Commit 2c44ab63 authored by Venkat Malladi's avatar Venkat Malladi
Browse files

Add in MCF-7 E2 analysis.

parent bcc6953b
......@@ -129,7 +129,7 @@ seqlevels(all_sn_tx,force=TRUE) <- c("chr1","chr2","chr3","chr4","chr5","chr6","
```
```{r alignments}
```{r alignments Basal}
MLK_RNA1 <- "/Volumes/project/GCRB/Lee_Lab/s163035/DK_RIP-seq/PARP1_RNAseq_in_AC16_MCF7_withTNFa_E2/raw/Sample_MLK_RNA1/align-star-se.sh-1.0.0/MLK_RNA1_AGTCAA_L008_R1.rDNA.filtered.fastq.gz_filtered_chrMAligned.sortedByCoord.out.bam"
MLK_RNA2 <- "/Volumes/project/GCRB/Lee_Lab/s163035/DK_RIP-seq/PARP1_RNAseq_in_AC16_MCF7_withTNFa_E2/raw/Sample_MLK_RNA2/align-star-se.sh-1.0.0/MLK_RNA2_GTCCGC_L008_R1.rDNA.filtered.fastq.gz_filtered_chrMAligned.sortedByCoord.out.bam"
......@@ -146,7 +146,7 @@ MPK_RIP_PARP1 <- "/Volumes/project/GCRB/Lee_Lab/s163035/DK_RIP-seq/PARP1_RIPseq_
MPK_RIP_PARP2 <- "/Volumes/project/GCRB/Lee_Lab/s163035/DK_RIP-seq/PARP1_RIPseq_in_AC16_MCF7_withTNFa_E2/raw/Sample_MPK_RIP2_PARP1/align-star-se.sh-2.0.0/MPK_RIP2_PARP1_ATGAGC_L008_R1.rDNA.filtered.fastq.gz_filtered_chrMAligned.sortedByCoord.out.bam"
```
```{r counts}
```{r counts Basal}
MLK_RNA1_counts_ref <- CountRefseq(ref_tx, MLK_RNA1, all_sn_tx, removeSNORNA=TRUE)
MLK_RNA2_counts_ref <- CountRefseq(ref_tx, MLK_RNA2, all_sn_tx, removeSNORNA=TRUE)
......@@ -200,7 +200,7 @@ MPK_RIP_PARP2_counts_sno <- CountSNRNA(sno_tx, MLK_RIP_PARP2)
# RPKM Cutoff
``` {r rpkm}
``` {r rpkm Basal}
MLK_RNA_counts_ref <- MLK_RNA1_counts_ref$counts + MLK_RNA2_counts_ref$counts
MLK_RNA_lib_ref <- MLK_RNA1_counts_ref$lib + MLK_RNA2_counts_ref$lib
MLK_RNA_ref_d <- DGEList(counts=as.matrix(MLK_RNA_counts_ref), lib.size=MLK_RNA_lib_ref)
......@@ -410,7 +410,7 @@ gencode_sn_mapping <-rbind(sno_mapping,sn_mapping)
sn_inx <- match(allsnotx_rpkm$tx_id, gencode_sn_mapping$V2)
allsnotx_rpkm$tx_name <- as.character(gencode_sn_mapping[sn_inx,"V4"])
allsnotx_rpkm$gene_name <- as.character(gencode_sn_mapping[sn_inx,"V3"])
write.table(allsnotx_rpkm, file="cf-7-basal-snRNA_RPKM_1_FC_2.tsv", quote=F, sep="\t", row.names=F, col.names=T)
write.table(allsnotx_rpkm, file="mcf-7-basal-snRNA_RPKM_1_FC_2.tsv", quote=F, sep="\t", row.names=F, col.names=T)
# Compare PARP-1 KD to normal PARP-1 levels
......@@ -455,3 +455,263 @@ dev.off()
wilcox.test(MPK_enrichment[,1], MPK_enrichment[,2],paired=T)
```
```{r alignments Estrogen}
```
```{r counts Estrogen}
MLKE_RNA1_counts_ref <- CountRefseq(ref_tx, MLKE_RNA1, all_sn_tx, removeSNORNA=TRUE)
MLKE_RNA2_counts_ref <- CountRefseq(ref_tx, MLKE_RNA2, all_sn_tx, removeSNORNA=TRUE)
MLKE_RNA1_counts_lnc <- CountRefseq(lnc_tx, MLKE_RNA1, all_sn_tx, removeSNORNA=TRUE)
MLKE_RNA2_counts_lnc <- CountRefseq(lnc_tx, MLKE_RNA2, all_sn_tx, removeSNORNA=TRUE)
MLKE_RNA1_counts_sn <- CountSNRNA(sn_tx, MLKE_RNA1)
MLKE_RNA2_counts_sn <- CountSNRNA(sn_tx, MLKE_RNA2)
MLKE_RNA1_counts_sno <- CountSNRNA(sno_tx, MLKE_RNA1)
MLKE_RNA2_counts_sno <- CountSNRNA(sno_tx, MLKE_RNA2)
MLKE_RIP_PI1_counts_ref <- CountRefseq(ref_tx, MLKE_RIP_PI1, all_sn_tx, removeSNORNA=TRUE)
MLKE_RIP_PI2_counts_ref <- CountRefseq(ref_tx, MLKE_RIP_PI2, all_sn_tx, removeSNORNA=TRUE)
MLKE_RIP_PI1_counts_lnc <- CountRefseq(lnc_tx, MLKE_RIP_PI1, all_sn_tx, removeSNORNA=TRUE)
MLKE_RIP_PI2_counts_lnc <- CountRefseq(lnc_tx, MLKE_RIP_PI2, all_sn_tx, removeSNORNA=TRUE)
MLKE_RIP_PI1_counts_sn <- CountSNRNA(sn_tx, MLKE_RIP_PI1)
MLKE_RIP_PI2_counts_sn <- CountSNRNA(sn_tx, MLKE_RIP_PI2)
MLKE_RIP_PI1_counts_sno <- CountSNRNA(sno_tx, MLKE_RIP_PI1)
MLKE_RIP_PI2_counts_sno <- CountSNRNA(sno_tx, MLKE_RIP_PI2)
MLKE_RIP_PARP1_counts_ref <- CountRefseq(ref_tx, MLKE_RIP_PARP1, all_sn_tx, removeSNORNA=TRUE)
MLKE_RIP_PARP2_counts_ref <- CountRefseq(ref_tx, MLKE_RIP_PARP2, all_sn_tx, removeSNORNA=TRUE)
MLKE_RIP_PARP1_counts_lnc <- CountRefseq(lnc_tx, MLKE_RIP_PARP1, all_sn_tx, removeSNORNA=TRUE)
MLKE_RIP_PARP2_counts_lnc <- CountRefseq(lnc_tx, MLKE_RIP_PARP2, all_sn_tx, removeSNORNA=TRUE)
MLKE_RIP_PARP1_counts_sn <- CountSNRNA(sn_tx, MLKE_RIP_PARP1)
MLKE_RIP_PARP2_counts_sn <- CountSNRNA(sn_tx, MLKE_RIP_PARP2)
MLKE_RIP_PARP1_counts_sno <- CountSNRNA(sno_tx, MLKE_RIP_PARP1)
MLKE_RIP_PARP2_counts_sno <- CountSNRNA(sno_tx, MLKE_RIP_PARP2)
```
# RPKM Cutoff
``` {r rpkm Estrogen}
MLKE_RNA_counts_ref <- MLKE_RNA1_counts_ref$counts + MLKE_RNA2_counts_ref$counts
MLKE_RNA_lib_ref <- MLKE_RNA1_counts_ref$lib + MLKE_RNA2_counts_ref$lib
MLKE_RNA_ref_d <- DGEList(counts=as.matrix(MLKE_RNA_counts_ref), lib.size=MLKE_RNA_lib_ref)
MLKE_RNA_ref_rpkm <- data.frame(rpkm(MLKE_RNA_ref_d,width(ref_tx)))
