{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# EGF and HRG Stimulation of ERBB2 Overexpressing HMEC Cells (Wolf Yadlin 2006)"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"#Supporting packages for analysis\n",
"import numpy as np\n",
"import pandas as pd\n",
"\n",
"#KSTAR imports\n",
"from kstar import config, helpers, calculate\n",
"from kstar.plot import DotPlot\n",
"\n",
"\n",
"\n",
"#Set matplotlib defaults for arial 12 point font\n",
"from matplotlib import rcParams\n",
"rcParams['font.family'] = 'sans-serif'\n",
"rcParams['font.sans-serif'] = ['Arial']\n",
"rcParams['font.size'] = 12\n",
"import matplotlib.pyplot as plt\n",
"\n",
"#where supplementary data was downloaded to (From https://figshare.com/articles/dataset/KSTAR_Supplementary_Data/14919726)\n",
"SUPPLEMENTS_DIR = './'\n",
"\n",
"#Directory where KSTAR Supplemental data was set \n",
"odir = SUPPLEMENTS_DIR+'Supplements/SupplementaryData/Control_Experiments/EGF_184A1_HER2_WolfYadlin2006/'\n",
"\n",
"#load the Mann Whitney activities and FPR for Tyrosine predictions, \n",
"#it will be faster and less data than loading all KSTAR outputs\n",
"activities = pd.read_csv(odir+'/RESULTS/EGF_HER2_Y_mann_whitney_activities.tsv', sep='\\t', index_col=0)\n",
"fpr = pd.read_csv(odir+'/RESULTS/EGF_HER2_Y_mann_whitney_fpr.tsv', sep='\\t', index_col=0)\n",
"\n",
"\n",
"#load kinase map from supplementary data\n",
"KINASE_MAP = pd.read_csv(SUPPLEMENTS_DIR+'SupplementaryData/Map/globalKinaseMap.csv', index_col = 0)\n",
"#set preferred kinase names from the kinase map (make a kinase_dict)\n",
"kinase_dict = {}\n",
"for kinase in activities.index:\n",
" kinase_dict[kinase] = KINASE_MAP.loc[kinase,'Preferred Name']"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"#set up a description table\n",
"cell_dict = {}\n",
"treatment_dict = {}\n",
"for col in activities.columns:\n",
" label = col.split(':')\n",
" descr = label[1]\n",
" descr_labels = descr.split('_')\n",
" cell_dict[col] = descr_labels[0]\n",
" treatment_dict[col] = descr_labels[1]\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"temp1 = pd.DataFrame.from_dict(cell_dict, orient='index', columns=['Cell Type'])\n",
"temp2 = pd.DataFrame.from_dict(treatment_dict, orient='index', columns=['Growth Factor'])\n",
"s1 = temp1.join(temp2)\n",
"s1['ID'] = s1.index"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Cell Type | \n",
" Growth Factor | \n",
" ID | \n",
"
\n",
" \n",
" \n",
" \n",
" | data:24H_EGF_0(min) | \n",
" 24H | \n",
" EGF | \n",
" data:24H_EGF_0(min) | \n",
"
\n",
" \n",
" | data:24H_EGF_5(min) | \n",
" 24H | \n",
" EGF | \n",
" data:24H_EGF_5(min) | \n",
"
\n",
" \n",
" | data:24H_EGF_10(min) | \n",
" 24H | \n",
" EGF | \n",
" data:24H_EGF_10(min) | \n",
"
\n",
" \n",
" | data:24H_EGF_30(min) | \n",
" 24H | \n",
" EGF | \n",
" data:24H_EGF_30(min) | \n",
"
\n",
" \n",
" | data:24H_HRG_0(min) | \n",
" 24H | \n",
" HRG | \n",
" data:24H_HRG_0(min) | \n",
"
\n",
" \n",
" | data:24H_HRG_5(min) | \n",
" 24H | \n",
" HRG | \n",
" data:24H_HRG_5(min) | \n",
"
\n",
" \n",
" | data:24H_HRG_10(min) | \n",
" 24H | \n",
" HRG | \n",
" data:24H_HRG_10(min) | \n",
"
\n",
" \n",
" | data:24H_HRG_30(min) | \n",
" 24H | \n",
" HRG | \n",
" data:24H_HRG_30(min) | \n",
"
\n",
" \n",
" | data:P_EGF_0(min) | \n",
" P | \n",
" EGF | \n",
" data:P_EGF_0(min) | \n",
"
\n",
" \n",
" | data:P_EGF_5(min) | \n",
" P | \n",
" EGF | \n",
" data:P_EGF_5(min) | \n",
"
\n",
" \n",
" | data:P_EGF_10(min) | \n",
" P | \n",
" EGF | \n",
" data:P_EGF_10(min) | \n",
"
\n",
" \n",
" | data:P_EGF_30(min) | \n",
" P | \n",
" EGF | \n",
" data:P_EGF_30(min) | \n",
"
\n",
" \n",
" | data:P_HRG_0(min) | \n",
" P | \n",
" HRG | \n",
" data:P_HRG_0(min) | \n",
"
\n",
" \n",
" | data:P_HRG_5(min) | \n",
" P | \n",
" HRG | \n",
" data:P_HRG_5(min) | \n",
"
\n",
" \n",
" | data:P_HRG_10(min) | \n",
" P | \n",
" HRG | \n",
" data:P_HRG_10(min) | \n",
"
\n",
" \n",
" | data:P_HRG_30(min) | \n",
" P | \n",
" HRG | \n",
" data:P_HRG_30(min) | \n",
"
\n",
" \n",
"
\n",
"