In omicsCore/SEQprocess: SEQprocess : a modularized and customizable pipeline framework for NGS processing in R package.
Variants
Total r report.summary$annot$total.variant(r report.summary$annot$min.variant-r report.summary$annot$max.variant, average: r report.summary$annot$mean.variant) variants were identified. The identified variants were classified according to their genomic coordinates in relation to the known genes.
Output summary is saved at r paste0(output.dir,"/06_annot").
\
if(length(report.summary$annot)!=0) {
func=report.summary$annot$Func
func=data.frame(Func.Name=rownames(func), func, row.names = NULL)
table.func=func
table.func[,-1]=format(table.func[,-1], big.mark=",")
specify_decimal <- function(x, k) trimws(format(round(x, k), nsmall=k))
func[,-1]=apply(func[,-1], 2, as.numeric)
stack.func=func
t.func=t(func)
t.func.name=t.func[1,]
t.func=t.func[-1,]
colnames(t.func)=t.func.name
trans.df=data.frame(Sample.Name=rownames(t.func), t.func, row.names = NULL)
table.func.df=trans.df
}
Gene Function Plot
\
\
func.df=melt(trans.df, id.vars = "Sample.Name")
func.df$value=as.numeric(as.character(func.df$value))
func.df$Sample.Name=factor(as.character(func.df$Sample.Name), levels = unique(func.df$Sample.Name))
if(length(unique(func.df[,1]))>10) coord_flip=coord_flip() else coord_flip=NULL
if(length(unique(func.df[,1]))<10) opts=theme(axis.text.x=element_text(angle=90 , hjust = 1)) else opts=NULL
func.plot=ggplot(func.df, aes(x=Sample.Name, y =value, fill=variable)) + geom_bar(stat = 'identity', position = 'stack',width=0.5) + coord_flip + opts +
theme(legend.position="bottom", axis.text.x = element_text(face="bold"), axis.text.y = element_text(face="bold")) + labs(fill = "") +
xlab("Sample Name") + ylab("count") +ggtitle("Scale of Variant Function") +
theme(plot.title = element_text(hjust = 0.5))
func.plot
\newpage
Exonic Function
The variants in each sample were classified according to their exonic functions as follows.
\
if(!is.null(report.summary$annot$ExonicFunc)){
exonic=report.summary$annot$ExonicFunc
exonic=data.frame(ExonicFunc.Name=rownames(exonic), exonic, row.names = NULL)
table.exonic=exonic
table.exonic[,-1]=format(table.exonic[,-1],big.mark=",")
exonic[,-1]=apply(exonic[,-1], 2, as.numeric)
stack.exonic=exonic
e.tot=colSums(exonic[,2:ncol(exonic)])
for(i in 1:length(e.tot)) stack.exonic[,i+1]=exonic[,i+1]/e.tot[i]
exonic.per=stack.exonic
exonic.per$Means=rowMeans(exonic.per[,-1])
exonic.per[,-1]=apply(exonic.per[,-1],2, function(a) specify_decimal(a*100,2))
table.exonic$Means=exonic.per$Means
colnames(table.exonic)[length(table.exonic)]="Means(%)"
t.exonic=t(stack.exonic)
t.exonic.name=t.exonic[1,]
t.exonic=t.exonic[-1,]
colnames(t.exonic)=t.exonic.name
trans.exonic.df=data.frame(Sample.Name=rownames(t.exonic), t.exonic, row.names = NULL)
trans.exonic.df[,-1]=apply(trans.exonic.df[,-1],2,as.numeric)
table.exonic.df=trans.exonic.df
table.exonic.df[,-1]=apply(table.exonic.df[,-1],2,function(a) specify_decimal(as.numeric(as.character(a))*100,1))
table.exonic.df.per=table.exonic.df
table.exonic.df.per[,-1]=apply(table.exonic.df[,-1],2,function(a) paste0(a,"%"))
o.table.exonic.df.per=table.exonic.df.per
colnames(o.table.exonic.df.per)=c('Sample\nName','frameshift\ndeletion','frameshift\ninsertion','non\nframeshift\ndeletion','non\nframeshift\ninsertion','non\nsynonymous\nSNV','stopgain','stoploss','synonymous\nSNV','unknown')
pander(o.table.exonic.df.per, justify = "center", style = "multiline", split.table = Inf, keep.line.breaks = TRUE , caption = "\t\t\t\t\tProportion(%) of Exonic Variant Function in each sample")
}