mlke_pc_rpkm <- ref_tx[MLKE_RNA_ref_rpkm>=1]
NROW(unique(unlist(mcols(mlke_pc_rpkm)$tx_name)))
NROW(unique(unlist(mcols(mlke_pc_rpkm)$gene_name)))
MLKE_RIP_PARP_counts_ref <- MLKE_RIP_PARP1_counts_ref$counts + MLKE_RIP_PARP2_counts_ref$counts
MLKE_RIP_PARP_lib_ref <- MLKE_RIP_PARP1_counts_ref$lib + MLKE_RIP_PARP2_counts_ref$lib
MLKE_RIP_PI_counts_ref <- MLKE_RIP_PI1_counts_ref$counts + MLKE_RIP_PI2_counts_ref$counts
MLKE_RIP_PI_lib_ref <- MLKE_RIP_PI1_counts_ref$lib + MLKE_RIP_PI1_counts_ref$lib
MLKE_RIP_PI_d <- DGEList(counts=as.matrix(MLKE_RIP_PI_counts_ref), lib.size=MLKE_RIP_PI_lib_ref)
MLKE_RIP_PI_rpkm <- data.frame(rpkm(MLKE_RIP_PI_d,width(ref_tx)))
MLKE_RIP_PARP_d <- DGEList(counts=as.matrix(MLKE_RIP_PARP_counts_ref), lib.size=MLKE_RIP_PARP_lib_ref)
MLKE_RIP_PARP_rpkm <- data.frame(rpkm(MLKE_RIP_PARP_d,width(ref_tx)))
MLKE_RIP_FC <- data.frame((MLKE_RIP_PARP_rpkm+1)/(MLKE_RIP_PI_rpkm+1))
mlke_pc_rpkm_fc <- ref_tx[MLKE_RNA_ref_rpkm>=1 & MLKE_RIP_FC>=2 ]
NROW(unique(unlist(mcols(mlke_pc_rpkm_fc)$tx_name)))
NROW(unique(unlist(mcols(mlke_pc_rpkm_fc)$gene_name)))
pc_ratio <- NROW(unique(unlist(mcols(mlke_pc_rpkm_fc)$gene_name)))/NROW(unique(unlist(mcols(mlke_pc_rpkm)$gene_name)))
MLKE_RNA_counts_lnc <- MLKE_RNA1_counts_lnc$counts + MLKE_RNA2_counts_lnc$counts
MLKE_RNA_lib_lnc <- MLKE_RNA1_counts_lnc$lib + MLKE_RNA2_counts_lnc$lib
MLKE_RNA_lnc_d <- DGEList(counts=as.matrix(MLKE_RNA_counts_lnc), lib.size=MLKE_RNA_lib_lnc)
MLKE_RNA_lnc_rpkm <- data.frame(rpkm(MLKE_RNA_lnc_d,width(lnc_tx)))
mlke_lnc_rpkm <- lnc_tx[MLKE_RNA_lnc_rpkm>=1]
NROW(unique(unlist(mcols(mlke_lnc_rpkm)$tx_name)))
NROW(unique(unlist(mcols(mlke_lnc_rpkm)$gene_id)))
MLKE_RIP_PARP_counts_lnc <- MLKE_RIP_PARP1_counts_lnc$counts + MLKE_RIP_PARP2_counts_lnc$counts
MLKE_RIP_PARP_lib_lnc<- MLKE_RIP_PARP1_counts_lnc$lib + MLKE_RIP_PARP2_counts_lnc$lib
MLKE_RIP_PI_counts_lnc <- MLKE_RIP_PI1_counts_lnc$counts + MLKE_RIP_PI2_counts_lnc$counts
MLKE_RIP_PI_lib_lnc <- MLKE_RIP_PI1_counts_lnc$lib + MLKE_RIP_PI1_counts_lnc$lib
MLKE_RIP_PI_d <- DGEList(counts=as.matrix(MLKE_RIP_PI_counts_lnc), lib.size=MLKE_RIP_PI_lib_lnc)
MLKE_RIP_PI_rpkm <- data.frame(rpkm(MLKE_RIP_PI_d,width(lnc_tx)))
MLKE_RIP_PARP_d <- DGEList(counts=as.matrix(MLKE_RIP_PARP_counts_lnc), lib.size=MLKE_RIP_PARP_lib_lnc)
MLKE_RIP_PARP_rpkm <- data.frame(rpkm(MLKE_RIP_PARP_d,width(lnc_tx)))
MLKE_RIP_FC <- data.frame((MLKE_RIP_PARP_rpkm+1)/(MLKE_RIP_PI_rpkm+1))
mlke_lnc_rpkm_fc <- lnc_tx[MLKE_RNA_lnc_rpkm>=1 & MLKE_RIP_FC>=2 ]
NROW(unique(unlist(mcols(mlke_lnc_rpkm_fc)$tx_name)))
NROW(unique(unlist(mcols(mlke_lnc_rpkm_fc)$gene_id)))
lnc_ratio <- NROW(unique(unlist(mcols(mlke_lnc_rpkm_fc)$gene_id)))/NROW(unique(unlist(mcols(mlke_lnc_rpkm)$gene_id)))
MLKE_RNA_counts_sno <- MLKE_RNA1_counts_sno$counts + MLKE_RNA2_counts_sno$counts
MLKE_RNA_lib_sno <- MLKE_RNA1_counts_sno$lib + MLKE_RNA1_counts_sno$lib
MLKE_RNA_sno_d <- DGEList(counts=as.matrix(MLKE_RNA_counts_sno), lib.size=MLKE_RNA_lib_sno)
MLKE_RNA_sno_rpkm <- data.frame(rpkm(MLKE_RNA_sno_d,width(sno_tx)))
mlke_sno_rpkm <- sno_tx[MLKE_RNA_sno_rpkm>=1]
NROW(unique(unlist(mcols(mlke_sno_rpkm)$tx_name)))
MLKE_RIP_PARP_counts_sno <- MLKE_RIP_PARP1_counts_sno$counts + MLKE_RIP_PARP2_counts_sno$counts
MLKE_RIP_PARP_lib_sno<- MLKE_RIP_PARP1_counts_sno$lib + MLKE_RIP_PARP2_counts_sno$lib
MLKE_RIP_PI_counts_sno <- MLKE_RIP_PI1_counts_sno$counts + MLKE_RIP_PI2_counts_sno$counts
MLKE_RIP_PI_lib_sno <- MLKE_RIP_PI1_counts_sno$lib + MLKE_RIP_PI1_counts_sno$lib
MLKE_RIP_PI_d <- DGEList(counts=as.matrix(MLKE_RIP_PI_counts_sno), lib.size=MLKE_RIP_PI_lib_sno)
MLKE_RIP_PI_rpkm <- data.frame(rpkm(MLKE_RIP_PI_d,width(sno_tx)))
MLKE_RIP_PARP_d <- DGEList(counts=as.matrix(MLKE_RIP_PARP_counts_sno), lib.size=MLKE_RIP_PARP_lib_sno)
MLKE_RIP_PARP_rpkm <- data.frame(rpkm(MLKE_RIP_PARP_d,width(sno_tx)))
MLKE_RIP_FC <- data.frame((MLKE_RIP_PARP_rpkm+1)/(MLKE_RIP_PI_rpkm+1))
mlke_sno_rpkm_fc <- sno_tx[MLKE_RNA_sno_rpkm>=1 & MLKE_RIP_FC>=2 ]
NROW(unique(unlist(mcols(mlke_sno_rpkm_fc)$tx_name)))
sno_ratio <- NROW(unique(unlist(mcols(mlke_sno_rpkm_fc)$tx_name)))/NROW(unique(unlist(mcols(mlke_sno_rpkm)$tx_name)))
MLKE_RIP_sno <- data.frame(MLKE_RIP_PI_rpkm,MLKE_RIP_PARP_rpkm)
colnames(MLKE_RIP_sno) <- c('PI', 'PARP1')
MLKE_RIP_sno_rpkm <- MLKE_RIP_sno[MLKE_RNA_sno_rpkm>=1 & MLKE_RIP_FC>=2,]
MLKE_RNA_counts_sn <- MLKE_RNA1_counts_sn$counts + MLKE_RNA2_counts_sn$counts
MLKE_RNA_lib_sn <- MLKE_RNA1_counts_sn$lib + MLKE_RNA1_counts_sn$lib
MLKE_RNA_sn_d <- DGEList(counts=as.matrix(MLKE_RNA_counts_sn), lib.size=MLKE_RNA_lib_sn)
