生信分析代谢通路可视化分析R工具包ggkegg的使用案例_怎么用r包对多个代谢物进行kegg通路分析

本文链接：https://blog.csdn.net/m0_60388419/article/details/138318883

vec <- 1
names(vec) <- c("hsa:51343")
new_g <- g |> mutate(num=node_numeric(vec))
new_g
#> # A tbl_graph: 134 nodes and 157 edges
#> #
#> # A directed acyclic multigraph with 40 components
#> #
#> # A tibble: 134 × 23
#>   name        type  reaction graphics_name     x     y width
#>   <chr>       <chr> <chr>    <chr>         <dbl> <dbl> <dbl>
#> 1 hsa:1029    gene  <NA>     CDKN2A, ARF,…   532  -218    46
#> 2 hsa:51343   gene  <NA>     FZR1, CDC20C…   981  -630    46
#> 3 hsa:4171 h… gene  <NA>     MCM2, BM28, …   553  -681    46
#> 4 hsa:23594 … gene  <NA>     ORC6, ORC6L.…   494  -681    46
#> 5 hsa:10393 … gene  <NA>     ANAPC10, APC…   981  -392    46
#> 6 hsa:10393 … gene  <NA>     ANAPC10, APC…   981  -613    46
#> # ℹ 128 more rows
#> # ℹ 16 more variables: height <dbl>, fgcolor <chr>,
#> #   bgcolor <chr>, graphics_type <chr>, coords <chr>,
#> #   xmin <dbl>, xmax <dbl>, ymin <dbl>, ymax <dbl>,
#> #   orig.id <chr>, pathway_id <chr>, deseq2 <dbl>,
#> #   padj <dbl>, converted_name <chr>, lfc <dbl>, num <dbl>
#> #
#> # A tibble: 157 × 6
#>    from    to type  subtype_name    subtype_value pathway_id
#>   <int> <int> <chr> <chr>           <chr>         <chr>     
#> 1   118    39 GErel expression      -->           hsa04110  
#> 2    50    61 PPrel inhibition      --|           hsa04110  
#> 3    50    61 PPrel phosphorylation +p            hsa04110  
#> # ℹ 154 more rows

将矩阵积分到`tbl_graph`

如果要在图形中反映表达式矩阵，则和函数可能很有用。通过指定基质和基因 ID，您可以将每个样品的数值分配给 . 分配由边连接的两个节点的总和，忽略组节点（Adnan 等人，2020 年）。edge_matrix``node_matrix``tbl_graph``edge_matrix

mat <- assay(vst(res))
new_g <- g |> edge_matrix(mat) |> node_matrix(mat)
new_g
#> # A tbl_graph: 134 nodes and 157 edges
#> #
#> # A directed acyclic multigraph with 40 components
#> #
#> # A tibble: 134 × 48
#>   name        type  reaction graphics_name     x     y width
#>   <chr>       <chr> <chr>    <chr>         <dbl> <dbl> <dbl>
#> 1 hsa:1029    gene  <NA>     CDKN2A, ARF,…   532  -218    46
#> 2 hsa:51343   gene  <NA>     FZR1, CDC20C…   981  -630    46
#> 3 hsa:4171 h… gene  <NA>     MCM2, BM28, …   553  -681    46
#> 4 hsa:23594 … gene  <NA>     ORC6, ORC6L.…   494  -681    46
#> 5 hsa:10393 … gene  <NA>     ANAPC10, APC…   981  -392    46
#> 6 hsa:10393 … gene  <NA>     ANAPC10, APC…   981  -613    46
#> # ℹ 128 more rows
#> # ℹ 41 more variables: height <dbl>, fgcolor <chr>,
#> #   bgcolor <chr>, graphics_type <chr>, coords <chr>,
#> #   xmin <dbl>, xmax <dbl>, ymin <dbl>, ymax <dbl>,
#> #   orig.id <chr>, pathway_id <chr>, deseq2 <dbl>,
#> #   padj <dbl>, converted_name <chr>, lfc <dbl>,
#> #   SRR14509882 <dbl>, SRR14509883 <dbl>, …
#> #
#> # A tibble: 157 × 34
#>    from    to type  subtype_name    subtype_value pathway_id
#>   <int> <int> <chr> <chr>           <chr>         <chr>     
#> 1   118    39 GErel expression      -->           hsa04110  
#> 2    50    61 PPrel inhibition      --|           hsa04110  
#> 3    50    61 PPrel phosphorylation +p            hsa04110  
#> # ℹ 154 more rows
#> # ℹ 28 more variables: from_nd <chr>, to_nd <chr>,
#> #   SRR14509882 <dbl>, SRR14509883 <dbl>,
#> #   SRR14509884 <dbl>, SRR14509885 <dbl>,
#> #   SRR14509886 <dbl>, SRR14509887 <dbl>,
#> #   SRR14509888 <dbl>, SRR14509889 <dbl>,
#> #   SRR14509890 <dbl>, SRR14509891 <dbl>, …

边值

相同的效果可以通过获得，使用命名数值向量作为输入。此函数根据节点值添加边值。以下示例显示了将 LFC 组合到边缘。这与的行为不同。edge_matrix``edge_numeric_sum``edge_numeric


## Numeric vector (name is SYMBOL)
vinflfc <- vinf$log2FoldChange |> setNames(row.names(vinf))

g |> 
  ## Use graphics_name to merge
  mutate(grname=strsplit(graphics_name, ",") |> vapply("[", 1, FUN.VALUE="a")) |>
  activate(edges) |>
  mutate(summed = edge_numeric_sum(vinflfc, name="grname")) |>
  filter(!is.na(summed)) |>
  activate(nodes) |> 
  mutate(x=NULL, y=NULL, deg=centrality_degree(mode="all")) |>
  filter(deg>0) |>
  ggraph(layout="nicely")+
  geom_edge_parallel(aes(color=summed, width=summed,
                         linetype=subtype_name),
                     arrow=arrow(length=unit(1,"mm")),
                     start_cap=circle(2,"mm"),
                     end_cap=circle(2,"mm"))+
  geom_node_point(aes(fill=I(bgcolor)))+
  geom_node_text(aes(label=grname,
                     filter=type=="gene"),
                 repel=TRUE, bg.colour="white")+
  scale_edge_width(range=c(0.1,2))+
  scale_edge_color_gradient(low="blue", high="red", name="Edge")+
  theme_void()

可视化多重富集结果

您可以可视化多个富集分析的结果。与将函数与类一起使用类似，可以在函数中使用一个函数。通过向此功能提供对象，如果结果中存在可视化的通路，则通路内的基因信息可以反映在图中。在这个例子中，除了上面提到的尿路上皮细胞的变化外，还比较了肾近端肾小管上皮细胞的变化（Assetta等人，2016）。ggkegg``enrichResult``append_cp``mutate``enrichResult


## These are RDAs storing DEGs
load("degListRPTEC.rda")
load("degURO.rda")

library(org.Hs.eg.db);
library(clusterProfiler);
input_uro <- bitr(uroUp, ## DEGs in urothelial cells
              fromType = "SYMBOL",
              toType = "ENTREZID",
              OrgDb = org.Hs.eg.db)$ENTREZID
input_rptec <- bitr(gls$day3_up_rptec, ## DEGs at 3 days post infection in RPTECs
              fromType = "SYMBOL",
              toType = "ENTREZID",
              OrgDb = org.Hs.eg.db)$ENTREZID

ekuro <- enrichKEGG(gene = input_uro)
ekrptec <- enrichKEGG(gene = input_rptec)

g1 <- pathway("hsa04110") |> mutate(uro=append_cp(ekuro, how="all"),
                                    rptec=append_cp(ekrptec, how="all"),
                                    converted_name=convert_id("hsa"))
ggraph(g1, layout="manual", x=x, y=y) + 
  geom_edge_parallel(width=0.5, arrow = arrow(length = unit(1, 'mm')), 
                 start_cap = square(1, 'cm&