各种id转换 kegg id kegg compound id 与HMDB转换

KEGG COMPOUND 数据库 - 简书 (jianshu.com)

kegg id号转换为可读 的name ：使用KEGGREST

 
#-------------kegg id的entry和Name转换            https://zhuanlan.zhihu.com/p/545494092
#BiocManager::install("KEGGREST") #安装KEGGREST这个包
library(KEGGREST) #加载该R包
listDatabases() #查看可以利用的数据库

keggList()
##获取pathway(所有物种)数据集中的数据
pathway<- keggList("pathway")
head(pathway)
rat_pathway=keggList("pathway",organism = "rno")
head(rat_pathway)


#hsa_pathway <- keggList("pathway","hsa") # 获取KEGG数据库中所有人类通路   https://zhuanlan.zhihu.com/p/434383719

hsa_pathway=rat_pathway
hsa_path <- data.frame(hsa_pathway) # 转成数据框,方便后续分析
print(head(hsa_path))
hsa_path$pathID <- substr(rownames(hsa_path),6,nchar(rownames(hsa_path)[1])) # 提取pathway ID

kegg compound id 与HMDB转换 ：使用metabolystr包

   {
     0. #kegg id
      library(KEGGREST) #加载该R包
      library(tibble)
      listDatabases() #查看可以利用的数据库
      
      keggList()
      ##获取pathway(所有物种)数据集中的数据
      pathway<- keggList("pathway")
      head(pathway)
      rat_pathway=keggList("pathway",organism = "rno") 
      rat_pathway=data.frame(rat_pathway) %>%rownames_to_column(var = "kegg entry id")
      rat_pathway$metabolic_pathway=str_split(rat_pathway$rat_pathway,pattern = " - Rattus norvegicus \\(rat\\)",simplify = T)[,1]
      print(head(rat_pathway))
      
      save.mat$metabolic_pathway=rownames(save.mat)
      print(head(save.mat))
      # Merge the data frames based on the "metabolic_pathway" column
      merged_data <- merge(save.mat, rat_pathway, by = "metabolic_pathway")
      
      # Print the first few rows of the merged data
      print(head(merged_data))
      
      1. #kegg compound id
      rm(mSet)
      mSet<-InitDataObjects("list", "msetora", FALSE)
      cmpd.vec<-tmp.vec
      mSet<-Setup.MapData(mSet, cmpd.vec);
      mSet<-CrossReferencing(mSet, "name");
      mSet<-CreateMappingResultTable(mSet)
      metabolite_hmdb_kegg=mSet[["dataSet"]][["map.table"]] %>% as.data.frame() 
      
      metabolite_hmdb_kegg=metabolite_hmdb_kegg[ metabolite_hmdb_kegg$KEGG!="NA"&
                                                  !is.na(metabolite_hmdb_kegg$KEGG),]
      print(head(metabolite_hmdb_kegg))
      dim(metabolite_hmdb_kegg)
      
   2.#uniport id   
      deg_proteins=read.csv("/home/data/t040413/wpx/wpx_proteinomics/1_model_success_3/LCT(14+28)-NT-D28-Normal_control _differential_proteins.csv")
      deg_proteins=deg_proteins[deg_proteins$regulate!="NOT",]$protein_name
      
      print(getwd())
     
      
      print(gene.idtype.list )
      data(rn.list);
      print(names(rn.list))
      gene.ensprot <- sim.mol.data(mol.type = "gene", id.type = gene.idtype.list[4]) 
      head(gene.ensprot)
      cpd.simtypes
      
      
      head(deg_proteins$protein_name)
      print(head(metabolite_hmdb_kegg$KEGG))
      head(merged_data)
      pv.out <- pathview(gene.data = deg_proteins$protein_name,
                         cpd.data = metabolite_hmdb_kegg$KEGG, 
                        
                          gene.idtype = "UNIPROT", cpd.idtype = "kegg",
                         
                         pathway.id = "rno01040", # merged_data[,"kegg entry id"] [1], 
                         species = "rno",            out.suffix = "sel.genes.sel.cpd", 
                         keys.align = "y", 
                         kegg.native = T, 
                         key.pos = demo.paths$kpos1[1], 
                          limit = list(gene = 1, cpd = 1),
                         bins = list(gene = 1, cpd = 1), 
                         na.col = "gray", discrete = list(gene = T, cpd = T))
      
      
      pv.out <- pathview(gene.data = deg_proteins$protein_name,
                         cpd.data = metabolite_hmdb_kegg$KEGG,  
                         pathway.id = "rno01040", 
                         gene.idtype = "UNIPROT", cpd.idtype = "kegg",
                         
                         species = "rno",        
                         out.suffix = "sgfssel.genes.sel.cpd ", 
                         keys.align = "y", kegg.native = T, 
                         key.pos = demo.paths$kpos1[i], 
                          limit = list(gene = 5, cpd = 2),
                          bins = list(gene = 5, cpd = 2), 
                         na.col = "gray", discrete = list(gene = T, cpd = T))
      
      
      
      
    }

kegg compound 数据库存储了在生命活动中发挥作用的各种小分子，生物大分子和其他类型的化学物质，采用C number 进行标识，比如C00047, 代表L-赖氨酸。除了名称等信息外，还存储了该物质的化学结构和其他相关信息；

对于所有compound 的分类详见 Brite 数据库

image

Module 是ko的集合，但是ko只是基因集，真正参与生命活动的是这些基因的产物，在产物发挥作用的时候，也需要compound 的参与，所有会给出compound 相关的module。

Enzyme 数据库保存各种酶的相关信息，酶作为催化剂调控一些生物学过程的发生和进行，在这个过程中肯定也会有compound 的参与；比如1.1.1.306 这种酶催化的反应中， 供体提供甲酸才能进行反应，所以会给出compound 对应的Enzyme 编号；

总结

1. compound 数据库存储了参与生命活动的各种分子的信息，数据库中的记录用C Number唯一标识， 每条分子都有对应的化学式，结构式，分子量等基本信息；

2. compound 和reaction , module， pathway， enzeme 等多个数据库都有联系；