create master table

gozdekibar · Feb 25, 2022 · c3a65ed · c3a65ed
1 parent 293257f
commit c3a65ed
Show file tree

Hide file tree

Showing 12 changed files with 78,941 additions and 5,902 deletions.
diff --git a/annotations/PLD_99p.xlsx → PLAAC/PLD_99p.xlsx b/annotations/PLD_99p.xlsx → PLAAC/PLD_99p.xlsx
diff --git a/annotations/PLD_IDs.txt → PLAAC/PLD_IDs.txt b/annotations/PLD_IDs.txt → PLAAC/PLD_IDs.txt
diff --git a/Quasi_IDR_Finder/run_Quazi_IDR_Finder.ipynb b/Quasi_IDR_Finder/run_Quazi_IDR_Finder.ipynb
diff --git a/annotations/TF_IDs.txt → TFs/TF_IDs.txt b/annotations/TF_IDs.txt → TFs/TF_IDs.txt
diff --git a/Plot/ContourPlots.ipynb → codesForPlots/ContourPlots.ipynb b/Plot/ContourPlots.ipynb → codesForPlots/ContourPlots.ipynb
@@ -2,16 +2,16 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
-    "#.libPaths(\"/pkg/R-4.1.0-0/lib/R/library\")"
+    ".libPaths(\"/pkg/R-4.1.0-0/lib/R/library\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -56,7 +56,7 @@
     }
    ],
    "source": [
-    "my_data_metapredict <- read_excel(\"./Dataset/MasterTable_canonicalHuman_qIDR.xlsx\")\n",
+    "my_data_metapredict <- read_excel(\"../MasterTable_canonicalHuman_qIDR.xlsx\")\n",
     "\n",
     "thre=0.001\n",
     "\n",
@@ -79,7 +79,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -91,10 +91,10 @@
     "my_data_all_qIDRs$`min(p-val)`[which(my_data_all_qIDRs$`min(p-val)`< thre)]=thre\n",
     "\n",
     "\n",
-    "keys <- read.csv(file = './Dataset/HG30_pep_annotation.csv')\n",
-    "TFnames <- read.table(\"./Dataset/annotations/TF_IDs.txt\",header = F)\n",
-    "PLDs <- read.table(\"./Dataset/annotations/PLD_IDs.txt\",header = F)\n",
-    "Pld_99 <- read_excel(\"./Dataset/annotations/PLD_99p.xlsx\")\n",
+    "keys <- read.csv(file = '../HG38_pep/HG30_pep_annotation.csv')\n",
+    "TFnames <- read.table(\"../TFs/TF_IDs.txt\",header = F)\n",
+    "PLDs <- read.table(\"../PLAAC/PLD_IDs.txt\",header = F)\n",
+    "Pld_99 <- read_excel(\"../PLAAC/PLD_99p.xlsx\")\n",
     "\n",
     "#convert PLD keys to match\n",
     "PLD_keys=keys$gene_symbol[match(PLDs$V1, keys$ID )]\n",
@@ -242,7 +242,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {

diff --git a/Plot/GseaPlots.ipynb → codesForPlots/GseaPlots.ipynb b/Plot/GseaPlots.ipynb → codesForPlots/GseaPlots.ipynb
@@ -53,7 +53,7 @@
    ],
    "source": [
     "\n",
-    "my_data_metapredict <- read_excel(\"./Dataset/MasterTable_canonicalHuman_qIDR.xlsx\")\n",
+    "my_data_metapredict <- read_excel(\"../MasterTable_canonicalHuman_qIDR.xlsx\")\n",
     "\n",
     "overlapped_names=my_data_metapredict[my_data_metapredict$overlap_metapredict == \"yes\", ]\n",
     "x=data.frame(overlapped_names$gene_symbol,overlapped_names$`min(p-val)`)\n",
@@ -88,7 +88,7 @@
     "\n",
     "\n",
     "# GSEA analysis for Rna Binding Proteins \n",
-    "c2 <- read.gmt(\"./Dataset/gmt_files/rna_binding_all.gmt.txt\")\n",
+    "c2 <- read.gmt(\"../gmt_files/rna_binding_all.gmt.txt\")\n",
     "\n",
     "msig <- GSEA(foldchanges, TERM2GENE=c2, verbose=FALSE)\n",
     "\n",
@@ -183,7 +183,7 @@
    ],
    "source": [
     "#GSEA analysis for GMTs\n",
-    "c2 <- read.gmt(\"./Dataset/gmt_files/PLDs.gmt.txt\")\n",
+    "c2 <- read.gmt(\"../gmt_files/PLDs.gmt.txt\")\n",
     "\n",
     "msig <- GSEA(foldchanges, TERM2GENE=c2, verbose=FALSE)\n",
     "\n",
@@ -250,7 +250,7 @@
    ],
    "source": [
     "##GSEA analysis for TFs\n",
-    "c2 <- read.gmt(\"./Dataset/gmt_files/tfs.gmt.txt\")\n",
+    "c2 <- read.gmt(\"../gmt_files/tfs.gmt.txt\")\n",
     "\n",
     "msig <- GSEA(foldchanges, TERM2GENE=c2, verbose=FALSE,maxGSSize = 700, pvalueCutoff = 1)\n",
     "gseaGO_results <- msig@result\n",

diff --git a/Plot/PlotDot.ipynb → codesForPlots/PlotDot.ipynb b/Plot/PlotDot.ipynb → codesForPlots/PlotDot.ipynb
@@ -42,7 +42,7 @@
    "source": [
     "\n",
     "#setwd(\"/Users/kibar/Desktop/QuasiIDRFinder\")\n",
-    "my_data_metapredict <- read_excel(\"./Dataset/MasterTable_canonicalHuman_qIDR.xlsx\")\n",
+    "my_data_metapredict <- read_excel(\"../MasterTable_canonicalHuman_qIDR.xlsx\")\n",
     "my_data_metapredict_top=head(my_data_metapredict,1000)\n",
     "\n",
     "overlapped_names=my_data_metapredict_top[my_data_metapredict_top$overlap_metapredict == \"yes\", ]\n",

diff --git a/Plot/Quasi_IDR_Finder_Plot.ipynb → codesForPlots/Quasi_IDR_Finder_Plot.ipynb b/Plot/Quasi_IDR_Finder_Plot.ipynb → codesForPlots/Quasi_IDR_Finder_Plot.ipynb
@@ -199,7 +199,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "## Plot for protein HNRNPA1 as an example"
+    "## Plot the p-values for protein HNRNPA1 as an example"
    ]
   },
   {
@@ -339,6 +339,7 @@
     }
    ],
    "source": [
+    "#KS statistics\n",
     "p_val"
    ]
   },
@@ -427,9 +428,9 @@
    "mimetype": "text/x-r-source",
    "name": "R",
    "pygments_lexer": "r",
-   "version": "3.6.1"
+   "version": "4.1.0"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }