Adding end-to-end tests hg19-chr22 (#61)

Closes: #61
Related-Issue: #61
Projected-Results-Impact: none

.gitattributes

@@ -0,0 +1,3 @@
+/tests/**/*.fa* filter=lfs diff=lfs merge=lfs -text
+/tests/**/*.ser filter=lfs diff=lfs merge=lfs -text
+/tests/**/*.vcf* filter=lfs diff=lfs merge=lfs -text

.github/workflows/ci.yml

@@ -49,19 +49,28 @@ jobs:
 
     steps:
       - uses: actions/checkout@v2
+        with:
+          lfs: true
+      - name: Check out LFS objects
+        run: git lfs checkout tests
       - name: Set up JDK
         uses: actions/setup-java@v2
         with:
           java-version: ${{ matrix.java }}
           distribution: 'adopt'
 
-      - name: Build with Maven and submit coverage report
+      - name: Build JAR with Maven without submitting coverage report
         run: >
           mvn
           --batch-mode
           --update-snapshots
           clean
-          test
+          package
+
+      - name: Run end-to-end tests
+        run: |
+          cd tests/hg19-chr22
+          bash run-tests.sh
 
   testing-coverage:
     runs-on: ubuntu-latest
@@ -78,7 +87,7 @@ jobs:
           java-version: ${{ matrix.java }}
           distribution: 'adopt'
 
-      - name: Build with Maven and submit coverage report
+      - name: Run test with Maven and submit coverage report
         run: >
           mvn
           --define repoToken=${{ secrets.COVERALLS_REPO_TOKEN }}

CHANGES.md

@@ -2,6 +2,8 @@
 
 ## v0.26-SNAPSHOT
 
+- Adding end-to-end tests `hg19-chr22` (#61)
+
 ## v0.25
 
 - Fixing unresolved issue with self-test (#51, #56)

README.md

@@ -62,3 +62,15 @@ The following will create `varfish-annotator-db-1906.h2.db` and fill it.
 ```
 # mvn com.coveo:fmt-maven-plugin:format -Dverbose=true
 ```
+
+## Tests
+
+The folder `/tests` contains some data sets that are appropriate for system (aka "end-to-end") tests of the software.
+
+- `hg19-chr22` --
+   This folder contains examples for annotating GATK HC and Delly2 calls on the first 20MB of chr22.
+   Only the variants overlapping with `ADA2` and `GAB4` are used.
+
+You can build the data sets with the `build.sh` script that is available in each folder.
+This script also serves for documenting the test data's provenance.
+The Jannovar software must be available as `jannovar` (e.g., through bioconda) on your `PATH` and you will need `samtools`.

tests/hg19-chr22/.gitignore

@@ -0,0 +1,6 @@
+*.tmp
+
+chr22.*
+chr22_part.fa
+
+/data

tests/hg19-chr22/Case_1_index.delly2.db-info.tsv-expected

@@ -0,0 +1,9 @@
+genomebuild	db_name	release
+GRCh37	clinvar	for-testing
+GRCh37	exac	r1.0
+GRCh37	gnomad_exomes	r2.1.1
+GRCh37	gnomad_genomes	r2.1.1
+GRCh37	hgmd_public	for-testing
+GRCh37	thousand_genomes	v3.20101123
+GRCh37	varfish-annotator	0.26-SNAPSHOT
+GRCh37	varfish-annotator-db	for-testing

tests/hg19-chr22/Case_1_index.delly2.feature-effects.tsv-expected

@@ -0,0 +1 @@
+case_id	set_id	sv_uuid	refseq_gene_id	refseq_transcript_id	refseq_transcript_coding	refseq_effect	ensembl_gene_id	ensembl_transcript_id	ensembl_transcript_coding	ensembl_effect

tests/hg19-chr22/Case_1_index.delly2.gts.tsv-expected

@@ -0,0 +1 @@
+release	chromosome	chromosome_no	bin	chromosome2	chromosome_no2	bin2	pe_orientation	start	end	start_ci_left	start_ci_right	end_ci_left	end_ci_right	case_id	set_id	sv_uuid	caller	sv_type	sv_sub_type	info	num_hom_alt	num_hom_ref	num_het	num_hemi_alt	num_hemi_ref	genotype

tests/hg19-chr22/Case_1_index.gatk_hc.db-info.tsv-expected

@@ -0,0 +1,9 @@
+genomebuild	db_name	release
+GRCh37	clinvar	for-testing
+GRCh37	exac	r1.0
+GRCh37	gnomad_exomes	r2.1.1
+GRCh37	gnomad_genomes	r2.1.1
+GRCh37	hgmd_public	for-testing
+GRCh37	thousand_genomes	v3.20101123
+GRCh37	varfish-annotator	0.26-SNAPSHOT
+GRCh37	varfish-annotator-db	for-testing

tests/hg19-chr22/Clinvar.tsv

@@ -0,0 +1 @@
+release	chromosome	start	end	bin	reference	alternative	clinvar_version	set_type	variation_type	symbols	hgnc_ids	vcv	summary_clinvar_review_status_label	summary_clinvar_pathogenicity_label	summary_clinvar_pathogenicity	summary_clinvar_gold_stars	summary_paranoid_review_status_label	summary_paranoid_pathogenicity_label	summary_paranoid_pathogenicity	summary_paranoid_gold_stars	details

tests/hg19-chr22/build.sh

@@ -0,0 +1,119 @@
+#!/usr/bin/bash
+
+set -euo pipefail
+set -x
+
+if [[ ! -e chr22.fa ]]; then
+  wget -O chr22.fa.gz.tmp https://hgdownload.cse.ucsc.edu/goldenpath/hg19/chromosomes/chr22.fa.gz
+  zcat chr22.fa.gz.tmp >chr22.fa.tmp
+  mv chr22.fa.tmp chr22.fa
+fi
+
+if [[ ! -e chr22_part.fa.fai ]]; then
+  samtools faidx chr22.fa chr22:1-22,000,000 > chr22_part.fa.tmp
+  perl -p -i -e 's/^>chr.*/>22/g' chr22_part.fa.tmp
+  gzip -c chr22_part.fa.tmp >chr22_part.fa.gz
+  mv chr22_part.fa.tmp chr22_part.fa
+  samtools faidx chr22_part.fa
+fi
+
+# ADA2(hg19): 22:17,660,192-17,680,545
+# GAB4(hg19): 22:17,442,827-17,489,112
+
+if [[ ! -e hg19_refseq.ser ]]; then
+  jannovar -Xmx4096m download -d hg19/ensembl --gene-ids ENSG00000093072 ENSG00000215568  # ADA2 GAB4
+  cp data/hg19_refseq.ser hg19_refseq.ser.tmp
+  mv hg19_refseq.ser.tmp hg19_refseq.ser
+fi
+
+if [[ ! -e hg19_ensembl.ser ]]; then
+  jannovar -Xmx4096m download -d hg19/ensembl --gene-ids 51816 128954  # ADA2 GAB4
+  cp data/hg19_ensembl.ser hg19_ensembl.ser.tmp
+  mv hg19_ensembl.ser.tmp hg19_ensembl.ser
+fi
+
+REGIONS="22:17,660,192-17,680,545 22:17,442,827-17,489,112"
+BASEDIR=/fast/groups/cubi/work/projects/2021-07-20_varfish-db-downloader-holtgrewe/varfish-db-downloader
+
+( \
+  tabix --only-header $BASEDIR/GRCh37/ExAC/r1/download/ExAC.r1.sites.vep.vcf.gz $REGIONS; \
+  tabix $BASEDIR/GRCh37/ExAC/r1/download/ExAC.r1.sites.vep.vcf.gz $REGIONS \
+  | sort -k1,1V -k2,2n \
+  | uniq; \
+) \
+| bgzip -c \
