|
0
|
1 #!/bin/bash
|
|
4
|
2 set -e
|
|
0
|
3 dir="$(cd "$(dirname "$0")" && pwd)"
|
|
|
4 input=$1
|
|
19
|
5 method=$2
|
|
|
6 output=$3
|
|
|
7 outdir=$4
|
|
|
8 title=$5
|
|
22
|
9 include_fr1=$6
|
|
0
|
10 mkdir $outdir
|
|
|
11
|
|
|
12 unzip $input -d $PWD/files/ > $PWD/unziplog.log
|
|
|
13 cat $PWD/files/*/1_* > $PWD/summary.txt
|
|
|
14 cat $PWD/files/*/7_* > $PWD/mutationanalysis.txt
|
|
|
15 cat $PWD/files/*/8_* > $PWD/mutationstats.txt
|
|
|
16 cat $PWD/files/*/10_* > $PWD/hotspots.txt
|
|
3
|
17
|
|
26
|
18 #BLASTN_DIR="/home/galaxy/tmp/blast/ncbi-blast-2.2.30+/bin"
|
|
19
|
19
|
|
|
20 echo "${BLASTN_DIR}"
|
|
|
21
|
|
|
22 echo "identification ($method)"
|
|
|
23
|
|
|
24 if [[ "${method}" == "custom" ]] ; then
|
|
|
25 python $dir/gene_identification.py --input $PWD/summary.txt --output $outdir/identified_genes.txt
|
|
|
26 else
|
|
|
27 ID_index=$(cat $PWD/summary.txt | grep -o -P ".+Sequence ID" | grep -o -P "\t" | wc -l)
|
|
|
28 ID_index=$((ID_index+1))
|
|
|
29 sequence_index=$(cat $PWD/summary.txt | grep -o -P ".+\tSequence" | grep -o -P "\t" | wc -l)
|
|
|
30 sequence_index=$((sequence_index+1))
|
|
|
31
|
|
|
32 echo "$ID_index ${sequence_index}"
|
|
|
33
|
|
|
34 cat $PWD/summary.txt | tail -n+2 | cut -f ${ID_index},${sequence_index} | awk '{print ">" $1 "\n" $2}' > $PWD/sequences.fasta
|
|
|
35
|
|
|
36 echo -e "qseqid\tsseqid\tpident\tlength\tmismatch\tgapopen\tqstart\tqend\tsstart\tsend\tevalue\tbitscore" > $outdir/identified_genes.txt
|
|
|
37 ${BLASTN_DIR}/blastn -task blastn -db $dir/subclass_definition.db -query $PWD/sequences.fasta -outfmt 6 >> $outdir/identified_genes.txt
|
|
|
38 fi
|
|
|
39
|
|
|
40
|
|
|
41
|
|
4
|
42 echo "merging"
|
|
19
|
43 Rscript $dir/merge_and_filter.r $PWD/summary.txt $PWD/mutationanalysis.txt $PWD/mutationstats.txt $PWD/hotspots.txt $outdir/identified_genes.txt $outdir/merged.txt $outdir/unmatched.txt $method
|
|
0
|
44
|
|
4
|
45 genes="ca,ca1,ca2,cg,cg1,cg2,cg3,cg4,cm"
|
|
|
46 echo "R mutation analysis"
|
|
22
|
47 Rscript $dir/mutation_analysis.r $outdir/merged.txt $genes $outdir ${include_fr1} 2>&1
|
|
4
|
48 echo "python mutation analysis"
|
|
31
|
49 python $dir/mutation_analysis.py --input $outdir/merged.txt --genes $genes --includefr1 "${inlcude_fr1}" --output $outdir/hotspot_analysis.txt
|
|
26
|
50 echo "R AA histogram"
|
|
|
51 Rscript $dir/aa_histogram.r $outdir/aa_mutations.txt $outdir/aa_histogram.png 2>&1
|
|
4
|
52
|
|
|
53 cat $outdir/mutations.txt $outdir/hotspot_analysis.txt > $outdir/result.txt
|
|
|
54
|
|
0
|
55 genes=(ca ca1 ca2 cg cg1 cg2 cg3 cg4 cm)
|
|
|
56
|
|
|
57
|
|
1
|
58 echo "<html><center><h1>$title</h1></center><table border='1'>" > $output
|
|
0
|
59 echo "<tr><th>info</th>" >> $output
|
|
4
|
60 for gene in ${genes[@]}
