-
Notifications
You must be signed in to change notification settings - Fork 1
Expand file tree
/
Copy pathrun_pi_bdgdiff.sh
More file actions
executable file
·291 lines (212 loc) · 16.9 KB
/
run_pi_bdgdiff.sh
File metadata and controls
executable file
·291 lines (212 loc) · 16.9 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
NAME=$1
SET=$2
TOOL=$3
mkdir -p results/$TOOL results/$TOOL/$SET
mkdir -p log/$TOOL
files=$(ls results/$TOOL/$SET/*.bed 2> /dev/null | wc -l)
if [ "$files" = "0" ]; then
echo "running $TOOL with: $1 $2 $3" #$4 $5 $6 $7 $8 $9 ${10} ${11} ${12} ${13}"
NAME1=$(basename $4 -rep1_mm.bam)
NAME2=$(basename $7 -rep1_mm.bam)
LOG="log/$TOOL/$SET.log"
OUT_NAME=$(basename $NAME _sample1-rep1_mm)
source /proj/chipseq_norm_diffbind_062017/analysis/03_db_analysis/python-virtual-environments/macs2_env/bin/activate
STARTTIME=`date +%s.%N`
#sharp 200
#merge both replicates and use -B to get bedgraph files
macs2 callpeak -B -t $4 $5 -c $6 -f BAM -n $NAME1 --nomodel --extsize 200 --outdir results/$TOOL/$SET -q 0.01 2>> $LOG
macs2 callpeak -B -t $7 $8 -c $9 -f BAM -n $NAME2 --nomodel --extsize 200 --outdir results/$TOOL/$SET -q 0.01 2>> $LOG
D1=$(egrep "tags after filtering in control" results/$TOOL/$SET/$NAME1"_peaks.xls" | cut -d' ' -f7)
D2=$(egrep "tags after filtering in control" results/$TOOL/$SET/$NAME2"_peaks.xls" | cut -d' ' -f7)
PREPDONE=`date +%s.%N`
#bgdiff
/usr/bin/time -o results/$TOOL/$SET/mem.txt -f "%K %M" macs2 bdgdiff \
--t1 results/$TOOL/$SET/$NAME1"_treat_pileup.bdg" --c1 results/$TOOL/$SET/$NAME1"_control_lambda.bdg" \
--t2 results/$TOOL/$SET/$NAME2"_treat_pileup.bdg" --c2 results/$TOOL/$SET/$NAME2"_control_lambda.bdg" \
--d1 $D1 --d2 $D2 -C 1 --o-prefix diff_c1_vs_c2_1 --outdir results/$TOOL/$SET 2>> $LOG
ENDTIME=`date +%s.%N`
TIMEDIFFPREP=`echo "$PREPDONE - $STARTTIME" | bc | awk -F"." '{print}'`
TIMEDIFF=`echo "$ENDTIME - $PREPDONE" | bc | awk -F"." '{print}'`
echo "prep $TIMEDIFFPREP" > results/$TOOL/$SET/time.txt
echo "1 $TIMEDIFF" >> results/$TOOL/$SET/time.txt
MEMUSAGE=$(sed '/non-zero status/d' results/$TOOL/$SET/mem.txt )
echo "1 $MEMUSAGE" >> results/$TOOL/$SET/memory.txt
#save result, add 1 or 2 for up in sample 1 or sample 2 and save as one csv
#add log2 fold-change of -1.3 and 1.3 to get over the threshold of 0.7 we were simulating
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_1_c1.0_cond1.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t1.3"}' | sort -k1,1 -k2,2n > results/$TOOL/$SET/$OUT_NAME"_1.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_1_c1.0_cond2.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t-1.3"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_1.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_1_c1.0_common.bed| grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t0"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_1.bed"
#clean up
rm results/$TOOL/$SET/diff_c1_vs_c2_1_c1*.bed results/$TOOL/$SET/mem.txt
#bgdiff with scaling from spike-in
SF1=$(echo "print int(((${10}+${11})/2)*1000000)" | python2) #mean spike-in scaling-factor of the replicates
SF2=$(echo "print int(((${12}+${13})/2)*1000000)" | python2)
STARTTIME=`date +%s.%N`
/usr/bin/time -o results/$TOOL/$SET/mem.txt -f "%K %M" macs2 bdgdiff \
--t1 results/$TOOL/$SET/$NAME1"_treat_pileup.bdg" --c1 results/$TOOL/$SET/$NAME1"_control_lambda.bdg" \
