Update migec_summary.Rmd

Line 169: We added unique as the factor levels were reading duplicates and causing an error. 
Line 209: We edited that line because the assemble.log.txt file did not contain a column under the name 'READS DROPPED WITHIN MIG'. It contained individual columns for MIG1 and MIG2 for fastq1 and fastq2. We summed it to suit the function. 
We suppressed the warnings - `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead. We DID NOT update the plotting functions, instead we suppressed the warning message to temporarily ignore the warnings on plots.

Author: entropicus96

util/migec_summary.Rmd

@@ -166,7 +166,7 @@ colnames(df) <- c("sample", "sample.type", "threshold", "peak", "mig.size", "cou
 # summarize by sample type, normalize within sample
 df <- aggregate(count ~ sample + mig.size + threshold + peak, data=df, FUN=sum)
 df.n <- ddply(df,.(sample),transform,count=count/sum(count))
-df.n$sample <-factor(df.n$sample, levels=df.n[order(df.n$peak), "sample"])
+df.n$sample <-factor(df.n$sample, levels=unique(df.n[order(df.n$peak), "sample"]))
 
 # plotting
 
@@ -206,6 +206,7 @@ require(scales)
 
 if (!is.null(assemble_path)) {
 df <- read.table(paste(assemble_path, "/assemble.log.txt", sep = "/"), header=T, comment ="")
+df$READS_DROPPED_WITHIN_MIG = df$READS_DROPPED_WITHIN_MIG_1 + df$READS_DROPPED_WITHIN_MIG_2
 df <- data.frame(sample <- df$X.SAMPLE_ID, 
                  migs.assembled <- df$MIGS_GOOD_TOTAL,
                  umi.fraction.assembled <- df$MIGS_GOOD_TOTAL / df$MIGS_TOTAL,
@@ -242,7 +243,7 @@ plotAsm.2 <- function(dd) {
 
 Below is a plot showing the total number of assembled MIGs per sample. The number of MIGs should be interpreted as the total number of starting molecules that have been successfully recovered.
 
-```{r, echo=FALSE, message=FALSE}
+```{r, echo=FALSE, message=FALSE, warning=FALSE}
 p<-"Nothing to plot"
 if (!is.null(assemble_path)) {
 df.1 <- subset(df, variable == "migs.assembled")
@@ -357,7 +358,7 @@ plotCdr.2 <- function(dd) {
 
 The plot below shows the total number of MIGs that contain good-quality CDR3 region in the consensus sequence
 
-```{r, echo=FALSE, message=FALSE}
+```{r, echo=FALSE, message=FALSE, warning=FALSE}
 p <- "Nothing to plot"
 if (!is.null(cdrblast_path)) {
 df.s <- subset(df, variable == "final.count" & type == "asm" & metric == "mig")
@@ -370,7 +371,7 @@ p
 
 Total number of reads that contain good-quality CDR3 region in raw reads
 
-```{r, echo=FALSE, message=FALSE}
+```{r, echo=FALSE, message=FALSE, warning=FALSE}
 p <- "Nothing to plot"
 if (!is.null(cdrblast_path)) {
 df.s <- subset(df, variable == "final.count" & type == "asm" & metric == "read")
@@ -385,7 +386,7 @@ Mapping rate, the fraction of reads/MIGs that contain a CDR3 region
 
 > Panels show assembled (**asm**) and unprocessed (**raw**) data. Values are given in number of molecules (**mig**, assembled samples only) and the corresponding read count (**read**)
 
-```{r, echo=FALSE, message=FALSE}
+```{r, echo=FALSE, message=FALSE, warning=FALSE}
 p <- "Nothing to plot"
 if (!is.null(cdrblast_path)) {
 df.s <- subset(df, variable == "map.rate")
@@ -400,7 +401,7 @@ Good-quality CDR3 sequence rate, the fraction of CDR3-containing reads/MIGs that
 
 > Note that while raw data is being filtered based on Phred quality score, consensus quality score (CQS, the ratio of major variant) is used for assembled data
 
-```{r, echo=FALSE, message=FALSE}
+```{r, echo=FALSE, message=FALSE, warning=FALSE}
 p <- "Nothing to plot"
 if (!is.null(cdrblast_path)) {
 df.s <- subset(df, variable == "qual.rate")
@@ -470,7 +471,7 @@ plotCdrFinal.2 <- function(dd) {
 
 Below is the plot of sample diversity, i.e. the number of clonotypes in a given sample
 
-```{r, echo=FALSE, message=FALSE}
+```{r, echo=FALSE, message=FALSE, warning=FALSE}
 p <- "Nothing to plot"
 if (!is.null(cdrfinal_path)) {
 df.1 <- data.frame(sample = df$sample, value = df$clones.count)
@@ -483,7 +484,7 @@ p
 
 Total number of molecules (MIGs) in final clonotype tables
 
-```{r, echo=FALSE, message=FALSE}
+```{r, echo=FALSE, message=FALSE, warning=FALSE}
 p <- "Nothing to plot"
 if (!is.null(cdrfinal_path)) {
 df.1 <- data.frame(sample = df$sample, value = df$migs.count)
@@ -498,7 +499,7 @@ Rate of hot-spot and singleton error filtering, in terms of clonotypes (**clone*
 
 > As clonotypes represented by a single MIG (singletons) have insufficient info to apply MiGEC-style error filtering, a simple frequency-based filtering is used for them.
 
-```{r, echo=FALSE, message=FALSE}
+```{r, echo=FALSE, message=FALSE, warning=FALSE}
 p <- "Nothing to plot"
 if (!is.null(cdrfinal_path)) {
 df.2 <- data.frame(sample = df$sample, mig = df$migs.filter.rate, clone = df$clones.filter.rate)
@@ -512,12 +513,12 @@ p
 
 Rate of non-coding CDR3 sequences, in terms of clonotypes (**clone** panel) and MIGs (**mig** panel)
 
-```{r, echo=FALSE, message=FALSE}
+```{r, echo=FALSE, message=FALSE, warning=FALSE}
 p <- "Nothing to plot"
 if (!is.null(cdrfinal_path)) {
 df.2 <- data.frame(sample = df$sample, mig = df$migs.nc.rate, clone = df$clones.nc.rate)
 df.2 <- melt(df.2)
 p<-plotCdrFinal.2(df.2)
 }
 p
-```
+```