addExamples

urmi-21 · Jan 16, 2020 · 4f99fc8 · 4f99fc8
1 parent 25c7c61
commit 4f99fc8
Showing 1 changed file with 111 additions and 5 deletions.
diff --git a/examples/Maize_lncRNA_prediction/Maize_lncRNAs.ipynb b/examples/Maize_lncRNA_prediction/Maize_lncRNAs.ipynb
@@ -2,16 +2,122 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[93mLogs will be saved to 2020-01-16-16_27_35_pyrpipe.log\u001b[0m\n"
+     ]
+    }
+   ],
    "source": [
     "from pyrpipe import sra,mapping,assembly,qc,tools\n",
     "#First get the srr accessions of the runs. For this one can use the python package pysradb or R package sradb\n",
-    "runsSmol=[]\n",
-    "maize_data=\"\"\n",
-    "working_dir=\"\""
+    "#runs=['SRR3098746','SRR3098745','SRR3098744'] #from the study SRP068369\n",
+    "runs=['SRR3098746'] #from the study SRP068369\n",
+    "#set up directories\n",
+    "maize_data=\"/home/usingh/work/urmi/hoap/test/maize/maize_data\"\n",
+    "workingDir=\"/home/usingh/work/urmi/hoap/test/maize\"\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Download data, pre-process"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sraObjects=[]\n",
+    "for x in runs:\n",
+    "    thisSraOb=sra.SRA(x,workingDir)\n",
+    "    if thisSraOb.download_sra():\n",
+    "        sraObjects.append(thisSraOb)\n",
+    "    else:\n",
+    "        print(\"Download failed:\"+x)\n",
+    "        \n",
+    "#perform fastq dump and qc\n",
+    "\n",
+    "#create a Trimgalore object\n",
+    "tgOpts={\"--cores\": \"10\"}\n",
+    "tg=qc.Trimgalore(**tgOpts)\n",
+    "\n",
+    "for x in sraObjects:\n",
+    "    #to fastq\n",
+    "    x.run_fasterqdump(delete_sra=True,**{\"-e\":\"20\",\"-f\":\"\",\"-t\":workingDir}) #use 20 threads\n",
+    "    #perform qc using trim galore\n",
+    "    x.perform_qc(tg)\n",
+    "    \n",
+    "\n",
+    "        "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Map using STAR"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[91m\u001b[1mCan not find STAR\u001b[0m\n"
+     ]
+    },
+    {
+     "ename": "Exception",
+     "evalue": "ERROR: STAR not found.",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mException\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-2-96d918c7c981>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      4\u001b[0m             }\n\u001b[1;32m      5\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 6\u001b[0;31m \u001b[0mstar\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmapping\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mStar\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstar_index\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mstarParams\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m#provided index is invalid\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      7\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      8\u001b[0m \u001b[0;31m#create star index\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/work/urmi/hoap/pyrpipe/pyrpipe/mapping.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, star_index, **kwargs)\u001b[0m\n\u001b[1;32m    312\u001b[0m         \u001b[0;31m#check if star exists\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    313\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mpe\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcheck_dependencies\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdep_list\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 314\u001b[0;31m             \u001b[0;32mraise\u001b[0m \u001b[0mException\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"ERROR: \"\u001b[0m\u001b[0;34m+\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprogramName\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0;34m\" not found.\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    315\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    316\u001b[0m         self.valid_args=['--help','--parametersFiles','--sysShell','--runMode','--runThreadN','--runDirPerm','--runRNGseed','--quantMode','--quantTranscriptomeBAMcompression','--quantTranscriptomeBan','--twopassMode','--twopass1readsN',\n",
+      "\u001b[0;31mException\u001b[0m: ERROR: STAR not found."
+     ]
+    }
+   ],
+   "source": [
+    "starParams={\"--outFilterType\":\"BySJout\",\n",
+    "            \"--runThreadN\":\"8\",\n",
+    "            \"--outSAMtype\": \"BAM SortedByCoordinate\"\n",
+    "            }\n",
+    "\n",
+    "star=mapping.Star(star_index=\"\",**starParams) #provided index is invalid\n",
+    "\n",
+    "#create star index\n",
+    "indexOut=maize_data+\"/starindex\"\n",
+    "inFasta=maize_data+\"Zea_mays.B73_RefGen_v4.dna.toplevel.1_10.fa\"\n",
+    "star.build_index(index_path=indexOut,inFasta)\n",
+    "\n",
+    "#after building index run star\n",
+    "star_out=[]\n",
+    "for x in sraObjects:\n",
+    "    star_out.append(star.perform_alignment(x))"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {