GOSEMSIM and Mantel test

MikheyevLab · Jul 1, 2019 · 0874a7d · 0874a7d
1 parent 3e8f2db
commit 0874a7d
Show file tree

Hide file tree

Showing 5 changed files with 230 additions and 0 deletions.
diff --git a/GOSEMSIM_matrix_microbiome_up.csv b/GOSEMSIM_matrix_microbiome_up.csv
@@ -0,0 +1,13 @@
+"","V1","V2","V3","V4","V5","V6","V7","V8","V9","V10","V11","V12"
+"1",0,0.95,0.933,0.941,0.953,0.951,0.942,0.935,0.932,0.938,0.945,0.936
+"2",0,0,0.956,0.929,0.96,0.962,0.944,0.961,0.958,0.956,0.945,0.973
+"3",0,0,0,0.938,0.942,0.948,0.954,0.962,0.96,0.956,0.953,0.957
+"4",0,0,0,0,0.941,0.937,0.963,0.943,0.942,0.954,0.979,0.938
+"5",0,0,0,0,0,0.965,0.938,0.958,0.953,0.948,0.953,0.949
+"6",0,0,0,0,0,0,0.951,0.946,0.943,0.963,0.949,0.944
+"7",0,0,0,0,0,0,0,0.953,0.954,0.975,0.969,0.949
+"8",0,0,0,0,0,0,0,0,0.992,0.957,0.959,0.97
+"9",0,0,0,0,0,0,0,0,0,0.958,0.958,0.967
+"10",0,0,0,0,0,0,0,0,0,0,0.964,0.953
+"11",0,0,0,0,0,0,0,0,0,0,0,0.953
+"12",0,0,0,0,0,0,0,0,0,0,0,0
diff --git a/GOSEMSIM_matrix_mite_up.csv b/GOSEMSIM_matrix_mite_up.csv
@@ -0,0 +1,13 @@
+"","V1","V2","V3","V4","V5","V6","V7","V8","V9","V10","V11","V12"
+"1",0,0.972,0.972,0.971,0.968,0.969,0.968,0.967,0.967,0.972,0.973,0.973
+"2",0,0,0.974,0.971,0.968,0.967,0.968,0.966,0.968,0.974,0.962,0.988
+"3",0,0,0,0.968,0.965,0.965,0.97,0.963,0.961,0.974,0.966,0.972
+"4",0,0,0,0,0.974,0.968,0.973,0.976,0.975,0.973,0.979,0.974
+"5",0,0,0,0,0,0.963,0.956,0.98,0.973,0.958,0.971,0.969
+"6",0,0,0,0,0,0,0.975,0.958,0.962,0.978,0.968,0.969
+"7",0,0,0,0,0,0,0,0.963,0.969,0.986,0.973,0.972
+"8",0,0,0,0,0,0,0,0,0.983,0.96,0.974,0.968
+"9",0,0,0,0,0,0,0,0,0,0.963,0.976,0.97
+"10",0,0,0,0,0,0,0,0,0,0,0.97,0.977
+"11",0,0,0,0,0,0,0,0,0,0,0,0.969
+"12",0,0,0,0,0,0,0,0,0,0,0,0
diff --git a/GOSemSim_Mantel.Rmd b/GOSemSim_Mantel.Rmd
@@ -0,0 +1,146 @@
+---
+title: "GOSemSim_mantel"
+output: html_document
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE, cache = T)
+```
+
+```{r}
+library(GOSemSim)
+library(org.Dm.eg.db)
+library(vegan)
+```
+###Reference for Fly
+```{r}
+d = godata('org.Dm.eg.db', ont = "BP", computeIC = FALSE)
+contrast = read.csv("contrasts_mite_life_stages.csv", header = F)
+```
+
+#UP_REGULATED
+##MITE
+```{r cachedChunk, cache=TRUE}
+GOSEMSIM_matrix_mite_up = matrix(0, 12, nrow=12)
+
+for(i in 1:(length(contrast$V1)-1))
+{
+  first_contrast = toString(contrast$V1[i])
+  second_contrast = toString(contrast$V2[i])
+  filename = paste("./GO_enrichment_output/contrast_", first_contrast, "_", second_contrast, "_upregulated", ".csv", sep = "")
+  GO1 = read.csv(filename, header = T)
+  GO1ID = as.character(GO1[,1])
+
+  for(j in (i+1):length(contrast$V1))
+  {
+    print(paste(i, j))
+    first_contrast = toString(contrast$V1[j])
+    second_contrast = toString(contrast$V2[j])
+    filename = paste("./GO_enrichment_output/contrast_", first_contrast, "_", second_contrast, "_upregulated", ".csv", sep = "")
+    GO2 = read.csv(filename, header = T)
+    GO2ID = as.character(GO2[,1])
+    GOSEMSIM_matrix_mite_up[i,j] <- mgoSim(GO1ID, GO2ID, semData = d, measure = "Wang", combine = "BMA")
+  }
+}
+```
+###MICROBIOME
+```{r cachedChunk, cache=TRUE}
+GOSEMSIM_matrix_microbiome_up = matrix(0, 12, nrow=12)
+
+for(i in 1:(length(contrast$V1)-1))
+{
+  first_contrast = toString(contrast$V1[i])
+  second_contrast = toString(contrast$V2[i])
+  filename = paste("./GO_enrichment_microbiome_output/contrast_", first_contrast, "_", second_contrast, "_upregulated", ".csv", sep = "")
+  GO1 = read.csv(filename, header = T)
+  GO1ID = as.character(GO1[,1])
+
+  for(j in (i+1):(length(contrast$V1)))
+  {
+    print(paste(i, j))
+    first_contrast = toString(contrast$V1[j])
+    second_contrast = toString(contrast$V2[j])
+    filename = paste("./GO_enrichment_microbiome_output/contrast_", first_contrast, "_", second_contrast, "_upregulated", ".csv", sep = "")
+    GO2 = read.csv(filename, header = T)
+    GO2ID = as.character(GO2[,1])
+    GOSEMSIM_matrix_microbiome_up[i,j] <- mgoSim(GO1ID, GO2ID, semData = d, measure = "Wang", combine = "BMA")
+  }
+}
+```
+
+```{r cachedChunk, cache=TRUE}
+microb_dist_up = as.dist(t(GOSEMSIM_matrix_microbiome_up))
+mite_dist_up = as.dist(t(GOSEMSIM_matrix_mite_up))
+mantel(mite_dist_up, microb_dist_up)
+```
+
+```{r}
+write.csv(as.data.frame(GOSEMSIM_matrix_microbiome_up), "GOSEMSIM_matrix_microbiome_up.csv")
+write.csv(as.data.frame(GOSEMSIM_matrix_mite_up), "GOSEMSIM_matrix_mite_up.csv")
+```
+
+#DOWN_REGULATED
+##MITE
+```{r cachedChunk, cache=TRUE}
+GOSEMSIM_matrix_mite_down = matrix(0, 12, nrow=12)
+
+for(i in 1:(length(contrast$V1)-1))
+{
+  first_contrast = toString(contrast$V1[i])
+  second_contrast = toString(contrast$V2[i])
+  filename = paste("./GO_enrichment_output/contrast_", first_contrast, "_", second_contrast, "_downregulated", ".csv", sep = "")
+  GO1 = read.csv(filename, header = T)
+  GO1ID = as.character(GO1[,1])
+
+  for(j in (i+1):length(contrast$V1))
+  {
+    print(paste(i, j))
+    first_contrast = toString(contrast$V1[j])
+    second_contrast = toString(contrast$V2[j])
+    filename = paste("./GO_enrichment_output/contrast_", first_contrast, "_", second_contrast, "_downregulated", ".csv", sep = "")
+    GO2 = read.csv(filename, header = T)
+    GO2ID = as.character(GO2[,1])
+    GOSEMSIM_matrix_mite_down[i,j] <- mgoSim(GO1ID, GO2ID, semData = d, measure = "Wang", combine = "BMA")
+  }
+}
+```
+###MICROBIOME
+```{r cachedChunk, cache=TRUE}
+GOSEMSIM_matrix_microbiome_down = matrix(0, 12, nrow=12)
+
+for(i in 1:(length(contrast$V1)-1))
+{
+  first_contrast = toString(contrast$V1[i])
+  second_contrast = toString(contrast$V2[i])
+  filename = paste("./GO_enrichment_microbiome_output/contrast_", first_contrast, "_", second_contrast, "_downregulated", ".csv", sep = "")
+  GO1 = read.csv(filename, header = T)
+  GO1ID = as.character(GO1[,1])
+
+  for(j in (i+1):(length(contrast$V1)))
+  {
+    print(paste(i, j))
+    first_contrast = toString(contrast$V1[j])
+    second_contrast = toString(contrast$V2[j])
+    filename = paste("./GO_enrichment_microbiome_output/contrast_", first_contrast, "_", second_contrast, "_downregulated", ".csv", sep = "")
+    GO2 = read.csv(filename, header = T)
+    GO2ID = as.character(GO2[,1])
+    GOSEMSIM_matrix_microbiome_down[i,j] <- mgoSim(GO1ID, GO2ID, semData = d, measure = "Wang", combine = "BMA")
+  }
+}
+```
+
+```{r cachedChunk, cache=TRUE}
+microb_dist_down = as.dist(t(GOSEMSIM_matrix_microbiome_down))
+mite_dist_down = as.dist(t(GOSEMSIM_matrix_mite_down))
+mantel(mite_dist_down, microb_dist_down)
+```
+
+```{r}
+write.csv(as.data.frame(GOSEMSIM_matrix_microbiome_down), "GOSEMSIM_matrix_microbiome_down.csv")
+write.csv(as.data.frame(GOSEMSIM_matrix_mite_down), "GOSEMSIM_matrix_mite_down.csv")
+```
+
+```{r cachedChunk, cache=TRUE}
+plot(microb_dist_down,mite_dist_down, main = "Down-regulated GO term correlation plot")
+```
+
diff --git a/GOSemSim_miteVSmicrobiome.R b/GOSemSim_miteVSmicrobiome.R
@@ -0,0 +1,45 @@
+library(GOSemSim)
+library(org.Dm.eg.db)
+#Reference for Fly
+d = godata('org.Dm.eg.db', ont = "BP", computeIC = FALSE)
+contrast = read.csv("contrasts_mite_life_stages.csv", header = F)
+
+similarities_upregulated = list()
+similarities_downregulated = list()
+contrast_names = list()
+
+for (id in 1:length(contrast$V1))
+{
+  print(paste(id, "id"))
+  first_contrast = toString(contrast$V1[id])
+  second_contrast = toString(contrast$V2[id])
+
+  #UP-REGULATED
+  filename = paste("./GO_enrichment_microbiome_output/contrast_", first_contrast, "_", second_contrast, "_upregulated", ".csv", sep = "")
+  GO1 = read.csv(filename, header = T)
+  GO1ID = as.character(GO1[,1])
+
+  filename = paste("./GO_enrichment_output/contrast_", first_contrast, "_", second_contrast, "_upregulated", ".csv", sep = "")
+  GO2 = read.csv(filename, header = T)
+  GO2ID = as.character(GO2[,1])
+
+  name = paste(first_contrast, "_", second_contrast,sep = "")
+  contrast_names[length(contrast_names)+1] = name
+  similarities_upregulated[[length(similarities_upregulated)+1]] = mgoSim(GO1ID, GO2ID, semData = d, measure = "Wang", combine = "BMA")
+
+  #DOWN-REGULATED
+  filename = paste("./GO_enrichment_microbiome_output/contrast_", first_contrast, "_", second_contrast, "_downregulated", ".csv", sep = "")
+  GO1 = read.csv(filename, header = T)
+  GO1ID = as.character(GO1[,1])
+
+  filename = paste("./GO_enrichment_output/contrast_", first_contrast, "_", second_contrast, "_downregulated", ".csv", sep = "")
+  GO2 = read.csv(filename, header = T)
+  GO2ID = as.character(GO2[,1])
+
+  similarities_downregulated[[length(similarities_downregulated)+1]] = mgoSim(GO1ID, GO2ID, semData = d, measure = "Wang", combine = "BMA")
+}
+
+names(similarities_downregulated) = as.vector(unlist(contrast_names))
+names(similarities_upregulated) = as.vector(unlist(contrast_names))
+GOSemSim_table = do.call(rbind, Map(data.frame, A=similarities_upregulated, B=similarities_downregulated))
+write.csv(GOSemSim_table, "GOSemSim_table.csv")
diff --git a/GOSemSim_table_miteVSmicrobiome.csv b/GOSemSim_table_miteVSmicrobiome.csv
@@ -0,0 +1,13 @@
+,Up_regulated,Down_regulated
+young_males,0.763,0.917
+young_phoretic,0.803,0.887
+phoretic_phoreticCaged,0.798,0.866
+phoretic_arresting,0.759,0.901
+arresting_prelaying,0.793,0.892
+prelaying_laying,0.799,0.899
+laying_postlaying,0.782,0.911
+postlaying_emerging,0.817,0.864
+postlaying_nonlaying,0.811,0.884
+laying_nonlaying,0.8,0.899
+emerging_phoretic,0.785,0.891
+emerging_young,0.816,0.881