if(!is.null(report.summary$annot$ExonicFunc)){cat("frameshift deletion : Deletion of one or more nucleotides that cause frameshift changes in protein coding sequence","frameshift insertion : Insertion of one or more nucleotides that cause frameshift changes in protein coding sequence","nonframeshift deletion : Deletion of 3 or mutliples of 3 nucleotides that do not cause frameshift changes in protein coding sequence","nonframeshift insertion : Insertion of 3 or multiples of 3 nucleotides that do not cause frameshift changes in protein coding sequence","nonsynonymous SNV : A single nucleotide change that cause an amino acid change","stopgain : Variant causes a STOP codon","stoploss : Variant causes stop codon to be mutated into a non-stop codon","synonymous SNV : A single nucleotide change that does not cause an amino acid change","unknown : unknown function (due to various errors in the gene structure definition in the database file)",sep = "\n")}
\
\
Exonic Function Plot
if(!is.null(report.summary$annot$ExonicFunc)) {
exonic.df=melt(trans.exonic.df, id.vars = "Sample.Name")
exonic.df$value=specify_decimal(as.numeric(as.character(exonic.df$value))*100,2)
exonic.df$value=as.numeric(exonic.df$value)
exonic.df$Sample.Name=factor(as.character(exonic.df$Sample.Name), levels = unique(exonic.df$Sample.Name))
if(length(unique(exonic.df[,1]))>10) coord_flip=coord_flip() else coord_flip=NULL
if(length(unique(exonic.df[,1]))<10) opts=theme(axis.text.x=element_text(angle=90 , hjust = 1)) else opts=NULL
exonicfunc.plot=ggplot(exonic.df ,aes(x=Sample.Name, y =value, fill=variable)) + geom_bar(stat = 'identity', position = 'stack',width=0.5) + coord_flip + opts + theme(legend.position="bottom", axis.text.x = element_text(face="bold"), axis.text.y = element_text(face="bold")) + labs(fill = "") + xlab("Sample Name") + ylab("Proportion(%)")+ggtitle("Proportion of Exonic Variant Function") +
theme(plot.title = element_text(hjust = 0.5))
exonicfunc.plot
}
\newpage
Mutation Type
\
The variants in each sample were classified according to mutation type as follows.
\
mut.type=report.summary$annot$mut.type
mut.type=data.frame(mut.type=rownames(mut.type), mut.type, row.names = NULL)
if(!is.element("indel",rownames(mut.type))) {
indel=rep(0,ncol(mut.type))
mut.type2=rbind(mut.type[1:3,], indel)
mut.type=rbind(mut.type2,mut.type[4:6,])
mut.type$mut.type[4]=as.character(mut.type$mut.type[4])
mut.type$mut.type[4]="indel"
rownames(mut.type)=1:length(rownames(mut.type))
}
table.mut.type=mut.type
table.mut.type[4:6,]=mut.type[5:7,]
table.mut.type[7,]=mut.type[4,]
table.mut.type[,-1]=format(table.mut.type[,-1], big.mark=",")
mut.type[,-1]=apply(mut.type[,-1], 2, as.numeric)
stack.mut.type=mut.type
mut.type.tot=colSums(mut.type[,2:ncol(mut.type)])
for(i in 1:length(mut.type.tot)) stack.mut.type[,i+1]=mut.type[,i+1]/mut.type.tot[i]
mut.type.per=stack.mut.type
mut.type.per$Means=rowMeans(mut.type.per[,-1])
mut.type.per[,-1]=apply(mut.type.per[,-1],2, function(a) specify_decimal(a*100,2))
table.mut.type$Means=mut.type.per$Means
colnames(table.mut.type)[length(table.mut.type)]="Means(%)"
t.mut.type=t(stack.mut.type)
t.mut.type.name=t.mut.type[1,]
t.mut.type=t.mut.type[-1,]
colnames(t.mut.type)=t.mut.type.name
trans.mut.type.df=data.frame(Sample.Name=rownames(t.mut.type), t.mut.type, row.names = NULL)
trans.mut.type.df[,-1]=apply(trans.mut.type.df[,-1],2,as.numeric)
t.mut.type.df=trans.mut.type.df
t.mut.type.df[,5:7]=trans.mut.type.df[,6:8]
t.mut.type.df[,8]=trans.mut.type.df[,5]
colnames(t.mut.type.df)[2]=('C>A/G>T(%)')
colnames(t.mut.type.df)[3]=('C>G/G>C(%)')
colnames(t.mut.type.df)[4]=('C>T/G>A(%)')
colnames(t.mut.type.df)[5]=('T>A/A>T(%)')
colnames(t.mut.type.df)[6]=('T>C/A>G(%)')
colnames(t.mut.type.df)[7]=('T>G/A>C(%)')
colnames(t.mut.type.df)[8]=('Indel(%)')
table.mut.type.df=t.mut.type.df
