Mercurial > repos > davidvanzessen > mutation_analysis

comparison wrapper.sh @ 0:74d2bc479bee draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Mon, 18 Aug 2014 04:04:37 -0400
parents
children 856b5b718d21
comparison
equal deleted inserted replaced
-1:000000000000 0:74d2bc479bee
1 #!/bin/bash
2 dir="$(cd "$(dirname "$0")" && pwd)"
3
4 input=$1
5 output=$2
6 outdir=$3
7 mkdir $outdir
8
9 unzip $input -d $PWD/files/ > $PWD/unziplog.log
10 cat $PWD/files/*/1_* > $PWD/summary.txt
11 cat $PWD/files/*/7_* > $PWD/mutationanalysis.txt
12 cat $PWD/files/*/8_* > $PWD/mutationstats.txt
13 cat $PWD/files/*/10_* > $PWD/hotspots.txt
14
15 mkdir $outdir/identification/
16 python $dir/gene_identification.py --input $PWD/summary.txt --outdir $outdir/identification/
17 genes=(ca ca1 ca2 cg cg1 cg2 cg3 cg4 cm)
18 tmp=$PWD/tmp
19 tmp2=$PWD/tmp2
20 hotspottmp=$PWD/hotspottmp
21 mutationtmp=$PWD/mutationtmp
22 touch $outdir/mutationandhotspot.txt
23 for gene in ${genes[@]}
24 do
25 echo "Running $gene <br />" >> $output
26 mkdir $outdir/$gene
27 echo "Filtering input..." >> $output
28 Rscript $dir/filter.r $PWD/summary.txt $outdir/identification/${gene}.txt $outdir/$gene/summary.txt
29 Rscript $dir/filter.r $PWD/mutationanalysis.txt $outdir/identification/${gene}.txt $outdir/$gene/mutationanalysis.txt
30 Rscript $dir/filter.r $PWD/mutationstats.txt $outdir/identification/${gene}.txt $outdir/$gene/mutationstats.txt
31 Rscript $dir/filter.r $PWD/hotspots.txt $outdir/identification/${gene}.txt $outdir/$gene/hotspots.txt
32 echo "done <br />" >> $output
33
34 echo "Running R script on $gene..." >> $output
35 Rscript --verbose $dir/mutation_analysis.r $outdir/$gene/mutationstats.txt $outdir/$gene/summary.txt $outdir/$gene/ 2>&1
36 echo "done <br />" >> $output
37
38 echo "Running Python script..." >> $output
39 python $dir/mutation_analysis.py --mutationfile $outdir/$gene/mutationanalysis.txt --hotspotfile $outdir/$gene/hotspots.txt --output $outdir/$gene/hotspot_analysis.txt
40 echo "done <br />" >> $output
41 echo "Done with $gene <br />" >> $output
42 cut $outdir/$gene/mutations.txt -d, -f2,3,4 > $mutationtmp
43 cut $outdir/$gene/hotspot_analysis.txt -d, -f2,3,4 > $hotspottmp
44 cat $mutationtmp $hotspottmp > $tmp
45 paste $outdir/mutationandhotspot.txt -d, $tmp > $tmp2
46 cat $tmp2 > $outdir/mutationandhotspot.txt
47 done
48
49 Rscript --verbose $dir/mutation_analysis.r $PWD/mutationstats.txt $PWD/summary.txt $outdir/ 2>&1
50 python $dir/mutation_analysis.py --mutationfile $PWD/mutationanalysis.txt --hotspotfile $PWD/hotspots.txt --output $outdir/hotspot_analysis.txt
51
52 cut $outdir/mutations.txt -d, -f2,3,4 > $mutationtmp
53 cut $outdir/hotspot_analysis.txt -d, -f2,3,4 > $hotspottmp
54 cat $mutationtmp $hotspottmp > $tmp
55 paste $outdir/mutationandhotspot.txt -d, $tmp > $tmp2
56 cat $tmp2 > $outdir/mutationandhotspot.txt
57
58 cut $outdir/ca1/mutations.txt -d, -f1 > $mutationtmp
59 cut $outdir/ca1/hotspot_analysis.txt -d, -f1 > $hotspottmp
60 cat $mutationtmp $hotspottmp > $tmp
61 paste $tmp $outdir/mutationandhotspot.txt -d, > $tmp2
62 cat $tmp2 | tr -s "," > $outdir/mutationandhotspot.txt
63
