前言

今天我们来演示MOVICS包的第二个模块，在上一篇推文中：MOVICS系列教程(一) GET Module分析后，我们得到了乳腺癌的5个亚型，那么此模块就是为了对这5种亚型间的分子特征进行展示。

因为需要上一部分的输出结果，大家必须跑完上一篇推文的代码才可以进行本篇推文的演示代码。

主要函数

同样的，我们先来看一下这个模块用到的函数：

compSurv(): compare survival outcome and generate a Kalan-Meier curve with pairwise comparison if possible

compClinvar(): compare and summarize clinical features among different identified subtypes

compMut(): compare mutational frequency and generate an OncoPrint with significant mutations

compTMB(): compare total mutation burden among subtypes and generate distribution of Transitions and Transversions

compFGA(): compare fraction genome altered among subtypes and generate a barplot for distribution comparison

compDrugsen(): compare estimated half maximal inhibitory concentration (IC50) for drug sensitivity and generate a boxviolin for distribution comparison

compAgree(): compare agreement of current subtypes with other pre-existed classifications and generate an alluvial diagram and an agreement barplot

主要是通过比较各亚型间肿瘤的主要特征(生存分析，临床特征，突变状态，TMB，药敏和一致性)，来揭示各亚型间不同的分子特征。

代码演示

# survival comparison
surv.brca <- compSurv(moic.res         = cmoic.brca,
                      surv.info        = surv.info,
                      convt.time       = "m", # convert day unit to month
                      surv.median.line = "h", # draw horizontal line at median survival
                      xyrs.est         = c(5,10), # estimate 5 and 10-year survival
                      fig.name         = "KAPLAN-MEIER CURVE OF CONSENSUSMOIC")

图片

# survival comparison
surv.brca <- compSurv(moic.res         = cmoic.brca,
                      surv.info        = surv.info,
                      convt.time       = "m", # convert day unit to month
                      surv.median.line = "h", # draw horizontal line at median survival
                      xyrs.est         = c(5,10), # estimate 5 and 10-year survival
                      fig.name         = "KAPLAN-MEIER CURVE OF CONSENSUSMOIC")

图片

# mutational frequency comparison
mut.brca <- compMut(moic.res     = cmoic.brca,
                    mut.matrix   = brca.tcga$mut.status, # binary somatic mutation matrix
                    doWord       = TRUE, # generate table in .docx format
                    doPlot       = TRUE, # draw OncoPrint
                    freq.cutoff  = 0.05, # keep those genes that mutated in at least 5% of samples
                    p.adj.cutoff = 0.05, # keep those genes with adjusted p value < 0.05 to draw OncoPrint
                    innerclust   = TRUE, # perform clustering within each subtype
                    annCol       = annCol, # same annotation for heatmap
                    annColors    = annColors, # same annotation color for heatmap
                    width        = 6, 
                    height       = 2,
                    fig.name     = "ONCOPRINT FOR SIGNIFICANT MUTATIONS",
                    tab.name     = "INDEPENDENT TEST BETWEEN SUBTYPE AND MUTATION")

图片

# compare TMB
tmb.brca <- compTMB(moic.res     = cmoic.brca,
                    maf          = maf,
                    rmDup        = TRUE, # remove duplicated variants per sample
                    rmFLAGS      = FALSE, # keep FLAGS mutations
                    exome.size   = 38, # estimated exome size
                    test.method  = "nonparametric", # statistical testing method
                    fig.name     = "DISTRIBUTION OF TMB AND TITV")

图片

# compare FGA, FGG, and FGL
fga.brca <- compFGA(moic.res     = cmoic.brca,
                    segment      = segment,
                    iscopynumber = FALSE, # this is a segmented copy number file
                    cnathreshold = 0.2, # threshold to determine CNA gain or loss
                    test.method  = "nonparametric", # statistical testing method
                    fig.name     = "BARPLOT OF FGA")

图片

# drug sensitivity comparison
drug.brca <- compDrugsen(moic.res    = cmoic.brca,
                         norm.expr   = fpkm[,cmoic.brca$clust.res$samID], # double guarantee sample order
                         drugs       = c("Cisplatin", "Paclitaxel"), # a vector of names of drug in GDSC
                         tissueType  = "breast", # choose specific tissue type to construct ridge regression model
                         test.method = "nonparametric", # statistical testing method
                         prefix      = "BOXVIOLIN OF ESTIMATED IC50")

图片

# customize the factor level for pstage
surv.info$pstage <- factor(surv.info$pstage, levels = c("TX","T1","T2","T3","T4"))

# agreement comparison (support up to 6 classifications include current subtype)
agree.brca <- compAgree(moic.res  = cmoic.brca,
                        subt2comp = surv.info[,c("PAM50","pstage")],
                        doPlot    = TRUE,
                        box.width = 0.2,
                        fig.name  = "AGREEMENT OF CONSENSUSMOIC WITH PAM50 AND PSTAGE")