]

See Also

parseInfoProfile, createVariableDistributionData, fullProcessedProfile, mainLongRaw

Examples

data("fullProcessedProfile", package="PhyloProfile")
data("mainLongRaw", package="PhyloProfile")
distributionData <- createVariableDistributionData(
    mainLongRaw, c(0, 1), c(0.5, 1)
)
selectedGenes <- "100136at6656"
selectedTaxa <- c("Mammalia", "Saccharomycetes", "Insecta")
createVariableDistributionDataSubset(
    fullProcessedProfile,
    distributionData,
    selectedGenes,
    selectedTaxa
)

Description

Create data for customized profile plot based on a selected list of genes and/or taxa, containing seed protein IDs (geneID), ortholog IDs (orthoID) together with their ncbi taxonomy IDs (ncbiID and abbrName), full names (fullName), indexed supertaxa (supertaxon), values for additional variables (var1, var2) and the aggregated values of those additional variables for each supertaxon (mVar1, mVar2), number of original and filtered co-orthologs in each supertaxon (paralog and paralogNew), number of species in each supertaxon (numberSpec) and the each supertaxon (presSpec).

Usage

dataCustomizedPlot(dataHeat = NULL, selectedTaxa = "all",
    selectedSeq = "all")

Arguments

Value

A dataframe contains data for plotting the customized profile.

Author(s)

Vinh Tran [email protected]

See Also

filterProfileData

Examples

data("finalProcessedProfile", package="PhyloProfile")
selectedTaxa <- c("Mammalia", "Saccharomycetes", "Insecta")
selectedSeq <- "all"
dataCustomizedPlot(finalProcessedProfile, selectedTaxa, selectedSeq)

Description

Create data for plotting the distribution of the protein domain features between 2 group of taxa for a selected gene (average number of feature occurrency per protein/ortholog).

Usage

dataFeatureTaxGroup(mainDf, domainDf, inGroup, gene)

Arguments

Value

Dataframe containing all feature names, their frequencies (absolute count and the average instances per protein - IPP) in each taxon group and the corresponding taxa group type (in- or out-group).

Author(s)

Vinh Tran ([email protected])

See Also

createLongMatrix, parseDomainInput

Examples

data("mainLongRaw", package="PhyloProfile")
mainDf <- mainLongRaw
gene <- "101621at6656"
inputFile <- system.file(
    "extdata", "domainFiles/101621at6656.domains",
    package = "PhyloProfile", mustWork = TRUE
)
type <- "file"
domainDf <- parseDomainInput(gene, inputFile, type)
inGroup <- c("ncbi9606", "ncbi10116")
dataFeatureTaxGroup(mainDf, domainDf, inGroup, gene)

Description

Create data for main profile plot

Usage

dataMainPlot(dataHeat = NULL)

Arguments

Value

A dataframe for plotting the phylogenetic profile, containing seed protein IDs (geneID), ortholog IDs (orthoID) together with their ncbi taxonomy IDs (ncbiID and abbrName), full names (fullName), indexed supertaxa (supertaxon), values for additional variables (var1, var2) and the aggregated values of those additional variables for each supertaxon (mVar1, mVar2), number of original and filtered co-orthologs in each supertaxon (paralog and paralogNew), number of species in each supertaxon (numberSpec) and the species that have orthologs in each supertaxon (presSpec).

Author(s)

Vinh Tran [email protected]

See Also

filterProfileData

Examples

data("finalProcessedProfile", package="PhyloProfile")
dataMainPlot(finalProcessedProfile)

Description

Create data for plotting the distribution comparison between 2 groups of taxa for a selected gene.

Usage

dataVarDistTaxGroup(data, inGroup, gene, variable)

Arguments

Value

Dataframe containing list of values for all available variables for the selected genes in in-group and out-group taxa (max. 3 columns).

Author(s)

Vinh Tran ([email protected])

See Also

createLongMatrix

Examples

data("mainLongRaw", package="PhyloProfile")
data <- mainLongRaw
inGroup <- c("ncbi9606", "ncbi10116")
variable <- colnames(data)[c(4, 5)]
dataVarDistTaxGroup(data, inGroup, "101621at6656", variable)

Description

This function tests the difference between the distributions of two input numeric samples using the statistical tess. First the Kolmogorov-Smirnov is used to check if 2 samples have the same distribution. If yes, Wilcoxon-Mann-Whitney will be used to compare the distribution difference.

Usage

distributionTest(varIn, varOut, significanceLevel)

Arguments

Value

p-value of the comparison test.

Author(s)

Carla Mölbert ([email protected])

Description

Calculate the phylogenetic gene age from the phylogenetic profiles

Usage

estimateGeneAge(processedProfileData, taxaCount, rankName, refTaxon,
    var1CO, var2CO, percentCO, taxDB = NULL)

Arguments

Value

A dataframe contains estimated gene ages for the seed proteins.

Author(s)

Vinh Tran [email protected]

See Also

parseInfoProfile for creating a full processed profile dataframe; getNameList and getTaxonomyMatrix for getting taxonomy info, fullProcessedProfile for a demo input dataframe

Examples

library(dplyr)
data("fullProcessedProfile", package="PhyloProfile")
rankName <- "class"
refTaxon <- "Mammalia"
processedProfileData <- fullProcessedProfile
taxonIDs <- levels(as.factor(processedProfileData$ncbiID))
sortedInputTaxa <- sortInputTaxa(
    taxonIDs, rankName, refTaxon, NULL, NULL
)
taxaCount <- sortedInputTaxa %>% dplyr::count(supertaxon)
var1Cutoff <- c(0, 1)
var2Cutoff <- c(0, 1)
percentCutoff <- c(0, 1)
estimateGeneAge(
    processedProfileData,
    taxaCount,
    rankName,
    refTaxon,
    var1Cutoff, var2Cutoff, percentCutoff
)

Description

Parse multi-fasta input file

Usage

fastaParser(inputFile = NULL)

Arguments

Value

A data frame of input data in long-format containing seed gene IDs ( or orthologous group IDs), their orthologous proteins together with the corresponding taxonomy IDs and values of (up to) two additional variables.

Author(s)

Vinh Tran [email protected]

Examples

inputFile <- system.file(
    "extdata", "test.main.fasta", package = "PhyloProfile", mustWork = TRUE
)
fastaParser(inputFile)

Description

Create protein feature distribution plots between 2 groups of taxa for a selected gene.

Usage

featureDistTaxPlot(data, plotParameters)

Arguments

Value

Distribution plots as a ggplot2 object.

Author(s)

Vinh Tran [email protected]

See Also

dataFeatureTaxGroup

Examples

data("mainLongRaw", package="PhyloProfile")
data <- mainLongRaw
gene <- "101621at6656"
inputFile <- system.file(
    "extdata", "domainFiles/101621at6656.domains",
    package = "PhyloProfile", mustWork = TRUE
)
type <- "file"
domainDf <- parseDomainInput(gene, inputFile, type)
inGroup <- c("ncbi9606", "ncbi10116")
plotDf <- dataFeatureTaxGroup(data, domainDf, inGroup, gene)
plotParameters <- list(
    "xSize" = 12,
    "ySize" = 12,
    "angle" = 15,
    "legendSize" = 12,
    "inGroupName" = "In-group",
    "outGroupName" = "Out-group",
    "flipPlot" = "No"
)
featureDistTaxPlot(plotDf, plotParameters)

Description

An example of a filtered phylogenetic profile

Usage

data(filteredProfile)

Format

Dataframe

Value

A data frame with 168 rows and 20 variables:

• geneID Seed or ortholog group ID, e.g. "100136at6656"

• supertaxon Supertaxon name together with its ordered index, e.g. "1001_Mammalia"

• ncbiID Taxon ID, e.g. "ncbi10116"

• orthoID Ortholog ID, e.g. "100136at6656|HUMAN@9606@1|Q9UNQ2|1"

• var1 First additional variable

• var2 Second additional variable

• paralog Number of co-orthologs in the current taxon

• abbrName NCBI ID of the ortholog, e.g. "ncbi9606"

• taxonID Taxon ID of the ortholog, in this case: "0"

• fullName Full taxon name of the ortholog, e.g. "Homo sapiens"

• supertaxonID Supertaxon ID (only different than ncbiID in case working with higher taxonomy rank than input's). e.g. "40674"

• rank Rank of the supertaxon, e.g. "class"

• category "cat

• numberSpec Total number of species in each supertaxon

• taxonMod Name of supersupertaxon w/o its index, e.g. "Mammalia"

• presSpec Percentage of taxa having orthologs in each supertaxon

• presentTaxa Number of taxa that have ortho in each supertaxon

• totalTaxa Total number of taxa in each supertaxon

• mVar1 Value of the 1. variable after grouping into supertaxon

• mVar2 Value of the 2. variable after grouping into supertaxon

Description

Create a filtered data needed for plotting or clustering phylogenetic profiles. NOTE: this function require some intermediate steps using the results from other functions. If you would like to get a full processed data from the raw input, please use the function fromInputToProfile() instead!

Usage

filterProfileData(DF, taxaCount, refTaxon = NULL,
    percentCO = c(0, 1), coorthoCOMax = 9999,
    var1CO  = c(0, 1), var2CO = c(0, 1), var1Rel = "protein",
    var2Rel = "protein", groupByCat = FALSE, catDt = NULL,
    var1AggregateBy = "max", var2AggregateBy = "max")

Arguments

Value

A filtered dataframe for generating profile plot including seed gene IDs (or orthologous group IDs), their ortholog IDs and the corresponding (super)taxa, (super)taxon IDs, number of co-orthologs in each (super)taxon, values for two additional variables var1, var2, supertaxon, and the categories of seed genes (or ortholog groups).

Author(s)

Vinh Tran [email protected]

See Also

parseInfoProfile and reduceProfile for generating input dataframe, fullProcessedProfile for a demo full processed profile dataframe, fromInputToProfile for generating fully processed data from raw input.

Examples

# NOTE: this function require some intermediate steps using the results from
# other functions. If you would like to get a full processed data from the
# raw input, please use the function fromInputToProfile() instead!
library(dplyr)
data("fullProcessedProfile", package="PhyloProfile")
rankName <- "class"
refTaxon <- "Mammalia"
percentCutoff <- c(0.0, 1.0)
coorthologCutoffMax <- 10
var1Cutoff <- c(0.75, 1.0)
var2Cutoff <- c(0.5, 1.0)
var1Relation <- "protein"
var2Relation <- "species"
groupByCat <- FALSE
catDt <- NULL
var1AggregateBy <- "max"
var2AggregateBy <- "max"
taxonIDs <- levels(as.factor(fullProcessedProfile$ncbiID))
sortedInputTaxa <- sortInputTaxa(
    taxonIDs, rankName, refTaxon, NULL, NULL
)
taxaCount <- sortedInputTaxa %>% dplyr::count(supertaxon)
filterProfileData(
    fullProcessedProfile,
    taxaCount,
    refTaxon,
    percentCutoff,
    coorthologCutoffMax,
    var1Cutoff,
    var2Cutoff,
    var1Relation,
    var2Relation,
    groupByCat,
    catDt,
    var1AggregateBy,
    var2AggregateBy
)

Description

An example of a final processed & filtered phylogenetic profile

Usage

data(finalProcessedProfile)

Format

Dataframe

Value

A data frame with 88 rows and 11 variables:

• geneID Seed or ortholog group ID, e.g. "100136at6656"

• supertaxon Supertaxon name together with its ordered index, e.g. "1001_Mammalia"

• supertaxonID Supertaxon ID (only different than ncbiID in case working with higher taxonomy rank than input's). e.g. "40674"

• var1 First additional variable

• presSpec The percentage of species presenting in each supertaxon

• category "cat"

• orthoID Ortholog ID, e.g. "100136at6656|RAT@10116@1|G3V7R8|1"

• var2 Second additional variable

• paralog Number of co-orthologs in the current taxon

• presentTaxa Number of taxa that have ortho in each supertaxon

• totalTaxa Total number of taxa in each supertaxon

Description

Create a processed and filtered data for plotting or analysing phylogenetic profiles from raw input file (from raw input to final filtered dataframe)

Usage

fromInputToProfile(rawInput, rankName, refTaxon = NULL,
    taxaTree = NULL, sortedTaxonList = NULL, var1AggregateBy = "max",
    var2AggregateBy = "max", percentCutoff = c(0, 1),
    coorthologCutoffMax = 9999, var1Cutoff = c(0, 1), var2Cutoff = c(0, 1),
    var1Relation = "protein", var2Relation = "protein", groupByCat = FALSE,
    catDt = NULL, taxDB = NULL)

Arguments

Value

Dataframe required for generating phylogenetic profile plot or clustering analysis. It contains seed gene IDs (or orthologous group IDs), their ortholog IDs and the corresponding (super)taxa, (super)taxon IDs, number of co-orthologs in each (super)taxon, values for two additional variables var1, var2, categories of seed genes (or ortholog groups).

Author(s)

Vinh Tran [email protected]

See Also

createLongMatrix, getInputTaxaID, getInputTaxaName, sortInputTaxa, parseInfoProfile, reduceProfile, filterProfileData

Examples

rawInput <- system.file(
    "extdata", "test.main.long", package = "PhyloProfile", mustWork = TRUE
)
rankName <- "class"
refTaxon <- "Mammalia"
taxaTree <- NULL
sortedTaxonList <- NULL
var1AggregateBy <- "max"
var2AggregateBy <- "mean"
percentCutoff <- c(0.0, 1.0)
coorthologCutoffMax <- 10
var1Cutoff <- c(0.75, 1.0)
var2Cutoff <- c(0.5, 1.0)
var1Relation <- "protein"
var2Relation <- "species"
groupByCat <- FALSE
catDt <- NULL
fromInputToProfile(
    rawInput,
    rankName,
    refTaxon,
    taxaTree,
    sortedTaxonList,
    var1AggregateBy,
    var2AggregateBy,
    percentCutoff,
    coorthologCutoffMax,
    var1Cutoff,
    var2Cutoff,
    var1Relation,
    var2Relation,
    groupByCat,
    catDt
)

Description

An example of a fully processed phylogenetic profile

Usage

data(fullProcessedProfile)

Format

Dataframe

Value

A data frame with 168 rows and 14 variables:

• supertaxon Supertaxon name together with its ordered index, e.g. "1001_Mammalia"

• ncbiID Taxon ID, e.g. "ncbi10116"

• geneID Seed or ortholog group ID, e.g. "100136at6656"

• orthoID Ortholog ID, e.g. "100136at6656|HUMAN@9606@1|Q9UNQ2|1"

• var1 First additional variable

• var2 Second additional variable

• paralog Number of co-orthologs in the current taxon

• abbrName NCBI ID of the ortholog, e.g. "ncbi9606"

• taxonID Taxon ID of the ortholog, in this case: "0"

• fullName Full taxon name of the ortholog, e.g. "Homo sapiens"

• supertaxonID Supertaxon ID (only different than ncbiID in case working with higher taxonomy rank than input's). e.g. "40674"

• rank Rank of the supertaxon, e.g. "class"

• category "cat

• numberSpec Total number of species in each supertaxon

Description

Create data for plotting gene ages

Usage

geneAgePlotDf(geneAgeDf)

Arguments

Value

A dataframe for plotting gene age plot containing the absolute number and percentage of genes for each calculated evolutionary ages and the corresponding position for writting those number on the plot.

Author(s)

Vinh Tran [email protected]

See Also

estimateGeneAge

Examples

geneAgeDf <- data.frame(
geneID = c("100136at6656", "100265at6656", "101621at6656", "103479at6656"),
cath = c("0000001", "0000011", "0000001", "0000011"),
age = c("07_LUCA", "06_Eukaryota", "07_LUCA", "06_Eukaryota")
)
geneAgePlotDf(geneAgeDf)

Description

Create a single violin distribution plot

Usage

generateSinglePlot(plotDf, parameters, variable)

Arguments

Value

A violin plot as a ggplot object.

Author(s)

Vinh Tran [email protected]

Examples

data("mainLongRaw", package="PhyloProfile")
data <- mainLongRaw
inGroup <- c("ncbi9606", "ncbi10116")
varNames <- colnames(data)[c(4, 5)]
plotDf <- dataVarDistTaxGroup(data, inGroup, "101621at6656", varNames)
plotParameters <- list(
    "xSize" = 12,
    "ySize" = 12,
    "titleSize" = 15,
    "legendSize" = 12,
    "legendPosition" = "right",
    "mValue" = "mean",
    "inGroupName" = "In-group",
    "outGroupName" = "Out-group",
    "title" = "101621at6656"
)
generateSinglePlot(plotDf, plotParameters, colnames(plotDf)[1])

Description

Create domain annotation dataframe from a raw OMA dataframe

Usage

getAllDomainsOma(finalOmaDf = NULL)

Arguments

Value

Dataframe of the domain annotation used for PhyloProfile, which contains seed IDs, ortholog IDs, ortholog lengths, annotated features, start and end positions of those features.

Author(s)

Vinh Tran [email protected]

See Also

getDataForOneOma

Examples

### Uncomment the following line to run the function
# omaData <- getDataForOneOma("HUMAN29397", "OG")
# getAllDomainsOma(omaData)

Description

Get all fasta sequences from a raw OMA dataframe

Usage

getAllFastaOma(finalOmaDf = NULL)

Arguments

Value

A list contains all protein sequences in fasta format.

Author(s)

Vinh Tran [email protected]

See Also

getDataForOneOma

Examples

### Uncomment the following line to run the function
# omaData <- getDataForOneOma("HUMAN29397", "OG")
# getAllFastaOma(omaData)

Description

Identify the common ancestor for a selected taxa and return a list of all taxa that have that common ancestor from an large input taxa set.

Usage

getCommonAncestor(inputTaxa = NULL, inGroup = NULL, taxDB = NULL)

Arguments

Value

A list containing the taxonomy rank and name of the common ancestor, together with a dataframe storing the full taxonomy info of all taxa that share that corresponding common ancestor.

Author(s)

Vinh Tran ([email protected])

Examples

inputTaxa <- c("ncbi34740", "ncbi9606", "ncbi374847", "ncbi123851",
    "ncbi5664", "ncbi189518", "ncbi418459", "ncbi10116", "ncbi284812",
    "ncbi35128", "ncbi7070")
inGroup <-  c("ncbi9606", "ncbi10116")
getCommonAncestor(inputTaxa, inGroup)

Description

Identify core genes for a list of selected (super)taxa. The identified core genes must be present in at least a certain proportion of species in each selected (super)taxon (identified via percentCutoff) and that criteria must be fullfilled for a certain percentage of selected taxa or all of them (determined via coreCoverage).

Usage

getCoreGene(rankName, taxaCore = c("none"), profileDt, taxaCount,
    var1Cutoff = c(0, 1), var2Cutoff = c(0, 1), percentCutoff = c(0, 1),
    coreCoverage = 100, taxDB = NULL)

Arguments

Value

A list of identified core genes.

Author(s)

Vinh Tran [email protected]

See Also

parseInfoProfile for creating a full processed profile dataframe

Examples

library(dplyr)
data("fullProcessedProfile", package="PhyloProfile")
rankName <- "class"
refTaxon <- "Mammalia"
taxaCore <- c("Mammalia", "Saccharomycetes", "Insecta")
profileDt <- fullProcessedProfile
taxonIDs <- levels(as.factor(fullProcessedProfile$ncbiID))
sortedInputTaxa <- sortInputTaxa(
    taxonIDs, rankName, refTaxon, NULL, NULL
)
taxaCount <- sortedInputTaxa %>% dplyr::count(supertaxon)
var1Cutoff <- c(0.75, 1.0)
var2Cutoff <- c(0.75, 1.0)
percentCutoff <- c(0.0, 1.0)
coreCoverage <- 100
getCoreGene(
    rankName,
    taxaCore,
    profileDt,
    taxaCount,
    var1Cutoff, var2Cutoff,
    percentCutoff, coreCoverage
)

Description

Get data for calculating distance matrix from phylogenetic profiles

Usage

getDataClustering(data, profileType = "binary", var1AggBy = "max",
    var2AggBy = "max")

Arguments

Value

A wide dataframe contains values for calculating distance matrix.

Author(s)

Carla Mölbert ([email protected]), Vinh Tran ([email protected])

See Also

fromInputToProfile

Examples

data("finalProcessedProfile", package="PhyloProfile")
data <- finalProcessedProfile
profileType <- "binary"
var1AggregateBy <- "max"
var2AggregateBy <- "mean"
getDataClustering(data, profileType, var1AggregateBy, var2AggregateBy)

Description

Get taxonomy IDs, sequences, length and annotations for an OMA orthologous group (or OMA HOG).

Usage

getDataForOneOma(seedID = NULL, orthoType = "OG")

Arguments

Value

Data frame contains info for all sequences of the input OMA group (or HOG). That info contains the protein IDs, taxonomy IDs, sequences, lengths, domain annotations (tab delimited) and the corresponding seed ID.

Author(s)

Vinh Tran [email protected]

Examples

### Uncomment the following line to run the function
# getDataForOneOma("HUMAN29397", "OG")

Description

Plot dendrogram tree

Usage

getDendrogram(dd = NULL)

Arguments

Value

A dendrogram plot for the genes in the input phylogenetic profiles.

Author(s)

Vinh Tran [email protected]

See Also

clusterDataDend

Examples

data("finalProcessedProfile", package="PhyloProfile")
data <- finalProcessedProfile
profileType <- "binary"
profiles <- getDataClustering(
    data, profileType, var1AggregateBy, var2AggregateBy)
distMethod <- "mutualInformation"
distanceMatrix <- getDistanceMatrix(profiles, distMethod)
clusterMethod <- "complete"
dd <- clusterDataDend(distanceMatrix, clusterMethod)
getDendrogram(dd)

Description

Calculate the distance matrix

Usage

getDistanceMatrix(profiles = NULL, method = "mutualInformation")

Arguments

Value

A calculated distance matrix for input phylogenetic profiles.

Author(s)

Carla Mölbert ([email protected]), Vinh Tran ([email protected])

See Also

getDataClustering

Examples

data("finalProcessedProfile", package="PhyloProfile")
data <- finalProcessedProfile
profileType <- "binary"
profiles <- getDataClustering(
    data, profileType, var1AggregateBy, var2AggregateBy)
method <- "mutualInformation"
getDistanceMatrix(profiles, method)

Description

Get domain file from a folder for a seed protein

Usage

getDomainFolder(seed, domainPath)

Arguments

Value

Domain file and its complete directory path for the selected protein.

Author(s)

Vinh Tran [email protected]

Examples

domainPath <- paste0(
    path.package("PhyloProfile", quiet = FALSE), "/extdata/domainFiles"
)
PhyloProfile:::getDomainFolder("101621at6656", domainPath)

Description

Get fasta sequences from main input file in multi-fasta format

Usage

getFastaFromFasInput(seqIDs = NULL, file = NULL)

Arguments

Value

A dataframe with one column contains sequences in fasta format.

Author(s)

Vinh Tran [email protected]

Examples

file <- system.file(
    "extdata", "test.main.fasta",
    package = "PhyloProfile", mustWork = TRUE
)
getFastaFromFasInput("all", file)

Description

Get fasta sequences from main input file in multi-fasta format

Usage

getFastaFromFile(seqIDs = NULL, concatFasta = NULL)

Arguments

Value

A dataframe with one column contains sequences in fasta format.

Author(s)

Vinh Tran [email protected]

Examples

concatFasta <- system.file(
    "extdata", "fastaFiles/concatenatedFile.fa",
    package = "PhyloProfile", mustWork = TRUE
)
getFastaFromFasInput("all", concatFasta)

Description

Get fasta sequences for the input phylogenetic profiles.

Usage

getFastaFromFolder(seqIDs = NULL, path = NULL, dirFormat = NULL,
    fileExt = NULL, idFormat = NULL)

Arguments

Value

A dataframe with one column contains sequences in fasta format.

Author(s)

Vinh Tran [email protected]

See Also

mainLongRaw

Examples

seqIDs <- "RAT@10116@1|D3ZUE4"
path <- system.file(
    "extdata", "fastaFiles", package = "PhyloProfile", mustWork = TRUE
)
dirFormat <- 1
fileExt <- "fa"
idFormat <- 3
getFastaFromFolder(seqIDs, path, dirFormat, fileExt, idFormat)

Description

Get NCBI taxonomy IDs, ranks and names for an input taxon list.

Usage

getIDsRank(inputTaxa = NULL, currentNCBIinfo = NULL)

Arguments

Value

A list of 3 dataframes: idList, rankList and reducedInfoList. The "rankList" contains taxon names and all taxonomy ranks of the input taxa including also the noranks from the input rank to the taxonomy root. The "idList" contains input taxon IDs, taxon names, all the ranks from current rank to the taxonomy root together with their IDs (with the format "id#rank"). The reducedInfoList is a subset of preProcessedTaxonomy.txt file, containing the NCBI IDs, taxon fullnames, their current rank and their direct parent ID.

Author(s)

Vinh Tran [email protected]

Examples

inputTaxa <- c("272557", "176299")
ncbiFilein <- system.file(
    "extdata", "data/preProcessedTaxonomy.txt",
    package = "PhyloProfile", mustWork = TRUE
)
currentNCBIinfo <- as.data.frame(data.table::fread(ncbiFilein))
getIDsRank(inputTaxa, currentNCBIinfo)

Description

Get ID list of input taxa from the main input

Usage

getInputTaxaID(rawProfile = NULL)

Arguments

Value

List of all input taxon IDs (e.g. ncbi1234). Default = NULL.

Author(s)

Vinh Tran [email protected]

See Also

createLongMatrix, mainLongRaw

Examples

data("mainLongRaw", package="PhyloProfile")
getInputTaxaID(mainLongRaw)

Description

Get NCBI taxon names from "PhyloProfile/data/taxonNamesReduced.txt" for a list of input taxa

Usage

getInputTaxaName(rankName, taxonIDs = NULL, taxDB = NULL)

Arguments

Value

Data frame contains a list of full names, taxonomy ranks and parent IDs for the input taxa.

Author(s)

Vinh Tran [email protected]

See Also

getInputTaxaID for getting input taxon IDs, getNameList for getting the full taxon name list

Examples

taxonIDs <- c("ncbi9606", "ncbi10116")
getInputTaxaName("species", taxonIDs)

Description

Get all NCBI taxon names from "PhyloProfile/data/taxonNamesReduced.txt"

Usage

getNameList(taxDB = NULL)

Arguments

Value

List of taxon IDs, their full names, taxonomy ranks and parent IDs obtained from "PhyloProfile/data/taxonNamesReduced.txt"

Author(s)

Vinh Tran [email protected]

Examples

getNameList()

Description

Get taxonomy ID, sequence and annotation for one OMA protein

Usage

getOmaDataForOneOrtholog(id = NULL)

Arguments

Value

Data frame contains the input protein ID with its taxonomy ID, sequence, length and domain annotations (tab delimited) for input OMA protein

Author(s)

Vinh Tran [email protected]

Examples

### Uncomment the following line to run the function
# getOmaDataForOneOrtholog("HUMAN29397")

Description

Get domain annotation from OMA Browser based on a URL or a raw data frame contains annotation info from OMA

Usage

getOmaDomainFromURL(domainURL = NULL)

Arguments

Value

Data frame contains feature names with their start and end positions

Author(s)

Vinh Tran [email protected]

Examples

### Uncomment the following line to run the function
# getOmaDomainFromURL("https://omabrowser.org/api/protein/7916808/domains/")

Description

Get OMA ortholog group, OMA HOG or OMA pair's members for a seed protein from OMA Browser.

Usage

getOmaMembers(id = NULL, orthoType = "OG")

Arguments

Value

List of OMA orthologs for an input seed protein.

Author(s)

Carla Mölbert [email protected]

Examples

### Uncomment the following line to run the function
# getOmaMembers("HUMAN29397", "OG")

Description

Get color for a list of items

Usage

getQualColForVector(x = NULL)

Arguments

Value

list of colors for each element (same elements will have the same color)

Author(s)

Vinh Tran [email protected]

See Also

qualitativeColours

Examples

items <- c("a", "b", "c")
getQualColForVector(items)

Description

Get selected fasta sequences from a raw OMA dataframe

Usage

getSelectedFastaOma(finalOmaDf = NULL, seqID = NULL)

Arguments

Value

Required protein sequence in fasta format.

Author(s)

Vinh Tran [email protected]

See Also

getDataForOneOma

Examples

### Uncomment the following line to run the function
# omaData <- getDataForOneOma("HUMAN29397", "OG")
# getSelectedFastaOma(omaData, "HUMAN29397")

Description

Get a subset of taxon ncbi IDs and names from an input list of taxa based on a selected supertaxon (identified by its taxonomy rank and supertaxon name or supertaxon ID).

Usage

getSelectedTaxonNames(inputTaxonIDs = NULL, rank = NULL,
    higherRank = NULL, higherID = NULL, higherName = NULL, taxDB = NULL)

Arguments

Value

A data frame contains ncbi IDs and names of taxa from the input taxon list that belong to the selected supertaxon.

Author(s)

Vinh Tran [email protected]

Examples

inputTaxonIDs <- c("10116", "122586", "123851", "13616", "188937", "189518",
"208964", "224129", "224324", "237631", "243230")
rank <- "species"
higherRank <- "phylum"
higherID <- 7711
getSelectedTaxonNames(inputTaxonIDs, rank, higherRank, higherID, NULL)
higherName <- "Chordata"
getSelectedTaxonNames(inputTaxonIDs, rank, higherRank, NULL, higherName,NULL)

Description

Get NCBI taxonomy hierarchy and URLs for an input taxon list.

Usage

getTaxHierarchy(inputTaxa = NULL, currentNCBIinfo = NULL)

Arguments

Value

A list of dataframs containing taxonomy hierarchy and its URL to NCBI database for input taxon IDs

Author(s)

Vinh Tran [email protected]

Examples

inputTaxa <- c("272557", "176299")
ncbiFilein <- system.file(
    "extdata", "data/preProcessedTaxonomy.txt",
    package = "PhyloProfile", mustWork = TRUE
)
currentNCBIinfo <- as.data.frame(data.table::fread(ncbiFilein))
PhyloProfile:::getTaxHierarchy(inputTaxa, currentNCBIinfo)

Description

Get taxonomy info for a list of input taxa

Usage

getTaxonomyInfo(inputTaxa = NULL, currentNCBIinfo = NULL)

Arguments

Value

A list of NCBI taxonomy info for input taxa, including the taxonomy IDs, full scientific names, taxonomy ranks and the parent IDs.

Author(s)

Vinh Tran [email protected]

Examples

inputTaxa <- c("272557", "176299")
ncbiFilein <- system.file(
    "extdata", "data/preProcessedTaxonomy.txt",
    package = "PhyloProfile", mustWork = TRUE
)
currentNCBIinfo <- as.data.frame(data.table::fread(ncbiFilein))
getTaxonomyInfo(inputTaxa, currentNCBIinfo)

Description

Get the (full or subset) taxonomy matrix from "data/taxonomyMatrix.txt" based on an input taxon list

Usage

getTaxonomyMatrix(taxDB = NULL, subsetTaxaCheck = FALSE, taxonIDs = NULL)

Arguments

Value

Data frame contains the (subset of) taxonomy matrix for list of input taxa.

Author(s)

Vinh Tran [email protected]

Examples

# get full pre-installed taxonomy matrix
getTaxonomyMatrix()
# get taxonomy matrix for a list of taxon IDs
taxonIDs <- c("ncbi9606", "ncbi10116")
getTaxonomyMatrix(NULL, TRUE, taxonIDs)

Description

Create a list containing all main taxanomy ranks

Usage

getTaxonomyRanks()

Value

A list of all main ranks (from strain to superkingdom)

Author(s)

Carla Mölbert ([email protected])

Examples

getTaxonomyRanks()

Description

Plot Multiple Graphs with Shared Legend in a Grid

Usage

gridArrangeSharedLegend(...,  ncol = length(list(...)), nrow = 1,
    position = c("bottom", "right"), title = NA, titleSize = 12)

Arguments

Value

Grid of plots with common legend

Note

adapted from https://rdrr.io/github/PhilBoileau/CLSAR/src/R/ gridArrangeSharedLegend.R

Author(s)

Phil Boileau, [email protected]

Examples

## Not run: 
data("mainLongRaw", package="PhyloProfile")
data <- mainLongRaw
inGroup <- c("ncbi9606", "ncbi10116")
varNames <- colnames(data)[c(4, 5)]
plotDf <- dataVarDistTaxGroup(data, inGroup, "101621at6656", varNames)
plotParameters <- list(
    "xSize" = 12,
    "ySize" = 12,
    "titleSize" = 15,
    "legendSize" = 12,
    "legendPosition" = "right",
    "mValue" = "mean",
    "inGroupName" = "In-group",
    "outGroupName" = "Out-group",
    "title" = "101621at6656"
)
plotVar1 <- generateSinglePlot(plotDf, plotParameters, colnames(plotDf)[1])
plotVar2 <- generateSinglePlot(plotDf, plotParameters, colnames(plotDf)[2])
g <- gridArrangeSharedLegend(
    plotVar1, plotVar2,
    position = plotParameters$legendPosition,
    title = plotParameters$title,
    size = plotParameters$titleSize
)

## End(Not run)

Description

Reduce the number of labels for UMAP plot based on the gene/taxon frequency

Usage

groupLabelUmapData(data4umap = NULL, freqCutoff = c(0,200))

Arguments

Value

A dataframe similar to input data4umap, but with modified Label column, where less frequent labels are grouped together as "Other"

Author(s)

Vinh Tran [email protected]

See Also

prepareUmapData

Examples

rawInput <- system.file(
   "extdata", "test.main.long", package = "PhyloProfile", mustWork = TRUE
)
longDf <- createLongMatrix(rawInput)
data4umap <- prepareUmapData(longDf, "phylum")
groupLabelUmapData(data4umap, freqCutoff = c(3,5))

Description

Create profile heatmap plot

Usage

heatmapPlotting(data = NULL, parm = NULL)

Arguments

Value

A profile heatmap plot as a ggplot object.

Author(s)

Vinh Tran [email protected]

See Also

dataMainPlot, dataCustomizedPlot

Examples

data("finalProcessedProfile", package="PhyloProfile")
plotDf <- dataMainPlot(finalProcessedProfile)
plotParameter <- list(
    "xAxis" = "taxa",
    "geneIdType" = "geneID",
    "var1ID" = "FAS_FW",
    "var2ID"  = "FAS_BW",
    "midVar1" = 0.5,
    "midColorVar1" =  "#FFFFFF",
    "lowColorVar1" =  "#FF8C00",
    "highColorVar1" = "#4682B4",
    "midVar2" = 1,
    "midColorVar2" =  "#FFFFFF",
    "lowColorVar2" = "#CB4C4E",
    "highColorVar2" = "#3E436F",
    "paraColor" = "#07D000",
    "xSize" = 8,
    "ySize" = 8,
    "legendSize" = 8,
    "mainLegend" = "top",
    "dotZoom" = 0,
    "xAngle" = 60,
    "guideline" = 0,
    "colorByGroup" = FALSE,
    "catColors" = NULL,
    "colorByOrthoID" = FALSE
)

heatmapPlotting(plotDf, plotParameter)

Description

Create profile heatmap plot using scattermore

Usage

heatmapPlottingFast(data = NULL, parm = NULL)

Arguments

Value

A profile heatmap plot as a ggplot object.

Author(s)

Vinh Tran [email protected]

See Also

dataMainPlot, dataCustomizedPlot

Examples

data("finalProcessedProfile", package="PhyloProfile")
plotDf <- dataMainPlot(finalProcessedProfile)
plotParameter <- list(
    "xAxis" = "taxa",
    "geneIdType" = "geneID",
    "var1ID" = "FAS_FW",
    "var2ID"  = "FAS_BW",
    "midVar1" = 0.5,
    "midColorVar1" =  "#FFFFFF",
    "lowColorVar1" =  "#FF8C00",
    "highColorVar1" = "#4682B4",
    "midVar2" = 1,
    "midColorVar2" =  "#FFFFFF",
    "lowColorVar2" = "#CB4C4E",
    "highColorVar2" = "#3E436F",
    "paraColor" = "#07D000",
    "xSize" = 8,
    "ySize" = 8,
    "legendSize" = 8,
    "mainLegend" = "top",
    "dotZoom" = 0,
    "colorVar" = "var1"
)

heatmapPlottingFast(plotDf, plotParameter)

Description

Highlight gene and/or taxon of interest on the phylogenetic profile plot

Usage

highlightProfilePlot(profilePlot = NULL, plotDf = NULL,
    taxonHighlight = "none", workingRank = "none", geneHighlight = NULL,
    taxDB = NULL, xAxis = "taxa")

Arguments

Value

A profile heatmap plot with highlighted gene and/or taxon of interest as ggplot object.

Author(s)

Vinh Tran [email protected]

See Also

dataMainPlot, dataCustomizedPlot, heatmapPlotting

Examples

data("finalProcessedProfile", package="PhyloProfile")
plotDf <- dataMainPlot(finalProcessedProfile)
plotParameter <- list(
    "xAxis" = "taxa",
    "geneIdType" = "geneID",
    "var1ID" = "FAS_FW",
    "var2ID"  = "FAS_BW",
    "midVar1" = 0.5,
    "midColorVar1" =  "#FFFFFF",
    "lowColorVar1" =  "#FF8C00",
    "highColorVar1" = "#4682B4",
    "midVar2" = 1,
    "midColorVar2" =  "#FFFFFF",
    "lowColorVar2" = "#CB4C4E",
    "highColorVar2" = "#3E436F",
    "paraColor" = "#07D000",
    "xSize" = 8,
    "ySize" = 8,
    "legendSize" = 8,
    "mainLegend" = "top",
    "dotZoom" = 0,
    "xAngle" = 60,
    "guideline" = 0,
    "colorByGroup" = FALSE,
    "colorByOrthoID" = FALSE
)
profilePlot <- heatmapPlotting(plotDf, plotParameter)
taxonHighlight <- "none"
workingRank <- "class"
geneHighlight <- "100265at6656"
highlightProfilePlot(
    profilePlot, plotDf, taxonHighlight, workingRank, geneHighlight,
    NULL, plotParameter$xAxis
)

Description

Get taxon names for a list of taxon IDs

Usage

id2name(idList = NULL, currentNCBIinfo = NULL)

Arguments

Value

A dataframe contains input taxon Ids and their full names.

Author(s)

Vinh Tran [email protected]

Examples

ncbiFilein <- system.file(
    "extdata", "data/preProcessedTaxonomy.txt",
    package = "PhyloProfile", mustWork = TRUE
)
currentNCBIinfo <- as.data.frame(data.table::fread(ncbiFilein))
idList <- c("9606", "5207", "40674", "4751")
id2name(idList, currentNCBIinfo)

Description

Data frame, in which each row contains the complete taxonomy ranks from the lowest systematic level (strain/species) upto the taxonomy root and the corresponding IDs for one taxon in the experimental data sets.

Usage

data(idList)

Format

Dataframe

Value

A data frame with up to 41 columns and 95 rows corresponding to 95 taxa in the 2 experimental data sets

Description

Join multiple plots and merge legends

Usage

joinPlotMergeLegends(
  df1 = NULL,
  df2 = NULL,
  plot1 = NULL,
  plot2 = NULL,
  position = c("bottom", "right"),
  font = "Arial"
)

Arguments

Value

joined plots with merged legend as a grid object

Author(s)

Vinh Tran [email protected]

Examples

seed <- "101621at6656"
ortho <- "101621at6656|AGRPL@224129@0|224129_0:001955|1"
ortho <- gsub("\\|", ":", ortho)
grepID <- paste(seed, "#", ortho, sep = "")
domainFile <- system.file(
    "extdata", "domainFiles/101621at6656.domains",
    package = "PhyloProfile", mustWork = TRUE
)
domainDf <- parseDomainInput(seed, domainFile, "file")
domainDf$feature_id_mod <- domainDf$feature_id
subdomainDf <- domainDf[grep(grepID, domainDf$seedID), ]
subdomainDf$feature <- as.character(subdomainDf$feature)
orthoDf <- subdomainDf[subdomainDf$orthoID == ortho,]
seedDf <- subdomainDf[subdomainDf$orthoID != ortho,]
minStart <- min(subdomainDf$start)
maxEnd <- max(c(subdomainDf$end, subdomainDf$length))
# resolve overlapping domains
seedDf <- PhyloProfile:::resolveOverlapFeatures(seedDf)
orthoDf <- PhyloProfile:::resolveOverlapFeatures(orthoDf)
# add feature colors
featureColorDf <- PhyloProfile:::addFeatureColors(seedDf, orthoDf)
seedDf <- featureColorDf[[1]]
orthoDf <- featureColorDf[[2]]
# generate plots
plotSeed <- PhyloProfile:::singleDomainPlotting(
    seedDf, seed, minStart = minStart, maxEnd = maxEnd, font = "sans"
)
plotOrtho <- PhyloProfile:::singleDomainPlotting(
    orthoDf, ortho, minStart = minStart, maxEnd = maxEnd, font = "sans"
)
# merge plots
PhyloProfile:::joinPlotMergeLegends(
    seedDf, orthoDf, plotSeed, plotOrtho, "bottom", font = "sans")

Description

Linearize PFAM/SMART annotations by best e-value/bitscore

Usage

linearizeArchitecture(domainDf = NULL, orthoID = NULL, value = "evalue")

Arguments

Value

Domain dataframe of the selected protein after linearization

Author(s)

Vinh Tran [email protected]

Examples

demoDomainDf <- data.frame(
    orthoID = rep("protID", 4),
    start = c(1, 5, 100, 80),
    end = c(30, 40, 130, 110),
    evalue = c(0.001, 0.0005, 0.2, 0.004),
    feature_type = c(rep("pfam", 2), rep("smart", 2)),
    feature_id = c("pf1", "pf2", "sm1", "sm2")
)
linearizeArchitecture(demoDomainDf, "protID", "evalue")

Description

An example of a raw long input file

Usage

data(mainLongRaw)

Format

Dataframe

Value

A data frame with 168 rows and 5 variables:

• geneID Seed or ortholog group ID, e.g. "100136at6656"

• ncbiID Taxon ID, e.g. "ncbi36329"

• orthoID Ortholog ID, e.g. "100136at6656|PLAF7@36329@1|Q8ILT8|1"

• FAS_F First additional variable

• FAS_B Second additional variable

Description

Get all NCBI taxonomy rank names

Usage

mainTaxonomyRank()

Value

A list of all available NCBI taxonomy rank names.

