go.DB 富集分析子集 go子集 offspring children多层次结构go

#####安装archr包##别处复制
.libPaths(c("/home/data/t040413/R/x86_64-pc-linux-gnu-library/4.2","/home/data/t040413/R/yll/usr/local/lib/R/site-library",  "/usr/local/lib/R/library",
            "/home/data/refdir/Rlib/",  "/home/data/t040413/R/x86_64-pc-linux-gnu-library/4.2", "/usr/local/lib/R/library"))

.libPaths()

print(getwd())
dir.create("/home/data/t040413/wpx/rna_protein")
setwd("/home/data/t040413/wpx/rna_protein")


#https://www.jianshu.com/p/4b19e7a9bbd3
#https://www.jianshu.com/p/3e5be5e75b20
#https://www.jianshu.com/p/52f462fdb950

#https://www.biostars.org/p/294268/

#https://www.biostars.org/p/287871/

if (F) {
  
  library(DOSE)
  #BiocManager::install("GOSemSim")
  library(GOSemSim)
  library(clusterProfiler)
  library(org.Hs.eg.db)
  # library(org.Mm.eg.db)
  library(org.Rn.eg.db)
  library(dplyr)
  library(GO.db)
  #
  get_GO_data <- function(OrgDb, ont, keytype) {
    GO_Env <- get_GO_Env()
    use_cached <- FALSE
    
    if (exists("organism", envir=GO_Env, inherits=FALSE) &&
        exists("keytype", envir=GO_Env, inherits=FALSE)) {
      
      org <- get("organism", envir=GO_Env)
      kt <- get("keytype", envir=GO_Env)
      
      if (org == DOSE:::get_organism(OrgDb) &&
          keytype == kt &&
          exists("goAnno", envir=GO_Env, inherits=FALSE)) {
        ## https://github.com/GuangchuangYu/clusterProfiler/issues/182
        ## && exists("GO2TERM", envir=GO_Env, inherits=FALSE)){
        
        use_cached <- TRUE
      }
    }
    
    if (use_cached) {
      goAnno <- get("goAnno", envir=GO_Env)
    } else {
      OrgDb <- GOSemSim:::load_OrgDb(OrgDb)
      kt <- keytypes(OrgDb)
      if (! keytype %in% kt) {
        stop("keytype is not supported...")
      }
      
      kk <- keys(OrgDb, keytype=keytype)
      goAnno <- suppressMessages(
        AnnotationDbi::select(OrgDb, keys=kk, keytype=keytype,
                              columns=c("GOALL", "ONTOLOGYALL")))
      
      goAnno <- unique(goAnno[!is.na(goAnno$GOALL), ])
      
      assign("goAnno", goAnno, envir=GO_Env)
      assign("keytype", keytype, envir=GO_Env)
      assign("organism", DOSE:::get_organism(OrgDb), envir=GO_Env)
    }
    
    if (ont == "ALL") {
      GO2GENE <- unique(goAnno[, c(2,1)])
    } else {
      GO2GENE <- unique(goAnno[goAnno$ONTOLOGYALL == ont, c(2,1)])
    }
    
    GO_DATA <- DOSE:::build_Anno(GO2GENE, get_GO2TERM_table())
    
    goOnt.df <- goAnno[, c("GOALL", "ONTOLOGYALL")] %>% unique
    goOnt <- goOnt.df[,2]
    names(goOnt) <- goOnt.df[,1]
    assign("GO2ONT", goOnt, envir=GO_DATA)
    return(GO_DATA)
  }
  
  get_GO_Env <- function () {
    if (!exists(".GO_clusterProfiler_Env", envir = .GlobalEnv)) {
      pos <- 1
      envir <- as.environment(pos)
      assign(".GO_clusterProfiler_Env", new.env(), envir=envir)
    }
    get(".GO_clusterProfiler_Env", envir = .GlobalEnv)
  }
  
  get_GO2TERM_table <- function() {
    GOTERM.df <- get_GOTERM()
    GOTERM.df[, c("go_id", "Term")] %>% unique
  }
  
  get_GOTERM <- function() {
    pos <- 1
    envir <- as.environment(pos)
    if (!exists(".GOTERM_Env", envir=envir)) {
      assign(".GOTERM_Env", new.env(), envir)
    }
    GOTERM_Env <- get(".GOTERM_Env", envir = envir)
    if (exists("GOTERM.df", envir = GOTERM_Env)) {
      GOTERM.df <- get("GOTERM.df", envir=GOTERM_Env)
    } else {
      GOTERM.df <- toTable(GOTERM)
      assign("GOTERM.df", GOTERM.df, envir = GOTERM_Env)
    }
    return(GOTERM.df)
  }
  

  print(getwd())
  dir.create("/home/data/t040413/wpx/rna_protein")
  setwd("/home/data/t040413/wpx/rna_protein")
  
  
}

library(GO.db)
ls("package:GO.db")


columns(GO.db)
GO_dbInfo()
GO_dbconn()
GO_dbfile()

# Find the children terms of the GO term "GO:0006412"
children_terms <- as.list(GOBPCHILDREN["GO:0006412"])
as.list(GOBPCHILDREN["GO:0006412"])
as.list(GOBPOFFSPRING["GO:0006412"])
if (F) {
  
  
  # Print the children terms
  print(children_terms)
  
  ## Bimap interface:
  # Convert the object to a list
  xx <- as.list(GOBPOFFSPRING)
  xx
  # Remove GO IDs that do not have any offspring
  xx <- xx[!is.na(xx)]
  if(length(xx) > 0){
    # Get the offspring GO IDs for the first two elents of xx
    goids <- xx[1:2]
  }
  
  
  ## Bimap interface:
  # Convert the object to a list
  xx <- as.list(GOBPANCESTOR)
  # Remove GO IDs that do not have any ancestor
  xx <- xx[!is.na(xx)]
  if(length(xx) > 0){
    # Get the ancestor GO IDs for the first two elents of xx
    goids <- xx[1:2]
  }
  goids
  
  
  # Convert the object to a list
  xx <- as.list(GOBPCHILDREN)
  # Remove GO IDs that do not have any children
  xx <- xx[!is.na(xx)]
  xx
  if(length(xx) > 0){
    # Get the parent GO IDs for the first elents of xx
    goids <- xx[[1]]
    # Find out the GO terms for the first parent goid
    GOID(GOTERM[[goids[1]]])
    Term(GOTERM[[goids[1]]])
    Synonym(GOTERM[[goids[1]]])
    Secondary(GOTERM[[goids[1]]])
    
    Definition(GOTERM[[goids[1]]])
    Ontology(GOTERM[[goids[1]]])
  }
  goids
  
}


myterm= c("GO:0007612")
union(as.list(GOBPOFFSPRING[myterm]) %>%unlist()   %>% unname(),  names(as.list(GOBPOFFSPRING[myterm])))

library(AnnotationDbi)
 k <- keys(GO.db, keytype = "GOID")[1:3]
 AnnotationDbi::select(GO.db,
         keys = k,
         columns = c("TERM","ONTOLOGY"),
         keytype="GOID")

 
 print(getwd())#----------------------------==========================================-==================================
 
load("/home/data/t040413/wpx/rna_protein/selected_go_terms.rds")
# go_file=list.files("~/wpx/wpx_transcriptomics_proteinomics_Metabolomics/transcriptomics/4_d28_vs_d14_treatment_effective_2",
#            full.names = TRUE,pattern = "GO_enrichment.xlsx") 
go_file=list.files(".",full.names = TRUE,pattern = "GO_enrichment.xlsx")[1]
a
rna_msc=openxlsx::read.xlsx(go_file)
head(rna_msc) 
rna_msc=rna_msc[grepl(rna_msc$Cluster,pattern="MSC-D28 VS LCT\\(14\\+28\\)-NT"),]
head(rna_msc)
rna_msc
rna_msc_id=rna_msc$ID
a 

if (F) {
  
  as.list(GOBPOFFSPRING[myterm]) %>%unlist()   %>% unname()
  as.list(GOBPOFFSPRING['GO:0016209']) %>%unlist()   %>% unname() 
  for (eachterm in a) {
    result <- try({
      try( as.list(GOBPOFFSPRING[eachterm]) %>% unlist() %>% unname() %>%print()  , silent = TRUE   ) |
        try(as.list(GOMFOFFSPRING[eachterm]) %>% unlist() %>% unname()%>%print(), silent = TRUE)
      
    }, silent = TRUE)
    print(paste0(eachterm,"-====================================================================="))
    
    
    # #  if (inherits(result, "try-error")) {
    #     cat("Error occurred for term:", eachterm, "\n")
    #   }
  }
  
  #grep(as.list(GOBPOFFSPRING) %>%unlist() %>%unname(),pattern("0016209"))
  rna_msc_match=list()
  if (F) {
    for (eachterm in a) {
      success <- TRUE
      
      tryCatch({
        target_terms <- union(as.list(GOBPOFFSPRING[eachterm]) %>% unlist() %>% unname(), names(as.list(GOBPOFFSPRING[eachterm])))
        rna_msc_match[[eachterm]] <- rna_msc[rna_msc_id %in% target_terms,]
        print(paste0(eachterm, "-========================GO============================================="))
      }, error = function(e) {#因为这是函数体内的函数 所以rna_msc_match与体外无关，如何改进呢
        cat("Error occurred for term:", eachterm, "\n")
        success <- FALSE
        print(paste(success,"-===="))
        
        
        if (!success) {
          target_terms <- union(as.list(GOMFOFFSPRING[eachterm]) %>% unlist() %>% unname(), names(as.list(GOMFOFFSPRING[eachterm])))
          rna_msc_match[[eachterm]] <- rna_msc[rna_msc_id %in% target_terms,]
          print(paste0(eachterm,100-1, "-===============================MF======================================"))
        }
        
        
      })
      
      
    }
    a
    names(rna_msc_match)
    
    
    
  }
  
}

colnames(GOBPOFFSPRING)
as.list(GOBPOFFSPRING)

rna_msc_match <- list()
i=1
for (eachterm in a) {
  # Check if GOBPOFFSPRING has the term, otherwise use GOMFOFFSPRING
  if ( eachterm %in% (union(as.list(GOBPOFFSPRING[[eachterm]]) %>% unlist() %>% unname(), eachterm)) ) {
    target_terms <- union(as.list(GOBPOFFSPRING[[eachterm]]) %>% unlist() %>% unname(), eachterm)
    print(paste0(eachterm,"___第几个：：",i, "-========================GO============================================="))
  } else {
    target_terms <- union(as.list(GOMFOFFSPRING[[eachterm]]) %>% unlist() %>% unname(), eachterm)
    print(paste0(eachterm,"___第几个：：",i, "-========================MF============================================="))
  }
  
  # Filter rna_msc based on target_terms
  rna_msc_match[[eachterm]] <- rna_msc[rna_msc_id %in% target_terms,]
  
 i=i+1
}
a
rna_msc_match %>%names()
rna_msc_match

a_list=rna_msc_match
do.call(cbind, lapply(lapply(a_list, unlist), `length<-`, max(lengths(a_list))))
#       cat  months dog 
my_list=a_list
# Step 1: 合并数据框
combined_df <- do.call(rbind, my_list)
# Step 2: 添加列表名
combined_df$List_Name <- unlist(lapply(seq_along(my_list), function(i) rep(names(my_list)[i], nrow(my_list[[i]]))))
a
combined_df=combined_df[!duplicated(combined_df$Description),]
combined_df


combined_df$Enrichment= -log2(combined_df$p.adjust) %>%as.numeric()
combined_df$"-log2(combined_df$pvalue)"=-log2(combined_df$pvalue)
combined_df$"-log2(combined_df$p.adjust)"=-log2(combined_df$p.adjust)
combined_df$Percentage=DOSE::parse_ratio(combined_df$GeneRatio) /DOSE::parse_ratio(combined_df$BgRatio)
combined_df
#library(tibble)

terms_for_heatmap=data.frame(row.names =combined_df$Description,
                                Enrichment=combined_df$Enrichment)
terms_for_heatmap



pheatmap(terms_for_heatmap,cluster_cols = FALSE,
         scale = "none",
         color = colorRampPalette(c( "pink","red"))(50), 
         cluster_rows = FALSE,gaps_row = seq(1,length(rownames(terms_for_heatmap)))
          )
#蛋白组
if (1) {
  
  go_file=list.files(".",full.names = TRUE,pattern = "protein")
  a
  go_file
  protein_msc=openxlsx::read.xlsx(go_file)
  head(protein_msc) 
  protein_msc=protein_msc[grepl(protein_msc$Cluster,pattern="MSC_D28-LCT_14_28_NT_D28"),]
  head(protein_msc)
  protein_msc
  protein_msc_id=protein_msc$ID
  a 
  
  if (F) {
    
    as.list(GOBPOFFSPRING[myterm]) %>%unlist()   %>% unname()
    as.list(GOBPOFFSPRING['GO:0016209']) %>%unlist()   %>% unname() 
    for (eachterm in a) {
      result <- try({
        try( as.list(GOBPOFFSPRING[eachterm]) %>% unlist() %>% unname() %>%print()  , silent = TRUE   ) |
          try(as.list(GOMFOFFSPRING[eachterm]) %>% unlist() %>% unname()%>%print(), silent = TRUE)
        
      }, silent = TRUE)
      print(paste0(eachterm,"-====================================================================="))
      
      
      # #  if (inherits(result, "try-error")) {
      #     cat("Error occurred for term:", eachterm, "\n")
      #   }
    }
    
    #grep(as.list(GOBPOFFSPRING) %>%unlist() %>%unname(),pattern("0016209"))
    protein_msc_match=list()
    if (F) {
      for (eachterm in a) {
        success <- TRUE
        
        tryCatch({
          target_terms <- union(as.list(GOBPOFFSPRING[eachterm]) %>% unlist() %>% unname(), names(as.list(GOBPOFFSPRING[eachterm])))
          protein_msc_match[[eachterm]] <- protein_msc[protein_msc_id %in% target_terms,]
          print(paste0(eachterm, "-========================GO============================================="))
        }, error = function(e) {#因为这是函数体内的函数 所以protein_msc_match与体外无关，如何改进呢
          cat("Error occurred for term:", eachterm, "\n")
          success <- FALSE
          print(paste(success,"-===="))
          
          
          if (!success) {
            target_terms <- union(as.list(GOMFOFFSPRING[eachterm]) %>% unlist() %>% unname(), names(as.list(GOMFOFFSPRING[eachterm])))
            protein_msc_match[[eachterm]] <- protein_msc[protein_msc_id %in% target_terms,]
            print(paste0(eachterm,100-1, "-===============================MF======================================"))
          }
          
          
        })
        
        
      }
      a
      names(protein_msc_match)
      
      
      
    }
    
  }
  
  colnames(GOBPOFFSPRING)
  as.list(GOBPOFFSPRING)
  
  protein_msc_match <- list()
  i=1
  for (eachterm in a) {
    # Check if GOBPOFFSPRING has the term, otherwise use GOMFOFFSPRING
    if ( eachterm %in% (union(as.list(GOBPOFFSPRING[[eachterm]]) %>% unlist() %>% unname(), eachterm)) ) {
      target_terms <- union(as.list(GOBPOFFSPRING[[eachterm]]) %>% unlist() %>% unname(), eachterm)
      print(paste0(eachterm,"___第几个：：",i, "-========================GO============================================="))
    } else {
      target_terms <- union(as.list(GOMFOFFSPRING[[eachterm]]) %>% unlist() %>% unname(), eachterm)
      print(paste0(eachterm,"___第几个：：",i, "-========================MF============================================="))
    }
    
