Installation of Bioconductor packages

if (!requireNamespace("BiocManager", quietly = TRUE))
    install.packages("BiocManager")
BiocManager::install('GmicR')

For macosx users experiencing WGCNA installation errors, try downloading a compiled version from:

• https://horvath.genetics.ucla.edu/html/CoexpressionNetwork/Rpackages/WGCNA/#manualInstall

For macosx users experiencing installation errors, try downloading OS X binaries from:

• https://CRAN.R-project.org/package=gRain
• https://CRAN.R-project.org/package=gRbase

Downloading expression data

url <- "http://xcell.ucsf.edu/iris_u133a_expr.txt"

dat_download <- data.frame(read.delim(url),
row.names = 1, stringsAsFactors = FALSE, check.rows = FALSE)

# data are transposed for processing
datExpr0<-data.frame(t(dat_download))

QC of expression data

WGCNA is used to for quality control of genes via the goodSamplesGenes function

library(WGCNA)
gsg = goodSamplesGenes(datExpr0, verbose = 3) # columns must be genes
#>  Flagging genes and samples with too many missing values...
#>   ..step 1
gsg$allOK
#> [1] TRUE

A sampleTree can be used to check for outlier samples. For this example all samples are kept.

sampleTree = hclust(dist(datExpr0), method = "average");

par(cex = 0.6);
par(mar = c(0,4,2,0))
plot(sampleTree, main = "Sample Filtering", 
labels = FALSE)

# final expression set ----------------------------------------------------
datExpr = datExpr0

Exporting expression data for xCell signature analysis

For cell signature detection using xCell, the expression data can be written to a csv file. The file can be uploaded at: http://xcell.ucsf.edu

Exps_for_xCell_analysis<-data.frame(t(datExpr), check.names = FALSE)

write.csv(Exps_for_xCell_analysis, file = "Exps_for_xCell_analysis.csv")

WGCNA module detection

Auto_WGCNA is a wrapper for WGCNA. Not all options are avaible. For more advanced features please use WGCNA.

library(GmicR)

GMIC_Builder<-Auto_WGCNA(sample_dat, 
  mergeCutHeight = 0.35, minModuleSize = 10,
  deepSplit = 4, networkType = "signed hybrid", TOMType = "unsigned",
  corFnc = "bicor",  sft_RsquaredCut = 0.85,
  reassignThreshold = 1e-06, maxBlockSize = 25000)
#> verify that colnames contain official gene symbols
#> Warning: executing %dopar% sequentially: no parallel backend registered
#> Table for modules and gene counts

Viewing input parameters

GMIC_Builder$Input_Parameters
#> $networkType
#> [1] "signed hybrid"
#> 
#> $TOMType
#> [1] "unsigned"
#> 
#> $corFnc
#> [1] "bicor"
#> 
#> $sft_RsquaredCut
#> [1] 0.85
#> 
#> $softPower
#> [1] 5
#> 
#> $minModuleSize
#> [1] 10
#> 
#> $deepSplit
#> [1] 4
#> 
#> $mergeCutHeight
#> [1] 0.35
#> 
#> $reassignThreshold
#> [1] 1e-06
#> 
#> $maxBlockSize
#> [1] 25000

Soft threshold plot

GMIC_Builder$Output_plots$soft_threshold_plot

module clustering

GMIC_Builder$Output_plots$module_clustering
#> Warning in restoreRecordedPlot(x, reloadPkgs): snapshot recorded in different R
#> version (3.5.3)

dendrogram

GMIC_Builder$Output_plots$net_dendrogram
#> Warning in restoreRecordedPlot(x, reloadPkgs): snapshot recorded in different R
#> version (3.5.3)

Module annotation

WGCNA functions intramodularConnectivity and chooseOneHubInEachModule are used to build a dataframe with gene module information.

# Module hubs and Gene influence
GMIC_Builder<-Query_Prep(GMIC_Builder,  
  calculate_intramodularConnectivity= TRUE,
  Find_hubs = TRUE)
#> alpha: 1.000000
#> alpha: 1.000000
#> alpha: 1.000000
#> alpha: 1.000000
#> alpha: 1.000000
#> alpha: 1.000000
#> alpha: 1.000000
#> alpha: 1.000000
#> alpha: 1.000000
#> alpha: 1.000000
#> alpha: 1.000000
#> alpha: 1.000000
#> alpha: 1.000000
#> alpha: 1.000000

head(GMIC_Builder$Query)
#>         ref_genes modules     hub Freq    kTotal   kWithin
#> SLC37A4   SLC37A4       0 SLC37A4  100 1.6525368 1.0000000
#> PEX10       PEX10       0 SLC37A4  100 1.6403205 0.8690595
#> GALNT12   GALNT12       0 SLC37A4  100 0.9325671 0.8025879
#> FGF3         FGF3       0 SLC37A4  100 2.2483526 0.7881512
#> ANGEL1     ANGEL1       0 SLC37A4  100 3.4791659 0.7681177
#> PER3         PER3       0 SLC37A4  100 0.8164831 0.7152039

This function constructs a library for gene ontology enrichment, which will be used for module naming with the GO_Module_NameR function.

GMIC_Builder<-GSEAGO_Builder(GMIC_Builder,
  species = "Homo sapiens", ontology = "BP")
#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().
#> Warning: Factors converted to character
#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().
#> Warning: Factors converted to character
#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().
#> Warning: Factors converted to character
#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().

