Merge pull request #696 from asp8200/md5_check_of_test_output

Adding md5-sums to the test-yml-files

CHANGELOG.md

@@ -16,6 +16,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#679](https://github.com/nf-core/sarek/pull/679) - Back to `dev`
 - [#685](https://github.com/nf-core/sarek/pull/685) - Updating the nf-core modules used by Sarek.
 - [#691](https://github.com/nf-core/sarek/pull/691) - To run the same pytest as before locally, use `PROFILE=docker`
+- [#696](https://github.com/nf-core/sarek/pull/696) - Adding check of md5-sums in CI-tests.
 
 ### Fixed
 

tests/test_aligner.yml

@@ -6,40 +6,73 @@
     - preprocessing
   files:
     - path: results/csv/markduplicates.csv
+      md5sum: 0d6120bb99e92f6810343270711ca53e
     - path: results/csv/markduplicates_no_table.csv
+      md5sum: 2a2d3d4842befd4def39156463859ee3
     - path: results/csv/recalibrated.csv
+      md5sum: 42628ec994c16f565e5407b40a9c1ac3
     - path: results/multiqc
     - path: results/preprocessing/markduplicates/test/test.md.cram
+    # binary changing on reruns
     - path: results/preprocessing/markduplicates/test/test.md.cram.crai
+    # binary changing on reruns
     - path: results/preprocessing/recal_table/test/test.recal.table
+      md5sum: 4ac774bf5f1157e77426fd82f5ac0fbe
     - path: results/preprocessing/recalibrated/test/test.recal.cram
+    # binary changing on reruns
     - path: results/preprocessing/recalibrated/test/test.recal.cram.crai
+    # binary changing on reruns
     - path: results/reference/bwamem2/genome.fasta.0123
+      md5sum: d73300d44f733bcdb7c988fc3ff3e3e9
     - path: results/reference/bwamem2/genome.fasta.amb
+      md5sum: 1891c1de381b3a96d4e72f590fde20c1
     - path: results/reference/bwamem2/genome.fasta.ann
+      md5sum: 2df4aa2d7580639fa0fcdbcad5e2e969
     - path: results/reference/bwamem2/genome.fasta.bwt.2bit.64
+      md5sum: cd4bdf496eab05228a50c45ee43c1ed0
     - path: results/reference/bwamem2/genome.fasta.pac
+      md5sum: 8569fbdb2c98c6fb16dfa73d8eacb070
     - path: results/reference/dbsnp/dbsnp_146.hg38.vcf.gz.tbi
+      md5sum: 628232d0c870f2dbf73c3e81aff7b4b4
     - path: results/reference/dict/genome.dict
+      md5sum: 2433fe2ba31257337bf4c4bd4cb8da15
     - path: results/reference/fai/genome.fasta.fai
+      md5sum: 3520cd30e1b100e55f578db9c855f685
     - path: results/reference/intervals/chr22_1-40001.bed
+      md5sum: 87a15eb9c2ff20ccd5cd8735a28708f7
     - path: results/reference/intervals/chr22_1-40001.bed.gz
+      md5sum: d3341fa28986c40b24fcc10a079dbb80
     - path: results/reference/intervals/genome.bed
+      md5sum: a87dc7d20ebca626f65cc16ff6c97a3e
     - path: results/reference/known_indels/mills_and_1000G.indels.vcf.gz.tbi
+      md5sum: 1bb7ab8f22eb798efd796439d3b29b7a
     - path: results/reports/fastqc/test-test_L1
     - path: results/reports/markduplicates/test/test.md.metrics
+      contains: ["test	8547	767	84	523391	3882	0	0	0.385081", "1.0	767	767"]