MLKE_RNA_sn_rpkm <- data.frame(rpkm(MLKE_RNA_sn_d,width(sn_tx)))
mlke_sn_rpkm <- sn_tx[MLKE_RNA_sn_rpkm>=1]
NROW(unique(unlist(mcols(mlke_sn_rpkm)$tx_name)))
MLKE_RIP_PARP_counts_sn <- MLKE_RIP_PARP1_counts_sn$counts + MLKE_RIP_PARP2_counts_sn$counts
MLKE_RIP_PARP_lib_sn<- MLKE_RIP_PARP1_counts_sn$lib + MLKE_RIP_PARP2_counts_sn$lib
MLKE_RIP_PI_counts_sn <- MLKE_RIP_PI1_counts_sn$counts + MLKE_RIP_PI2_counts_sn$counts
MLKE_RIP_PI_lib_sn <- MLKE_RIP_PI1_counts_sn$lib + MLKE_RIP_PI1_counts_sn$lib
MLKE_RIP_PI_d <- DGEList(counts=as.matrix(MLKE_RIP_PI_counts_sn), lib.size=MLKE_RIP_PI_lib_sn)
MLKE_RIP_PI_rpkm <- data.frame(rpkm(MLKE_RIP_PI_d,width(sn_tx)))
MLKE_RIP_PARP_d <- DGEList(counts=as.matrix(MLKE_RIP_PARP_counts_sn), lib.size=MLKE_RIP_PARP_lib_sn)
MLKE_RIP_PARP_rpkm <- data.frame(rpkm(MLKE_RIP_PARP_d,width(sn_tx)))
MLKE_RIP_FC <- data.frame((MLKE_RIP_PARP_rpkm+1)/(MLKE_RIP_PI_rpkm+1))
mlke_sn_rpkm_fc <- sn_tx[MLKE_RNA_sn_rpkm>=1 & MLKE_RIP_FC>=2 ]
NROW(unique(unlist(mcols(mlke_sn_rpkm_fc)$tx_name)))
sn_ratio <- NROW(unique(unlist(mcols(mlke_sn_rpkm_fc)$tx_name)))/NROW(unique(unlist(mcols(mlke_sn_rpkm)$tx_name)))
MLKE_RIP_sn <- data.frame(MLKE_RIP_PI_rpkm,MLKE_RIP_PARP_rpkm)
colnames(MLKE_RIP_sn) <- c('PI', 'PARP1')
MLKE_RIP_sn_rpkm <- MLKE_RIP_sn[MLKE_RNA_sn_rpkm>=1 & MLKE_RIP_FC>=2,]
mlke_allsno <- c(mlke_sno_rpkm_fc,mlke_sn_rpkm_fc)
mlke_allsno_rpkm <- rbind(MLKE_RIP_sno_rpkm,MLKE_RIP_sn_rpkm)
# bar plot figure (B)
# Grouped Bar Plot
jpeg('barchart-mcf-7-e2-species.jpg')
ratios <- c(pc_ratio,lnc_ratio,sno_ratio,sn_ratio)
barplot(ratios, main="SNORNA MCF-7 E2", col=c("red","black", "dimgrey", "lightgrey"),ylim=c(0,.5))
dev.off()
boundTesting <-matrix(c(519,5882,170,260),nrow = 2,dimnames = list(Guess = c("bound", "unbound"),Truth = c("mRNA", "snoRNA")))
fisher.test(boundTesting)
# Boxplot of Preimmune vs PARP-1 (C)
jpeg('boxplot-mcf-7-e2-species.jpg')
boxplot(MLKE_RIP_sno_rpkm,col=(c("orange","blue")),outline=FALSE,ylim = c(0,300),yaxt="n", cex.axis=1,las=2,lwd=4,lty=1)
axis(2, at=seq(0,300,100))
dev.off()
wilcox.test(MLKE_RIP_sno_rpkm[,1], MLKE_RIP_sno_rpkm[,2],paired=T)
# Get Categories of snoRNA
mlke_gr_snotx <- data.frame(seqnames=seqnames(mlke_sno_rpkm),
starts=start(mlke_sno_rpkm)-1,
ends=end(mlke_sno_rpkm),
