Add LotfollahiTheis2023

dataset_processing/notebooks/LotfollahiTheis2023.ipynb

@@ -0,0 +1,214 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "338742b7-7103-4475-adf1-0b6122dd3abb",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "!pip install mygene statannotations scrublet scanpy scvelo decoupler matplotlib_venn goatools gseapy scperturb biomart PyComplexHeatmap statsmodels omnipath git+https://github.com/saezlab/pypath.git --quiet"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "bdf19927-f5a5-49e3-85ee-9b22bbed4b30",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>.container { width:95% !important; }</style>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import subprocess\n",
+    "import os\n",
+    "import sys\n",
+    "import matplotlib.backends.backend_pdf\n",
+    "import scanpy as sc\n",
+    "import matplotlib.pyplot as pl\n",
+    "import anndata as ad\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import seaborn as sns\n",
+    "import scvelo as scv\n",
+    "scv.settings.verbosity=1\n",
+    "\n",
+    "from pathlib import Path\n",
+    "\n",
+    "# Jupyter stuff\n",
+    "from tqdm.notebook import tqdm\n",
+    "from IPython.display import clear_output\n",
+    "from IPython.core.display import display, HTML\n",
+    "display(HTML(\"<style>.container { width:95% !important; }</style>\"))\n",
+    "\n",
+    "%matplotlib inline\n",
+    "\n",
+    "# Custom functions\n",
+    "sys.path.insert(1, '../')\n",
+    "from utils import *\n",
+    "\n",
+    "# scperturb package\n",
+    "sys.path.insert(1, '../package/src/')\n",
+    "from scperturb import *\n",
+    "\n",
+    "from pathlib import Path\n",
+    "figure_path = Path('../figures/')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "1276f674-d382-4a04-a5a1-89034a5d6892",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "TEMPDIR = Path('/scratch/peidli/scPerturb/')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "c604eabe-3e9e-48f7-a090-3fd76bc847f3",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['GSE206741_cell_metadata.tsv',\n",
+       " 'GSE206741_count_matrix.mtx',\n",
+       " 'GSE206741_gene_metadata.tsv']"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sorted([file.name for file in (TEMPDIR / 'LotfollahiTheis2023/').glob('*')])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "027e6124-715a-453c-81a2-e74b7166bfcf",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from scipy.io import mmread\n",
+    "from scipy.sparse import csr_matrix\n",
+    "obs = pd.read_csv(TEMPDIR / f'LotfollahiTheis2023/GSE206741_cell_metadata.tsv', index_col=0, sep='\\t')\n",
+    "var = pd.read_csv(TEMPDIR / f'LotfollahiTheis2023/GSE206741_gene_metadata.tsv', index_col=0, sep='\\t')\n",
+    "X = csr_matrix(mmread(TEMPDIR / f'LotfollahiTheis2023/GSE206741_count_matrix.mtx'))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "1697c169-08b2-4714-9d8d-f4c18980d494",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "adata = sc.AnnData(X.T, obs, var)\n",
+    "\n",
+    "adata.var.set_index('gene_short_name', inplace=True, drop=False)\n",
+    "adata.var.columns = ['ensembl_id']\n",
+    "adata.var.index.name = 'gene_symbol'\n",
+    "\n",
+    "adata.obs['perturbation'] = ['_'.join(np.sort([d1,d2])).replace('\\xa0','') for d1, d2 in zip(adata.obs.Drug1, adata.obs.Drug2)]\n",
+    "adata.obs['perturbation'] = [x.replace('DMSO_', '').replace('_DMSO', '').replace('DMSO', 'control') for x in adata.obs.perturbation]\n",
+    "adata.obs.index.name = 'cell_barcode'\n",
+    "adata.obs.rename({\n",
+    "    'n.umi': 'ncounts', \n",
+    "}, axis=1, inplace=True)\n",
+    "adata.obs.drop(['sample', 'Drug1', 'Drug2'], axis=1, inplace=True)\n",
+    "adata.obs = adata.obs[['perturbation', 'Size_Factor', 'ncounts', 'RT_well', 'Well']]\n",
+    "adata.obs['nperts'] = [p.count('_')+1-p.count('control') if type(p)==str else 0 for p in adata.obs.perturbation]\n",
+    "adata.obs['perturbation_type'] = 'drug'\n",
+    "adata.obs['disease'] = \"lung adenocarcinoma\"\n",
+    "adata.obs['cancer'] = True\n",
+    "adata.obs['tissue_type']=\"cell_line\"\n",
+    "adata.obs[\"cell_line\"] = \"A549\"\n",
+    "adata.obs[\"celltype\"] = 'lung epthelial cells'\n",
+    "adata.obs['organism'] = 'human'\n",
+    "#annotate_qc(adata, species='human')\n",
+    "#assert_annotations(adata)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "88c75250-16de-427c-b0a1-02b5a4cd75db",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fd6705a5-e938-41d9-af0b-c08651210975",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "08ad720e-25ee-42b5-a4b1-b5e6ea5091d3",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6a27157d-43c2-4017-85c6-1333e05dd182",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}