|
0
|
1 #!/bin/bash
|
|
4
|
2 set -e
|
|
0
|
3 dir="$(cd "$(dirname "$0")" && pwd)"
|
|
|
4 input=$1
|
|
19
|
5 method=$2
|
|
102
|
6 log=$3 #becomes the main html page at the end
|
|
19
|
7 outdir=$4
|
|
102
|
8 output="$outdir/index.html" #copied to $log location at the end
|
|
19
|
9 title=$5
|
|
22
|
10 include_fr1=$6
|
|
34
|
11 functionality=$7
|
|
|
12 unique=$8
|
|
69
|
13 naive_output_ca=$9
|
|
|
14 naive_output_cg=${10}
|
|
|
15 naive_output_cm=${11}
|
|
|
16 filter_unique=${12}
|
|
|
17 class_filter=${13}
|
|
0
|
18 mkdir $outdir
|
|
|
19
|
|
55
|
20 echo "---------------- read parameters ----------------"
|
|
102
|
21 echo "---------------- read parameters ----------------<br />" > $log
|
|
55
|
22
|
|
|
23 echo "unpacking IMGT file"
|
|
|
24
|
|
89
|
25
|
|
|
26
|
|
35
|
27 type="`file $input`"
|
|
|
28 if [[ "$type" == *"Zip archive"* ]] ; then
|
|
|
29 echo "Zip archive"
|
|
|
30 echo "unzip $input -d $PWD/files/"
|
|
|
31 unzip $input -d $PWD/files/
|
|
|
32 elif [[ "$type" == *"XZ compressed data"* ]] ; then
|
|
|
33 echo "ZX archive"
|
|
|
34 echo "tar -xJf $input -C $PWD/files/"
|
|
|
35 mkdir -p $PWD/files/$title
|
|
|
36 tar -xJf $input -C $PWD/files/$title
|
|
|
37 fi
|
|
|
38
|
|
64
|
39 cat `find $PWD/files/ -name "1_*"` > $PWD/summary.txt
|
|
|
40 cat `find $PWD/files/ -name "3_*"` > $PWD/sequences.txt
|
|
|
41 cat `find $PWD/files/ -name "5_*"` > $PWD/aa.txt
|
|
|
42 cat `find $PWD/files/ -name "6_*"` > $PWD/junction.txt
|
|
|
43 cat `find $PWD/files/ -name "7_*"` > $PWD/mutationanalysis.txt
|
|
|
44 cat `find $PWD/files/ -name "8_*"` > $PWD/mutationstats.txt
|
|
|
45 cat `find $PWD/files/ -name "10_*"` > $PWD/hotspots.txt
|
|
|
46
|
|
|
47 #cat $PWD/files/*/1_* > $PWD/summary.txt
|
|
|
48 #cat $PWD/files/*/3_* > $PWD/sequences.txt
|
|
|
49 #cat $PWD/files/*/5_* > $PWD/aa.txt
|
|
|
50 #cat $PWD/files/*/6_* > $PWD/junction.txt
|
|
|
51 #cat $PWD/files/*/7_* > $PWD/mutationanalysis.txt
|
|
|
52 #cat $PWD/files/*/8_* > $PWD/mutationstats.txt
|
|
|
53 #cat $PWD/files/*/10_* > $PWD/hotspots.txt
|
|
3
|
54
|
|
26
|
55 #BLASTN_DIR="/home/galaxy/tmp/blast/ncbi-blast-2.2.30+/bin"
|
|
19
|
56
|
|
|
57 echo "${BLASTN_DIR}"
|
|
|
58
|
|
89
|
59 echo "---------------- identification ($method) ----------------"
|
|
102
|
60 echo "---------------- identification ($method) ----------------<br />" >> $log
|
|
55
|
61
|
|
19
|
62 if [[ "${method}" == "custom" ]] ; then
|
|
|
63 python $dir/gene_identification.py --input $PWD/summary.txt --output $outdir/identified_genes.txt
|
|
|
64 else
|
|
|
65 ID_index=$(cat $PWD/summary.txt | grep -o -P ".+Sequence ID" | grep -o -P "\t" | wc -l)
|
|
|
66 ID_index=$((ID_index+1))
|
|
|
