In ahopki14/tcrSeqR: Tools for analyzing data from Adaptive's ImmunoSeq platform

SBRT Study

Created r format(Sys.Date(),"%m/%d/%y")

require(rmarkdown)
require(immunoSeqR)
require(ggplot2)
require(gridExtra)
require(knitr)
require(reshape2)
first_run <- FALSE
verbose=FALSE
r <- function(){render('~/Documents/emj/ImmunoseqResults/immunoSeqR/scripts/rmd/sbrt.Rmd',
output_file='~/Documents/emj/ImmunoseqResults/new/sbrt.pdf')}

ds <- readRDS('~/Documents/emj/ImmunoseqResults/data/sbrt/ds_agg.Rds')
load('~/Documents/emj/ImmunoseqResults/data/sbrt/sum.ds.Rda')
dict <- readRDS('~/Documents/emj/ImmunoseqResults/data/sbrt/dict.Rds')
plot_ds <- readRDS('~/Documents/emj/ImmunoseqResults/data/sbrt/plot_ds.Rds')
stats <- readRDS('~/Documents/emj/ImmunoseqResults/data/sbrt/stats.Rds')
load('~/Documents/emj/ImmunoseqResults/data/sbrt/olm.Rda')

Background

Dataset

The data set contains r sum.ds$nsamp samples, of r sum.ds$ntypes types. There are r sum.ds$unique.tcr unique TCRs, collapsed from r sum.ds$total.tcr distinct productive CDR3 sequences. This represents an average synonymity of r sum.ds$avg.syn. The maximum synonymity (in the parent data set) was r sum.ds$max.syn (clone sequence r sum.ds$max.syn.aa).\par

Metadata

The available metadata fields in the dictionary are: r paste(names(dict)[-1],collapse=', '). The statistics computed are r paste(names(stats)[names(stats)!='fn'],collapse=', ').

\clearpage

Overlaps

rownames(mm) <- paste0(dict$patient,dict$type)
colnames(mm) <- rownames(mm)
#w <- c(which(dict$response=='NR'),which(dict$response=='R'))
tdict <- dict[,]
tmm <- mm
tmm.m <- melt(tmm)
g <- ggplot(tmm.m,aes(x=Var1,y=Var2)) +
    geom_tile(aes(fill=value)) +
    coord_fixed() +
    scale_fill_gradient(low='white',high='black')+
    theme(axis.text=element_text(size=5,color='black'),
            axis.text.x=element_text(angle=90,hjust=1,vjust=0.5))+
    xlab('') + ylab('') + ggtitle('Morisita Overlap')
g

Expanded Clones

Pre vs Post-SBRT

w <- grep('Number of Expanded',names(plot_ds))
g <- iseqr_plot_factor(plot_ds,names(plot_ds)[w],'arm',type='POSTSBRT') + xlab('Arm')
g

w <- grep('Number of Expanded',names(plot_ds))
g <- iseqr_plot_factor(plot_ds,names(plot_ds)[w],'arm',type='POSTFOLF') + xlab('Arm')
f

resp <- sapply(names(out2$num_exp),FUN=iseqr_lookup,dict=tdict,o_col='os.tert')
pt <- sapply(names(out2$num_exp),FUN=iseqr_lookup,dict=tdict,o_col='ptv80.tert')
arm <- sapply(names(out2$num_exp),FUN=iseqr_lookup,dict=tdict,o_col='arm')
df <- data.frame(patient=names(out2$num_exp),response=resp,arm=arm,pt=pt,num_exp=out2$num_exp)
g <- iseqr_plot_factor(df,'num_exp','response',NA)
g <- g + ylab('Number of Expanded Clones') + xlab('Survival Tertile')
f <- iseqr_plot_factor(df,'num_exp','arm',NA) + xlab('Arm')
f <- f + ylab('Number of Expanded Clones')
i <- iseqr_plot_factor(df,'num_exp','pt',NA) + xlab('PTV80 Tertile')
i <- i + ylab('Number of Expanded Clones')

grid.arrange(f,g,i,ncol=3)

By Type

#put sum of seqs at the end
stats <- stats[,c(1,3,2,4)]
plot_ds <- merge(dict,stats)

metrics <- names(stats[names(stats)!='fn'])
types <- levels(plot_ds$type)
l <- vector('list')
for(b in metrics){
        l[[b]] <- iseqr_plot_factor(plot_ds,b,'type',NA) + theme(axis.text=element_text(size=5))
}
do.call(grid.arrange,c(l,ncol=length(types)))

for(a in metrics){
    print(kable(iseqr_summarize(plot_ds,'type',metric=a),
        format='markdown',
        digits=3,
        align='c'))
}

\clearpage

By Treatment Arm

x_val <- 'arm'
metrics <- names(stats[names(stats)!='fn'])
types <- levels(plot_ds$type)
for(b in metrics){
    l <- vector('list')
    for(a in types){
        l[[a]] <- iseqr_plot_factor(plot_ds,b,x_val,a)
    }
    do.call(grid.arrange,c(l,ncol=length(types)))
}

\clearpage

By Overall Survival

x_val <- 'os'
metrics <- names(stats[names(stats)!='fn'])
types <- levels(plot_ds$type)
for(b in metrics){
    l <- vector('list')
    for(a in types[types!='PDAC']){
        l[[a]] <- iseqr_plot_metrics(plot_ds[!is.na(plot_ds$os),],b,x_val,a) +
                    theme(axis.text=element_text(size=5))
    }
    do.call(grid.arrange,c(l,ncol=length(types)))
    cat('  \n')
}

By Survival Tertile

x_val <- 'os.tert'
metrics <- names(stats[names(stats)!='fn'])
types <- levels(plot_ds$type)
for(b in metrics){
    l <- vector('list')
    for(a in types){
        l[[a]] <- iseqr_plot_factor(plot_ds,b,x_val,a)
    }
    do.call(grid.arrange,c(l,ncol=length(types)))
}

\clearpage

By PTV80

x_val <- 'ptv80'
metrics <- names(stats[names(stats)!='fn'])
types <- levels(plot_ds$type)
for(b in metrics){
    l <- vector('list')
    for(a in types[types!='PDAC']){
        l[[a]] <- iseqr_plot_metrics(plot_ds[!is.na(plot_ds$ptv80),],b,x_val,a) +
                    theme(axis.text=element_text(size=5))
    }
    do.call(grid.arrange,c(l,ncol=length(types)))
    cat('  \n')
}

By PTV80 Tertile

x_val <- 'ptv80.tert'
metrics <- names(stats[names(stats)!='fn'])
types <- levels(plot_ds$type)
for(b in metrics){
    l <- vector('list')
    for(a in types){
        l[[a]] <- iseqr_plot_factor(plot_ds,b,x_val,a)
    }
    do.call(grid.arrange,c(l,ncol=length(types)))
}

\clearpage

Confounders

Cell Number

x_val <- 'cells'
metrics <- names(stats[names(stats)!='fn'])
types <- levels(plot_ds$type)
for(b in metrics){
    l <- vector('list')
    for(a in types[types!='PDAC']){
        l[[a]] <- iseqr_plot_metrics(plot_ds[!is.na(plot_ds$cells),],b,x_val,a) + 
                    theme(axis.text=element_text(size=5))
    }
    do.call(grid.arrange,c(l,ncol=length(types)))  
    cat('  \n')
}

Age

x_val <- 'age'
metrics <- names(stats[names(stats)!='fn'])
types <- levels(plot_ds$type)
for(b in metrics){
    l <- vector('list')
    for(a in types[types!='PDAC']){
        l[[a]] <- iseqr_plot_metrics(plot_ds[!is.na(plot_ds$cells),],b,x_val,a) +
                    theme(axis.text=element_text(size=5))
    }
    do.call(grid.arrange,c(l,ncol=length(types)))
    cat('  \n')
}

ahopki14/tcrSeqR documentation built on May 16, 2019, 6:56 p.m.