Mercurial > repos > davidvanzessen > mutation_analysis

comparison wrapper.sh @ 95:a66eb1c5374c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Wed, 08 Jun 2016 03:54:49 -0400
parents e39176ccddc8
children 5ffbf40cdd4b
comparison
equal deleted inserted replaced
94:e39176ccddc8 95:a66eb1c5374c
75 echo "---------------- merge_and_filter.r ----------------" 75 echo "---------------- merge_and_filter.r ----------------"
76 echo "---------------- merge_and_filter.r ----------------<br />" >> $output 76 echo "---------------- merge_and_filter.r ----------------<br />" >> $output
77 77
78 Rscript $dir/merge_and_filter.r $PWD/summary.txt $PWD/sequences.txt $PWD/mutationanalysis.txt $PWD/mutationstats.txt $PWD/hotspots.txt $outdir/identified_genes.txt $outdir/merged.txt $outdir/before_unique_filter.txt $outdir/unmatched.txt $method $functionality $unique ${filter_unique} ${class_filter} 2>&1 78 Rscript $dir/merge_and_filter.r $PWD/summary.txt $PWD/sequences.txt $PWD/mutationanalysis.txt $PWD/mutationstats.txt $PWD/hotspots.txt $outdir/identified_genes.txt $outdir/merged.txt $outdir/before_unique_filter.txt $outdir/unmatched.txt $method $functionality $unique ${filter_unique} ${class_filter} 2>&1
79 79
80 echo "---------------- creating new IMGT zip ----------------<br />"
81 echo "---------------- creating new IMGT zip ----------------<br />" >> $output
82
83 mkdir $outdir/new_IMGT
84
85 cat `find $PWD/files/ -name "1_*"` > "$outdir/new_IMGT/1_Summary.txt"
86 cat `find $PWD/files/ -name "2_*"` > "$outdir/new_IMGT/2_IMGT-gapped-nt-sequences.txt"
87 cat `find $PWD/files/ -name "3_*"` > "$outdir/new_IMGT/3_Nt-sequences.txt"
88 cat `find $PWD/files/ -name "4_*"` > "$outdir/new_IMGT/4_IMGT-gapped-AA-sequences.txt"
89 cat `find $PWD/files/ -name "5_*"` > "$outdir/new_IMGT/5_AA-sequences.txt"
90 cat `find $PWD/files/ -name "6_*"` > "$outdir/new_IMGT/6_Junction.txt"
91 cat `find $PWD/files/ -name "7_*"` > "$outdir/new_IMGT/7_V-REGION-mutation-and-AA-change-table.txt"
92 cat `find $PWD/files/ -name "8_*"` > "$outdir/new_IMGT/8_V-REGION-nt-mutation-statistics.txt"
93 cat `find $PWD/files/ -name "9_*"` > "$outdir/new_IMGT/9_V-REGION-AA-change-statistics.txt"
94 cat `find $PWD/files/ -name "10_*"` > "$outdir/new_IMGT/10_V-REGION-mutation-hotspots.txt"
95
96 Rscript $dir/tmp/igat.r $outdir/new_IMGT/ $outdir/merged.txt 2>&1
97
98
99 tmp="$PWD"
100 cd $outdir/new_IMGT/ #tar weirdness...
101 tar -cJf ../new_IMGT.txz *
102
103 cp $dir/tmp/IgAT.xlsm $outdir/new_IMGT/IgAT.xlsm
104
105 #tar -cJf ../IgAT.txz *
106 zip -r ../IgAT.zip *
107
108 cd $tmp
109
110
80 echo "---------------- mutation_analysis.r ----------------" 111 echo "---------------- mutation_analysis.r ----------------"
81 echo "---------------- mutation_analysis.r ----------------<br />" >> $output 112 echo "---------------- mutation_analysis.r ----------------<br />" >> $output
82 113
83 classes="ca,ca1,ca2,cg,cg1,cg2,cg3,cg4,cm,unmatched" 114 classes="ca,ca1,ca2,cg,cg1,cg2,cg3,cg4,cm,unmatched"
84 echo "R mutation analysis" 115 echo "R mutation analysis"
98 genes=(ca ca1 ca2 cg cg1 cg2 cg3 cg4 cm) 129 genes=(ca ca1 ca2 cg cg1 cg2 cg3 cg4 cm)
99 130
100 funcs=(sum mean median) 131 funcs=(sum mean median)
101 132
102 echo "---------------- sequence_overview.r ----------------" 133 echo "---------------- sequence_overview.r ----------------"
134 echo "---------------- sequence_overview.r ----------------" >> $output
103 135
104 mkdir $outdir/sequence_overview 136 mkdir $outdir/sequence_overview
105 137
106 #Rscript $dir/sequence_overview.r $outdir/identified_genes.txt $PWD/sequences.txt $outdir/merged.txt $outdir/sequence_overview $classes $outdir/hotspot_analysis_sum.txt 2>&1 138 #Rscript $dir/sequence_overview.r $outdir/identified_genes.txt $PWD/sequences.txt $outdir/merged.txt $outdir/sequence_overview $classes $outdir/hotspot_analysis_sum.txt 2>&1
107 Rscript $dir/sequence_overview.r $outdir/before_unique_filter.txt $outdir/merged.txt $outdir/sequence_overview $classes $outdir/hotspot_analysis_sum.txt 2>&1 139 Rscript $dir/sequence_overview.r $outdir/before_unique_filter.txt $outdir/merged.txt $outdir/sequence_overview $classes $outdir/hotspot_analysis_sum.txt 2>&1
171 echo "<a href='mutation_by_id.txt'>mutations by id</a><br />" >> $output 203 echo "<a href='mutation_by_id.txt'>mutations by id</a><br />" >> $output
172 echo "<a href='aa_id_mutations.txt'>AA mutations location by id</a><br />" >> $output 204 echo "<a href='aa_id_mutations.txt'>AA mutations location by id</a><br />" >> $output
173 echo "<a href='absent_aa_id.txt'>Absant AA locations by id</a><br />" >> $output 205 echo "<a href='absent_aa_id.txt'>Absant AA locations by id</a><br />" >> $output
174 echo "<a href='sequence_overview/index.html'>Sequence Overview</a><br />" >> $output 206 echo "<a href='sequence_overview/index.html'>Sequence Overview</a><br />" >> $output
175 echo "<a href='base_overview.html'>Base overview</a><br />" >> $output 207 echo "<a href='base_overview.html'>Base overview</a><br />" >> $output
208 echo "<a href='baseline.pdf'>Baseline PDF</a><br />" >> $output
209 echo "<a href='baseline.txt'>Baseline Table</a><br />" >> $output
210 echo "<a href='IgAT.zip'>IgAT zip</a><br />" >> $output
176 211
177 echo "---------------- images ----------------" 212 echo "---------------- images ----------------"
178 213
179 echo "<img src='all.png'/><br />" >> $output 214 echo "<img src='all.png'/><br />" >> $output
180 echo "<a href='all.txt'>download data</a><br />" >> $output 215 echo "<a href='all.txt'>download data</a><br />" >> $output
222 done < $outdir/transitions_all_sum.txt 257 done < $outdir/transitions_all_sum.txt
223 echo "</table>" >> $output 258 echo "</table>" >> $output
224 259
225 echo "</html>" >> $output 260 echo "</html>" >> $output
226 261
262 echo "---------------- baseline ----------------"
263 bash $dir/tmp/baseline/wrapper.sh 1 1 1 1 0 0 "25:26:38:55:65:104:-" $outdir/new_IMGT.txz "sample name" "$dir/tmp/baseline/IMGT-reference-seqs-IGHV-2015-11-05.fa" "$outdir/baseline.pdf" "Sequence.ID" "$outdir/baseline.txt"
227 264
228 #optional output for naive 265 #optional output for naive
229 266
230 echo "---------------- naive_output.r ----------------" 267 echo "---------------- naive_output.r ----------------"
231 268
232 if [[ "$naive_output" != "None" ]] 269 if [[ "$naive_output" != "None" ]]
233 then 270 then
234 echo "---------------- imgt_loader.r ----------------" 271 echo "---------------- imgt_loader.r ----------------"
235 #python $dir/imgt_loader.py --summ $PWD/summary.txt --aa $PWD/aa.txt --junction $PWD/junction.txt --output $naive_output 272 #python $dir/imgt_loader.py --summ $PWD/summary.txt --aa $PWD/aa.txt --junction $PWD/junction.txt --output $naive_output
236 Rscript --verbose $dir/imgt_loader.r $PWD/summary.txt $PWD/aa.txt $PWD/junction.txt $outdir/loader_output.txt 2>&1 273 Rscript --verbose $dir/imgt_loader.r $PWD/summary.txt $PWD/aa.txt $PWD/junction.txt $outdir/loader_output.txt 2>&1
274
237 echo "---------------- naive_output.r ----------------" 275 echo "---------------- naive_output.r ----------------"
238 Rscript $dir/naive_output.r $outdir/loader_output.txt $outdir/merged.txt ${naive_output_ca} ${naive_output_cg} ${naive_output_cm} $outdir/ntoverview.txt $outdir/ntsum.txt 2>&1 276 Rscript $dir/naive_output.r $outdir/loader_output.txt $outdir/merged.txt ${naive_output_ca} ${naive_output_cg} ${naive_output_cm} $outdir/ntoverview.txt $outdir/ntsum.txt 2>&1
239 fi 277 fi
240 278
241 echo "</table>" >> $outdir/base_overview.html 279 echo "</table>" >> $outdir/base_overview.html