67 sequence_index=$(cat $PWD/summary.txt | grep -o -P ".+\tSequence" | grep -o -P "\t" | wc -l)
|
|
|
68 sequence_index=$((sequence_index+1))
|
|
|
69
|
|
|
70 cat $PWD/summary.txt | tail -n+2 | cut -f ${ID_index},${sequence_index} | awk '{print ">" $1 "\n" $2}' > $PWD/sequences.fasta
|
|
|
71
|
|
|
72 echo -e "qseqid\tsseqid\tpident\tlength\tmismatch\tgapopen\tqstart\tqend\tsstart\tsend\tevalue\tbitscore" > $outdir/identified_genes.txt
|
|
|
73 ${BLASTN_DIR}/blastn -task blastn -db $dir/subclass_definition.db -query $PWD/sequences.fasta -outfmt 6 >> $outdir/identified_genes.txt
|
|
|
74 fi
|
|
|
75
|
|
55
|
76 echo "---------------- merge_and_filter.r ----------------"
|
|
102
|
77 echo "---------------- merge_and_filter.r ----------------<br />" >> $log
|
|
19
|
78
|
|
90
|
79 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
|
|
0
|
80
|
|
98
|
81 echo "---------------- creating new IMGT zip ----------------"
|
|
102
|
82 echo "---------------- creating new IMGT zip ----------------<br />" >> $log
|
|
95
|
83
|
|
|
84 mkdir $outdir/new_IMGT
|
|
|
85
|
|
|
86 cat `find $PWD/files/ -name "1_*"` > "$outdir/new_IMGT/1_Summary.txt"
|
|
|
87 cat `find $PWD/files/ -name "2_*"` > "$outdir/new_IMGT/2_IMGT-gapped-nt-sequences.txt"
|
|
|
88 cat `find $PWD/files/ -name "3_*"` > "$outdir/new_IMGT/3_Nt-sequences.txt"
|
|
|
89 cat `find $PWD/files/ -name "4_*"` > "$outdir/new_IMGT/4_IMGT-gapped-AA-sequences.txt"
|
|
|
90 cat `find $PWD/files/ -name "5_*"` > "$outdir/new_IMGT/5_AA-sequences.txt"
|
|
|
91 cat `find $PWD/files/ -name "6_*"` > "$outdir/new_IMGT/6_Junction.txt"
|
|
|
92 cat `find $PWD/files/ -name "7_*"` > "$outdir/new_IMGT/7_V-REGION-mutation-and-AA-change-table.txt"
|
|
|
93 cat `find $PWD/files/ -name "8_*"` > "$outdir/new_IMGT/8_V-REGION-nt-mutation-statistics.txt"
|
|
|
94 cat `find $PWD/files/ -name "9_*"` > "$outdir/new_IMGT/9_V-REGION-AA-change-statistics.txt"
|
|
|
95 cat `find $PWD/files/ -name "10_*"` > "$outdir/new_IMGT/10_V-REGION-mutation-hotspots.txt"
|
|
|
96
|
|
99
|
97 mkdir $outdir/new_IMGT_ca
|
|
|
98 cp $outdir/new_IMGT/* $outdir/new_IMGT_ca
|
|
|
99
|
|
|
100 mkdir $outdir/new_IMGT_cg
|
|
|
101 cp $outdir/new_IMGT/* $outdir/new_IMGT_cg
|
|
|
102
|
|
|
103 mkdir $outdir/new_IMGT_cm
|
|
|
104 cp $outdir/new_IMGT/* $outdir/new_IMGT_cm
|
|
|
105
|
|
|
106 Rscript $dir/tmp/igat.r $outdir/new_IMGT/ $outdir/merged.txt "-" 2>&1
|
|
101
|
107 Rscript $dir/tmp/igat.r $outdir/new_IMGT_ca/ $outdir/merged.txt "ca" 2>&1
|
|
|
108 Rscript $dir/tmp/igat.r $outdir/new_IMGT_cg/ $outdir/merged.txt "cg" 2>&1
|
|
|
109 Rscript $dir/tmp/igat.r $outdir/new_IMGT_cm/ $outdir/merged.txt "cm" 2>&1
|
|
95
|
110
|
|
|
111
|
|
|
112 tmp="$PWD"
|
|
|
113 cd $outdir/new_IMGT/ #tar weirdness...
|
|
|
114 tar -cJf ../new_IMGT.txz *
|
|
|
115 cp $dir/tmp/IgAT.xlsm $outdir/new_IMGT/IgAT.xlsm
|
|
|
116 zip -r ../IgAT.zip *
|
|
|
117
|
|
99
|
118 cd $outdir/new_IMGT_ca/
|
|
|
119 tar -cJf ../new_IMGT_ca.txz *
|
|
|
120 cp $dir/tmp/IgAT.xlsm $outdir/new_IMGT_ca/IgAT.xlsm
|
|
|
121 zip -r ../IgAT_ca.zip *
|
|
|
122
|
|
|
123 cd $outdir/new_IMGT_cg/
|
|
|
124 tar -cJf ../new_IMGT_cg.txz *
|
|
|
125 cp $dir/tmp/IgAT.xlsm $outdir/new_IMGT_cg/IgAT.xlsm
|
|
|
126 zip -r ../IgAT_cg.zip *
|
|
|
127
|
|
|
128 cd $outdir/new_IMGT_cm/
|
|
|
129 tar -cJf ../new_IMGT_cm.txz *
|
|
|
130 cp $dir/tmp/IgAT.xlsm $outdir/new_IMGT_cm/IgAT.xlsm
|
|
|
131 zip -r ../IgAT_cm.zip *
|
|
|
132
|
|
95
|
133 cd $tmp
|
|
|
134
|
|
55
|
135 echo "---------------- mutation_analysis.r ----------------"
|
|
102
|
136 echo "---------------- mutation_analysis.r ----------------<br />" >> $log
|
|
55
|
137
|
|
82
|
138 classes="ca,ca1,ca2,cg,cg1,cg2,cg3,cg4,cm,unmatched"
|
|
4
|
139 echo "R mutation analysis"
|
|
82
|
140 Rscript $dir/mutation_analysis.r $outdir/merged.txt $classes $outdir ${include_fr1} 2>&1
|
|
53
|
141
|
|
55
|
142
|
|
|
143 echo "---------------- mutation_analysis.py ----------------"
|
|
102
|
144 echo "---------------- mutation_analysis.py ----------------<br />" >> $log
|
|
55
|
145
|
|
82
|
146 python $dir/mutation_analysis.py --input $outdir/merged.txt --genes $classes --includefr1 "${include_fr1}" --output $outdir/hotspot_analysis.txt
|
|
55
|
147
|
|
|
148 echo "---------------- aa_histogram.r ----------------"
|
|
63
|
149 echo "---------------- aa_histogram.r ----------------<br />" >> $output
|
|
55
|
150
|
|
104
|
151 Rscript $dir/aa_histogram.r $outdir/aa_mutations.txt $outdir/aa_histogram.png "" 2>&1
|
|
|
152 Rscript $dir/aa_histogram.r $outdir/aa_mutations_ca.txt $outdir/aa_histogram_ca.png "ca" 2>&1
|
|
|
153 Rscript $dir/aa_histogram.r $outdir/aa_mutations_cg.txt $outdir/aa_histogram_cg.png "cg" 2>&1
|
|
|
154 Rscript $dir/aa_histogram.r $outdir/aa_mutations_cm.txt $outdir/aa_histogram_cm.png "cm" 2>&1
|
|
4
|
155
|
|
0
|
156 genes=(ca ca1 ca2 cg cg1 cg2 cg3 cg4 cm)
|
|
|
157
|
|
53
|
158 funcs=(sum mean median)
|
|
0
|
159
|
|
82
|
160 echo "---------------- sequence_overview.r ----------------"
|
|
102
|
161 echo "---------------- sequence_overview.r ----------------<br />" >> $log
|
|
82
|
162
|
|
|
163 mkdir $outdir/sequence_overview
|
|
|
164
|
|
90
|
165 #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
|
|
100
|
166 Rscript $dir/sequence_overview.r $outdir/before_unique_filter.txt $outdir/merged.txt $outdir/sequence_overview $classes $outdir/hotspot_analysis_sum.txt 2>&1
|
|
82
|
167
|
|
|
168 echo "<table border='1'>" > $outdir/base_overview.html
|
|
|
169
|
|
92
|
170 while IFS=$'\t' read ID class seq A C G T
|
|
82
|
171 do
|
|
85
|
172 echo "<tr><td>$ID</td><td>$seq</td><td>$class</td><td>$A</td><td>$C</td><td>$G</td><td>$T</td></tr>" >> $outdir/base_overview.html
|
|
82
|
173 done < $outdir/sequence_overview/ntoverview.txt
|
|
|
174
|
|
62
|
175 echo "<html><center><h1>$title</h1></center>" > $output
|
|
|
176
|
|
|
177 #display the matched/unmatched for clearity
|
|
|
178
|
|
98
|
179 matched_count="`cat $outdir/merged.txt | grep -v 'unmatched' | tail -n +2 | wc -l`"
|
|
62
|
180 unmatched_count="`cat $outdir/unmatched.txt | tail -n +2 | wc -l`"
|
|
|
181 total_count=$((matched_count + unmatched_count))
|
|
|
182 perc_count=$((unmatched_count / total_count * 100))
|
|
|
183 perc_count=`bc -l <<< "scale=2; ${unmatched_count} / ${total_count} * 100"`
|
|
|
184 perc_count=`bc -l <<< "scale=2; (${unmatched_count} / ${total_count} * 100 ) / 1"`
|
|
|
185
|
|
|
186 echo "<center><h2>Total: ${total_count}</h2></center>" >> $output
|
|
|
187 echo "<center><h2>Matched: ${matched_count} Unmatched: ${unmatched_count}</h2></center>" >> $output
|
|
|
188 echo "<center><h2>Percentage unmatched: ${perc_count}</h2></center>" >> $output
|
|
|
189
|
|
55
|
190 echo "---------------- main tables ----------------"
|
|
102
|
191 echo "---------------- main tables ----------------<br />" >> $log
|
|
53
|
192 for func in ${funcs[@]}
|
|
4
|
193 do
|
|
55
|
194
|
|
|
195 echo "---------------- $func table ----------------"
|
|
102
|
196 echo "---------------- $func table ----------------<br />" >> $log
|
|
55
|
197
|
|
94
|
198 cat $outdir/mutations_${func}.txt $outdir/hotspot_analysis_${func}.txt > $outdir/data_${func}.txt
|
|
53
|
199
|
|
98
|
200 echo "<table border='1' width='100%'><caption><h3><a href='data_${func}.txt'>${func} table</a></h3></caption>" >> $output
|
|
58
|
201 echo "<tr><th>info</th>" >> $output
|
|
53
|
202 for gene in ${genes[@]}
|
|
|
203 do
|
|
|
204 tmp=`cat $outdir/${gene}_${func}_n.txt`
|
|
|
205 echo "<th><a href='matched_${gene}_${func}.txt'>${gene} (N = $tmp)</a></th>" >> $output
|
|
|
206 done
|
|
78
|
207
|
|
|
208 tmp=`cat $outdir/unmatched_${func}_n.txt`
|
|
79
|
209 echo "<th><a href='unmatched.txt'>unmatched (N = ${unmatched_count})</a></th>" >> $output
|
|
53
|
210 tmp=`cat $outdir/all_${func}_n.txt`
|
|
89
|
211 echo "<th><a href='matched_all_${func}.txt'>all (N = $tmp)</a></th>" >> $output
|
|
4
|
212
|
|
78
|
213 while IFS=, read name cax cay caz ca1x ca1y ca1z ca2x ca2y ca2z cgx cgy cgz cg1x cg1y cg1z cg2x cg2y cg2z cg3x cg3y cg3z cg4x cg4y cg4z cmx cmy cmz unx uny unz allx ally allz
|
|
53
|
214 do
|
|
|
215 if [ "$name" == "FR S/R (ratio)" ] || [ "$name" == "CDR S/R (ratio)" ] ; then #meh
|
|
|
216 echo "<tr><td>$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>" >> $output
|
|
|
217 else
|
|
78
|
218 echo "<tr><td>$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} (${cmz}%)</td><td>${unx}/${uny} (${unz}%)</td><td>${allx}/${ally} (${allz}%)</td></tr>" >> $output
