Compare new and old peaks

Total

totalPeakUs=read.table("../data/phenotype/APApeak_Phenotype_GeneLocAnno.Total.fc", header = T, stringsAsFactors = F) %>% separate(chrom, sep = ":", into = c("chr", "start", "end", "id")) %>% separate(id, sep="_", into=c("gene", "loc", "strand", "peak"))

Warning: Expected 4 pieces. Additional pieces discarded in 4 rows [14735,
14736, 14737, 14738].

ind=colnames(totalPeakUs)[8:dim(totalPeakUs)[2]]
totalPeakUs_CountNum=read.table("../data/phenotype/APApeak_Phenotype_GeneLocAnno.Total.CountsOnlyNumeric", col.names = ind)


#numeric with anno
totalPeak=as.data.frame(cbind(totalPeakUs[,1:7], totalPeakUs_CountNum))

totalPeakUs_CountNum_mean=rowMeans(totalPeakUs_CountNum)

#append mean to anno
TotalPeakUSMean=as.data.frame(cbind(totalPeakUs[,1:7],mean=totalPeakUs_CountNum_mean))

uniqnewPasnum=uniqnew  %>% separate(ID ,into=c("peaknum", "geneloc"),sep=":") %>% mutate(peak=paste("peak", peaknum, sep="")) %>% select(peak)

Filter these inthe mean usage:

TotalPeakUSMeanClass= TotalPeakUSMean %>% mutate(New=ifelse(peak %in% uniqnewPasnum$peak,"new", "original")) %>% mutate(Cutoff=ifelse(mean>=.05, "Yes", "No"))

mean(TotalPeakUSMean$mean)

[1] 0.2378282

Plot:

ggplot(TotalPeakUSMeanClass, aes(y=mean,x=New)) + geom_violin() + geom_hline(yintercept = mean(TotalPeakUSMean$mean), col="red") +  geom_hline(yintercept = .05, col="Blue")

Past versions of unnamed-chunk-6-1.png

TotalPeakUSMeanClass_newonly= TotalPeakUSMeanClass %>% filter(New=="new")

ggplot(TotalPeakUSMeanClass_newonly, aes(y=mean, x="")) + geom_violin() + geom_hline(yintercept = mean(TotalPeakUSMean$mean), col="red") +  geom_hline(yintercept = .05, col="Blue") + labs(x="", y="Mean Usage", title="Mean Usage of New PAS")

Past versions of unnamed-chunk-7-1.png

ggplot(TotalPeakUSMeanClass_newonly, aes(x=mean)) + geom_histogram(bins=50) + geom_vline(xintercept = mean(TotalPeakUSMean$mean), col="red")

Past versions of unnamed-chunk-8-1.png

This shows me the new peaks are the peaks that barely passed the cuttoff before.

write out file with information about new and old peaks

Peak_newOld=TotalPeakUSMeanClass %>% select(-mean)
write.table(Peak_newOld, file="../data/peaks_5perc/NewVOldPeaks.txt", col.names = T, row.names = F, quote=F)

Total:

First I will upload the usage dataframe.

totCounts=read.table("../data/phenotype/APApeak_Phenotype_GeneLocAnno.Total.fc", stringsAsFactors = F, header = T)
ind=colnames(totCounts)[2:55]
totUsage=read.table("../data/phenotype/APApeak_Phenotype_GeneLocAnno.Total.CountsOnlyNumeric", stringsAsFactors = F, header = F,col.names = ind)



batch1.2.3=read.table("../data/MetaDataSequencing.txt", header=T,stringsAsFactors = F)%>% filter(fraction=="total") %>%  select(line, batch) %>% filter(batch != 4)
oldind=batch1.2.3$line

batch4=read.table("../data/MetaDataSequencing.txt", header=T,stringsAsFactors = F)%>% filter(fraction=="total") %>%  select(line, batch) %>% filter(batch == 4)

newInd=batch4$line

UsageHist= function(indVec,title,totUsage=totUsage){
  totUsage_ind=totUsage %>% select(indVec)
  meanVec=rowMeans(totUsage_ind)
  hist(meanVec, main=title,xlab="Mean Usage")
}

RUn this for different itterations of individuals:

