Mercurial > repos > iuc > homer_gtf_to_annotations

comparison test-data/generate_tests.sh @ 0:8ebb6520eef4 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/homer commit e49d856e0181edc6120220a1b819cba2466a4289"
author iuc
date Sun, 08 Aug 2021 11:04:17 +0000
parents
children 396cf2c12173
comparison
equal deleted inserted replaced
-1:000000000000 0:8ebb6520eef4
1 #! /usr/bin/bash
2 ## Generate input data:
3 if [ ! -e test-data/small_simplified.gtf ]; then
4 wget http://ftp.ensembl.org/pub/release-102/gtf/mus_musculus/Mus_musculus.GRCm38.102.gtf.gz -O /tmp/Mus_musculus.GRCm38.102.gtf.gz
5 zcat /tmp/Mus_musculus.GRCm38.102.gtf.gz | head -n 5 > test-data/small.gtf
6 zcat /tmp/Mus_musculus.GRCm38.102.gtf.gz | awk -v OFS="\t" -v start=74667792 -v end=74748393 '$1 == "2" && $5 > start && $4 < end{print "chr"$0}' >> test-data/small.gtf
7 # annotatePeaks.pl gives different results all time. I need to simplify the gtf.
8 cat test-data/small.gtf | grep -v -P "ENSMUST00000152027|ENSMUST00000156342|ENSMUST00000139005|ENSMUST00000144544|ENSMUST00000111982|ENSMUST00000140666|ENSMUST00000190553|ENSMUST00000132326|ENSMUST00000047830|ENSMUST00000047904|ENSMUST00000111980|ENSMUSG00000065500|ENSMUSG00000100642" > test-data/small_simplified.gtf
9 fi
10 if [ ! -e test-data/CTCF_peaks.bed ]; then
11 wget https://raw.githubusercontent.com/lldelisle/scriptsForWilleminEtAl2021/main/CTCF/E12_Limbs_Wt_CTCF_colored.bed -O test-data/CTCF_peaks.bed
12 fi
13 if [ ! -e test-data/CTCF_peaks_shifted.bed ]; then
14 cat test-data/CTCF_peaks.bed | grep "chr2" | awk -v OFS="\t" '{$1="mm10_dna"; $2-=73740000; $3-=73740000; print}' > test-data/CTCF_peaks_shifted.bed
15 fi
16 # chr2_subset.fa was downloaded from UCSC
17 # https://genome.ucsc.edu/cgi-bin/hgc?hgsid=1136019667_XgAJOvV4a3CY4ibCu6RrUcvGxLNo&g=htcGetDna2&table=&i=mixed&o=56694975&l=56694975&r=56714605&getDnaPos=chr2%3A73740000-75787000&db=mm10&hgSeq.cdsExon=1&hgSeq.padding5=0&hgSeq.padding3=0&hgSeq.casing=upper&hgSeq.maskRepeats=on&boolshad.hgSeq.maskRepeats=0&hgSeq.repMasking=lower&boolshad.hgSeq.revComp=0&submit=get+DNA
18
19 . <(planemo conda_env homer_gtf_to_annotation.xml)
20 echo "$(which homer)"
21 ## homer_gtf_to_annotation
22 ## First test
23 parseGTF.pl test-data/small.gtf ann -features exon start_codon stop_codon > /tmp/annotations.txt
24 assignGenomeAnnotation /tmp/annotations.txt /tmp/annotations.txt -prioritize test-data/annotations_default.txt > test-data/annotations_default_stats.txt
25 ## Second test
26 parseGTF.pl test-data/small.gtf ann -features exon start_codon > /tmp/annotations2.txt
27 assignGenomeAnnotation /tmp/annotations2.txt /tmp/annotations2.txt -prioritize test-data/annotations_exon_start.txt > test-data/annotations_exon_start_stats.txt
28 ## Third test
29 parseGTF.pl test-data/small.gtf ann -features exon start_codon stop_codon -annTSSstartOffset -50 -annTSSendOffset 50 -annTTSstartOffset -50 -annTTSendOffset 50 > /tmp/annotations3.txt
30 assignGenomeAnnotation /tmp/annotations3.txt /tmp/annotations3.txt -prioritize test-data/annotations_small_TSSTTS.txt > test-data/annotations_small_TSSTTS_stats.txt
31
32 ## For annotatePeaks.pl
33 parseGTF.pl test-data/small_simplified.gtf ann -features exon start_codon stop_codon > /tmp/annotations.txt
34 assignGenomeAnnotation /tmp/annotations.txt /tmp/annotations.txt -prioritize test-data/annotations_default_simplified.txt
35
36 ## homer_annotatePeaks
37 ## First test
38 annotatePeaks.pl test-data/CTCF_peaks.bed none -gtf test-data/small_simplified.gtf -ann test-data/annotations_default_simplified.txt > test-data/CTCF_peaks_first.txt
39 ## Second test
40 annotatePeaks.pl test-data/CTCF_peaks.bed none -ann test-data/annotations_default.txt > test-data/CTCF_peaks_second.txt
41 ## Third test
42 annotatePeaks.pl test-data/CTCF_peaks.bed none -gtf test-data/small_simplified.gtf > test-data/CTCF_peaks_third.txt
43 ## Fourth test
44 annotatePeaks.pl test-data/fake_phix_peaks.bed test-data/phiX174.fasta -CpG > test-data/phiXcpg.txt
45 ## Fifth test
46 annotatePeaks.pl test-data/fake_phix_peaks.bed none > test-data/phiX_nothing.txt
47
48 ## findMotifsGenome
49 # ! Genome preparsing is giving different results...
50 findMotifsGenome.pl test-data/fake_phix_peaks.bed test-data/phiX174.fasta fake_phix_peaks_bed_motif
51 mv fake_phix_peaks_bed_motif test-data/motif_test1
52 # Thus I needed to use has_text for the other outputs
53 # findMotifsGenome.pl test-data/CTCF_peaks_shifted.bed test-data/chr2_subset.fa CTCF_peaks_shifted_bed_motif
54 # mv CTCF_peaks_shifted_bed_motif test-data/motif_test2
55 # findMotifsGenome.pl test-data/CTCF_peaks_shifted.bed test-data/chr2_subset.fa CTCF_peaks_shifted_bed_motif -mask
56 # mv CTCF_peaks_shifted_bed_motif test-data/motif_test3
57 # findMotifsGenome.pl test-data/CTCF_peaks_shifted.bed test-data/chr2_subset.fa CTCF_peaks_shifted_bed_motif -mset plants -nomotif
58 # mv CTCF_peaks_shifted_bed_motif test-data/motif_test4
59