HMDB pathway enrichment

Xiaotao Shen PhD (https://www.shenxt.info/)

Created on 2020-03-28 and updated on 2022-09-19

Source: vignettes/hmdb_pathway_enrichment.Rmd

Load HMDB pathway database 

data("hmdb_pathway", package = "metpath")
hmdb_pathway
#> ---------Pathway source&version---------
#> SMPDB & 2021-03-02 
#> -----------Pathway information------------
#> 48703 pathways 
#> 0 pathways have genes 
#> 48642 pathways have proteins 
#> 48674 pathways have compounds 
#> Pathway class (top 10): Metabolic;primary_pathway 
#> 
get_pathway_class(hmdb_pathway)
#> # A tibble: 12 × 2
#>    class                               n
#>    <chr>                           <int>
#>  1 Disease                         20016
#>  2 Disease;primary_pathway           232
#>  3 Drug Action                         1
#>  4 Drug Action;primary_pathway       403
#>  5 Drug Metabolism;primary_pathway    64
#>  6 Metabolic                       27777
#>  7 Metabolic;primary_pathway         105
#>  8 Physiological                       2
#>  9 Physiological;primary_pathway      14
#> 10 Protein;primary_pathway            76
#> 11 Signaling                           1
#> 12 Signaling;primary_pathway          12

Pathway enrichment

We use the demo compound list from metpath.

data("query_id_hmdb", package = "metpath")
query_id_hmdb
#>  [1] "HMDB0000060" "HMDB0000056" "HMDB0000064" "HMDB0000092" "HMDB0000134"
#>  [6] "HMDB0000123" "HMDB0000742" "HMDB0000574" "HMDB0000159" "HMDB0000187"
#> [11] "HMDB0000167" "HMDB0000158" "HMDB0000883" "HMDB0000205" "HMDB0000237"
#> [16] "HMDB0000243" "HMDB0000271"

Only remain the Metabolic;primary_pathway.

#get the class of pathways
pathway_class = 
  metpath::pathway_class(hmdb_pathway) 

remain_idx = which(unlist(pathway_class) == "Metabolic;primary_pathway")

remain_idx
#> SMP0000055 SMP0000067 SMP0000072 SMP0000015 SMP0000057 SMP0000018 SMP0000029 
#>          1          2          3          4          5          6          7 
#> SMP0000045 SMP0000009 SMP0000020 SMP0000007 SMP0000123 SMP0000066 SMP0000073 
#>          8          9         10         11         12         13         14 
#> SMP0000028 SMP0000465 SMP0000012 SMP0000013 SMP0000036 SMP0000468 SMP0000449 
#>         15         16         17         18         19         20         21 
#> SMP0000054 SMP0000051 SMP0000053 SMP0000064 SMP0000124 SMP0000455 SMP0000071 
#>         22         23         24         25         26         27         28 
#> SMP0000037 SMP0000129 SMP0000010 SMP0000027 SMP0000126 SMP0000459 SMP0000070 
#>         29         30         31         32         33         34         35 
#> SMP0000076 SMP0000445 SMP0000021 SMP0000065 SMP0000041 SMP0000450 SMP0000008 
#>         36         37         38         39         40         41         42 
#> SMP0000044 SMP0000075 SMP0000068 SMP0000127 SMP0000464 SMP0000025 SMP0000444 
#>         43         44         45         46         47         48         49 
#> SMP0000023 SMP0000032 SMP0000050 SMP0000017 SMP0000060 SMP0000031 SMP0000033 
#>         50         51         52         53         54         55         56 
#> SMP0000005 SMP0000130 SMP0000006 SMP0000011 SMP0000039 SMP0000035 SMP0000040 
#>        140        141        142        143        144        145        146 
#> SMP0000034 SMP0000016 SMP0000058 SMP0000048 SMP0000128 SMP0000457 SMP0000466 
#>        148        149        150        151        152        153        154 
#> SMP0000030 SMP0000462 SMP0000004 SMP0000024 SMP0000043 SMP0000046 SMP0000052 
#>        155        156        157        158        159        160        161 
#> SMP0000059 SMP0000063 SMP0000074 SMP0000355 SMP0000452 SMP0000456 SMP0000463 
#>        162        163        164        165        166        167        168 
#> SMP0000467 SMP0000479 SMP0000480 SMP0000481 SMP0000482 SMP0000477 SMP0000478 
#>        169        170        171        172        173        453        454 
#> SMP0000654 SMP0000715 SMP0000716 SMP0014212 SMP0015896 SMP0020986 SMP0029731 
#>        623        684        685        725       2406       7488      16221 
#> SMP0030406 SMP0030880 SMP0121055 SMP0121057 SMP0121060 SMP0121123 SMP0121131 
#>      16889      16890      48697      48698      48699      48700      48703

hmdb_pathway = 
  hmdb_pathway[remain_idx]

hmdb_pathway
#> ---------Pathway source&version---------
#> SMPDB & 2021-03-02 
#> -----------Pathway information------------
#> 105 pathways 
#> 0 pathways have genes 
#> 99 pathways have proteins 
#> 98 pathways have compounds 
#> Pathway class (top 10): Metabolic;primary_pathway 
#> 
result = 
enrich_hmdb(query_id = query_id_hmdb, 
            query_type = "compound", 
            id_type = "HMDB",
            pathway_database = hmdb_pathway,
            only_primary_pathway = TRUE,
            p_cutoff = 0.05, 
            p_adjust_method = "BH", 
            threads = 3)

Check the result:

result
#> ---------Pathway database&version---------
#> SMPDB & 2021-03-02 
#> -----------Enrichment result------------
#> 98 pathways are enriched 
#> 8 pathways p-values < 0.05 
#> Glycine and Serine Metabolism;Methionine Metabolism;Phenylalanine and Tyrosine Metabolism;Homocysteine Degradation;Ammonia Recycling ... (only top 5 shows)
#>

Plot to show pathway enrichment 

enrich_bar_plot(
  object = result,
  x_axis = "p_value_adjust",
  cutoff = 0.05,
  top = 10
)

enrich_scatter_plot(object = result)

enrich_network(object = result)