table.mut.type.df[,-1]=apply(table.mut.type.df[,-1],2,function(a) specify_decimal(as.numeric(as.character(a))*100,1))
table.mut.type.df.per=table.mut.type.df
table.mut.type.df.per[,-1]=apply(table.mut.type.df[,-1],2,function(a) paste0(a,","))
table.mut.type.df2=table.mut.type.df
colnames(table.mut.type.df2)[1]='Sample\nName'
colnames(table.mut.type.df2)[2]=('C>A/\nG>T(%)')
colnames(table.mut.type.df2)[3]=('C>G/\nG>C(%)')
colnames(table.mut.type.df2)[4]=('C>T/\nG>A(%)')
colnames(table.mut.type.df2)[5]=('T>A/\nA>T(%)')
colnames(table.mut.type.df2)[6]=('T>C/\nA>G(%)')
colnames(table.mut.type.df2)[7]=('T>G/\nA>C(%)')
colnames(table.mut.type.df2)[8]=('Indel(%)')
pander(table.mut.type.df2, justify = "center", style = "multiline", split.table = Inf,caption = "\t\t\t\t\t\t\t\tProportion of SNP in each sample")
cat("mut.type : Mutation type")
\
\
Mutation Type Plot
mut.type.df=melt(t.mut.type.df, id.vars = "Sample.Name")
mut.type.df$value=as.numeric(specify_decimal(as.numeric(as.character(mut.type.df$value))*100,2))
mut.type.df$Sample.Name=factor(as.character(mut.type.df$Sample.Name), levels = unique(mut.type.df$Sample.Name))
if(length(unique(mut.type.df[,1]))>10) coord_flip=coord_flip() else coord_flip=NULL
if(length(unique(mut.type.df[,1]))<10) opts=theme(axis.text.x=element_text(angle=90 , hjust = 1)) else opts=NULL
mut.type.plot=ggplot(mut.type.df, aes(x=Sample.Name, y=value , fill=variable)) + geom_bar(stat = 'identity', position = 'stack',width=0.5) + coord_flip + opts +
theme(legend.position="bottom",axis.text.x = element_text(face="bold"), axis.text.y = element_text(face="bold")) + labs(fill = "") +
xlab("Sample Name") + ylab("Proportion(%)") +ggtitle("Proportion of SNP") +
theme(plot.title = element_text(hjust = 0.5))
mut.type.plot
omicsCore/SEQprocess documentation built on May 7, 2020, 4:18 a.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Variants
Total r report.summary$annot$total.variant(r report.summary$annot$min.variant-r report.summary$annot$max.variant, average: r report.summary$annot$mean.variant) variants were identified. The identified variants were classified according to their genomic coordinates in relation to the known genes.
Output summary is saved at r paste0(output.dir,"/06_annot").
\
if(length(report.summary$annot)!=0) { func=report.summary$annot$Func func=data.frame(Func.Name=rownames(func), func, row.names = NULL) table.func=func table.func[,-1]=format(table.func[,-1], big.mark=",") specify_decimal <- function(x, k) trimws(format(round(x, k), nsmall=k)) func[,-1]=apply(func[,-1], 2, as.numeric) stack.func=func t.func=t(func) t.func.name=t.func[1,] t.func=t.func[-1,] colnames(t.func)=t.func.name trans.df=data.frame(Sample.Name=rownames(t.func), t.func, row.names = NULL) table.func.df=trans.df }
Gene Function Plot
\
\
func.df=melt(trans.df, id.vars = "Sample.Name") func.df$value=as.numeric(as.character(func.df$value)) func.df$Sample.Name=factor(as.character(func.df$Sample.Name), levels = unique(func.df$Sample.Name)) if(length(unique(func.df[,1]))>10) coord_flip=coord_flip() else coord_flip=NULL if(length(unique(func.df[,1]))<10) opts=theme(axis.text.x=element_text(angle=90 , hjust = 1)) else opts=NULL func.plot=ggplot(func.df, aes(x=Sample.Name, y =value, fill=variable)) + geom_bar(stat = 'identity', position = 'stack',width=0.5) + coord_flip + opts + theme(legend.position="bottom", axis.text.x = element_text(face="bold"), axis.text.y = element_text(face="bold")) + labs(fill = "") + xlab("Sample Name") + ylab("count") +ggtitle("Scale of Variant Function") + theme(plot.title = element_text(hjust = 0.5)) func.plot
\newpage
Exonic Function
The variants in each sample were classified according to their exonic functions as follows. \
