Mercurial > repos > davidvanzessen > shm_csr

comparison baseline/wrapper.sh @ 81:b6f9a640e098 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Fri, 19 Feb 2021 15:10:54 +0000
parents
children d714f5ea83d7
comparison
equal deleted inserted replaced
80:a4617f1d1d89 81:b6f9a640e098
1 #!/bin/bash
2 dir="$(cd "$(dirname "$0")" && pwd)"
3
4 testID=$1
5 species=$2
6 substitutionModel=$3
7 mutabilityModel=$4
8 clonal=$5
9 fixIndels=$6
10 region=$7
11 inputs=$8
12 inputs=($inputs)
13 IDs=$9
14 IDs=($IDs)
15 ref=${10}
16 output=${11}
17 selection=${12}
18 output_table=${13}
19 outID="result"
20
21 echo "$PWD"
22
23 echo "testID = $testID"
24 echo "species = $species"
25 echo "substitutionModel = $substitutionModel"
26 echo "mutabilityModel = $mutabilityModel"
27 echo "clonal = $clonal"
28 echo "fixIndels = $fixIndels"
29 echo "region = $region"
30 echo "inputs = ${inputs[@]}"
31 echo "IDs = ${IDs[@]}"
32 echo "ref = $ref"
33 echo "output = $output"
34 echo "outID = $outID"
35
36 fasta="$PWD/baseline.fasta"
37
38
39 count=0
40 for current in ${inputs[@]}
41 do
42 f=$(file $current)
43 zipType="Zip archive"
44 if [[ "$f" == *"Zip archive"* ]] || [[ "$f" == *"XZ compressed data"* ]]
45 then
46 id=${IDs[$count]}
47 echo "id=$id"
48 if [[ "$f" == *"Zip archive"* ]] ; then
49 echo "Zip archive"
50 echo "unzip $input -d $PWD/files/"
51 unzip $current -d "$PWD/$id/"
52 elif [[ "$f" == *"XZ compressed data"* ]] ; then
53 echo "ZX archive"
54 echo "tar -xJf $input -C $PWD/files/"
55 mkdir -p "$PWD/$id/files"
56 tar -xJf $current -C "$PWD/$id/files/"
57 fi
58 filtered="$PWD/filtered_${id}.txt"
59 imgt_1_file="`find $PWD/$id -name '1_*.txt'`"
60 imgt_2_file="`find $PWD/$id -name '2_*.txt'`"
61 echo "1_Summary file: ${imgt_1_file}"
62 echo "2_IMGT-gapped file: ${imgt_2_file}"
63 echo "filter.r for $id"
64 Rscript $dir/filter.r ${imgt_1_file} ${imgt_2_file} "$selection" $filtered 2>&1
65
66 final="$PWD/final_${id}.txt"
67 cat $filtered | cut -f2,4,7 > $final
68 python $dir/script_imgt.py --input $final --ref $ref --output $fasta --id $id
69 else
70 python $dir/script_xlsx.py --input $current --ref $ref --output $fasta
71 fi
72 count=$((count+1))
73 done
74 workdir="$PWD"
75 cd $dir
76 echo "file: ${inputs[0]}"
77 #Rscript --verbose $dir/Baseline_Main.r $testID $species $substitutionModel $mutabilityModel $clonal $fixIndels $region ${inputs[0]} $workdir/ $outID 2>&1
78 Rscript --verbose $dir/Baseline_Main.r $testID $species $substitutionModel $mutabilityModel $clonal $fixIndels $region $fasta $workdir/ $outID 2>&1
79
80 echo "$workdir/${outID}.txt"
81
82 rows=`tail -n +2 $workdir/${outID}.txt | grep -v "All sequences combined" | grep -n 'Group' | grep -Eoh '^[0-9]+' | tr '\n' ' '`
83 rows=($rows)
84 #unset rows[${#rows[@]}-1]
85
86 cd $dir
87 Rscript --verbose $dir/comparePDFs.r $workdir/${outID}.RData $output ${rows[@]} 2>&1
88 cp $workdir/result.txt ${output_table}
89
90
91
92