     - path: results/reports/mosdepth/test/test.md.mosdepth.global.dist.txt
+      md5sum: 76fa71922a3f748e507c2364c531dfcb
     - path: results/reports/mosdepth/test/test.md.mosdepth.region.dist.txt
+      md5sum: abc5df85e302b79985627888870882da
     - path: results/reports/mosdepth/test/test.md.mosdepth.summary.txt
+      md5sum: d536456436eb275159b8c6af83213d80
     - path: results/reports/mosdepth/test/test.md.regions.bed.gz
+      md5sum: 38fe39894abe62e38f8ac214cba64f2b
     - path: results/reports/mosdepth/test/test.md.regions.bed.gz.csi
+      md5sum: b1c2a861f64e20a94108a6de3b76c582
     - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt
+      md5sum: 76fa71922a3f748e507c2364c531dfcb
     - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt
+      md5sum: abc5df85e302b79985627888870882da
     - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt
+      md5sum: d536456436eb275159b8c6af83213d80
     - path: results/reports/mosdepth/test/test.recal.regions.bed.gz
+      md5sum: 38fe39894abe62e38f8ac214cba64f2b
     - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi
+      md5sum: b1c2a861f64e20a94108a6de3b76c582
     - path: results/reports/samtools/test/test.md.cram.stats
+      md5sum: dcf70bbcfb92e01027978f28d2035d78
     - path: results/reports/samtools/test/test.recal.cram.stats
+      md5sum: 5528d952f5dc74a39f28e27165bf96be
 - name: Run dragmap
   command: nextflow run main.nf -profile test,docker --aligner dragmap --save_reference
   tags:
@@ -48,40 +81,85 @@
     - preprocessing
   files:
     - path: results/csv/markduplicates.csv
+      md5sum: 0d6120bb99e92f6810343270711ca53e
     - path: results/csv/markduplicates_no_table.csv
+      md5sum: 2a2d3d4842befd4def39156463859ee3
     - path: results/csv/recalibrated.csv
+      md5sum: 42628ec994c16f565e5407b40a9c1ac3
     - path: results/multiqc
     - path: results/preprocessing/markduplicates/test/test.md.cram
+    # binary changing on reruns
     - path: results/preprocessing/markduplicates/test/test.md.cram.crai
+    # binary changing on reruns
     - path: results/preprocessing/recal_table/test/test.recal.table
+      md5sum: 75ba4376a17ca69c5134153302f82e92
     - path: results/preprocessing/recalibrated/test/test.recal.cram
+    # binary changing on reruns
     - path: results/preprocessing/recalibrated/test/test.recal.cram.crai
+    # binary changing on reruns
     - path: results/reference/dbsnp/dbsnp_146.hg38.vcf.gz.tbi
+      md5sum: 628232d0c870f2dbf73c3e81aff7b4b4
     - path: results/reference/dict/genome.dict
+      md5sum: 2433fe2ba31257337bf4c4bd4cb8da15
     - path: results/reference/dragmap/hash_table.cfg
+      # hash_table.cfg contains many strings which we could test for - which do we want to test?
+      contains:
+        [
+          "reference_sequences  = 1",
+          "reference_len        = 368640",
+          "reference_len_raw    = 40001",
+          "reference_len_not_n  = 40001",
+          "reference_alt_seed   = 204800",
+        ]
     - path: results/reference/dragmap/hash_table.cfg.bin
+    # binary changing on reruns
     - path: results/reference/dragmap/hash_table.cmp
+      md5sum: 1caab4ffc89f81ace615a2e813295cf4
     - path: results/reference/dragmap/hash_table_stats.txt
+      # hash_table_stats.txt contains many string which we could test for - which do we want to test?
+      contains: ["A bases:       10934", "C bases:        8612", "G bases:        8608", "T bases:       11847"]
     - path: results/reference/dragmap/ref_index.bin
+      md5sum: dbb5c7d26b974e0ac338024fe4535044
     - path: results/reference/dragmap/reference.bin
+      md5sum: be67b80ee48aa96b383fd72f1ccfefea
     - path: results/reference/dragmap/repeat_mask.bin
+      md5sum: 294939f1f80aa7f4a70b9b537e4c0f21
     - path: results/reference/dragmap/str_table.bin
+      md5sum: 45f7818c4a10fdeed04db7a34b5f9ff1
     - path: results/reference/fai/genome.fasta.fai
+      md5sum: 3520cd30e1b100e55f578db9c855f685
     - path: results/reference/intervals/chr22_1-40001.bed
+      md5sum: 87a15eb9c2ff20ccd5cd8735a28708f7
     - path: results/reference/intervals/chr22_1-40001.bed.gz
+      md5sum: d3341fa28986c40b24fcc10a079dbb80
     - path: results/reference/intervals/genome.bed
+      md5sum: a87dc7d20ebca626f65cc16ff6c97a3e
     - path: results/reference/known_indels/mills_and_1000G.indels.vcf.gz.tbi
+      md5sum: 1bb7ab8f22eb798efd796439d3b29b7a
     - path: results/reports/fastqc/test-test_L1
     - path: results/reports/markduplicates/test/test.md.metrics
+      contains: ["LB0	13607	543	161	518779	6410	0	0	0.436262"]
     - path: results/reports/mosdepth/test/test.md.mosdepth.global.dist.txt
+      md5sum: be1a800868fc1ce26711654525224e59
     - path: results/reports/mosdepth/test/test.md.mosdepth.region.dist.txt
+      md5sum: 2a3f0fab66518ef0786235470f1f28d0
     - path: results/reports/mosdepth/test/test.md.mosdepth.summary.txt
+      md5sum: d38ab9b0e0e551dc22919304929dd71c
     - path: results/reports/mosdepth/test/test.md.regions.bed.gz
+      md5sum: 0d92f4c698a6476ccaf798aa31a557bc
     - path: results/reports/mosdepth/test/test.md.regions.bed.gz.csi
+      md5sum: d5f1c9389ecf52ba839e834780a94549
     - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt
+      md5sum: be1a800868fc1ce26711654525224e59
     - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt
+      md5sum: 2a3f0fab66518ef0786235470f1f28d0
     - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt
+      md5sum: d38ab9b0e0e551dc22919304929dd71c
     - path: results/reports/mosdepth/test/test.recal.regions.bed.gz
+      md5sum: 0d92f4c698a6476ccaf798aa31a557bc
     - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi
+      md5sum: d5f1c9389ecf52ba839e834780a94549
     - path: results/reports/samtools/test/test.md.cram.stats
+      md5sum: f2ae8b531aa1fb2fbffe9a92e4c81493
     - path: results/reports/samtools/test/test.recal.cram.stats
+      md5sum: f7bab59db4fb8ab49eea71b668d351d5

tests/test_annotation.yml

@@ -5,20 +5,52 @@
     - snpeff
   files:
     - path: results/annotation/test/test_snpEff.ann.vcf.gz
+      md5sum: 01f24fdd76f73eefd695beea7b3d3d8e
     - path: results/annotation/test/test_snpEff.ann.vcf.gz.tbi
+      md5sum: 51e418d9be9bb33f1d4123493b15b6c9
     - path: results/multiqc
     - path: results/reports/snpeff/test/snpEff_summary.html
+      # snpEff_summary.html changes md5sums on reruns.
+      contains: ["<b> Genome total length </b>", "<td> 100,286,402 </td>", "<td> MT192765.1 </td>"]
     - path: results/reports/snpeff/test/test_snpEff.csv
+      # test_snpEff.csv changes md5sums on reruns.
+      contains:
+        [
+          "Values , 50,100",
+          "Count , 1,8",
+          "Reference , 0",
+          "Het , 1",
+          "Hom , 8",
+          "Missing , 0",
+          "MT192765.1, Position,0,1",
+          "MT192765.1,Count,0,0",
+        ]
     - path: results/reports/snpeff/test/test_snpEff.genes.txt
+      md5sum: 130536bf0237d7f3f746d32aaa32840a
 - name: Run VEP
   command: nextflow run main.nf -profile test,annotation --tools vep --skip_tools multiqc
   tags:
     - annotation
     - vep
   files:
     - path: results/annotation/test/test_VEP.ann.vcf.gz
+    # binary changes md5sums on reruns.
     - path: results/annotation/test/test_VEP.ann.vcf.gz.tbi
+      md5sum: 4cb176febbc8c26d717a6c6e67b9c905
     - path: results/reports/EnsemblVEP/test/test_VEP.summary.html
+      # test_VEP.summary.html changes md5sums on reruns.
+      contains:
+        [
+          "<tr><td>Input file</td><td>test.vcf.gz</td></tr><tr><td>Output file</td><td>test_VEP.ann.vcf</td></tr>",
+          "General statistics",
+          "Lines of input read",
+          "Variants processed",
+          "Variants filtered out",
+          "Novel / existing variants",
+          "Overlapped genes",
+          "Overlapped transcripts",
+          "Overlapped regulatory features",
+        ]
 - name: Run snpEff followed by VEP
   command: nextflow run main.nf -profile test,annotation --tools merge --skip_tools multiqc
   tags:
@@ -28,8 +60,23 @@
     - vep
   files:
     - path: results/annotation/test/test_snpEff_VEP.ann.vcf.gz
+    # binary changes md5sums on reruns.
     - path: results/annotation/test/test_snpEff_VEP.ann.vcf.gz.tbi
+      md5sum: 4cb176febbc8c26d717a6c6e67b9c905
     - path: results/reports/EnsemblVEP/test/test_snpEff_VEP.summary.html
+      # test_snpEff_VEP.summary.html changes md5sums on reruns.
+      contains:
+        [
+          "<tr><td>Input file</td><td>test_snpEff.ann.vcf.gz</td></tr><tr><td>Output file</td><td>test_snpEff_VEP.ann.vcf</td></tr>",
+          "General statistics",
+          "Lines of input read",
+          "Variants processed",
+          "Variants filtered out",
+          "Novel / existing variants",
+          "Overlapped genes",
+          "Overlapped transcripts",
+          "Overlapped regulatory features",
+        ]
     - path: results/annotation/test/test_snpEff.ann.vcf.gz
       should_exist: false
     - path: results/annotation/test/test_snpEff.ann.vcf.gz.tbi
@@ -55,22 +102,36 @@
     - vep
   files:
     - path: results/annotation/test/test_VEP.ann.vcf.gz
+    # binary changes md5sums on reruns.
     - path: results/annotation/test/test_VEP.ann.vcf.gz.tbi
+      md5sum: 4cb176febbc8c26d717a6c6e67b9c905
     - path: results/annotation/test/test_snpEff.ann.vcf.gz
+      md5sum: 01f24fdd76f73eefd695beea7b3d3d8e
     - path: results/annotation/test/test_snpEff.ann.vcf.gz.tbi
+      md5sum: 51e418d9be9bb33f1d4123493b15b6c9
     - path: results/annotation/test/test_snpEff_VEP.ann.vcf.gz
+    # binary changes md5sums on reruns.
     - path: results/annotation/test/test_snpEff_VEP.ann.vcf.gz.tbi
+      md5sum: 4cb176febbc8c26d717a6c6e67b9c905
     - path: results/reports/EnsemblVEP/test/test_VEP.summary.html
+    # text-based file changes md5sums on reruns.
     - path: results/reports/EnsemblVEP/test/test_snpEff_VEP.summary.html
+    # text-based file changes md5sums on reruns.
     - path: results/reports/snpeff/test/snpEff_summary.html
+    # text-based file changes md5sums on reruns.
     - path: results/reports/snpeff/test/test_snpEff.csv
+    # text-based file changes md5sums on reruns.
     - path: results/reports/snpeff/test/test_snpEff.genes.txt
+      md5sum: 130536bf0237d7f3f746d32aaa32840a
 - name: Run VEP with fasta
   command: nextflow run main.nf -profile test,annotation --tools vep --vep_include_fasta --skip_tools multiqc
   tags:
     - annotation
     - vep
   files:
     - path: results/annotation/test/test_VEP.ann.vcf.gz
+    # binary changes md5sums on reruns.
     - path: results/annotation/test/test_VEP.ann.vcf.gz.tbi
+      md5sum: 4cb176febbc8c26d717a6c6e67b9c905
     - path: results/reports/EnsemblVEP/test/test_VEP.summary.html
+    # text-based file changes md5sums on reruns.

tests/test_bam_remap.yml

@@ -4,40 +4,76 @@
     - alignment_to_fastq
   files:
     - path: results/cat/test-1_1.merged.fastq.gz
+      md5sum: 27b1dd4720d589cda1f33028798e859b
     - path: results/cat/test-1_2.merged.fastq.gz
+      md5sum: 2bbac774fffd1a9df53f9ab2fc2b86ab
     - path: results/collate/test-1.mapped_1.fq.gz
+      md5sum: 992b824d00359782db5240eee42d5f06
     - path: results/collate/test-1.mapped_2.fq.gz
+      md5sum: 118bff0ec11c9cc0427a7db21bdebc9c
     - path: results/collate/test-1.mapped_other.fq.gz
+      md5sum: 709872fc2910431b1e8b7074bfe38c67
     - path: results/collate/test-1.mapped_singleton.fq.gz
+      md5sum: 709872fc2910431b1e8b7074bfe38c67
     - path: results/collate/test-1.unmapped_1.fq.gz
+      md5sum: b79faf89e96948ea52f3ca41bee7de9a
     - path: results/collate/test-1.unmapped_2.fq.gz
+      md5sum: 8e18a94bfd77739e184856ac95d5b26a
     - path: results/collate/test-1.unmapped_other.fq.gz
+      md5sum: 709872fc2910431b1e8b7074bfe38c67
     - path: results/collate/test-1.unmapped_singleton.fq.gz
+      md5sum: 709872fc2910431b1e8b7074bfe38c67
     - path: results/csv/markduplicates.csv
+      md5sum: 0d6120bb99e92f6810343270711ca53e
     - path: results/csv/markduplicates_no_table.csv
+      md5sum: 2a2d3d4842befd4def39156463859ee3
     - path: results/csv/recalibrated.csv
+      md5sum: 42628ec994c16f565e5407b40a9c1ac3
     - path: results/multiqc
     - path: results/preprocessing/markduplicates/test/test.md.cram
+    # binary changes md5sums on reruns.
     - path: results/preprocessing/markduplicates/test/test.md.cram.crai
+    # binary changes md5sums on reruns.
     - path: results/preprocessing/recal_table/test/test.recal.table
+      md5sum: 9c0517ffdc5d30a5c73b9f7df1ff3060
     - path: results/preprocessing/recalibrated/test/test.recal.cram
+    # binary changes md5sums on reruns.
     - path: results/preprocessing/recalibrated/test/test.recal.cram.crai
+    # binary changes md5sums on reruns.
     - path: results/reports/fastqc/test-1
     - path: results/reports/markduplicates/test/test.md.metrics
+      contains: ["test	0	2820	2	2	0	828	0	0.293617	3807", "1.0	0.999986	1178	1178", "2.0	1.47674	800	800", "100.0	1.911145	0	0"]
     - path: results/reports/mosdepth/test/test.md.mosdepth.global.dist.txt
+      md5sum: 9cb9b181119256ed17a77dcf44d58285
     - path: results/reports/mosdepth/test/test.md.mosdepth.region.dist.txt
+      md5sum: 75e1ce7e55af51f4985fa91654a5ea2d
     - path: results/reports/mosdepth/test/test.md.mosdepth.summary.txt
+      md5sum: dbe376360e437c89190139ef0ae6769a
     - path: results/reports/mosdepth/test/test.md.regions.bed.gz
+      md5sum: d9b53915d473710ff0260a0ff694fd32
     - path: results/reports/mosdepth/test/test.md.regions.bed.gz.csi
+      md5sum: d0713716f63ac573f4a3385733e9a537
     - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt
+      md5sum: 9cb9b181119256ed17a77dcf44d58285
     - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt
+      md5sum: 75e1ce7e55af51f4985fa91654a5ea2d
     - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt
+      md5sum: dbe376360e437c89190139ef0ae6769a
     - path: results/reports/mosdepth/test/test.recal.regions.bed.gz
+      md5sum: d9b53915d473710ff0260a0ff694fd32
     - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi
+      md5sum: d0713716f63ac573f4a3385733e9a537
     - path: results/reports/samtools/test/test.md.cram.stats
+      md5sum: 5201890d36c1dd127b930373b6e823e5
     - path: results/reports/samtools/test/test.recal.cram.stats
+      md5sum: bb2fc6118a1404c45f9e828600df8fb1
     - path: results/samtools/test-1.bam
+    # binary changes md5sums on reruns.
     - path: results/samtools/test-1.map_map.bam
+      md5sum: e1d347ccaec52f690c0313047fecf7e6
     - path: results/samtools/test-1.map_unmap.bam
+      md5sum: 0be5ce27b94e047a1437596a91560982
     - path: results/samtools/test-1.unmap_map.bam
+      md5sum: 53423525e9bf327c60916aded73ba8a6
     - path: results/samtools/test-1.unmap_unmap.bam
+      md5sum: 60a80b7e380e228555b8d90990e1c788