mastertable fix

gozdekibar · Feb 25, 2022 · 424c7eb · 424c7eb
1 parent ea9631a
commit 424c7eb
Showing 1 changed file with 33 additions and 74 deletions.
diff --git a/create_MasterTable.ipynb b/create_MasterTable.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -18,108 +18,67 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
-    ".libPaths( c(\"/home/kibar/R/x86_64-pc-linux-gnu-library/4.1\" , .libPaths() ) )"
+    "#### import metapredict indexes\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
-    ".libPaths( c(\"/home/kibar/R/x86_64-conda-linux-gnu-library/4.1\" , .libPaths() ) )"
+    "json_data_metapredict<- fromJSON(txt='./metapredict/metapredict_least20_concIDRs.json')"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 10,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "               _                           \n",
-       "platform       x86_64-pc-linux-gnu         \n",
-       "arch           x86_64                      \n",
-       "os             linux-gnu                   \n",
-       "system         x86_64, linux-gnu           \n",
-       "status                                     \n",
-       "major          4                           \n",
-       "minor          1.0                         \n",
-       "year           2021                        \n",
-       "month          05                          \n",
-       "day            18                          \n",
-       "svn rev        80317                       \n",
-       "language       R                           \n",
-       "version.string R version 4.1.0 (2021-05-18)\n",
-       "nickname       Camp Pontanezen             "
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
    "source": [
-    "R.version"
+    "#### import Quazi IDR Finder Table"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "outcome_IDP_predictor_counts<- fromJSON(\"./Quasi_IDR_Finder/output_quaziIDRFinder_canonical_all_qIDR.json\")\n"
+   ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
-    "#import metapredict indexes\n",
-    "json_data_metapredict<- fromJSON(txt='./metapredict/metapredict_least20_concIDRs.json')"
+    "outcome_IDP_predictor=outcome_IDP_predictor_counts[lengths(outcome_IDP_predictor_counts) != 0]"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 6,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "\n",
-    "#import Quazi IDR Finder Table\n",
-    "\n",
-    "outcome_IDP_predictor_counts<- fromJSON(\"./Quasi_IDR_Finder/output_quaziIDRFinder_canonical_all_qIDR.json\")\n"
+    "#### get protein names that have longer than 100 aas"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
-    "outcome_IDP_predictor=outcome_IDP_predictor_counts[lengths(outcome_IDP_predictor_counts) != 0]"
+    "dict_keys_lenlongerthan100<- fromJSON('./HG38_pep/longerthan100dic.json')"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 8,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "dict_keys_lenlongerthan100<- fromJSON('./HG38_pep/longerthan100dic.json')"
+    "#### intersect Quazi IDR found keys and metapredict prediction found keys"
    ]
   },
   {
@@ -128,17 +87,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "##intersect Quazi IDR found keys and metapredict prediction found keys\n",
     "int_keys=intersect(names(outcome_IDP_predictor),names(json_data_metapredict))"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 10,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "###check if metapredict and Quasi IDR regions overlap"
+    "#### check if metapredict and Quasi IDR regions overlap"
    ]
   },
   {
@@ -245,12 +201,10 @@
    "source": []
   },
   {
-   "cell_type": "code",
-   "execution_count": 13,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "##for PLAAC comparison, get PLAAC annotations"
+    "#### for PLAAC comparison, get PLAAC annotations"
    ]
   },
   {
@@ -324,6 +278,13 @@
     "head(PLACC_annot)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### check if keys have a PLAAC regions inside their qIDR regions"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 15,
@@ -393,12 +354,10 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 17,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "##add interpro annotations to the table "
+    "#### check if keys have a InterProt regions inside their qIDR regions"
    ]
   },
   {
@@ -628,7 +587,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Add INTERPROT AND PLAAC annotations and regions to the table "
+    "### merge dataframes"
    ]
   },
   {