diff --git a/notebooks/CapeTown_Genomics_Tutorial_partII.ipynb b/notebooks/CapeTown_Genomics_Tutorial_partII.ipynb
index c67c16f1b414831c2e5fe5ad4be54845e399a713..c7e25353a370357cb5f71a48c799ceda5e75dc06 100644
--- a/notebooks/CapeTown_Genomics_Tutorial_partII.ipynb
+++ b/notebooks/CapeTown_Genomics_Tutorial_partII.ipynb
@@ -253,7 +253,7 @@
},
"outputs": [],
"source": [
- "! head ERR760779_paired.sam"
+ "! head $HOME/ERR760779_paired.sam"
]
},
{
@@ -271,7 +271,7 @@
},
"outputs": [],
"source": [
- "! du -h ERR760779_paired.sam"
+ "! du -h $HOME/ERR760779_paired.sam"
]
},
{
@@ -282,7 +282,7 @@
},
"outputs": [],
"source": [
- "! du -h ERR760779_1U.sam"
+ "! du -h $HOME/ERR760779_1U.sam"
]
},
{
@@ -293,7 +293,7 @@
},
"outputs": [],
"source": [
- "! du -h ERR760779_2U.sam"
+ "! du -h $HOME/ERR760779_2U.sam"
]
},
{
@@ -351,7 +351,7 @@
},
"outputs": [],
"source": [
- "! du -h ERR760779_paired.bam"
+ "! du -h $HOME/ERR760779_paired.bam"
]
},
{
@@ -462,7 +462,7 @@
},
"outputs": [],
"source": [
- "! cat ERR760779.markduplicates.metrics"
+ "! cat $HOME/ERR760779.markduplicates.metrics"
]
},
{
@@ -512,7 +512,47 @@
"it is common to realign reads around small indels. Since, differences in resolving the indels may\n",
"cause artificial SNPs in the downstream analysis.\n",
"The\n",
- "GATK software for instance offers the possibility to realign"
+ "GATK software for instance offers the possibility to realign\n",
+ "\n",
+ "\n",
+ "\n",
+ "Please run in the command line:\n",
+ " - sbatch ~/Workshop_SA/notebooks/slurm_scripts/launch_GATK.slurm\n",
+ "\n",
+ "\n",
+ "Then you have to index the newly produced BAM:\n",
+ " - sbatch ~/Workshop_SA/notebooks/slurm_scripts/launch_index2.slurm"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "#!/bin/bash \r\n",
+ "\r\n",
+ "#SBATCH --job-name=GATK\r\n",
+ "#SBATCH --cpus-per-task=1\r\n",
+ "#SBATCH --mem-per-cpu=4G\r\n",
+ "#SBATCH --time=6:00:00\r\n",
+ "#SBATCH --output=GATK.o\r\n",
+ "#SBATCH --error=GATK.e\r\n",
+ "\r\n",
+ "singularity exec container.img gatk-launch -T RealignerTargetCreator -nt 1 -R ~/Workshop_SA/notebooks/reference_genome/MTB_ancestor_reference.fasta -o ERR760779.intervals -I ERR760779.dedup.bam\r\n",
+ "\r\n",
+ "\r\n",
+ "singularity exec container.img gatk-launch --disable_bam_indexing -T IndelRealigner R ~/Workshop_SA/notebooks/reference_genome/MTB_ancestor_reference.fasta -targetIntervals ERR760779.intervals -I ERR760779.dedup.bam -o ERR760779.dedup.realigned.bam\r\n"
+ ]
+ }
+ ],
+ "source": [
+ "! cat /scicore/home/gagneux/loiseau/Workshop_SA/notebooks/slurm_scripts/launch_GATK.slurm"
]
},
{
diff --git a/notebooks/CapeTown_Genomics_Tutorial_partIII.ipynb b/notebooks/CapeTown_Genomics_Tutorial_partIII.ipynb
index 1bdd61f9db32a09774663509ffaa8c918e1a6137..0915b67c27576e6d8ff6d913efcf6f1a5fb66f3a 100644
--- a/notebooks/CapeTown_Genomics_Tutorial_partIII.ipynb
+++ b/notebooks/CapeTown_Genomics_Tutorial_partIII.ipynb
@@ -413,7 +413,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 9,
"metadata": {
"collapsed": true
},
@@ -507,9 +507,28 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 6,
"metadata": {
- "collapsed": true
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "/scicore/home/gagneux/loiseau\n"
+ ]
+ }
+ ],
+ "source": [
+ "%cd loiseau/"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {
+ "collapsed": false
},
"outputs": [],
"source": [
@@ -537,14 +556,37 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 13,
"metadata": {
- "collapsed": true
+ "collapsed": false
},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "['761110', 'A', 'T', 'Rv0667', 'D435V', 'RIF', 'Walker_resistant-resistant']\n",
+ "['4247431', 'G', 'C', 'Rv3795', 'M306I', 'EMB', 'Walker_resistant-resistant']\n",
+ "['4249583', 'G', 'A', 'Rv3795', 'D1024N', 'EMB', 'Boettger_DST']\n",