strand=strand(mlke_sno_rpkm),
tx_name = elementMetadata(mlke_sno_rpkm)$tx_name,
gene_id = unlist(elementMetadata(mlke_sno_rpkm)$gene_id))
sno_annotations <- read.table('RNA_small_nucleolar.txt',header = TRUE, sep = "\t")
sno_inx <- match(matrix(unlist(strsplit(as.character(mlke_gr_snotx$gene_id),split='.',fixed=T)),ncol=2,byrow=T)[,1], sno_annotations$ensembl_gene_id)
mlke_gr_snotx$symbol <- as.character(sno_annotations[sno_inx,"symbol"])
mlke_gr_snotx$gene_family <- as.character(sno_annotations[sno_inx,"gene_family"])
mlke_gr_snotx$gene_family[mlke_gr_snotx$gene_family == "Small nucleolar RNAs, H/ACA box"] <- "H/ACA box"
mlke_gr_snotx$gene_family[mlke_gr_snotx$gene_family == "Small nucleolar RNAs, C/D box"] <- "C/D box"
mlke_gr_snotx$gene_family[mlke_gr_snotx$gene_family == "Small Cajal body-specific RNAs"] <- "scaRNA"
mlke_gr_snotx$gene_family[mlke_gr_snotx$gene_family == ""] <- "Other"
mlke_gr_snotx$gene_family[is.na(mlke_gr_snotx$gene_family)] <- "Other"
ha_rna <- dim(mlke_gr_snotx[mlke_gr_snotx$gene_family == "H/ACA box",])[1]
cd_rna <- dim(mlke_gr_snotx[mlke_gr_snotx$gene_family == "C/D box",])[1]
sc_rna <- dim(mlke_gr_snotx[mlke_gr_snotx$gene_family == "scaRNA",])[1]
dat = data.frame(count=c(ha_rna, cd_rna, sc_rna), category=c("H/ACA box", "C/D box", "scaRNA"))
dat$fraction = dat$count / sum(dat$count)
dat$ymax = cumsum(dat$fraction)
dat$ymin = c(0, head(dat$ymax, n=-1))
dat$category <- factor(dat$category, levels = c("H/ACA box", "C/D box", "scaRNA"))
# (E)
jpeg('piechart-mcf-7-e2-species.jpg')
ggplot(dat, aes(fill=category, ymax=ymax, ymin=ymin, xmax=4, xmin=2)) +
geom_rect(fill=c('darkorchid1', "darkorange1","darkgreen")) +
coord_polar(theta="y") +
xlim(c(0, 4)) +
theme_bw() +
theme(panel.grid=element_blank()) +
theme(axis.text=element_blank()) +
theme(axis.ticks=element_blank())
dev.off()
mlke_gr_snotx <- data.frame(seqnames=seqnames(mlke_sno_rpkm_fc),
starts=start(mlke_sno_rpkm_fc)-1,
ends=end(mlke_sno_rpkm_fc),
strand=strand(mlke_sno_rpkm_fc),
tx_name = elementMetadata(mlke_sno_rpkm_fc)$tx_name,
gene_id = unlist(elementMetadata(mlke_sno_rpkm_fc)$gene_id))
sno_inx <- match(matrix(unlist(strsplit(as.character(mlke_gr_snotx$gene_id),split='.',fixed=T)),ncol=2,byrow=T)[,1], sno_annotations$ensembl_gene_id)