|
|
|
61 do
|
|
|
62 tmp=`cat $outdir/${gene}_n.txt`
|
|
|
63 echo "<th><a href='matched_${gene}.txt'>${gene} (N = $tmp)</a></th>" >> $output
|
|
|
64 done
|
|
|
65 tmp=`cat $outdir/total_n.txt`
|
|
|
66 echo "<th><a href='matched_all.txt'>all (N = $tmp)</a></th>" >> $output
|
|
|
67
|
|
0
|
68 while IFS=, read name cax cay caz ca1x ca1y ca1z ca2x ca2y ca2z cgx cgy cgz cg1x cg1y cg1z cg2x cg2y cg2z cg3x cg3y cg3z cg4x cg4y cg4z cmx cmy cmz allx ally allz
|
|
25
|
69 do
|
|
|
70 if [ "$name" == "FR S/R (ratio)" ] || [ "$name" == "CDR S/R (ratio)" ] ; then #meh
|
|
|
71 echo "<tr><td>$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>" >> $output
|
|
|
72 else
|
|
0
|
73 echo "<tr><td>$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
|
|
25
|
74 fi
|
|
4
|
75 done < $outdir/result.txt
|
|
0
|
76 echo "</table>" >> $output
|
|
21
|
77 echo "<a href='unmatched.txt'>unmatched</a><br /><a href='motif_per_seq.txt'>motif per sequence</a><br />" >> $output
|
|
2
|
78
|
|
|
79
|
|
4
|
80 echo "<img src='all.png'/><br />" >> $output
|
|
26
|
81 echo "<a href='all.txt'>download data</a><br />" >> $output
|
|
4
|
82 if [ -a $outdir/ca.png ]
|
|
|
83 then
|
|
|
84 echo "<img src='ca.png'/><br />" >> $output
|
|
26
|
85 echo "<a href='ca.txt'>download data</a><br />" >> $output
|
|
4
|
86 fi
|
|
|
87 if [ -a $outdir/cg.png ]
|
|
|
88 then
|
|
|
89 echo "<img src='cg.png'/><br />" >> $output
|
|
26
|
90 echo "<a href='cg.txt'>download data</a><br />" >> $output
|
|
4
|
91 fi
|
|
22
|
92 if [ -a $outdir/scatter.png ]
|
|
|
93 then
|
|
|
94 echo "<img src='scatter.png'/><br />" >> $output
|
|
26
|
95 echo "<a href='scatter.txt'>download data</a><br />" >> $output
|
|
|
96 fi
|
|
|
97 if [ -a $outdir/aa_histogram.png ]
|
|
|
98 then
|
|
|
99 echo "<img src='aa_histogram.png'/><br />" >> $output
|
|
|
100 echo "<a href='aa_histogram.txt'>download data</a><br />" >> $output
|
|
22
|
101 fi
|
|
2
|
102
|
|
0
|
103 for gene in ${genes[@]}
|
|
|
104 do
|
|
|
105 echo "<table border='1'><caption>$gene transition table</caption>" >> $output
|
|
|
106 while IFS=, read from a c g t
|
|
|
107 do
|
|
|
108 echo "<tr><td>$from</td><td>$a</td><td>$c</td><td>$g</td><td>$t</td></tr>" >> $output
|
|
4
|
109 done < $outdir/transitions_${gene}.txt
|
|
0
|
110 echo "</table>" >> $output
|
|
|
111 done
|
|
|
112
|
|
|
113 echo "<table border='1'><caption>All transition table</caption>" >> $output
|
|
|
114 while IFS=, read from a c g t
|
|
|
115 do
|
|
|
116 echo "<tr><td>$from</td><td>$a</td><td>$c</td><td>$g</td><td>$t</td></tr>" >> $output
|
|
|
117 done < $outdir/transitions.txt
|
|
|
118 echo "</table>" >> $output
|
|
|
119
|
|
|
120 echo "</html>" >> $output
|
|
2
|
121
|
|
|
122 #rm $outdir/HS12RSS.txt
|
|
|
123 #rm $outdir/HS23RSS.txt
|