Pick 15 random individuals from old:

sampl1=sample(oldind, 15)
sampl2=sample(oldind, 15)
sampl3=sample(oldind, 15)
sampl4=sample(oldind, 15)

png("../output/newtot.png")
par(mfrow=c(3,2))
UsageHist(indVec=newInd,title="Total Usage New (15ind)",totUsage=totUsage)
UsageHist(indVec=oldind,title="Total Usage Old (39 ind)",totUsage=totUsage)
UsageHist(indVec=sampl1,title="Total Usage Sample 15 Old",totUsage=totUsage)
UsageHist(indVec=sampl2,title="Total Usage Sample 15 Old",totUsage=totUsage)
UsageHist(indVec=sampl3,title="Total Usage Sample 15 Old",totUsage=totUsage)
UsageHist(indVec=sampl4,title="Total Usage Sample 15 Old",totUsage=totUsage)
dev.off()

png 
  2 

Nuclear

nucCounts=read.table("../data/phenotype/APApeak_Phenotype_GeneLocAnno.Nuclear.fc", stringsAsFactors = F, header = T)
ind=colnames(nucCounts)[2:55]
nucUsage=read.table("../data/phenotype/APApeak_Phenotype_GeneLocAnno.Nuclear.CountsOnlyNumeric", stringsAsFactors = F, header = F,col.names = ind)

UsageHist_nuc= function(indVec,title,nucUsage=nucUsage){
  nucUsage_ind=nucUsage %>% select(indVec)
  meanVec=rowMeans(nucUsage_ind)
  hist(meanVec, main=title,xlab="Mean Usage")
}

png("../output/newnuc.png")
par(mfrow=c(3,2))
UsageHist_nuc(indVec=newInd,title="Nuclear Usage New (15ind)",nucUsage=nucUsage)
UsageHist_nuc(indVec=oldind,title="Nuclear Usage Old (39ind)",nucUsage=nucUsage)
UsageHist_nuc(indVec=sampl1,title="Nuclear Usage Sample 15 Old",nucUsage=nucUsage)
UsageHist_nuc(indVec=sampl2,title="Nuclear Usage Sample 15 Old",nucUsage=nucUsage)
UsageHist_nuc(indVec=sampl3,title="Nuclear Usage Sample 15 Old",nucUsage=nucUsage)
UsageHist_nuc(indVec=sampl4,title="Nuclear Usage Sample 15 Old",nucUsage=nucUsage)
dev.off()

png 
  2 

Old

oldtotalCount=read.table("../../threeprimeseq/data/phenotypes_filtPeakTranscript_noMP_GeneLocAnno/filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Total.fixed.pheno.fc",header=T,stringsAsFactors = F)
indOld=colnames(oldtotalCount)[2:56]
oldtotalUsage=read.table("../../threeprimeseq/data/phenotypes_filtPeakTranscript_noMP_GeneLocAnno/filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Total.fixed.pheno.CountsOnlyNumeric.txt",col.names = indOld,stringsAsFactors = F)

png("../output/oldtot.png")
par(mfrow=c(3,2))
UsageHist(indVec=newInd,title="Old total Usage (15ind)",totUsage=oldtotalUsage)
UsageHist(indVec=oldind,title="Old total Usage (39ind)",totUsage=oldtotalUsage)
UsageHist(indVec=sampl1,title="Old total Usage sample 15 ind",totUsage=oldtotalUsage)
UsageHist(indVec=sampl2,title="Old total Usage sample 15 ind",totUsage=oldtotalUsage)
UsageHist(indVec=sampl3,title="Old total Usage sample 15 ind",totUsage=oldtotalUsage)
UsageHist(indVec=sampl4,title="Old total Usage sample 15 ind",totUsage=oldtotalUsage)
dev.off()

png 
  2 

oldnuclearCount=read.table("../../threeprimeseq/data/phenotypes_filtPeakTranscript_noMP_GeneLocAnno/filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Nuclear.fixed.pheno.fc",header=T,stringsAsFactors = F)
indOldN=colnames(oldnuclearCount)[2:56]
oldnuclearUsage=read.table("../../threeprimeseq/data/phenotypes_filtPeakTranscript_noMP_GeneLocAnno/filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Nuclear.fixed.pheno.CountsOnlyNumeric.txt",col.names = indOldN,stringsAsFactors = F)

png("../output/oldnuc.png")
par(mfrow=c(3,2))
UsageHist_nuc(indVec=newInd,title="Old nuclear Usage (15ind)",nucUsage=oldnuclearUsage)
UsageHist_nuc(indVec=oldind,title="Old nuclear Usage (39ind)",nucUsage=oldnuclearUsage)
UsageHist_nuc(indVec=sampl1,title="Old nuclear Usage sample 15 ind",nucUsage=oldnuclearUsage)
UsageHist_nuc(indVec=sampl2,title="Old nuclear Usage sample 15 ind",nucUsage=oldnuclearUsage)
UsageHist_nuc(indVec=sampl3,title="Old nuclear Usage sample 15 ind",nucUsage=oldnuclearUsage)
UsageHist_nuc(indVec=sampl4,title="Old nuclear Usage sample 15 ind",nucUsage=oldnuclearUsage)
dev.off()

png 
  2 

Total

totalPeak_inNew=totalPeak %>% filter(peak %in% uniqnewPasnum$peak)

totalPeak_inNew_melt=melt(totalPeak_inNew,id.vars=c("chr", "start","end", "gene","loc", "peak","strand"),value.name = "Usage" ,variable.name = "Ind") %>% mutate(New15=ifelse(Ind %in% batch4$line, "Yes", "No"))


ggplot(totalPeak_inNew_melt, aes(x=New15, y=Usage, fill=New15))+geom_boxplot(width=.5) + theme(legend.position = "none") + labs(x="Individuals in New batch")

Look if means are different:

totalPeak_inNew_meltGroup=totalPeak_inNew_melt %>% group_by(New15,peak) %>% summarise(meanUsage=mean(Usage))

ggplot(totalPeak_inNew_meltGroup, aes(x=New15, y=meanUsage, fill=New15))+geom_boxplot(width=.5) + theme(legend.position = "none") + labs(x="Individuals in New batch", y="Mean Usage in Group", title="Mean usage for new PAS in 39 ind v new 15")

ggplot(totalPeak_inNew_meltGroup, aes(x=meanUsage, group=New15, fill=New15))+geom_density(alpha=.3)  + labs( x="Mean Usage in Group", title="Mean usage for new PAS in 39 ind v new 15")+ scale_fill_discrete(name = "Ind in new 15")

Session information

sessionInfo()

R version 3.5.1 (2018-07-02)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Scientific Linux 7.4 (Nitrogen)

Matrix products: default
BLAS/LAPACK: /software/openblas-0.2.19-el7-x86_64/lib/libopenblas_haswellp-r0.2.19.so

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
 [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
 [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
 [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
 [9] LC_ADDRESS=C               LC_TELEPHONE=C            
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] workflowr_1.3.0 forcats_0.3.0   stringr_1.3.1   dplyr_0.8.0.1  
 [5] purrr_0.3.2     readr_1.3.1     tidyr_0.8.3     tibble_2.1.1   
 [9] ggplot2_3.1.0   tidyverse_1.2.1 reshape2_1.4.3 

loaded via a namespace (and not attached):
 [1] Rcpp_1.0.0       cellranger_1.1.0 compiler_3.5.1   pillar_1.3.1    
 [5] git2r_0.23.0     plyr_1.8.4       tools_3.5.1      digest_0.6.18   
 [9] lubridate_1.7.4  jsonlite_1.6     evaluate_0.12    nlme_3.1-137    
[13] gtable_0.2.0     lattice_0.20-38  pkgconfig_2.0.2  rlang_0.3.1     
[17] cli_1.0.1        rstudioapi_0.10  yaml_2.2.0       haven_1.1.2     
[21] withr_2.1.2      xml2_1.2.0       httr_1.3.1       knitr_1.20      
[25] hms_0.4.2        generics_0.0.2   fs_1.2.6         rprojroot_1.3-2 
[29] grid_3.5.1       tidyselect_0.2.5 glue_1.3.0       R6_2.3.0        
[33] readxl_1.1.0     rmarkdown_1.10   modelr_0.1.2     magrittr_1.5    
[37] whisker_0.3-2    backports_1.1.2  scales_1.0.0     htmltools_0.3.6 
[41] rvest_0.3.2      assertthat_0.2.0 colorspace_1.3-2 labeling_0.3    
[45] stringi_1.2.4    lazyeval_0.2.1   munsell_0.5.0    broom_0.5.1     
[49] crayon_1.3.4