bulk_oct23

1 Functions

2 Data

gsub(x = names(my_data),pattern = "_C",replacement = "_ctrl")%>% gsub(pattern = "p_OR",replacement = "_osiRoxaPersistors") %>% gsub(pattern = "p_O",replacement = "_osiPersistors") %>% gsub(pattern = "_R",replacement = "_roxa")%>% gsub(,pattern = "_O",replacement = "_osi")

 [1] "H1975_ctrl1"              "H1975_ctrl2"              "H1975_ctrl3"              "H1975_roxa1"              "H1975_roxa2"             
 [6] "H1975_roxa3"              "H1975_osi1"               "H1975_osi2"               "H1975_osi3"               "H1975_osiPersistors1"    
[11] "H1975_osiPersistors2"     "H1975_osiPersistors3"     "H1975_osiRoxaPersistors1" "H1975_osiRoxaPersistors2" "H1975_osiRoxaPersistors3"
[16] "HCC827_ctrl1"             "HCC827_ctrl2"             "HCC827_ctrl3"             "HCC827_roxa1"             "HCC827_roxa2"            
[21] "HCC827_roxa3"             "HCC827_osi1"              "HCC827_osi2"              "HCC827_osi3"              "M2_ctrl"                 
[26] "M21_ctrl"                 "M36_ctrl"                 "M14_osi"                  "M33_osi"                  "M14_2_osi"               
[31] "M20_roxa"                 "M30_roxa"                 "M31_roxa"                 "M3_combo"                 "M26_combo"               
[36] "M32_combo"               

cell.labels = names(my_data)
cell_type = str_extract(cell.labels, "^[A-Z]{1,3}[0-9]{3}")
condition = str_extract(cell.labels, "osiPersistors|osiRoxaPersistor|osi|ctrl|roxa")
condition = paste(cell_type,condition,sep = "_")
replicate = str_extract(cell.labels, ".$")
metadata = data.frame(cell_type = cell_type, condition = condition, replicate = replicate, row.names = colnames(counts))

library(DESeq2)
dds <- DESeqDataSetFromMatrix(countData = round(my_data),
                              colData = metadata,
                              design = ~condition)

converting counts to integer mode
Warning in DESeqDataSet(se, design = design, ignoreRank) :
  some variables in design formula are characters, converting to factors

nrow(dds)

[1] 32780

dds1 <- dds[ rowSums(counts(dds)) >= 3, ]
nrow(dds1)

[1] 9980

vst = vst(dds1, blind=FALSE)

-- note: fitType='parametric', but the dispersion trend was not well captured by the
   function: y = a/x + b, and a local regression fit was automatically substituted.
   specify fitType='local' or 'mean' to avoid this message next time.

library("ggfortify")
PCAdata <- prcomp(t(assay(vst)))
autoplot(PCAdata, data = metadata,colour = "condition",label = FALSE, main="PCA") # Show dots

autoplot(PCAdata, data = metadata,colour = "cell_type",label = FALSE, main="PCA") # Show dots

dds <- DESeq(dds)

estimating size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
-- note: fitType='parametric', but the dispersion trend was not well captured by the
   function: y = a/x + b, and a local regression fit was automatically substituted.
   specify fitType='local' or 'mean' to avoid this message next time.
final dispersion estimates
fitting model and testing

H1975_roxaVSctrl <- results(dds,contrast = c("condition","H197_roxa","H197_ctrl"))  %>% as.data.frame()

Error in h(simpleError(msg, call)) : 
  error in evaluating the argument 'x' in selecting a method for function 'as.data.frame': couldn't find results. you should first run DESeq()

down_genes

 [1] "TFPI2"      "PON2"       "CTGF"       "WISP2"      "CEACAM7"    "AFAP1L2"    "NANOS1"     "CREB3L2"    "BPGM"       "SKIL"       "AC006504.5"
[12] "AC006504.8"

hyp_obj <- hypeR(up_genes, genesets, test = "hypergeometric", fdr=1, plotting=F,background = rownames(H1975_cpVSop))
 hyp_dots(hyp_obj,size_by = "none",title = paste0("cluster",chosen_clusters))

hyp_obj <- hypeR(down_genes, genesets, test = "hypergeometric", fdr=1, plotting=F,background = rownames(H1975_cpVSop))
 hyp_dots(hyp_obj,size_by = "none",title = paste0("cluster",chosen_clusters))