64 ca_n=`cat $outdir/ca/n.txt`
65 ca1_n=`cat $outdir/ca1/n.txt`
66 ca2_n=`cat $outdir/ca2/n.txt`
67 cg_n=`cat $outdir/cg/n.txt`
68 cg1_n=`cat $outdir/cg1/n.txt`
69 cg2_n=`cat $outdir/cg2/n.txt`
70 cg3_n=`cat $outdir/cg3/n.txt`
71 cg4_n=`cat $outdir/cg4/n.txt`
72 cm_n=`cat $outdir/cm/n.txt`
73 #all_n=$((ca_n + cg_n + cm_n))
74 all_n=`cat $outdir/n.txt`
75
76
77 echo "<html><table border='1'>" > $output
78 echo "<tr><th>info</th>" >> $output
79 echo "<th><a href='identification/ca.txt'>ca (N = $ca_n)</a></th>" >> $output
80 echo "<th><a href='identification/ca1.txt'>ca1 (N = $ca1_n)</a></th>" >> $output
81 echo "<th><a href='identification/ca2.txt'>ca2 (N = $ca2_n)</a></th>" >> $output
82 echo "<th><a href='identification/cg.txt'>cg (N = $cg_n)</a></th>" >> $output
83 echo "<th><a href='identification/cg1.txt'>cg1 (N = $cg1_n)</a></th>" >> $output
84 echo "<th><a href='identification/cg2.txt'>cg2 (N = $cg2_n)</a></th>" >> $output
85 echo "<th><a href='identification/cg3.txt'>cg3 (N = $cg3_n)</a></th>" >> $output
86 echo "<th><a href='identification/cg4.txt'>cg4 (N = $cg4_n)</a></th>" >> $output
87 echo "<th><a href='identification/cm.txt'>cm (N = $cm_n)</a></th>" >> $output
88 echo "<th>all (N = $all_n)</th></tr>" >> $output
89 while IFS=, read name cax cay caz ca1x ca1y ca1z ca2x ca2y ca2z cgx cgy cgz cg1x cg1y cg1z cg2x cg2y cg2z cg3x cg3y cg3z cg4x cg4y cg4z cmx cmy cmz allx ally allz
90 do
91 echo "<tr><td>$name</td><td>${cax}/${cay} (${caz}%)</td><td>${ca1x}/${ca1y} (${ca1z}%)</td><td>${ca2x}/${ca2y} (${ca2z}%)</td><td>${cgx}/${cgy} (${cgz}%)</td><td>${cg1x}/${cg1y} (${cg1z}%)</td><td>${cg2x}/${cg2y} (${cg2z}%)</td><td>${cg3x}/${cg3y} (${cg3z}%)</td><td>${cg4x}/${cg4y} (${cg4z}%)</td><td>${cmx}/${cmy} (${cmz}%)</td><td>${allx}/${ally} (${allz}%)</td></tr>" >> $output
92 done < $outdir/mutationandhotspot.txt
93 echo "</table>" >> $output
94 echo "<a href='identification/unmatched.txt'>umatched</a><br />" >> $output
95
96 Rscript $dir/piechart.r "${ca_n},${cg_n},${cm_n}" "IgA - ${ca_n},IgG - ${cg_n},IgM? - ${cm_n}" "Ig* (N = $all_n)" $outdir/all.png 2>&1
97 Rscript $dir/piechart.r "${ca1_n},${ca2_n}" "IgA1 - ${ca1_n},IgA2 - ${ca2_n}" "IgA (N = $ca_n)" $outdir/ca.png 2>&1
98 Rscript $dir/piechart.r "${cg1_n},${cg2_n},${cg3_n},${cg4_n}" "IgG1 - ${cg1_n},IgG2 - ${cg2_n},IgG3 - ${cg3_n},IgG4 - ${cg4_n}" "IgG (N = $cg_n)" $outdir/cg.png 2>&1
99
100 echo "<img src='all.png'/>" >> $output
101 echo "<img src='ca.png'/>" >> $output
102 echo "<img src='cg.png'/>" >> $output
103
104 for gene in ${genes[@]}
105 do
106 echo "<table border='1'><caption>$gene transition table</caption>" >> $output
107 while IFS=, read from a c g t
108 do
109 echo "<tr><td>$from</td><td>$a</td><td>$c</td><td>$g</td><td>$t</td></tr>" >> $output
110 done < $outdir/$gene/transitions.txt
111 echo "</table>" >> $output
112 done
113
114 echo "<table border='1'><caption>All transition table</caption>" >> $output
115 while IFS=, read from a c g t
116 do
117 echo "<tr><td>$from</td><td>$a</td><td>$c</td><td>$g</td><td>$t</td></tr>" >> $output
118 done < $outdir/transitions.txt
119 echo "</table>" >> $output
120
121 echo "</html>" >> $output