From a97f556e676b56137b53acae1d45a8af13b907c5 Mon Sep 17 00:00:00 2001
From: Julien Cornut <julien.cornut@hesge.ch>
Date: Fri, 26 Feb 2016 11:58:01 +0100
Subject: [PATCH] Automatic Update
---
ProcessFASTQ.ipynb | 34 ++++++++++++++++++++++++++++++++++
1 file changed, 34 insertions(+)
diff --git a/ProcessFASTQ.ipynb b/ProcessFASTQ.ipynb
index 3555de0..1175871 100644
--- a/ProcessFASTQ.ipynb
+++ b/ProcessFASTQ.ipynb
@@ -751,6 +751,40 @@
"print(\"Filtering non-codant tRNA run time : {0}\".format(delta))"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "# Testing\n",
+ "\n",
+ "with open(\"3-Filtered/\" +fname+\".fastq\",\"r\") as filtered, \\\n",
+ " open(\"4-Bowtied/\" +fname+\".sam\",\"r\") as matches, \\\n",
+ " open(\"5-ncRNA-Removed/\"+fname+\".fastq\",\"w\") as substracted: \n",
+ " \n",
+ " # Iterator over fastq file\n",
+ " filt_iter = SeqIO.parse(filtered,\"fastq\")\n",
+ " \n",
+ " # Strip header (as in original script)\n",
+ " for _ in range(415-3): matches.readline()\n",
+ "\n",
+ " # Check last lines\n",
+ " print(matches.readline())\n",
+ " print(matches.readline())\n",
+ " print(matches.readline())\n",
+ " \n",
+ " # Generator over fastq where the corresponding sam field is 4,\n",
+ " # meaning no reported alignment\n",
+ " sub_iter = (rec for rec in filt_iter \\\n",
+ " if matches.readline().split('\\t')[1] == '4')\n",
+ "\n",
+ " # Write back fastq\n",
+ " SeqIO.write(sub_iter,substracted,\"fastq\")"
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {},
--
GitLab