|
|
53
|
219 fi
|
|
94
|
220 done < $outdir/data_${func}.txt
|
|
|
221 echo "</table>" >> $output
|
|
|
222 #echo "<a href='data_${func}.txt'>Download data</a>" >> $output
|
|
53
|
223 done
|
|
|
224
|
|
55
|
225 echo "---------------- download links ----------------"
|
|
102
|
226 echo "---------------- download links ----------------<br />" >> $log
|
|
55
|
227
|
|
94
|
228
|
|
53
|
229 echo "<a href='unmatched.txt'>unmatched</a><br />" >> $output
|
|
|
230 echo "<a href='motif_per_seq.txt'>motif per sequence</a><br />" >> $output
|
|
|
231 echo "<a href='merged.txt'>all data</a><br />" >> $output
|
|
|
232 echo "<a href='mutation_by_id.txt'>mutations by id</a><br />" >> $output
|
|
|
233 echo "<a href='aa_id_mutations.txt'>AA mutations location by id</a><br />" >> $output
|
|
|
234 echo "<a href='absent_aa_id.txt'>Absant AA locations by id</a><br />" >> $output
|
|
77
|
235 echo "<a href='sequence_overview/index.html'>Sequence Overview</a><br />" >> $output
|
|
81
|
236 echo "<a href='base_overview.html'>Base overview</a><br />" >> $output
|
|
95
|
237 echo "<a href='baseline.pdf'>Baseline PDF</a><br />" >> $output
|
|
|
238 echo "<a href='baseline.txt'>Baseline Table</a><br />" >> $output
|
|
99
|
239 echo "<a href='baseline_ca.pdf'>Baseline ca PDF</a><br />" >> $output
|
|
|
240 echo "<a href='baseline_ca.txt'>Baseline ca Table</a><br />" >> $output
|
|
|
241 echo "<a href='baseline_cg.pdf'>Baseline cg PDF</a><br />" >> $output
|
|
|
242 echo "<a href='baseline_cg.txt'>Baseline cg Table</a><br />" >> $output
|
|
|
243 echo "<a href='baseline_cm.pdf'>Baseline cm PDF</a><br />" >> $output
|
|
|
244 echo "<a href='baseline_cm.txt'>Baseline cm Table</a><br />" >> $output
|
|
95
|
245 echo "<a href='IgAT.zip'>IgAT zip</a><br />" >> $output
|
|
99
|
246 echo "<a href='IgAT_ca.zip'>IgAT ca zip</a><br />" >> $output
|
|
|
247 echo "<a href='IgAT_cg.zip'>IgAT cg zip</a><br />" >> $output
|
|
|
248 echo "<a href='IgAT_cm.zip'>IgAT cm zip</a><br />" >> $output
|
|
|
249 echo "<a href='new_IMGT.txz'>Filtered IMGT zip</a><br />" >> $output
|
|
|
250 echo "<a href='new_IMGT_ca.txz'>Filtered ca IMGT zip</a><br />" >> $output
|
|
|
251 echo "<a href='new_IMGT_cg.txz'>Filtered cg IMGT zip</a><br />" >> $output
|
|
|
252 echo "<a href='new_IMGT_cm.txz'>Filtered cm IMGT zip</a><br />" >> $output
|
|
|
253
|
|
2
|
254
|
|
55
|
255 echo "---------------- images ----------------"
|
|
102
|
256 echo "---------------- images ----------------<br />" >> $log
|
|
55
|
257
|
|
4
|
258 echo "<img src='all.png'/><br />" >> $output
|
|
26
|
259 echo "<a href='all.txt'>download data</a><br />" >> $output
|
|
4
|
260 if [ -a $outdir/ca.png ]
|
|
|
261 then
|
|
|
262 echo "<img src='ca.png'/><br />" >> $output
|
|
26
|
263 echo "<a href='ca.txt'>download data</a><br />" >> $output