--t2 results/$TOOL/$SET/$NAME2"_treat_pileup.bdg" --c2 results/$TOOL/$SET/$NAME2"_control_lambda.bdg" \
--d1 $SF1 --d2 $SF2 -C 1 --o-prefix diff_c1_vs_c2_si1 --outdir results/$TOOL/$SET 2>> $LOG
ENDTIME=`date +%s.%N`
TIMEDIFF=`echo "$ENDTIME - $STARTTIME" | bc | awk -F"." '{print}'`
echo "1si $TIMEDIFF" >> results/$TOOL/$SET/time.txt
MEMUSAGE=$(sed '/non-zero status/d' results/$TOOL/$SET/mem.txt )
echo "1si $MEMUSAGE" >> results/$TOOL/$SET/memory.txt
#save result, add 1 or 2 for up in sample 1 or sample 2 and save as one csv
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_si1_c1.0_cond1.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t1.3"}' | sort -k1,1 -k2,2n > results/$TOOL/$SET/$OUT_NAME"_1si.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_si1_c1.0_cond2.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t-1.3"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_1si.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_si1_c1.0_common.bed| grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t0"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_1si.bed"
#clean up
rm results/$TOOL/$SET/diff_c1_vs_c2_si1_c1*.bed results/$TOOL/$SET/mem.txt
rm results/$TOOL/$SET/$NAME1*peaks.narrowPeak results/$TOOL/$SET/$NAME1*summits.bed
rm results/$TOOL/$SET/$NAME2*peaks.narrowPeak results/$TOOL/$SET/$NAME2*summits.bed
rm results/$TOOL/$SET/$NAME1*xls results/$TOOL/$SET/$NAME2*xls
rm results/$TOOL/$SET/$NAME1*control_lambda.bdg results/$TOOL/$SET/$NAME1*treat_pileup.bdg
rm results/$TOOL/$SET/$NAME2*control_lambda.bdg results/$TOOL/$SET/$NAME2*treat_pileup.bdg
#sharp model
#merge both replicates and use -B to get bedgraph files
macs2 callpeak -B -t $4 $5 -c $6 -f BAM -n $NAME1 --outdir results/$TOOL/$SET -q 0.01 2>> $LOG
macs2 callpeak -B -t $7 $8 -c $9 -f BAM -n $NAME2 --outdir results/$TOOL/$SET -q 0.01 2>> $LOG
D1=$(egrep "tags after filtering in control" results/$TOOL/$SET/$NAME1"_peaks.xls" | cut -d' ' -f7)
D2=$(egrep "tags after filtering in control" results/$TOOL/$SET/$NAME2"_peaks.xls" | cut -d' ' -f7)
STARTTIME=`date +%s.%N`
#bgdiff
/usr/bin/time -o results/$TOOL/$SET/mem.txt -f "%K %M" macs2 bdgdiff \
--t1 results/$TOOL/$SET/$NAME1"_treat_pileup.bdg" --c1 results/$TOOL/$SET/$NAME1"_control_lambda.bdg" \
--t2 results/$TOOL/$SET/$NAME2"_treat_pileup.bdg" --c2 results/$TOOL/$SET/$NAME2"_control_lambda.bdg" \
--d1 $D1 --d2 $D2 -C 1 --o-prefix diff_c1_vs_c2_1 --outdir results/$TOOL/$SET 2>> $LOG
ENDTIME=`date +%s.%N`
TIMEDIFF=`echo "$ENDTIME - $STARTTIME" | bc | awk -F"." '{print}'`
echo "2 $TIMEDIFF" >> results/$TOOL/$SET/time.txt
MEMUSAGE=$(sed '/non-zero status/d' results/$TOOL/$SET/mem.txt )
echo "2 $MEMUSAGE" >> results/$TOOL/$SET/memory.txt
#save result, add 1 or 2 for up in sample 1 or sample 2 and save as one csv
#add log2 fold-change of -1.3 and 1.3 to get over the threshold of 0.7 we were simulating
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_1_c1.0_cond1.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t1.3"}' | sort -k1,1 -k2,2n > results/$TOOL/$SET/$OUT_NAME"_2.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_1_c1.0_cond2.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t-1.3"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_2.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_1_c1.0_common.bed| grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t0"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_2.bed"