Author(s)

Vinh Tran [email protected]

Examples

mainTaxonomyRank()

Description

Simplify feature names (e.g. TM for transmembrane domain, LCR for low complexity regions, remove tool names from domain name) and add weight to feature names (if available)

Usage

modifyFeatureName(domainDf = NULL)

Arguments

Value

Dataframe contains simlified domain names in yLabel column

Author(s)

Vinh Tran [email protected]

Examples

domainFile <- system.file(
    "extdata", "domainFiles/101621at6656.domains",
    package = "PhyloProfile", mustWork = TRUE
)
seedID <- "101621at6656"
domainDf <- parseDomainInput(seedID, domainFile, "file")
PhyloProfile:::modifyFeatureName(domainDf)

Description

Create architecure plot for a pair of seed and ortholog protein

Usage

pairDomainPlotting(seed, ortho, seedDf, orthoDf, minStart, maxEnd,
    labelSize, titleSize, showScore, showWeight, namePosition, firstDist,
    nameType, nameSize, segmentSize, nameColor, labelPos, colorPalette, font)

Arguments

Value

Domain plot of a pair proteins as a arrangeGrob object.

Author(s)

Vinh Tran [email protected]

See Also

singleDomainPlotting, sortDomains, parseDomainInput

Examples

seed <- "101621at6656"
ortho <- "101621at6656|AGRPL@224129@0|224129_0:001955|1"
ortho <- gsub("\\|", ":", ortho)
grepID <- paste(seed, "#", ortho, sep = "")
domainFile <- system.file(
    "extdata", "domainFiles/101621at6656.domains",
    package = "PhyloProfile", mustWork = TRUE
)
domainDf <- parseDomainInput(seed, domainFile, "file")
domainDf$feature_id_mod <- domainDf$feature_id
subdomainDf <- domainDf[grep(grepID, domainDf$seedID), ]
subdomainDf$feature <- as.character(subdomainDf$feature)
orthoDf <- subdomainDf[subdomainDf$orthoID == ortho,]
seedDf <- subdomainDf[subdomainDf$orthoID != ortho,]
minStart <- min(subdomainDf$start)
maxEnd <- max(c(subdomainDf$end, subdomainDf$length))
# resolve overlapping domains
seedDf <- PhyloProfile:::resolveOverlapFeatures(seedDf)
orthoDf <- PhyloProfile:::resolveOverlapFeatures(orthoDf)
# add feature colors
featureColorDf <- PhyloProfile:::addFeatureColors(seedDf, orthoDf)
seedDf <- featureColorDf[[1]]
orthoDf <- featureColorDf[[2]]
# do plot
g <- PhyloProfile:::pairDomainPlotting(
   seed,ortho,seedDf,orthoDf,minStart,maxEnd, font = "sans"
)
grid::grid.draw(g)

Description

Get all domain annotations for one seed protein IDs.

Usage

parseDomainInput(seed = NULL, inputFile = NULL, type = "file")

Arguments

Value

A dataframe for protein domains including seed ID, its orthologs IDs, sequence lengths, feature names, start and end positions, feature weights (optional) and the status to determine if that feature is important for comparison the architecture between 2 proteins* (e.g. seed protein vs ortholog) (optional).

Author(s)

Vinh Tran [email protected]

See Also

getDomainFolder

Examples

seed <- "101621at6656"
inputFile <- system.file(
    "extdata", "domainFiles/101621at6656.domains",
    package = "PhyloProfile", mustWork = TRUE
)
type <- "file"
parseDomainInput(seed, inputFile, type)

Description

Creating main dataframe for the input phylogenetic profiles based on selected input taxonomy level (e.g. strain, species) and reference taxon. The output contains the number of paralogs, the max/min/mean/median of VAR1 and VAR2.

Usage

parseInfoProfile(inputDf, sortedInputTaxa, taxaCount, coorthoCOMax)

Arguments

Value

A dataframe contains all info for the input phylogenetic profiles. This full processed profile that is required for several profiling analyses e.g. estimation of gene age (?estimateGeneAge) or identification of core gene (?getCoreGene).

Author(s)

Vinh Tran [email protected]

See Also

createLongMatrix, sortInputTaxa, calcPresSpec, mainLongRaw

Examples

library(dplyr)
data("mainLongRaw", package="PhyloProfile")
taxonIDs <- getInputTaxaID(mainLongRaw)
sortedInputTaxa <- sortInputTaxa(
    taxonIDs, "class", "Mammalia", NULL, NULL
)
taxaCount <- sortedInputTaxa %>% dplyr::count(supertaxon)
coorthoCOMax <- 999
parseInfoProfile(
    mainLongRaw, sortedInputTaxa, taxaCount, coorthoCOMax
)

Description

Create UMAP cluster plot

Usage

plotUmap(plotDf = NULL, legendPos = "bottom", colorPalette = "Set2", 
    transparent = 0, textSize = 12, font = "Arial", highlightTaxa = NULL,
    dotZoom = 0)

Arguments

Value

A plot as ggplot object

Author(s)

Vinh Tran [email protected]

See Also

prepareUmapData, umapClustering, createUmapPlotData

Examples

rawInput <- system.file(
   "extdata", "test.main.long", package = "PhyloProfile", mustWork = TRUE
)
longDf <- createLongMatrix(rawInput)
umapData <- prepareUmapData(longDf, "phylum")
data.umap <- umapClustering(umapData)
plotDf <- createUmapPlotData(data.umap, umapData)
plotUmap(plotDf, font = "sans")

Description

Create UMAP cluster 3D plot

Usage

plotUmap3D(plotDf = NULL, legendPos = "bottom", 
    colorPalette = "Set2", transparent = 0,highlightTaxa = NULL, 
    dotZoom = 0)

Arguments

Value

A plot as ggplot object

Author(s)

Vinh Tran [email protected]

See Also

prepareUmapData, umapClustering, createUmapPlotData

Examples

rawInput <- system.file(
   "extdata", "test.main.long", package = "PhyloProfile", mustWork = TRUE
)
longDf <- createLongMatrix(rawInput)
umapData <- prepareUmapData(longDf, "phylum")
data.umap <- umapClustering3D(umapData)
plotDf <- createUmapPlotData(data.umap, umapData)
plotUmap3D(plotDf)

Description

An example of a taxonomy matrix

Usage

data(ppTaxonomyMatrix)

Format

Dataframe

Value

A data frame with 10 rows and 162 variables:

• abbrName e.g. "ncbi10090"

• ncbiID e.g. "10090"

• fullName e.g. "Mus musculus"

• strain e.g. "10090" ...

Description

An example of a taxonomy tree in newick format

Usage

data(ppTree)

Format

Dataframe

Value

A data frame with only one entry

• V1 tree in newick format

Description

Prepare data for UMAP

Usage

prepareUmapData(longDf = NULL, taxonRank = NULL, type = "taxa", 
    taxDB = NULL, filterVar = "both", cutoff = 0, groupLabelsBy = "taxa")

Arguments

Value

A dataframe in wide format

Author(s)

Vinh Tran [email protected]

Examples

rawInput <- system.file(
   "extdata", "test.main.long", package = "PhyloProfile", mustWork = TRUE
)
longDf <- createLongMatrix(rawInput)
prepareUmapData(longDf, "phylum")

Description

Download NCBI taxonomy database and parse information that are needed for PhyloProfile, including taxon IDs, their scientific names, systematic ranks, and parent (next higher) rank IDs.

Usage

processNcbiTaxonomy()

Value

A dataframe contains NCBI taxon IDs, taxon names, taxon ranks and the next higher taxon IDs (parent's IDs) of all taxa in the NCBI taxonomy database.

Author(s)

Vinh Tran [email protected]

Examples

## Not run: 
?processNcbiTaxonomy
preProcessedTaxonomy <- PhyloProfile:::processNcbiTaxonomy()
# save to text (tab-delimited) file
write.table(
    preProcessedTaxonomy,
    file = "preProcessedTaxonomy.txt",
    col.names = TRUE,
    row.names = FALSE,
    quote = FALSE,
    sep = "\t"
)
# save to rdata file
save(
    preProcessedTaxonomy, file = "preProcessedTaxonomy.RData", compress='xz'
)

## End(Not run)

Description

Process ortholog IDs to identify duplicated IDs

Usage

processOrthoID(dataHeat = NULL)

Arguments

Value

the same dataframe as input, but the ortholog IDs are changed into <taxID:orthoID>. New column "orthoFreq" specifies if the ortholog IDs are single or duplicated

Author(s)

Vinh Tran [email protected]

Examples

?processOrthoID
data("finalProcessedProfile", package="PhyloProfile")
processOrthoID(finalProcessedProfile)

Description

An example of a raw long input file together with the taxonomy info

Usage

data(profileWithTaxonomy)

Format

Dataframe

Value

A data frame with 20 rows and 12 variables:

• geneID Seed or ortholog group ID, e.g. "OG_1017"

• ncbiID Taxon ID, e.g. "ncbi176299"

• orthoID Ortholog ID, e.g. "A.fabrum@176299@1582"

• var1 First additional variable

• var2 Second additional variable

• paralog Number of co-orthologs in the current taxon

• abbrName e.g. "ncbi176299"

• taxonID Taxon ID, e.g. "176299"

• fullName Full taxon name, e.g. "Agrobacterium fabrum str. C58"

• supertaxonID Supertaxon ID (only different than ncbiID in case working with higher taxonomy rank than input's)

• supertaxon Name of the corresponding supertaxon

• rank Rank of the supertaxon

Description

Create qualitative colours

Usage

qualitativeColours(n, light = FALSE)

Arguments

Value

list of n different colors

Source

Modified based on https://gist.github.com/peterk87/6011397

Examples

PhyloProfile:::qualitativeColours(5)

Description

Indexing all available ranks (including norank)

Usage

rankIndexing(rankListFile = NULL)

Arguments

Value

A dataframe containing a list of all possible ranks and their indexed values.

Author(s)

Vinh Tran [email protected]

Examples

rankListFile <- system.file(
    "extdata", "data/rankList.txt", package = "PhyloProfile", mustWork = TRUE
)
PhyloProfile:::rankIndexing(rankListFile)

Description

Data frame, in which each row contains the complete taxonomy ranks from the lowest systematic level (strain/species) upto the taxonomy root for one taxon in the experimental data sets.

Usage

data(rankList)

Format

Dataframe

Value

A data frame with up to 41 columns and 95 rows corresponding to 95 taxa in the 2 experimental data sets

Description

Reduce data of the processed phylogenetic profiles from input taxonomy rank into supertaxon level (e.g. from species to phylum)

Usage

reduceProfile(filteredProfile)

Arguments

Value

A reduced dataframe contains only profile data for the selected supertaxon rank. This dataframe contains only supertaxa and their value (mVar1 & mVar2) for each gene.

Author(s)

Vinh Tran [email protected]

See Also

parseInfoProfile for creating a full processed profile dataframe, filterProfileData for filter processed profile and filteredProfile for a demo filtered profile dataframe

Examples

data("filteredProfile", package="PhyloProfile")
reduceProfile(filteredProfile)

Description

Modify domain dataframe to resolve overlapped domains/features

Usage

resolveOverlapFeatures(domainDf)

Arguments

Value

Domain dataframe with modified feature names that join multiple domains of the same type that are not overlapped

Author(s)

Vinh Tran [email protected]

Examples

# get domain data
seedID <- "101621at6656"
domainFile <- system.file(
    "extdata", "domainFiles/101621at6656.domains",
    package = "PhyloProfile", mustWork = TRUE
)
domainDf <- parseDomainInput(seedID, domainFile, "file")
# get seedDf and orthoDf
subDf <- domainDf[
    domainDf$seedID ==
    "101621at6656#101621at6656:AGRPL@224129@0:224129_0:001955:1",]
orthoDf <- subDf[subDf$orthoID == "101621at6656:DROME@7227@1:Q9VG04",]
# resolve overlapped featuers
PhyloProfile:::resolveOverlapFeatures(orthoDf)

Description

Run PhyloProfile app

Usage

runPhyloProfile(configFile = NULL, host = NULL, port = NULL)

Arguments

Value

A shiny application - GUI version of PhyloProfile

Examples

## Not run: 
?runPhyloProfile
runPhyloProfile()

## End(Not run)

Description

Create architecure plot for a single protein

Usage

singleDomainPlotting(df, geneID, sep, labelSize, titleSize, minStart,
    maxEnd, colorPalette, showScore, showWeight, namePosition, firstDist,
    nameType, nameSize, segmentSize, nameColor, labelPos, font)

Arguments

Value

Domain plot of a single protein as a ggplot object.

Author(s)

Vinh Tran [email protected]

See Also

parseDomainInput

Examples

seed <- "101621at6656"
ortho <- "101621at6656|AGRPL@224129@0|224129_0:001955|1"
ortho <- gsub("\\|", ":", ortho)
grepID <- paste(seed, "#", ortho, sep = "")
domainFile <- system.file(
    "extdata", "domainFiles/101621at6656.domains",
    package = "PhyloProfile", mustWork = TRUE
)
domainDf <- parseDomainInput(seed, domainFile, "file")
domainDf$feature_id_mod <- domainDf$feature_id
subdomainDf <- domainDf[grep(grepID, domainDf$seedID), ]
subdomainDf$feature <- as.character(subdomainDf$feature)
orthoDf <- subdomainDf[subdomainDf$orthoID == ortho,]
seedDf <- subdomainDf[subdomainDf$orthoID != ortho,]
minStart <- min(subdomainDf$start)
maxEnd <- max(c(subdomainDf$end, subdomainDf$length))
# resolve overlapping domains
seedDf <- PhyloProfile:::resolveOverlapFeatures(seedDf)
orthoDf <- PhyloProfile:::resolveOverlapFeatures(orthoDf)
# add feature colors
featureColorDf <- PhyloProfile:::addFeatureColors(seedDf, orthoDf)
seedDf <- featureColorDf[[1]]
orthoDf <- featureColorDf[[2]]
# do plot
g <- PhyloProfile:::singleDomainPlotting(
   seedDf, seed, minStart = minStart, maxEnd = maxEnd, font = "sans"
)
grid::grid.draw(g)

Description

Sort domain dataframe of one protein (either seed or ortholog) based on the dataframe of the its paired protein, in order to bring the common domain feature in the same order which make it easy for comparing.

Usage

sortDomains(seedDf, orthoDf)