if(!is.null(report.summary$annot$ExonicFunc)){ exonic=report.summary$annot$ExonicFunc exonic=data.frame(ExonicFunc.Name=rownames(exonic), exonic, row.names = NULL) table.exonic=exonic table.exonic[,-1]=format(table.exonic[,-1],big.mark=",") exonic[,-1]=apply(exonic[,-1], 2, as.numeric) stack.exonic=exonic e.tot=colSums(exonic[,2:ncol(exonic)]) for(i in 1:length(e.tot)) stack.exonic[,i+1]=exonic[,i+1]/e.tot[i] exonic.per=stack.exonic exonic.per$Means=rowMeans(exonic.per[,-1]) exonic.per[,-1]=apply(exonic.per[,-1],2, function(a) specify_decimal(a*100,2)) table.exonic$Means=exonic.per$Means colnames(table.exonic)[length(table.exonic)]="Means(%)" t.exonic=t(stack.exonic) t.exonic.name=t.exonic[1,] t.exonic=t.exonic[-1,] colnames(t.exonic)=t.exonic.name trans.exonic.df=data.frame(Sample.Name=rownames(t.exonic), t.exonic, row.names = NULL) trans.exonic.df[,-1]=apply(trans.exonic.df[,-1],2,as.numeric) table.exonic.df=trans.exonic.df table.exonic.df[,-1]=apply(table.exonic.df[,-1],2,function(a) specify_decimal(as.numeric(as.character(a))*100,1)) table.exonic.df.per=table.exonic.df table.exonic.df.per[,-1]=apply(table.exonic.df[,-1],2,function(a) paste0(a,"%")) o.table.exonic.df.per=table.exonic.df.per colnames(o.table.exonic.df.per)=c('Sample\nName','frameshift\ndeletion','frameshift\ninsertion','non\nframeshift\ndeletion','non\nframeshift\ninsertion','non\nsynonymous\nSNV','stopgain','stoploss','synonymous\nSNV','unknown') pander(o.table.exonic.df.per, justify = "center", style = "multiline", split.table = Inf, keep.line.breaks = TRUE , caption = "\t\t\t\t\tProportion(%) of Exonic Variant Function in each sample") }
if(!is.null(report.summary$annot$ExonicFunc)){cat("frameshift deletion : Deletion of one or more nucleotides that cause frameshift changes in protein coding sequence","frameshift insertion : Insertion of one or more nucleotides that cause frameshift changes in protein coding sequence","nonframeshift deletion : Deletion of 3 or mutliples of 3 nucleotides that do not cause frameshift changes in protein coding sequence","nonframeshift insertion : Insertion of 3 or multiples of 3 nucleotides that do not cause frameshift changes in protein coding sequence","nonsynonymous SNV : A single nucleotide change that cause an amino acid change","stopgain : Variant causes a STOP codon","stoploss : Variant causes stop codon to be mutated into a non-stop codon","synonymous SNV : A single nucleotide change that does not cause an amino acid change","unknown : unknown function (due to various errors in the gene structure definition in the database file)",sep = "\n")}
\
\
Exonic Function Plot
if(!is.null(report.summary$annot$ExonicFunc)) { exonic.df=melt(trans.exonic.df, id.vars = "Sample.Name") exonic.df$value=specify_decimal(as.numeric(as.character(exonic.df$value))*100,2) exonic.df$value=as.numeric(exonic.df$value) exonic.df$Sample.Name=factor(as.character(exonic.df$Sample.Name), levels = unique(exonic.df$Sample.Name)) if(length(unique(exonic.df[,1]))>10) coord_flip=coord_flip() else coord_flip=NULL if(length(unique(exonic.df[,1]))<10) opts=theme(axis.text.x=element_text(angle=90 , hjust = 1)) else opts=NULL exonicfunc.plot=ggplot(exonic.df ,aes(x=Sample.Name, y =value, fill=variable)) + geom_bar(stat = 'identity', position = 'stack',width=0.5) + coord_flip + opts + theme(legend.position="bottom", axis.text.x = element_text(face="bold"), axis.text.y = element_text(face="bold")) + labs(fill = "") + xlab("Sample Name") + ylab("Proportion(%)")+ggtitle("Proportion of Exonic Variant Function") + theme(plot.title = element_text(hjust = 0.5)) exonicfunc.plot }
\newpage
Mutation Type
\
The variants in each sample were classified according to mutation type as follows.