#clean up
rm results/$TOOL/$SET/diff_c1_vs_c2_1_c1*.bed results/$TOOL/$SET/mem.txt
#bgdiff with scaling from spike-in
SF1=$(echo "print int(((${10}+${11})/2)*1000000)" | python2) #mean spike-in scaling-factor of the replicates
SF2=$(echo "print int(((${12}+${13})/2)*1000000)" | python2)
STARTTIME=`date +%s.%N`
/usr/bin/time -o results/$TOOL/$SET/mem.txt -f "%K %M" macs2 bdgdiff \
--t1 results/$TOOL/$SET/$NAME1"_treat_pileup.bdg" --c1 results/$TOOL/$SET/$NAME1"_control_lambda.bdg" \
--t2 results/$TOOL/$SET/$NAME2"_treat_pileup.bdg" --c2 results/$TOOL/$SET/$NAME2"_control_lambda.bdg" \
--d1 $SF1 --d2 $SF2 -C 1 --o-prefix diff_c1_vs_c2_si1 --outdir results/$TOOL/$SET 2>> $LOG
ENDTIME=`date +%s.%N`
TIMEDIFF=`echo "$ENDTIME - $STARTTIME" | bc | awk -F"." '{print}'`
echo "2si $TIMEDIFF" >> results/$TOOL/$SET/time.txt
MEMUSAGE=$(sed '/non-zero status/d' results/$TOOL/$SET/mem.txt )
echo "2si $MEMUSAGE" >> results/$TOOL/$SET/memory.txt
#save result, add 1 or 2 for up in sample 1 or sample 2 and save as one csv
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_si1_c1.0_cond1.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t1.3"}' | sort -k1,1 -k2,2n > results/$TOOL/$SET/$OUT_NAME"_2si.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_si1_c1.0_cond2.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t-1.3"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_2si.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_si1_c1.0_common.bed| grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t0"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_2si.bed"
#clean up
rm results/$TOOL/$SET/diff_c1_vs_c2_si1_c1*.bed results/$TOOL/$SET/*model.r results/$TOOL/$SET/mem.txt
rm results/$TOOL/$SET/$NAME1*peaks.narrowPeak results/$TOOL/$SET/$NAME1*summits.bed
rm results/$TOOL/$SET/$NAME2*peaks.narrowPeak results/$TOOL/$SET/$NAME2*summits.bed
rm results/$TOOL/$SET/$NAME1*xls results/$TOOL/$SET/$NAME2*xls
rm results/$TOOL/$SET/$NAME1*control_lambda.bdg results/$TOOL/$SET/$NAME1*treat_pileup.bdg
rm results/$TOOL/$SET/$NAME2*control_lambda.bdg results/$TOOL/$SET/$NAME2*treat_pileup.bdg
#broad 200
macs2 callpeak --broad -B -t $4 $5 -c $6 -f BAM -n $NAME1 --nomodel --extsize 200 --outdir results/$TOOL/$SET -q 0.01 2>> $LOG
macs2 callpeak --broad -B -t $7 $8 -c $9 -f BAM -n $NAME2 --nomodel --extsize 200 --outdir results/$TOOL/$SET -q 0.01 2>> $LOG
D1=$(egrep "tags after filtering in control" results/$TOOL/$SET/$NAME1"_peaks.xls" | cut -d' ' -f7)
D2=$(egrep "tags after filtering in control" results/$TOOL/$SET/$NAME2"_peaks.xls" | cut -d' ' -f7)
STARTTIME=`date +%s.%N`
#bgdiff broad
/usr/bin/time -o results/$TOOL/$SET/mem.txt -f "%K %M" macs2 bdgdiff \
--t1 results/$TOOL/$SET/$NAME1"_treat_pileup.bdg" --c1 results/$TOOL/$SET/$NAME1"_control_lambda.bdg" \
--t2 results/$TOOL/$SET/$NAME2"_treat_pileup.bdg" --c2 results/$TOOL/$SET/$NAME2"_control_lambda.bdg" \
--d1 $D1 --d2 $D2 -C 1 --o-prefix diff_c1_vs_c2_1 --outdir results/$TOOL/$SET 2>> $LOG
ENDTIME=`date +%s.%N`
TIMEDIFF=`echo "$ENDTIME - $STARTTIME" | bc | awk -F"." '{print}'`
echo "3 $TIMEDIFF" >> results/$TOOL/$SET/time.txt
MEMUSAGE=$(sed '/non-zero status/d' results/$TOOL/$SET/mem.txt )
echo "3 $MEMUSAGE" >> results/$TOOL/$SET/memory.txt
#save result, add 1 or 2 for up in sample 1 or sample 2 and save as one csv
#add log2 fold-change of -1.3 and 1.3 to get over the threshold of 0.7 we were simulating
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_1_c1.0_cond1.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t1.3"}' | sort -k1,1 -k2,2n > results/$TOOL/$SET/$OUT_NAME"_3.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_1_c1.0_cond2.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t-1.3"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_3.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_1_c1.0_common.bed| grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t0"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_3.bed"
#clean up
rm results/$TOOL/$SET/diff_c1_vs_c2_1_c1*.bed results/$TOOL/$SET/mem.txt
#bgdiff with scaling from spike-in broad
SF1=$(echo "print int(((${10}+${11})/2)*1000000)" | python2) #mean spike-in scaling-factor of the replicates
SF2=$(echo "print int(((${12}+${13})/2)*1000000)" | python2)
STARTTIME=`date +%s.%N`
/usr/bin/time -o results/$TOOL/$SET/mem.txt -f "%K %M" macs2 bdgdiff \
--t1 results/$TOOL/$SET/$NAME1"_treat_pileup.bdg" --c1 results/$TOOL/$SET/$NAME1"_control_lambda.bdg" \
--t2 results/$TOOL/$SET/$NAME2"_treat_pileup.bdg" --c2 results/$TOOL/$SET/$NAME2"_control_lambda.bdg" \
--d1 $SF1 --d2 $SF2 -C 1 --o-prefix diff_c1_vs_c2_si1 --outdir results/$TOOL/$SET 2>> $LOG
ENDTIME=`date +%s.%N`
TIMEDIFF=`echo "$ENDTIME - $STARTTIME" | bc | awk -F"." '{print}'`
echo "3si $TIMEDIFF" >> results/$TOOL/$SET/time.txt
MEMUSAGE=$(sed '/non-zero status/d' results/$TOOL/$SET/mem.txt )
echo "3si $MEMUSAGE" >> results/$TOOL/$SET/memory.txt
#save result, add 1 or 2 for up in sample 1 or sample 2 and save as one csv
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_si1_c1.0_cond1.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t1.3"}' | sort -k1,1 -k2,2n > results/$TOOL/$SET/$OUT_NAME"_3si.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_si1_c1.0_cond2.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t-1.3"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_3si.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_si1_c1.0_common.bed| grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t0"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_3si.bed"
#clean up
rm results/$TOOL/$SET/diff_c1_vs_c2_si1_c1*.bed results/$TOOL/$SET/mem.txt
rm results/$TOOL/$SET/$NAME1*peaks.broadPeak results/$TOOL/$SET/$NAME1*gappedPeak
rm results/$TOOL/$SET/$NAME2*peaks.broadPeak results/$TOOL/$SET/$NAME2*gappedPeak
rm results/$TOOL/$SET/$NAME1*xls results/$TOOL/$SET/$NAME2*xls
rm results/$TOOL/$SET/$NAME1*control_lambda.bdg results/$TOOL/$SET/$NAME1*treat_pileup.bdg
rm results/$TOOL/$SET/$NAME2*control_lambda.bdg results/$TOOL/$SET/$NAME2*treat_pileup.bdg
#broad model
macs2 callpeak --broad -B -t $4 $5 -c $6 -f BAM -n $NAME1 --outdir results/$TOOL/$SET -q 0.01 2>> $LOG
macs2 callpeak --broad -B -t $7 $8 -c $9 -f BAM -n $NAME2 --outdir results/$TOOL/$SET -q 0.01 2>> $LOG
D1=$(egrep "tags after filtering in control" results/$TOOL/$SET/$NAME1"_peaks.xls" | cut -d' ' -f7)
D2=$(egrep "tags after filtering in control" results/$TOOL/$SET/$NAME2"_peaks.xls" | cut -d' ' -f7)
STARTTIME=`date +%s.%N`
#bgdiff broad
/usr/bin/time -o results/$TOOL/$SET/mem.txt -f "%K %M" macs2 bdgdiff \
--t1 results/$TOOL/$SET/$NAME1"_treat_pileup.bdg" --c1 results/$TOOL/$SET/$NAME1"_control_lambda.bdg" \
--t2 results/$TOOL/$SET/$NAME2"_treat_pileup.bdg" --c2 results/$TOOL/$SET/$NAME2"_control_lambda.bdg" \