mlke_gr_snotx$symbol <- as.character(sno_annotations[sno_inx,"symbol"])
mlke_gr_snotx$gene_family <- as.character(sno_annotations[sno_inx,"gene_family"])
mlke_gr_snotx$gene_family[mlke_gr_snotx$gene_family == "Small nucleolar RNAs, H/ACA box"] <- "H/ACA box"
mlke_gr_snotx$gene_family[mlke_gr_snotx$gene_family == "Small nucleolar RNAs, C/D box"] <- "C/D box"
mlke_gr_snotx$gene_family[mlke_gr_snotx$gene_family == "Small Cajal body-specific RNAs"] <- "scaRNA"
mlke_gr_snotx$gene_family[mlke_gr_snotx$gene_family == ""] <- "Other"
mlke_gr_snotx$gene_family[is.na(mlke_gr_snotx$gene_family)] <- "Other"
ha_rip <- dim(mlke_gr_snotx[mlke_gr_snotx$gene_family == "H/ACA box",])[1]
cd_rip <- dim(mlke_gr_snotx[mlke_gr_snotx$gene_family == "C/D box",])[1]
sc_rip<- dim(mlke_gr_snotx[mlke_gr_snotx$gene_family == "scaRNA",])[1]
# bar plot figure (F)
# Bar plot
jpeg('barchart-mcf-7-e2-species_snospecies.jpg')
ratios <- c(sn_ratio,ha_rip/ha_rna,cd_rip/cd_rna,sc_rip/sc_rna)
barplot(ratios, main="snoRNA species MCF-7 E2", col=c('pink1','darkorchid1', "darkorange1","darkgreen"),ylim=c(0,1))
dev.off()
typeTesting <-matrix(c(56,22,32,82),nrow = 2,dimnames = list(Guess = c("bound", "unbound"),Truth = c("HA", "CD")))
fisher.test(typeTesting)
# Combine snRNA and snoRNA and print out
allsnotx_e2 <- data.frame(seqnames=seqnames(mlke_allsno),
starts=start(mlke_allsno)-1,
ends=end(mlke_allsno),
strand=strand(mlke_allsno),
tx_id = elementMetadata(mlke_allsno)$tx_name,
gene_id = unlist(elementMetadata(mlke_allsno)$gene_id))
allsnotx_e2_rpkm <- cbind(allsnotx_e2,mlke_allsno_rpkm)
sno_mapping <- read.csv("./gencode.v19.annotation_snoRNA_mapping.txt", header=F, sep=',')
sn_mapping <- read.csv("./gencode.v19.annotation_snRNA_mapping.txt", header=F, sep=',')
gencode_sn_mapping <-rbind(sno_mapping,sn_mapping)
sn_inx <- match(allsnotx_e2_rpkm$tx_id, gencode_sn_mapping$V2)
allsnotx_e2_rpkm$tx_name <- as.character(gencode_sn_mapping[sn_inx,"V4"])
allsnotx_e2_rpkm$gene_name <- as.character(gencode_sn_mapping[sn_inx,"V3"])
write.table(allsnotx_e2_rpkm, file="mcf-7-e2-snRNA_RPKM_1_FC_2.tsv", quote=F, sep="\t", row.names=F, col.names=T)
```
No preview for this file type
No preview for this file type
This diff is collapsed.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment