2021-03-01 探索 msigdbr 包

> library(msigdbr)
> msigdbr_species()
# A tibble: 11 x 2
   species_name             species_common_name      
   <chr>                    <chr>                    
 1 Bos taurus               cattle                   
 2 Caenorhabditis elegans   roundworm                
 3 Canis lupus familiaris   dog                      
 4 Danio rerio              zebrafish                
 5 Drosophila melanogaster  fruit fly                
 6 Gallus gallus            chicken                  
 7 Homo sapiens             human                    
 8 Mus musculus             house mouse              
 9 Rattus norvegicus        Norway rat               
10 Saccharomyces cerevisiae baker's or brewer's yeast
11 Sus scrofa               pig      
  
> temp=msigdbr(species = "Mus musculus")
> head(temp)
# A tibble: 6 x 17
  gs_cat gs_subcat gs_name entrez_gene gene_symbol human_entrez_ge~
  <chr>  <chr>     <chr>         <int> <chr>                  <int>
1 C3     MIR:MIR_~ AAACCA~      239273 Abcc4                  10257
2 C3     MIR:MIR_~ AAACCA~      109359 Abraxas2               23172
3 C3     MIR:MIR_~ AAACCA~       60595 Actn4                     81
4 C3     MIR:MIR_~ AAACCA~       11477 Acvr1                     90
5 C3     MIR:MIR_~ AAACCA~       11502 Adam9                   8754
6 C3     MIR:MIR_~ AAACCA~       23794 Adamts5                11096
# ... with 11 more variables: human_gene_symbol <chr>, gs_id <chr>,
#   gs_pmid <chr>, gs_geoid <chr>, gs_exact_source <chr>, gs_url <chr>,
#   gs_description <chr>, species_name <chr>, species_common_name <chr>,
#   ortholog_sources <chr>, num_ortholog_sources <dbl>


> a=data.frame(temp[,1],temp[,2])
> table(a)
      gs_subcat
gs_cat           CGN    CGP     CM     CP CP:BIOCARTA CP:KEGG CP:PID
    C1  18362      0      0      0      0           0       0      0
    C2      0      0 363345      0   4343        4761   12525   8017
    C3      0      0      0      0      0           0       0      0
    C4      0  41371      0  47519      0           0       0      0
    C5      0      0      0      0      0           0       0      0
    C6  29262      0      0      0      0           0       0      0
    C7 921461      0      0      0      0           0       0      0
    C8  52047      0      0      0      0           0       0      0
    H    7309      0      0      0      0           0       0      0
      gs_subcat
gs_cat CP:REACTOME CP:WIKIPATHWAYS  GO:BP  GO:CC  GO:MF    HPO
    C1           0               0      0      0      0      0
    C2       84995           25514      0      0      0      0
    C3           0               0      0      0      0      0
    C4           0               0      0      0      0      0
    C5           0               0 630418  92266  99925 352419
    C6           0               0      0      0      0      0
    C7           0               0      0      0      0      0
    C8           0               0      0      0      0      0
    H            0               0      0      0      0      0
      gs_subcat
gs_cat MIR:MIR_Legacy MIR:MIRDB TFT:GTRD TFT:TFT_Legacy
    C1              0         0        0              0
    C2              0         0        0              0
    C3          33873    363011   142328         151761
    C4              0         0        0              0
    C5              0         0        0              0
    C6              0         0        0              0
    C7              0         0        0              0
    C8              0         0        0              0
    H               0         0   
              

http://bioinf.wehi.edu.au/software/MSigDB/

image.png

提取KEGG,GO_BP dataframe

> KEGG_df = msigdbr(species = "Mus musculus",category = "C2",subcategory = "CP:KEGG")
> GO_df = msigdbr(species = "Mus musculus",category = "C5",subcategory = "GO:BP")