#> Warning in result_fetch(res@ptr, n = n): SQL statements must be issued with
#> dbExecute() or dbSendStatement() instead of dbGetQuery() or dbSendQuery().
#> 
#> Attaching package: 'BiocGenerics'
#> The following objects are masked from 'package:parallel':
#> 
#>     clusterApply, clusterApplyLB, clusterCall, clusterEvalQ,
#>     clusterExport, clusterMap, parApply, parCapply, parLapply,
#>     parLapplyLB, parRapply, parSapply, parSapplyLB
#> The following objects are masked from 'package:stats':
#> 
#>     IQR, mad, sd, var, xtabs
#> The following objects are masked from 'package:base':
#> 
#>     Filter, Find, Map, Position, Reduce, anyDuplicated, append,
#>     as.data.frame, basename, cbind, colnames, dirname, do.call,
#>     duplicated, eval, evalq, get, grep, grepl, intersect, is.unsorted,
#>     lapply, mapply, match, mget, order, paste, pmax, pmax.int, pmin,
#>     pmin.int, rank, rbind, rownames, sapply, setdiff, sort, table,
#>     tapply, union, unique, unsplit, which, which.max, which.min
#> Welcome to Bioconductor
#> 
#>     Vignettes contain introductory material; view with
#>     'browseVignettes()'. To cite Bioconductor, see
#>     'citation("Biobase")', and for packages 'citation("pkgname")'.
#> 
#> Attaching package: 'S4Vectors'
#> The following object is masked from 'package:base':
#> 
#>     expand.grid
#> [1] 0
#> [1] 1
#> [1] 2
#> [1] 3
#> [1] 4
#> [1] 5
#> [1] 6
#> [1] 7
#> [1] 8
#> [1] 9
#> [1] 10
#> [1] 11
#> [1] 12

GO_Module_NameR will assign a name to each module based on ontology size. A smaller cut off size will generate a more specific term.

GMIC_Builder<-GO_Module_NameR(GMIC_Builder, cutoff_size = 100)

This table provides a summary of detected modules. “Freq” indicates the total genes within each module

head(GMIC_Builder$GO_table, n = 4)
#>              GO_module_name modules     hub Freq
#> ME0                module 0       0 SLC37A4  100
#> ME1           cell adhesion       1    SGCD  319
#> ME2 chromosome organization       2  ANP32B  187
#> ME3         cell activation       3 CYP27A1   88

A searchable dataframe is also generated

head(GMIC_Builder$GO_Query, n = 4)
#>         modules ref_genes     hub Freq    kTotal   kWithin GO_module_name
#> SLC37A4       0   SLC37A4 SLC37A4  100 1.6525368 1.0000000       module 0
#> PEX10         0     PEX10 SLC37A4  100 1.6403205 0.8690595       module 0
#> GALNT12       0   GALNT12 SLC37A4  100 0.9325671 0.8025879       module 0
#> FGF3          0      FGF3 SLC37A4  100 2.2483526 0.7881512       module 0

Specify the “xCell results” file directory

For this example, we are using cell signatures provided by the GmicR package, which were generated using the xCell web portal.

file_dir<-system.file("extdata", "IRIS_xCell_sig.txt", 
                      package = "GmicR", mustWork = TRUE)

Discretization

This function merges module eigengenes with xCell signatures prior to discretization. Only xCell signatures are supported. Discretization is carried out with bnlearning using “hartemink” method. For detailed information discretization see: http://www.bnlearn.com/documentation/man/preprocessing.html

GMIC_Builder_disc<-Data_Prep(GMIC_Builder,  
  xCell_Signatures = file_dir, 
ibreaks=10, Remove_ME0 = TRUE)
#> ImmuneScore, StromaScore, and MicroenvironmentScore removed

head(GMIC_Builder_disc$disc_data[sample(seq(1,64),4)])
#>           DC Bcells ME12 CLP
#> GSM565337  L      M    L   M
#> GSM565326  L      H    L   M
#> GSM565270  L      M    L   M
#> GSM565341  L      M    L   M
#> GSM565276  L      L    L   M
#> GSM565358  M      M    L   H

Bayesian network learing with bootstrapping.

Although the default score for this function is Bayesian Dirichlet equivalent score (bde), for this example we will use the Bayesian Dirichlet sparse score (bds). For sparse data, such as the data used in this example, the bds score is better suited: https://arxiv.org/abs/1605.03884.

GMIC_net<-bn_tabu_gen(GMIC_Builder_disc, 
  bootstraps_replicates = 50, score = "bds")

Detecting arcs for inversly related nodes

For hypothesis generation, it may be helpful to distiguish positive relationships from negative. The InverseARCs function from GmicR identifies these relationships from probability distributions generated from mutilated network queries. A correlation matrix is generated and a threshold is applied to specify a slope cut off for inverse relationships. By default the threhold is set to -0.3.

    GMIC_Final<-InverseARCs(GMIC_net, threshold = -0.3)
#> Please update to bnlearn 4.6 from https://www.bnlearn.com/

GmicR shiny app

Once complete, the GMIC network can be viewed using the Gmic_viz shiny app.

GMIC_Final_dir<-system.file("extdata", "GMIC_Final.Rdata", 
                          package = "GmicR", mustWork = TRUE)
load(GMIC_Final_dir)

if(interactive()){
Gmic_viz(GMIC_Final)
}