    # Filter protein_msc based on target_terms
    protein_msc_match[[eachterm]] <- protein_msc[protein_msc_id %in% target_terms,]
    
    i=i+1
  }
  a
  protein_msc_match %>%names()
  protein_msc_match
  
  a_list=protein_msc_match
  do.call(cbind, lapply(lapply(a_list, unlist), `length<-`, max(lengths(a_list))))
  #       cat  months dog 
  my_list=a_list
  # Step 1: 合并数据框
  combined_df_protein <- do.call(rbind, my_list)
  # Step 2: 添加列表名
  combined_df_protein$List_Name <- unlist(lapply(seq_along(my_list), function(i) rep(names(my_list)[i], nrow(my_list[[i]]))))
  a
  combined_df_protein=combined_df_protein[!duplicated(combined_df_protein$Description),]
  combined_df_protein
  
  
  combined_df_protein$Enrichment= -log2(combined_df_protein$p.adjust) %>%as.numeric()
  combined_df_protein$"-log2(combined_df_protein$pvalue)"=-log2(combined_df_protein$pvalue)
  combined_df_protein$"-log2(combined_df_protein$p.adjust)"=-log2(combined_df_protein$p.adjust)
  combined_df_protein$Percentage=DOSE::parse_ratio(combined_df_protein$GeneRatio) /DOSE::parse_ratio(combined_df_protein$BgRatio)
  combined_df_protein
  #library(tibble)
  
  terms_for_heatmap_protein=data.frame(row.names =combined_df_protein$Description,
                                       Enrichment=combined_df_protein$Enrichment)
  terms_for_heatmap_protein
  
  
  
  pheatmap(terms_for_heatmap_protein,cluster_cols = FALSE,
           scale = 'none',
           color = colorRampPalette(c( "pink","red"))(50), 
           cluster_rows = FALSE,gaps_row = seq(1,length(rownames(terms_for_heatmap_protein)))
  )
  
  
  
}



common=intersect(rownames(terms_for_heatmap),rownames(terms_for_heatmap_protein))

common_df=data.frame(transcript_enrichment=terms_for_heatmap[common,],
                     protein_enrichment=terms_for_heatmap_protein[common,],
                     names=common)


list_save=list(transcript=combined_df,
               protein=combined_df_protein,
               combined=common_df)

openxlsx::write.xlsx(list_save,file = "commbined_protein_transcript_GO_enrichments.xlsx")





library(ggplot2)
library(reshape2)



data=data.frame(transcript_enrichment=terms_for_heatmap[common,],
                protein_enrichment=terms_for_heatmap_protein[common,],
                row.names =common)

combined_df %>%head()
p=pheatmap::pheatmap(data,
                   cellwidth = 33,
                   cellheight = 23,border_color = "white",
                   legend_labels = "Enrichments",
                   main =  "Enrichments",
                   cluster_cols = FALSE,
                   scale = 'none',
                   color = colorRampPalette(c( "pink","red"))(50), 
                   cluster_rows = FALSE,gaps_row = seq(1,length(rownames(data))),
                   gaps_col = seq(1,length(colnames(data)))
)

ggsave(plot = p,filename = "commbined_protein_transcript_GO_enrichment.pdf",
       height = 10,width = 10,
       limitsize = FALSE)



p=pheatmap::pheatmap(data,
                     cellwidth = 33,
                     cellheight = 23,border_color = "white",
                     legend_labels = "Enrichments",
                     main =  "Enrichments",display_numbers = T,
                     cluster_cols = FALSE,
                     scale = 'none',
                     color = colorRampPalette(c( "pink","red"))(50), 
                     cluster_rows = FALSE,gaps_row = seq(1,length(rownames(data))),
                     gaps_col = seq(1,length(colnames(data)))
)

ggsave(plot = p,filename = "commbined_protein_transcript_GO_enrichment_with_numbers.pdf",
       height = 10,width = 10,
       limitsize = FALSE)