|
|
4
|
264 fi
|
|
|
265 if [ -a $outdir/cg.png ]
|
|
|
266 then
|
|
|
267 echo "<img src='cg.png'/><br />" >> $output
|
|
26
|
268 echo "<a href='cg.txt'>download data</a><br />" >> $output
|
|
4
|
269 fi
|
|
22
|
270 if [ -a $outdir/scatter.png ]
|
|
|
271 then
|
|
|
272 echo "<img src='scatter.png'/><br />" >> $output
|
|
26
|
273 echo "<a href='scatter.txt'>download data</a><br />" >> $output
|
|
|
274 fi
|
|
49
|
275 if [ -a $outdir/frequency_ranges.png ]
|
|
|
276 then
|
|
|
277 echo "<img src='frequency_ranges.png'/><br />" >> $output
|
|
|
278 echo "<a href='frequency_ranges_classes.txt'>download class data</a><br />" >> $output
|
|
|
279 echo "<a href='frequency_ranges_subclasses.txt'>download subclass data</a><br />" >> $output
|
|
|
280 fi
|
|
26
|
281 if [ -a $outdir/aa_histogram.png ]
|
|
|
282 then
|
|
|
283 echo "<img src='aa_histogram.png'/><br />" >> $output
|
|
|
284 echo "<a href='aa_histogram.txt'>download data</a><br />" >> $output
|
|
104
|
285 echo "<img src='aa_histogram_ca.png'/><br />" >> $output
|
|
|
286 echo "<a href='aa_histogram_ca.txt'>download data</a><br />" >> $output
|
|
|
287 echo "<img src='aa_histogram_cg.png'/><br />" >> $output
|
|
|
288 echo "<a href='aa_histogram_cg.txt'>download data</a><br />" >> $output
|
|
|
289 echo "<img src='aa_histogram_cm.png'/><br />" >> $output
|
|
|
290 echo "<a href='aa_histogram_cm.txt'>download data</a><br />" >> $output
|
|
22
|
291 fi
|
|
2
|
292
|
|
0
|
293 for gene in ${genes[@]}
|
|
|
294 do
|
|
|
295 echo "<table border='1'><caption>$gene transition table</caption>" >> $output
|
|
|
296 while IFS=, read from a c g t
|
|
|
297 do
|
|
|
298 echo "<tr><td>$from</td><td>$a</td><td>$c</td><td>$g</td><td>$t</td></tr>" >> $output
|
|
53
|
299 done < $outdir/transitions_${gene}_sum.txt
|
|
0
|
300 echo "</table>" >> $output
|
|
|
301 done
|
|
|
302
|
|
|
303 echo "<table border='1'><caption>All transition table</caption>" >> $output
|
|
|
304 while IFS=, read from a c g t
|
|
|
305 do
|
|
|
306 echo "<tr><td>$from</td><td>$a</td><td>$c</td><td>$g</td><td>$t</td></tr>" >> $output
|
|
53
|
307 done < $outdir/transitions_all_sum.txt
|
|
0
|
308 echo "</table>" >> $output
|
|
|
309
|
|
|
310 echo "</html>" >> $output
|
|
2
|
311
|
|
95
|
312 echo "---------------- baseline ----------------"
|
|
102
|
313 echo "---------------- baseline ----------------<br />" >> $log
|
|
101
|
314 tmp="$PWD"
|
|
|
315
|
|
|
316 mkdir $outdir/baseline
|
|
|
317
|
|
|
318
|
|
|
319 mkdir $outdir/baseline/ca_cg_cm
|
|
102
|
320 if [[ $(wc -l < $outdir/new_IMGT/1_Summary.txt) -gt "1" ]]; then
|
|
|
321 cd $outdir/baseline/ca_cg_cm
|
|
|
322 bash $dir/tmp/baseline/wrapper.sh 1 1 1 1 0 0 "25:26:38:55:65:104:-" $outdir/new_IMGT.txz "ca_cg_cm" "$dir/tmp/baseline/IMGT-reference-seqs-IGHV-2015-11-05.fa" "$outdir/baseline.pdf" "Sequence.ID" "$outdir/baseline.txt"