--d1 $D1 --d2 $D2 -C 1 --o-prefix diff_c1_vs_c2_1 --outdir results/$TOOL/$SET 2>> $LOG
ENDTIME=`date +%s.%N`
TIMEDIFF=`echo "$ENDTIME - $STARTTIME" | bc | awk -F"." '{print}'`
echo "4 $TIMEDIFF" >> results/$TOOL/$SET/time.txt
MEMUSAGE=$(sed '/non-zero status/d' results/$TOOL/$SET/mem.txt )
echo "4 $MEMUSAGE" >> results/$TOOL/$SET/memory.txt
#save result, add 1 or 2 for up in sample 1 or sample 2 and save as one csv
#add log2 fold-change of -1.3 and 1.3 to get over the threshold of 0.7 we were simulating
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_1_c1.0_cond1.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t1.3"}' | sort -k1,1 -k2,2n > results/$TOOL/$SET/$OUT_NAME"_4.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_1_c1.0_cond2.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t-1.3"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_4.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_1_c1.0_common.bed| grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t0"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_4.bed"
#clean up
rm results/$TOOL/$SET/diff_c1_vs_c2_1_c1*.bed results/$TOOL/$SET/mem.txt
#bgdiff with scaling from spike-in broad
SF1=$(echo "print int(((${10}+${11})/2)*1000000)" | python2) #mean spike-in scaling-factor of the replicates
SF2=$(echo "print int(((${12}+${13})/2)*1000000)" | python2)
STARTTIME=`date +%s.%N`
/usr/bin/time -o results/$TOOL/$SET/mem.txt -f "%K %M" macs2 bdgdiff \
--t1 results/$TOOL/$SET/$NAME1"_treat_pileup.bdg" --c1 results/$TOOL/$SET/$NAME1"_control_lambda.bdg" \
--t2 results/$TOOL/$SET/$NAME2"_treat_pileup.bdg" --c2 results/$TOOL/$SET/$NAME2"_control_lambda.bdg" \
--d1 $SF1 --d2 $SF2 -C 1 --o-prefix diff_c1_vs_c2_si1 --outdir results/$TOOL/$SET 2>> $LOG
ENDTIME=`date +%s.%N`
TIMEDIFF=`echo "$ENDTIME - $STARTTIME" | bc | awk -F"." '{print}'`
echo "4si $TIMEDIFF" >> results/$TOOL/$SET/time.txt
MEMUSAGE=$(sed '/non-zero status/d' results/$TOOL/$SET/mem.txt )
echo "4si $MEMUSAGE" >> results/$TOOL/$SET/memory.txt
#save result, add 1 or 2 for up in sample 1 or sample 2 and save as one csv
#add log2 fold-change of -1.3 and 1.3 to get over the threshold of 0.7 we were simulating
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_si1_c1.0_cond1.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t1.3"}' | sort -k1,1 -k2,2n > results/$TOOL/$SET/$OUT_NAME"_4si.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_si1_c1.0_cond2.bed | grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t-1.3"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_4si.bed"
cut -f1,2,3,5 results/$TOOL/$SET/diff_c1_vs_c2_si1_c1.0_common.bed| grep -v "^track" | awk '{print $1"\t"$2"\t"$3"\t"$4"\t0"}' | sort -k1,1 -k2,2n >> results/$TOOL/$SET/$OUT_NAME"_4si.bed"
#clean up
rm results/$TOOL/$SET/diff_c1_vs_c2_si1_c1*.bed results/$TOOL/$SET/*model.r results/$TOOL/$SET/mem.txt
rm results/$TOOL/$SET/$NAME1*peaks.broadPeak results/$TOOL/$SET/$NAME1*gappedPeak
rm results/$TOOL/$SET/$NAME2*peaks.broadPeak results/$TOOL/$SET/$NAME2*gappedPeak
rm results/$TOOL/$SET/$NAME1*xls results/$TOOL/$SET/$NAME2*xls
rm results/$TOOL/$SET/$NAME1*control_lambda.bdg results/$TOOL/$SET/$NAME1*treat_pileup.bdg
rm results/$TOOL/$SET/$NAME2*control_lambda.bdg results/$TOOL/$SET/$NAME2*treat_pileup.bdg
#leave virtual environment
deactivate
else
echo "results/$TOOL/$SET/bed already exists exiting..."
fi