\
mut.type=report.summary$annot$mut.type mut.type=data.frame(mut.type=rownames(mut.type), mut.type, row.names = NULL) if(!is.element("indel",rownames(mut.type))) { indel=rep(0,ncol(mut.type)) mut.type2=rbind(mut.type[1:3,], indel) mut.type=rbind(mut.type2,mut.type[4:6,]) mut.type$mut.type[4]=as.character(mut.type$mut.type[4]) mut.type$mut.type[4]="indel" rownames(mut.type)=1:length(rownames(mut.type)) } table.mut.type=mut.type table.mut.type[4:6,]=mut.type[5:7,] table.mut.type[7,]=mut.type[4,] table.mut.type[,-1]=format(table.mut.type[,-1], big.mark=",") mut.type[,-1]=apply(mut.type[,-1], 2, as.numeric) stack.mut.type=mut.type mut.type.tot=colSums(mut.type[,2:ncol(mut.type)]) for(i in 1:length(mut.type.tot)) stack.mut.type[,i+1]=mut.type[,i+1]/mut.type.tot[i] mut.type.per=stack.mut.type mut.type.per$Means=rowMeans(mut.type.per[,-1]) mut.type.per[,-1]=apply(mut.type.per[,-1],2, function(a) specify_decimal(a*100,2)) table.mut.type$Means=mut.type.per$Means colnames(table.mut.type)[length(table.mut.type)]="Means(%)" t.mut.type=t(stack.mut.type) t.mut.type.name=t.mut.type[1,] t.mut.type=t.mut.type[-1,] colnames(t.mut.type)=t.mut.type.name trans.mut.type.df=data.frame(Sample.Name=rownames(t.mut.type), t.mut.type, row.names = NULL) trans.mut.type.df[,-1]=apply(trans.mut.type.df[,-1],2,as.numeric) t.mut.type.df=trans.mut.type.df t.mut.type.df[,5:7]=trans.mut.type.df[,6:8] t.mut.type.df[,8]=trans.mut.type.df[,5] colnames(t.mut.type.df)[2]=('C>A/G>T(%)') colnames(t.mut.type.df)[3]=('C>G/G>C(%)') colnames(t.mut.type.df)[4]=('C>T/G>A(%)') colnames(t.mut.type.df)[5]=('T>A/A>T(%)') colnames(t.mut.type.df)[6]=('T>C/A>G(%)') colnames(t.mut.type.df)[7]=('T>G/A>C(%)') colnames(t.mut.type.df)[8]=('Indel(%)') table.mut.type.df=t.mut.type.df table.mut.type.df[,-1]=apply(table.mut.type.df[,-1],2,function(a) specify_decimal(as.numeric(as.character(a))*100,1)) table.mut.type.df.per=table.mut.type.df table.mut.type.df.per[,-1]=apply(table.mut.type.df[,-1],2,function(a) paste0(a,",")) table.mut.type.df2=table.mut.type.df colnames(table.mut.type.df2)[1]='Sample\nName' colnames(table.mut.type.df2)[2]=('C>A/\nG>T(%)') colnames(table.mut.type.df2)[3]=('C>G/\nG>C(%)') colnames(table.mut.type.df2)[4]=('C>T/\nG>A(%)') colnames(table.mut.type.df2)[5]=('T>A/\nA>T(%)') colnames(table.mut.type.df2)[6]=('T>C/\nA>G(%)') colnames(table.mut.type.df2)[7]=('T>G/\nA>C(%)') colnames(table.mut.type.df2)[8]=('Indel(%)') pander(table.mut.type.df2, justify = "center", style = "multiline", split.table = Inf,caption = "\t\t\t\t\t\t\t\tProportion of SNP in each sample") cat("mut.type : Mutation type")
\
\
Mutation Type Plot
mut.type.df=melt(t.mut.type.df, id.vars = "Sample.Name") mut.type.df$value=as.numeric(specify_decimal(as.numeric(as.character(mut.type.df$value))*100,2)) mut.type.df$Sample.Name=factor(as.character(mut.type.df$Sample.Name), levels = unique(mut.type.df$Sample.Name)) if(length(unique(mut.type.df[,1]))>10) coord_flip=coord_flip() else coord_flip=NULL if(length(unique(mut.type.df[,1]))<10) opts=theme(axis.text.x=element_text(angle=90 , hjust = 1)) else opts=NULL mut.type.plot=ggplot(mut.type.df, aes(x=Sample.Name, y=value , fill=variable)) + geom_bar(stat = 'identity', position = 'stack',width=0.5) + coord_flip + opts + theme(legend.position="bottom",axis.text.x = element_text(face="bold"), axis.text.y = element_text(face="bold")) + labs(fill = "") + xlab("Sample Name") + ylab("Proportion(%)") +ggtitle("Proportion of SNP") + theme(plot.title = element_text(hjust = 0.5)) mut.type.plot
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.