{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Cell/particle Counting and scoring stained objects using CellProfiler"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebook demonstrates how to process plates associated to the paper ['Integration of biological data by kernels on graph nodes allows prediction of new genes involved in mitotic chromosome condensation.'](http://dx.doi.org/10.1091/mbc.E13-04-0221) using [CellProfiler](http://cellprofiler.org/).\n",
    "We use the example pipeline [Cell/particle counting, and scoring the percentage of stained objects](http://cellprofiler.org/examples/#PercentPositive). This pipeline is for two channels images only."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Import Packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# %tb\n",
    "\n",
    "# Import Cell Profiler Dependencies\n",
    "import cellprofiler\n",
    "import cellprofiler.preferences as cpprefs\n",
    "import cellprofiler.module as cpm\n",
    "import cellprofiler.pipeline as cpp\n",
    "cpprefs.set_headless()\n",
    "\n",
    "# Inject Image module used to inject OMERO image planes into Cell Profiler Pipeline\n",
    "from cellprofiler.modules.injectimage import InjectImage\n",
    "\n",
    "# Import Numpy\n",
    "import numpy as np\n",
    "\n",
    "# Import Python System Packages\n",
    "import os\n",
    "import tempfile\n",
    "import pandas\n",
    "import warnings\n",
    "\n",
    "# Import Matplotlib\n",
    "import matplotlib\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Set Cell Output Directory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "new_output_directory = os.path.normcase(tempfile.mkdtemp())\n",
    "cpprefs.set_default_output_directory(new_output_directory)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Create connection to IDR (Public Database : Read-only!)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
   "from idr import connection; \n",
    "conn = connection()\n",
    "print conn"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Fetch the Plate that contains the Images to be analysed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plate_id = 422\n",
    "plate = conn.getObject(\"Plate\", plate_id)\n",
    "print 'Plate Name: ', plate.getName()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load pipeline and inspect modules\n",
    "from os.path import expanduser\n",
    "home = expanduser(\"~\")\n",
    "pipeline = cpp.Pipeline()\n",
    "pipeline.load(home+\"/notebooks/includes/ExamplePercentPositive.cppipe\")\n",
    "\n",
    "# Remove first 4 modules: Images, Metadata, NamesAndTypes, Groups...\n",
    "# (replaced by InjectImage module below)\n",
    "for i in range(4):\n",
    "    print 'Remove module: ', pipeline.modules()[0].module_name\n",
    "    pipeline.remove_module(1)\n",
    "\n",
    "print 'Pipeline modules:'\n",
    "for module in pipeline.modules():\n",
    "    print module.module_num, module.module_name"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Run Cell Profiler Pipeline on a Plate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "Nuclei = pandas.DataFrame()\n",
    "files = list()\n",
    "\n",
    "# create list from generator\n",
    "wells = list(plate.listChildren())\n",
    "well_count = len(wells)\n",
    "\n",
    "# Set the limit to a lower value e.g. 10 wells to speed up the process.\n",
    "limit = well_count\n",
    "for count, well in zip(range(limit), wells):\n",
    "    print 'Well: %s/%s' % (count + 1, well_count), 'row:', well.row, 'column:', well.column\n",
    "    # Load a single Image per Well\n",
    "    image = well.getImage(0)\n",
    "    pixels = image.getPrimaryPixels()\n",
    "    size_c = image.getSizeC()\n",
    "    \n",
    "    # For each Image in IDR, we copy the pipeline and inject image modules\n",
    "    pipeline_copy = pipeline.copy()\n",
    "    \n",
    "    # Inject image for each Channel (pipeline only handles 2 channels)\n",
    "    for c in range(0, size_c):\n",
    "        \n",
    "        plane = pixels.getPlane(0, c, 0)\n",
    "        image_name = image.getName()\n",
    "        \n",
    "        # Name of the channel expected in the pipeline\n",
    "        if c == 0:\n",
    "            image_name = 'OrigBlue'\n",
    "        if c == 1:\n",
    "            image_name = 'OrigGreen'\n",
    "        \n",
    "        inject_image_module = InjectImage(image_name, plane)\n",
    "        inject_image_module.set_module_num(1)\n",
    "        pipeline_copy.add_module(inject_image_module)\n",
    "    \n",
    "    m = pipeline_copy.run()\n",
    "    \n",
    "    #Results obtained as CSV from Cell Profiler\n",
    "    path = new_output_directory + '/Nuclei.csv'\n",
    "    f = pandas.read_csv(path, index_col=None, header=0)\n",
    "    f['Image'] = image.getId()\n",
    "    f['Well'] = well.getId()\n",
    "    f['Cell_Count'] = len(f.index)\n",
    "    files.append(f)\n",
    "\n",
    "Nuclei = pandas.concat(files, ignore_index=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Calculate statistics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "Nuclei.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "matplotlib.rcParams['figure.figsize'] = (32.0, 30.0)\n",
    "#Drop few columns\n",
    "df = Nuclei.drop(['Image', 'ImageNumber', 'Well', 'ObjectNumber', 'Number_Object_Number', 'Classify_PH3Neg', 'Classify_PH3Pos'], axis=1)\n",
    "df.hist();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<br>\n",
    "### Close the connection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "conn.close()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "### License\n",
    "\n",
    "Copyright (C) 2018 University of Dundee. All Rights Reserved.\n",
    "\n",
    "This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version.\n",
    "\n",
    "This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program; if not, write to the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "OMERO Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}