Update normalize_bam CI function and checksums

.circ

@@ -9,7 +9,7 @@ _ci_usage() {
 		clean        remove the temporary directory used for vaildation
 
 		Notes:
-		If '\$CI_DIR' is in the Nextflow asset folder the pipeline is run using the GitHub repository 
+		If '\$CI_DIR' is in the Nextflow asset folder the pipeline is run using the GitHub repository
 		to allow to change revision from the comand line, e.g.:
 
 		CI_DIR=~/.nextflow/assets/guigolab/grape-nf ci test -r v0.4.1
@@ -23,12 +23,12 @@ _ci_canonicalize_path() {
     else
         _ci_canonicalize_file_path "$1"
     fi
-}   
+}
 
 # Get canonical path of a directory
 _ci_canonicalize_dir_path() {
-    (cd "$1" 2>/dev/null && pwd -P) 
-}           
+    (cd "$1" 2>/dev/null && pwd -P)
+}
 
 # Get canonical path of a file
 _ci_canonicalize_file_path() {
@@ -38,11 +38,11 @@ _ci_canonicalize_file_path() {
     (cd "$dir" 2>/dev/null && printf '%s/%s\n' "$(pwd -P)" "$file")
 }
 
-# Check that Nextflow is installed and download it to the current 
+# Check that Nextflow is installed and download it to the current
 # folder otherwise
 _ci_setup_nxf() {
 	if ! nextflow &>/dev/null; then
-		export PATH=$PWD:$PATH 
+		export PATH=$PWD:$PATH
 		if [ ! -x nextflow ]; then
 			curl -fsSL get.nextflow.io | bash && chmod +x nextflow
 		fi
@@ -51,10 +51,10 @@ _ci_setup_nxf() {
 
 # Get the content of a BAM file for checksum
 _ci_normalize_bam() {
-	docker run --rm -v $1:$1 -w $PWD grapenf/samtools:1.3.1 bash -c "samtools view -h $2 | grep -v '@CO\|@PG' | samtools view -Sb - > $(basename $2) 2>/dev/null"
+	docker run --rm -v $CI_DIR:$CI_DIR -v $1:$1 -w $PWD grapenf/samtools:1.3.1 bash -c "samtools view -h $2 | grep -v '@CO\|@PG' | LC_ALL=C sort > $(basename $2) 2>/dev/null"
 }
 
-# Get file to the CI output directory either by creating a symlink 
+# Get file to the CI output directory either by creating a symlink
 # or normalizing a BAM file
 _ci_get_file() {
 	local baseDir=$1
@@ -95,7 +95,7 @@ _ci_check() {
 	(mkdir -p $CI_OUTDIR && cd $CI_OUTDIR
 	echo $CI_PROFILE > .ci_profile
 	cut -f 3 ../pipeline.db | while read f
-	do	
+	do
 		_ci_get_file $(_ci_canonicalize_path ..) $f
 	done
 	md5sum -c ${CI_DIR}/data/$CI_PROFILE.md5)
@@ -141,7 +141,7 @@ ci() {
 		test)
 			shift
 			(_ci_test "$@");;
-		*) 
+		*)
 			_ci_usage;;
 	esac
 }
@@ -151,4 +151,4 @@ CI_DIR=$(_ci_get_script_dir $0)
 CI_LOG=pipeline-ci.log
 CI_PROFILE="starrsem"
 CI_OUTDIR="checksum"
-CI_RUNOPTS=("-process.errorStrategy=terminate" "-with-docker")
+CI_RUNOPTS=("-process.errorStrategy=terminate" "-with-docker")

data/gemflux.md5

@@ -1,21 +1,21 @@
 60e3b244d81b235f4da09c6d0a216413  sample1.contigs.bed
 9b31baf13928228a90c34ed11100ea5a  sample1.genes.gff
 092b15fa6e2f0b16bbe3ac5a77706f39  sample1.isoforms.gtf
-cfe300e64671bbdee6652ce92ae5a053  sample1_m4_n10_toGenome.bam
+ccee0df1e95b1a37fdde16f5b84911ca  sample1_m4_n10_toGenome.bam
 4ec7f9268c5dcef3b537c88169f89e19  sample1.minusRaw.bw
 7ae99c171a210009538ddcd0ca016d6c  sample1.plusRaw.bw
 3aab7ddeea72e1e9c383ef99e8cb6c51  sample1_stats.json
 80c3892ceee10325d96ccab6f1e64557  sample2.contigs.bed
 13a9a9480dbff4e9e70d60b46ddd9e89  sample2.genes.gff
 8941bc59f0e957058c4535c9f33977cb  sample2.isoforms.gtf
-63ae7df24c69cc8e6cc17ad81cc36331  sample2_m4_n10_toGenome.bam
+f0233b16d583f683b45bede3b23f4afa  sample2_m4_n10_toGenome.bam
 4c852dab27a29718d4393b9514b6ca41  sample2.minusRaw.bw
 e66ef8cf062e662d5975bef6cab7a645  sample2.plusRaw.bw
 fd49b1c19e153c8ee112609e1ce757a0  sample2_stats.json
 89f19344b1f1a346a105f2b3f9443f9e  sample3.contigs.bed
 74f9de8e31ff2c24bc45af5f8ec73530  sample3.genes.gff
 1a039c489fdeb3e0ab4ff768424b5997  sample3.isoforms.gtf
-7a342ac43535d6f56492ea081f956779  sample3_m4_n10_toGenome.bam
+5f321238975bdde3bd81aee70ccb1f77  sample3_m4_n10_toGenome.bam
 db10a50bb7eebec0f3421f4460d4cae8  sample3.minusRaw.bw
 235e2d65c856c969048e432234c04ff4  sample3.plusRaw.bw
 77c72bef6f1410e33c90dbc01697fffc  sample3_stats.json

data/ihec.md5

@@ -1,8 +1,8 @@
 30245cd4c1b37b323a1428e6a79b6b46  sample1.contigs.bed
 5dd20d4ee5a2c161536ef43460c3537a  sample1.genes.results
 d2ce2685d81e4d3cafd42ff91284139c  sample1.isoforms.results
-a79f77a6ce5b6c1f47c38b1a038a4a50  sample1_m4_n10_toGenome.markdup.bam
-33428e053dfb80aab625e422cb45aec6  sample1_m4_n10_toTranscriptome.bam
+2dcd9d3a6981957cf9aee98e33658161  sample1_m4_n10_toGenome.markdup.bam
+8d88fb9910efc782292322ab22ebff8c  sample1_m4_n10_toTranscriptome.bam
 2cbe0ae71670342704ecfbda2d64ac25  sample1_stats.json
 b8c92ab59a2366efef9342c762ad6aa3  sample1.Unique.minusRaw.bw
 5a4ed2441202cb0ee4e1a8ce9842d7d4  sample1.UniqueMultiple.minusRaw.bw
@@ -11,8 +11,8 @@ b461f2bde79dfeadcfbf49762937d584  sample1.Unique.plusRaw.bw
 982947ea8922d0751a3e92407a14fe69  sample2.contigs.bed
 134b79ef252a55eac18a282f990d881c  sample2.genes.results
 9935f541a76a39c53a3909f350fabb1f  sample2.isoforms.results
-fd65d80492ed977584d287b76df9d4fe  sample2_m4_n10_toGenome.markdup.bam
-db09bcc2983231ac2dca933837d1bdb5  sample2_m4_n10_toTranscriptome.bam
+356564de835d5469c57eecb450b53fd3  sample2_m4_n10_toGenome.markdup.bam
+001e4af88d8713bd610492ccf859f128  sample2_m4_n10_toTranscriptome.bam
 5b99c51cc11b8dc0d0f41566a1459ca5  sample2_stats.json
 99858805585a1dae5a247e39e5bb3943  sample2.Unique.minusRaw.bw
 b5197e0220965ebbda74b7d3b77558d7  sample2.UniqueMultiple.minusRaw.bw
@@ -21,8 +21,8 @@ b5197e0220965ebbda74b7d3b77558d7  sample2.UniqueMultiple.minusRaw.bw
 89f19344b1f1a346a105f2b3f9443f9e  sample3.contigs.bed
 568855cd154369988f0e9120660dcea6  sample3.genes.results
 a2ddfd7d7919830d69f941176ddff86f  sample3.isoforms.results
-b23e2d5f4a21ce71c27a82b768033883  sample3_m4_n10_toGenome.markdup.bam
-6be11c68c6bfe99900982a848a7989bb  sample3_m4_n10_toTranscriptome.bam
+11e62a11f474ffa979ff9417c8d6c46b  sample3_m4_n10_toGenome.markdup.bam
+aa9845bc886d5f5183d123b481a22404  sample3_m4_n10_toTranscriptome.bam
 93ac7fc04304459ca7f85472ab5b700f  sample3_stats.json
 d7832747e6cc087ae631d22895adeac0  sample3.Unique.minusRaw.bw
 0c15bda07bcb2f2424925b27f6394656  sample3.UniqueMultiple.minusRaw.bw

data/markdup.md5

@@ -1,8 +1,8 @@
 30245cd4c1b37b323a1428e6a79b6b46  sample1.contigs.bed
 5dd20d4ee5a2c161536ef43460c3537a  sample1.genes.results
 d2ce2685d81e4d3cafd42ff91284139c  sample1.isoforms.results
-7991bd2774d8a9b6001c97fe45ab70e4  sample1_m4_n10_toGenome.markdup.bam
-33428e053dfb80aab625e422cb45aec6  sample1_m4_n10_toTranscriptome.bam
+2dcd9d3a6981957cf9aee98e33658161  sample1_m4_n10_toGenome.markdup.bam
+8d88fb9910efc782292322ab22ebff8c  sample1_m4_n10_toTranscriptome.bam
 2cbe0ae71670342704ecfbda2d64ac25  sample1_stats.json
 b8c92ab59a2366efef9342c762ad6aa3  sample1.Unique.minusRaw.bw
 5a4ed2441202cb0ee4e1a8ce9842d7d4  sample1.UniqueMultiple.minusRaw.bw
@@ -11,8 +11,8 @@ b461f2bde79dfeadcfbf49762937d584  sample1.Unique.plusRaw.bw
 982947ea8922d0751a3e92407a14fe69  sample2.contigs.bed
 134b79ef252a55eac18a282f990d881c  sample2.genes.results
 9935f541a76a39c53a3909f350fabb1f  sample2.isoforms.results
-cae7766b2971d54dd96612385140f0c0  sample2_m4_n10_toGenome.markdup.bam
-db09bcc2983231ac2dca933837d1bdb5  sample2_m4_n10_toTranscriptome.bam
+356564de835d5469c57eecb450b53fd3  sample2_m4_n10_toGenome.markdup.bam
+001e4af88d8713bd610492ccf859f128  sample2_m4_n10_toTranscriptome.bam
 5b99c51cc11b8dc0d0f41566a1459ca5  sample2_stats.json
 99858805585a1dae5a247e39e5bb3943  sample2.Unique.minusRaw.bw
 b5197e0220965ebbda74b7d3b77558d7  sample2.UniqueMultiple.minusRaw.bw
@@ -21,8 +21,8 @@ b5197e0220965ebbda74b7d3b77558d7  sample2.UniqueMultiple.minusRaw.bw
 89f19344b1f1a346a105f2b3f9443f9e  sample3.contigs.bed
 568855cd154369988f0e9120660dcea6  sample3.genes.results
 a2ddfd7d7919830d69f941176ddff86f  sample3.isoforms.results
-b23e2d5f4a21ce71c27a82b768033883  sample3_m4_n10_toGenome.markdup.bam
-6be11c68c6bfe99900982a848a7989bb  sample3_m4_n10_toTranscriptome.bam
+11e62a11f474ffa979ff9417c8d6c46b  sample3_m4_n10_toGenome.markdup.bam
+aa9845bc886d5f5183d123b481a22404  sample3_m4_n10_toTranscriptome.bam
 93ac7fc04304459ca7f85472ab5b700f  sample3_stats.json
 d7832747e6cc087ae631d22895adeac0  sample3.Unique.minusRaw.bw
 0c15bda07bcb2f2424925b27f6394656  sample3.UniqueMultiple.minusRaw.bw

data/rmdup.md5

@@ -1,8 +1,8 @@
 5afcc490a6b5717cf42c42ff093951be  sample1.contigs.bed
 5dd20d4ee5a2c161536ef43460c3537a  sample1.genes.results
 d2ce2685d81e4d3cafd42ff91284139c  sample1.isoforms.results
-1ff1cfff22531c949f2db0b69488a03c  sample1_m4_n10_toGenome.markdup.bam
-33428e053dfb80aab625e422cb45aec6  sample1_m4_n10_toTranscriptome.bam
+09eb9f6d52dc4decd5f78c41a7cee613  sample1_m4_n10_toGenome.markdup.bam
+8d88fb9910efc782292322ab22ebff8c  sample1_m4_n10_toTranscriptome.bam
 788498a850584e3ab55218e626e032fe  sample1_stats.json
 cff57373d6acc0a902058cadf06c17b2  sample1.Unique.minusRaw.bw
 f726544d2bd353c08c28adf3d81240b2  sample1.UniqueMultiple.minusRaw.bw
@@ -11,8 +11,8 @@ c59cb9486bd2d3abe21d123e538e02b0  sample1.UniqueMultiple.plusRaw.bw
 bfc9a9c5501bbb0d1d60ee2b47a53916  sample2.contigs.bed
 134b79ef252a55eac18a282f990d881c  sample2.genes.results
 9935f541a76a39c53a3909f350fabb1f  sample2.isoforms.results
-f762079c74bc01b3654b6cb2d62c1f1c  sample2_m4_n10_toGenome.markdup.bam
-db09bcc2983231ac2dca933837d1bdb5  sample2_m4_n10_toTranscriptome.bam
+66bf139ee0e17a4ac24eb8ea58112c30  sample2_m4_n10_toGenome.markdup.bam
+001e4af88d8713bd610492ccf859f128  sample2_m4_n10_toTranscriptome.bam
 b50b1fbf7a9d04bd78a1d5427f7356ae  sample2_stats.json
 7362829e0b4279f23a13c7e5546bd134  sample2.Unique.minusRaw.bw
 f1a2be88768194dfa2ad4cf3f3cfe496  sample2.UniqueMultiple.minusRaw.bw
@@ -21,8 +21,8 @@ d14e02cf22f15c9d49af61d8fda1718a  sample2.Unique.plusRaw.bw
 a14c5872ab9a2dcf55a70a7b17f449ea  sample3.contigs.bed
 568855cd154369988f0e9120660dcea6  sample3.genes.results
 a2ddfd7d7919830d69f941176ddff86f  sample3.isoforms.results
-1b979a874a8c1f5068a305dc6a216618  sample3_m4_n10_toGenome.markdup.bam
-6be11c68c6bfe99900982a848a7989bb  sample3_m4_n10_toTranscriptome.bam
+a17775628cbaae90ec26687f98b417c5  sample3_m4_n10_toGenome.markdup.bam
+aa9845bc886d5f5183d123b481a22404  sample3_m4_n10_toTranscriptome.bam
 bc7ecf0db0ed5b035fac07f521849de6  sample3_stats.json
 811d8dde82e960f098854f2384507778  sample3.Unique.minusRaw.bw
 8e197ae04a0f9b4ddee9ad7eaa43e396  sample3.UniqueMultiple.minusRaw.bw

data/starflux.md5

@@ -1,7 +1,7 @@
 30245cd4c1b37b323a1428e6a79b6b46  sample1.contigs.bed
 94884593db9b76caa87bf2c3b09c4671  sample1.genes.gff
 c3cfd6d32e8bd3258bb1cb6127157a99  sample1.isoforms.gtf
-e1cf9e315706bf0eb08258d503a36274  sample1_m4_n10_toGenome.bam
+62dcbc3b66c603e998a7e1f564e3743a  sample1_m4_n10_toGenome.bam
 6936e714ac8f98c951ba52ec8fd0e441  sample1_stats.json
 37aa4ae5af33a81f8775440bbfd21fba  sample1.Unique.minusRaw.bw
 ffce7ba84865e21df6bf8fb849822545  sample1.UniqueMultiple.minusRaw.bw
@@ -10,7 +10,7 @@ b2d459ec4663d01769e97352c2b59de2  sample1.UniqueMultiple.plusRaw.bw
 982947ea8922d0751a3e92407a14fe69  sample2.contigs.bed
 342fe787dd63b159919b99f9223d00c9  sample2.genes.gff
 f2b8f02792b460063ab3dd9d74a0e460  sample2.isoforms.gtf
-25d835f345f074934e63c5b6d87a77ab  sample2_m4_n10_toGenome.bam
+c3b825e524cd9143a85c46d3807a7c87  sample2_m4_n10_toGenome.bam
 0295d0759fbf5a2df7035f8ff5333e5e  sample2_stats.json
 1de3717e5641e2eccd5f1c939c606f3d  sample2.Unique.minusRaw.bw
 3da795eb593185afb75c9aea84c82b87  sample2.UniqueMultiple.minusRaw.bw
@@ -19,7 +19,7 @@ c7ad3d6214f976735c7e621b9f78d323  sample2.UniqueMultiple.plusRaw.bw
 89f19344b1f1a346a105f2b3f9443f9e  sample3.contigs.bed
 74f9de8e31ff2c24bc45af5f8ec73530  sample3.genes.gff
 1a039c489fdeb3e0ab4ff768424b5997  sample3.isoforms.gtf
-7a342ac43535d6f56492ea081f956779  sample3_m4_n10_toGenome.bam
+5f321238975bdde3bd81aee70ccb1f77  sample3_m4_n10_toGenome.bam
 77c72bef6f1410e33c90dbc01697fffc  sample3_stats.json
 1363d4e278c9024433c2901996ab730a  sample3.Unique.minusRaw.bw
 2deb1fd284c866ff5faec6ceba351d56  sample3.UniqueMultiple.minusRaw.bw

data/starrsem.md5

@@ -1,8 +1,8 @@
 30245cd4c1b37b323a1428e6a79b6b46  sample1.contigs.bed
 5dd20d4ee5a2c161536ef43460c3537a  sample1.genes.results
 d2ce2685d81e4d3cafd42ff91284139c  sample1.isoforms.results
-e1cf9e315706bf0eb08258d503a36274  sample1_m4_n10_toGenome.bam
-33428e053dfb80aab625e422cb45aec6  sample1_m4_n10_toTranscriptome.bam
+62dcbc3b66c603e998a7e1f564e3743a  sample1_m4_n10_toGenome.bam
+8d88fb9910efc782292322ab22ebff8c  sample1_m4_n10_toTranscriptome.bam
 6936e714ac8f98c951ba52ec8fd0e441  sample1_stats.json
 37aa4ae5af33a81f8775440bbfd21fba  sample1.Unique.minusRaw.bw
 ffce7ba84865e21df6bf8fb849822545  sample1.UniqueMultiple.minusRaw.bw
@@ -11,8 +11,8 @@ b2d459ec4663d01769e97352c2b59de2  sample1.UniqueMultiple.plusRaw.bw
 982947ea8922d0751a3e92407a14fe69  sample2.contigs.bed
 134b79ef252a55eac18a282f990d881c  sample2.genes.results
 9935f541a76a39c53a3909f350fabb1f  sample2.isoforms.results
-25d835f345f074934e63c5b6d87a77ab  sample2_m4_n10_toGenome.bam
-db09bcc2983231ac2dca933837d1bdb5  sample2_m4_n10_toTranscriptome.bam
+c3b825e524cd9143a85c46d3807a7c87  sample2_m4_n10_toGenome.bam
+001e4af88d8713bd610492ccf859f128  sample2_m4_n10_toTranscriptome.bam
 0295d0759fbf5a2df7035f8ff5333e5e  sample2_stats.json
 1de3717e5641e2eccd5f1c939c606f3d  sample2.Unique.minusRaw.bw
 3da795eb593185afb75c9aea84c82b87  sample2.UniqueMultiple.minusRaw.bw
@@ -21,8 +21,8 @@ c7ad3d6214f976735c7e621b9f78d323  sample2.UniqueMultiple.plusRaw.bw
 89f19344b1f1a346a105f2b3f9443f9e  sample3.contigs.bed
 568855cd154369988f0e9120660dcea6  sample3.genes.results
 a2ddfd7d7919830d69f941176ddff86f  sample3.isoforms.results
-7a342ac43535d6f56492ea081f956779  sample3_m4_n10_toGenome.bam
-6be11c68c6bfe99900982a848a7989bb  sample3_m4_n10_toTranscriptome.bam
+5f321238975bdde3bd81aee70ccb1f77  sample3_m4_n10_toGenome.bam
+aa9845bc886d5f5183d123b481a22404  sample3_m4_n10_toTranscriptome.bam
 77c72bef6f1410e33c90dbc01697fffc  sample3_stats.json
 1363d4e278c9024433c2901996ab730a  sample3.Unique.minusRaw.bw
 2deb1fd284c866ff5faec6ceba351d56  sample3.UniqueMultiple.minusRaw.bw