-
Notifications
You must be signed in to change notification settings - Fork 21
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'master' of https://github.com/fraenkel-lab/OmicsIntegra…
- Loading branch information
Showing
2 changed files
with
245 additions
and
0 deletions.
There are no files selected for viewing
Git LFS file not shown
242 changes: 242 additions & 0 deletions
242
interactomes/PreProcess_PCNet_For_OmicsIntegrator.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,242 @@ | ||
| { | ||
| "cells": [ | ||
| { | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "# PreProcessing PCNet for OmicsIntegrator\n", | ||
| "\n", | ||
| "All Fraenkel-lab interactomes have been pre-processed to have 3 columns: 2 interactors and a scalar confidence\n", | ||
| "However, OmicsIntegrator requires that edges have a cost, not a confidence. This notebook sets costs on the edges and augments those interactomes for use in OmicsIntegrator." | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 1, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "import numpy as np\n", | ||
| "import pandas as pd\n", | ||
| "import matplotlib.pyplot as plt\n", | ||
| "%matplotlib inline" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 2, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
| "data": { | ||
| "text/html": [ | ||
| "<div>\n", | ||
| "<style scoped>\n", | ||
| " .dataframe tbody tr th:only-of-type {\n", | ||
| " vertical-align: middle;\n", | ||
| " }\n", | ||
| "\n", | ||
| " .dataframe tbody tr th {\n", | ||
| " vertical-align: top;\n", | ||
| " }\n", | ||
| "\n", | ||
| " .dataframe thead th {\n", | ||
| " text-align: right;\n", | ||
| " }\n", | ||
| "</style>\n", | ||
| "<table border=\"1\" class=\"dataframe\">\n", | ||
| " <thead>\n", | ||
| " <tr style=\"text-align: right;\">\n", | ||
| " <th></th>\n", | ||
| " <th>protein1</th>\n", | ||
| " <th>protein2</th>\n", | ||
| " <th>confidence</th>\n", | ||
| " </tr>\n", | ||
| " </thead>\n", | ||
| " <tbody>\n", | ||
| " <tr>\n", | ||
| " <th>0</th>\n", | ||
| " <td>A1BG</td>\n", | ||
| " <td>A2M</td>\n", | ||
| " <td>NaN</td>\n", | ||
| " </tr>\n", | ||
| " <tr>\n", | ||
| " <th>1</th>\n", | ||
| " <td>A1BG</td>\n", | ||
| " <td>ABCC6</td>\n", | ||
| " <td>NaN</td>\n", | ||
| " </tr>\n", | ||
| " <tr>\n", | ||
| " <th>2</th>\n", | ||
| " <td>A1BG</td>\n", | ||
| " <td>ACOT12</td>\n", | ||
| " <td>NaN</td>\n", | ||
| " </tr>\n", | ||
| " <tr>\n", | ||
| " <th>3</th>\n", | ||
| " <td>A1BG</td>\n", | ||
| " <td>ADH1A</td>\n", | ||
| " <td>NaN</td>\n", | ||
| " </tr>\n", | ||
| " <tr>\n", | ||
| " <th>4</th>\n", | ||
| " <td>A1BG</td>\n", | ||
| " <td>ADH4</td>\n", | ||
| " <td>NaN</td>\n", | ||
| " </tr>\n", | ||
| " </tbody>\n", | ||
| "</table>\n", | ||
| "</div>" | ||
| ], | ||
| "text/plain": [ | ||
| " protein1 protein2 confidence\n", | ||
| "0 A1BG A2M NaN\n", | ||
| "1 A1BG ABCC6 NaN\n", | ||
| "2 A1BG ACOT12 NaN\n", | ||
| "3 A1BG ADH1A NaN\n", | ||
| "4 A1BG ADH4 NaN" | ||
| ] | ||
| }, | ||
| "execution_count": 2, | ||
| "metadata": {}, | ||
| "output_type": "execute_result" | ||
| } | ||
| ], | ||
| "source": [ | ||
| "pcnet = pd.read_pickle(\"../../interactomes/PCNet/PCNet.05_2018.cleaned.namespace-mapped.full.pickle\")\n", | ||
| "pcnet.head()" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "### PCNet is relatively unique in that we don't have confidences for the edges. We'll need to set them arbitrarily" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 3, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
| "data": { | ||
| "text/html": [ | ||
| "<div>\n", | ||
| "<style scoped>\n", | ||
| " .dataframe tbody tr th:only-of-type {\n", | ||
| " vertical-align: middle;\n", | ||
| " }\n", | ||
| "\n", | ||
| " .dataframe tbody tr th {\n", | ||
| " vertical-align: top;\n", | ||
| " }\n", | ||
| "\n", | ||
| " .dataframe thead th {\n", | ||
| " text-align: right;\n", | ||
| " }\n", | ||
| "</style>\n", | ||
| "<table border=\"1\" class=\"dataframe\">\n", | ||
| " <thead>\n", | ||
| " <tr style=\"text-align: right;\">\n", | ||
| " <th></th>\n", | ||
| " <th>protein1</th>\n", | ||
| " <th>protein2</th>\n", | ||
| " <th>cost</th>\n", | ||
| " </tr>\n", | ||
| " </thead>\n", | ||
| " <tbody>\n", | ||
| " <tr>\n", | ||
| " <th>0</th>\n", | ||
| " <td>A1BG</td>\n", | ||
| " <td>A2M</td>\n", | ||
| " <td>1.0</td>\n", | ||
| " </tr>\n", | ||
| " <tr>\n", | ||
| " <th>1</th>\n", | ||
| " <td>A1BG</td>\n", | ||
| " <td>ABCC6</td>\n", | ||
| " <td>1.0</td>\n", | ||
| " </tr>\n", | ||
| " <tr>\n", | ||
| " <th>2</th>\n", | ||
| " <td>A1BG</td>\n", | ||
| " <td>ACOT12</td>\n", | ||
| " <td>1.0</td>\n", | ||
| " </tr>\n", | ||
| " <tr>\n", | ||
| " <th>3</th>\n", | ||
| " <td>A1BG</td>\n", | ||
| " <td>ADH1A</td>\n", | ||
| " <td>1.0</td>\n", | ||
| " </tr>\n", | ||
| " <tr>\n", | ||
| " <th>4</th>\n", | ||
| " <td>A1BG</td>\n", | ||
| " <td>ADH4</td>\n", | ||
| " <td>1.0</td>\n", | ||
| " </tr>\n", | ||
| " </tbody>\n", | ||
| "</table>\n", | ||
| "</div>" | ||
| ], | ||
| "text/plain": [ | ||
| " protein1 protein2 cost\n", | ||
| "0 A1BG A2M 1.0\n", | ||
| "1 A1BG ABCC6 1.0\n", | ||
| "2 A1BG ACOT12 1.0\n", | ||
| "3 A1BG ADH1A 1.0\n", | ||
| "4 A1BG ADH4 1.0" | ||
| ] | ||
| }, | ||
| "execution_count": 3, | ||
| "metadata": {}, | ||
| "output_type": "execute_result" | ||
| } | ||
| ], | ||
| "source": [ | ||
| "pcnet['cost'] = 1.0\n", | ||
| "del pcnet['confidence']\n", | ||
| "\n", | ||
| "pcnet.head()" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 4, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "pcnet.to_csv('PCNet.05_2018.oi2', sep='\\t', index=False)\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [] | ||
| } | ||
| ], | ||
| "metadata": { | ||
| "kernelspec": { | ||
| "display_name": "Python 3", | ||
| "language": "python", | ||
| "name": "python3" | ||
| }, | ||
| "language_info": { | ||
| "codemirror_mode": { | ||
| "name": "ipython", | ||
| "version": 3 | ||
| }, | ||
| "file_extension": ".py", | ||
| "mimetype": "text/x-python", | ||
| "name": "python", | ||
| "nbconvert_exporter": "python", | ||
| "pygments_lexer": "ipython3", | ||
| "version": "3.6.5" | ||
| } | ||
| }, | ||
| "nbformat": 4, | ||
| "nbformat_minor": 2 | ||
| } |