+ "['761100', 'C', 'A', 'Rv0667', 'Q432K', 'RIF', 'Walker_resistant-resistant']\n",
+ "['2155168', 'C', 'G', 'Rv1908c', 'S315T', 'INH', 'Walker_resistant-resistant']\n",
+ "['761155', 'C', 'T', 'Rv0667', 'S450L', 'RIF', 'Walker_resistant-resistant']\n",
+ "['761140', 'A', 'G', 'Rv0667', 'H445R', 'RIF', 'Walker_resistant-resistant']\n",
+ "['7581', 'G', 'A', 'Rv0006', 'D94N', 'FQ', 'Walker_resistant-resistant']\n",
+ "['7582', 'A', 'G', 'Rv0006', 'D94G', 'FQ', 'Walker_resistant-resistant']\n",
+ "['4247429', 'A', 'G', 'Rv3795', 'M306V', 'EMB', 'Walker_resistant-resistant']\n",
+ "['7570', 'C', 'T', 'Rv0006', 'A90V', 'FQ', 'Walker_resistant-resistant']\n",
+ "['1473246', 'A', 'G', 'rrs', 'A1401G', 'AK;CAP;KAN', 'Walker_resistant-resistant']\n",
+ "['1673432', 'T', 'C', 'Rv1483', 'T-8C', 'INH;ETH', 'Walker_resistant-resistant;Boettger_DST']\n",
+ "['761139', 'C', 'T', 'Rv0667', 'H445Y', 'RIF', 'Walker_resistant-resistant']\n",
+ "['1673425', 'C', 'T', 'Rv1483', 'C-15T', 'INH;ETH', 'Walker_resistant-resistant;Boettger_DST']\n",
+ "['4247730', 'G', 'C', 'Rv3795', 'G406A', 'EMB', 'Walker_resistant-resistant']\n"
+ ]
+ }
+ ],
"source": [
"with open('all_DRM_in_Eldholm.txt','w') as DRM_Eldholm_output_file:\n",
- " DRM_Eldholm_output_file.write('position\\tref\\talt\\t'+'\\t'.join(list_of_sample_names)+'\\n')\n",
+ " DRM_Eldholm_output_file.write('position\\tref\\talt\\tlocus\\tmutation\\t'+'\\t'.join(list_of_sample_names)+'\\n')\n",
" for items in VCF_merged_dico.items():\n",
" genomic_position = items[0]\n",
" ann = items[1]\n",
@@ -561,11 +603,34 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 14,
"metadata": {
- "collapsed": true
+ "collapsed": false
},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "('D435V', 4, 0)\n",
+ "('M306I', 1, 0)\n",
+ "('D1024N', 1, 0)\n",
+ "('Q432K', 1, 0)\n",
+ "('S315T', 248, 0)\n",
+ "('S450L', 234, 1)\n",
+ "('H445R', 1, 0)\n",
+ "('D94N', 0, 1)\n",
+ "('D94G', 3, 0)\n",
+ "('M306V', 1, 0)\n",
+ "('A90V', 3, 0)\n",
+ "('A1401G', 230, 0)\n",
+ "('T-8C', 1, 0)\n",
+ "('H445Y', 3, 0)\n",
+ "('C-15T', 1, 0)\n",
+ "('G406A', 234, 0)\n"
+ ]
+ }
+ ],
"source": [
"\n",
"with open('all_DRM_in_Eldholm.txt','r') as ifile:\n",
@@ -578,6 +643,15 @@
"\n",
" "
]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": []
}
],
"metadata": {
@@ -585,18 +659,6 @@
"display_name": "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": "2.7.11"
}
},
"nbformat": 4,
diff --git a/notebooks/slurm_scripts/launch_bamqc.slurm b/notebooks/slurm_scripts/launch_bamqc.slurm
index 434c173131b3401021f29a7f3ed72fff557628f8..42919a9555bcbb285326e96afd14f1849eb777a5 100644
--- a/notebooks/slurm_scripts/launch_bamqc.slurm
+++ b/notebooks/slurm_scripts/launch_bamqc.slurm
@@ -4,4 +4,4 @@
#SBATCH --cpus-per-task=1
#SBATCH --mem-per-cpu=4G
-singularity exec /home/container.img qualimap bamqc -bam ERR760779.dedup.bam -sd -sdmode 1 -outdir . -outfile ERR760779_bamqc
+singularity exec /home/container.img qualimap bamqc -bam ERR760779.dedup.realigned.bam -sd -sdmode 1 -outdir . -outfile ERR760779_bamqc
diff --git a/notebooks/slurm_scripts/launch_mpileup.slurm b/notebooks/slurm_scripts/launch_mpileup.slurm
index d737accc19399e483851c7fdad071fd3d8323e6a..aca1de106c3dfa65a4beb45dfcc0f0a65d481aa8 100644
--- a/notebooks/slurm_scripts/launch_mpileup.slurm
+++ b/notebooks/slurm_scripts/launch_mpileup.slurm
@@ -4,5 +4,5 @@
#SBATCH --cpus-per-task=1
#SBATCH --mem-per-cpu=4G
-singularity exec /home/container.img samtools mpileup -ABQ0 -q 20 -f ~/Workshop_SA/notebooks/reference_genome/MTB_ancestor_reference.fasta ERR760779.dedup.bam > ERR760779.pileup
+singularity exec /home/container.img samtools mpileup -ABQ0 -q 20 -f ~/Workshop_SA/notebooks/reference_genome/MTB_ancestor_reference.fasta ERR760779.dedup.realigned.bam > ERR760779.pileup