|
11
|
1 #/bin/bash
|
|
|
2 ##
|
|
|
3 # This program is free software; you can redistribute it and/or modify
|
|
|
4 # it under the terms of the GNU General Public License as published by
|
|
|
5 # the Free Software Foundation; either version 3 of the License, or
|
|
|
6 # (at your option) any later version.
|
|
|
7 #
|
|
|
8 # Copyright (C) 2013 Memorial Sloan-Kettering Cancer Center
|
|
|
9 ##
|
|
|
10
|
|
|
11 set -e
|
|
|
12
|
|
|
13 PROG=`basename $0`
|
|
|
14 DIR=`dirname $0`
|
|
|
15
|
|
|
16 . ${DIR}/../bin/dexseq_config.sh
|
|
|
17
|
|
|
18 echo
|
|
|
19 echo ${PROG}: Oqtans http://galaxy.cbio.mskcc.org Galaxy wrapper for the DEXSeq version ${DEXSEQ_VERSION}.
|
|
|
20 echo
|
|
|
21 echo DEXSeq: Detecting differential usage of exons from RNA-seq data.
|
|
|
22 echo
|
|
|
23
|
|
|
24 ## input arguments from the interface
|
|
|
25 GFF_IN=${1}
|
|
|
26 shift
|
|
|
27 MATE_PAIR=${1}
|
|
|
28 shift
|
|
|
29 LIBTP=${1}
|
|
|
30 shift
|
|
|
31 minQL=${1}
|
|
|
32 shift
|
|
|
33 RES_FILE=${1}
|
|
|
34 shift
|
|
|
35 RES_WD=${1}
|
|
|
36 shift
|
|
|
37
|
|
|
38 ## associated array with sequencing type.
|
|
|
39 declare -A SEQ_TYPE=( [no]=SE [yes]=PE )
|
|
|
40
|
|
|
41 echo %%%%%%%%%%%%%%%%%%%%%%%
|
|
|
42 echo % 1. Data preparation %
|
|
|
43 echo %%%%%%%%%%%%%%%%%%%%%%%
|
|
|
44 echo
|
|
|
45
|
|
|
46 mkdir -p ${RES_WD}
|
|
|
47 echo extra file path $RES_WD
|
|
|
48 tmpGTF=`mktemp --tmpdir=/tmp`
|
|
|
49
|
|
|
50 echo load the genome annotation in GFF file
|
|
|
51
|
|
|
52 ${PYTHON_PATH} ${DIR}/dexseq_prepare_annotation.py ${GFF_IN} ${tmpGTF}
|
|
|
53 echo genome annotation stored in ${tmpGTF}
|
|
|
54 echo
|
|
|
55
|
|
|
56 echo %%%%%%%%%%%%%%%%%%%%
|
|
|
57 echo % 2. Read counting %
|
|
|
58 echo %%%%%%%%%%%%%%%%%%%%
|
|
|
59 echo
|
|
|
60
|
|
|
61 tmpFILE=`mktemp --tmpdir=/tmp`
|
|
|
62 echo $tmpFILE
|
|
|
63 echo -e '\t'condition'\t'libType > ${tmpFILE}_CONDITIONS.tab
|
|
|
64
|
|
|
65 COND=0
|
|
|
66 for REPLICATE_GROUP in $@
|
|
|
67 do
|
|
|
68 IFS=':'
|
|
|
69 COND=$((COND+1))
|
|
|
70 for BAM_FILE in ${REPLICATE_GROUP}
|
|
|
71 do
|
|
|
72 ## different group information
|
|
|
73 REPNAME=$(basename ${BAM_FILE%.dat})
|
|
|
74 echo -e ${REPNAME}"\t"$COND"\t"${SEQ_TYPE[$MATE_PAIR]} >> ${tmpFILE}_CONDITIONS.tab
|
|
|
75
|
|
|
76 ## counting the reads
|
|
|
77 ${SAMTOOLS_DIR}/samtools view -h $BAM_FILE | ${PYTHON_PATH} ${DIR}/dexseq_count.py -p ${MATE_PAIR} -s ${LIBTP} -a ${minQL} ${tmpGTF} - ${RES_WD}/${REPNAME}
|
|
|
78
|
|
|
79 echo
|
|
|
80 done
|
|
|
81 echo conuted condition ${COND}
|
|
|
82 done
|
|
|
83 echo counted reads map to each exon.
|
|
|
84 echo
|
|
|
85
|
|
|
86 echo %%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
|
87 echo % 3. Differential testing %
|
|
|
88 echo %%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
|
89 echo
|
|
|
90
|
|
|
91 echo "cat ${DIR}/run_DEXseq.R | $R_PATH --slave --args $tmpFILE $RES_WD $tmpGTF ${RES_FILE} $#"
|
|
|
92 cat ${DIR}/run_DEXseq.R | $R_PATH --slave --args $tmpFILE $RES_WD $tmpGTF ${RES_FILE}
|
|
|
93
|
|
|
94 ## clean up
|
|
|
95 rm -fr ${RES_WD} ${tmpGTF} ${tmpFILE}
|
|
|
96 echo %%%%%%%%
|
|
|
97 echo % Done %
|
|
|
98 echo %%%%%%%%
|