|
|
|
323 else
|
|
|
324 echo "No sequences" > "$outdir/baseline.txt"
|
|
|
325 fi
|
|
101
|
326
|
|
|
327 mkdir $outdir/baseline/ca
|
|
102
|
328 if [[ $(wc -l < $outdir/new_IMGT_ca/1_Summary.txt) -gt "1" ]]; then
|
|
|
329 cd $outdir/baseline/ca
|
|
|
330 bash $dir/tmp/baseline/wrapper.sh 1 1 1 1 0 0 "25:26:38:55:65:104:-" $outdir/new_IMGT_ca.txz "ca" "$dir/tmp/baseline/IMGT-reference-seqs-IGHV-2015-11-05.fa" "$outdir/baseline_ca.pdf" "Sequence.ID" "$outdir/baseline_ca.txt"
|
|
|
331 else
|
|
|
332 echo "No ca sequences" > "$outdir/baseline_ca.txt"
|
|
|
333 fi
|
|
101
|
334
|
|
|
335 mkdir $outdir/baseline/cg
|
|
102
|
336 if [[ $(wc -l < $outdir/new_IMGT_cg/1_Summary.txt) -gt "1" ]]; then
|
|
|
337 cd $outdir/baseline/cg
|
|
|
338 bash $dir/tmp/baseline/wrapper.sh 1 1 1 1 0 0 "25:26:38:55:65:104:-" $outdir/new_IMGT_cg.txz "cg" "$dir/tmp/baseline/IMGT-reference-seqs-IGHV-2015-11-05.fa" "$outdir/baseline_cg.pdf" "Sequence.ID" "$outdir/baseline_cg.txt"
|
|
|
339 else
|
|
|
340 echo "No cg sequences" > "$outdir/baseline_cg.txt"
|
|
|
341 fi
|
|
101
|
342
|
|
|
343 mkdir $outdir/baseline/cm
|
|
102
|
344 if [[ $(wc -l < $outdir/new_IMGT_cm/1_Summary.txt) -gt "1" ]]; then
|
|
|
345 cd $outdir/baseline/cm
|
|
|
346 bash $dir/tmp/baseline/wrapper.sh 1 1 1 1 0 0 "25:26:38:55:65:104:-" $outdir/new_IMGT_cm.txz "cm" "$dir/tmp/baseline/IMGT-reference-seqs-IGHV-2015-11-05.fa" "$outdir/baseline_cm.pdf" "Sequence.ID" "$outdir/baseline_cm.txt"
|
|
|
347 else
|
|
|
348 echo "No cm sequences" > "$outdir/baseline_cm.txt"
|
|
|
349 fi
|
|
47
|
350
|
|
101
|
351 cd $tmp
|
|
|
352
|
|
82
|
353 echo "---------------- naive_output.r ----------------"
|
|
102
|
354 echo "---------------- naive_output.r ----------------<br />" >> $log
|
|
55
|
355
|
|
47
|
356 if [[ "$naive_output" != "None" ]]
|
|
|
357 then
|
|
55
|
358 echo "---------------- imgt_loader.r ----------------"
|
|
102
|
359 echo "---------------- imgt_loader.r ----------------<br />" >> $log
|
|
50
|
360 #python $dir/imgt_loader.py --summ $PWD/summary.txt --aa $PWD/aa.txt --junction $PWD/junction.txt --output $naive_output
|
|
80
|
361 Rscript --verbose $dir/imgt_loader.r $PWD/summary.txt $PWD/aa.txt $PWD/junction.txt $outdir/loader_output.txt 2>&1
|
|
95
|
362
|
|
55
|
363 echo "---------------- naive_output.r ----------------"
|
|
102
|
364 echo "---------------- naive_output.r ----------------<br />" >> $log
|
|
81
|
365 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
|
|
47
|
366 fi
|
|
|
367
|
|
81
|
368 echo "</table>" >> $outdir/base_overview.html
|
|
|
369
|
|
|
370 echo "---------------- Done! ----------------"
|
|
102
|
371 echo "---------------- Done! ----------------<br />" >> $log
|
|
47
|
372
|
|
102
|
373 mv $log $outdir/log.html
|
|
|
374
|
|
|
375 mv $outdir/index.html $log
|
|
|
376
|