+> ExAC.r1.sites.vep.vcf.gz
+tabix -f ExAC.r1.sites.vep.vcf.gz
+
+( \
+  tabix --only-header $BASEDIR/GRCh37/gnomAD_exomes/r2.1.1/download/gnomad.exomes.r2.1.1.sites.chr22.vcf.bgz $REGIONS; \
+  tabix $BASEDIR/GRCh37/gnomAD_exomes/r2.1.1/download/gnomad.exomes.r2.1.1.sites.chr22.vcf.bgz $REGIONS \
+  | sort -k1,1V -k2,2n \
+  | uniq; \
+) \
+| bgzip -c \
+> gnomad.exomes.r2.1.1.sites.chr22.vcf.bgz
+tabix -f gnomad.exomes.r2.1.1.sites.chr22.vcf.bgz
+
+( \
+  tabix --only-header $BASEDIR/GRCh37/gnomAD_genomes/r2.1.1/download/gnomad.genomes.r2.1.1.sites.chr22.vcf.bgz $REGIONS; \
+  tabix $BASEDIR/GRCh37/gnomAD_genomes/r2.1.1/download/gnomad.genomes.r2.1.1.sites.chr22.vcf.bgz $REGIONS \
+  | sort -k1,1V -k2,2n \
+  | uniq; \
+) \
+| bgzip -c \
+> gnomad.genomes.r2.1.1.sites.chr22.vcf.bgz
+tabix -f gnomad.genomes.r2.1.1.sites.chr22.vcf.bgz
+
+( \
+  tabix --only-header $BASEDIR/GRCh37/thousand_genomes/phase3/ALL.chr22.phase3_shapeit2_mvncall_integrated_v5b.20130502.sites.vcf.gz; \
+  tabix $BASEDIR/GRCh37/thousand_genomes/phase3/ALL.chr22.phase3_shapeit2_mvncall_integrated_v5b.20130502.sites.vcf.gz $REGIONS \
+  | sort -k1,1V -k2,2n \
+  | uniq; \
+) \
+| bgzip -c \
+> ALL.chr22.phase3_shapeit2_mvncall_integrated_v5b.20130502.sites.vcf.gz
+tabix -f ALL.chr22.phase3_shapeit2_mvncall_integrated_v5b.20130502.sites.vcf.gz
+
+(head -n 1 /tmp/Clinvar.tsv; tail -n +2 /tmp/Clinvar.tsv | sort -k2,2V -k3,3n -k4,4n) \
+| bgzip -c >/tmp/Clinvar.tsv.gz
+tabix -S 1 -b 3 -e 4 -s 2 -f /tmp/Clinvar.tsv.gz
+head -n 1 /tmp/Clinvar.tsv >Clinvar.tsv.tmp
+tabix /tmp/Clinvar.tsv.gz $REGIONS \
+>>Clinvar.tsv.tmp
+gzip Clinvar.tsv.tmp
+mv Clinvar.tsv.tmp.gz Clinvar.tsv.gz
+
+(head -n 1 /tmp/HgmdPublicLocus.tsv; tail -n +2 /tmp/HgmdPublicLocus.tsv | sort -k2,2V -k3,3n -k4,4n) \
+| bgzip -c >/tmp/HgmdPublicLocus.tsv.gz
+tabix -S 1 -b 3 -e 4 -s 2 -f /tmp/HgmdPublicLocus.tsv.gz
+head -n 1 /tmp/HgmdPublicLocus.tsv >HgmdPublicLocus.tsv.tmp
+tabix /tmp/HgmdPublicLocus.tsv.gz $REGIONS \
+>>HgmdPublicLocus.tsv.tmp
+gzip HgmdPublicLocus.tsv.tmp
+mv HgmdPublicLocus.tsv.tmp.gz HgmdPublicLocus.tsv.gz
+
+BASEDIR=/fast/groups/cubi/work/projects/2022-07-06_VarFish_Course_Data/snappy-processing/
+VCF=$BASEDIR/variant_calling/output/bwa.gatk_hc.Case_1_index-N1-DNA1-WGS1/out/bwa.gatk_hc.Case_1_index-N1-DNA1-WGS1.vcf.gz
+
+( \
+  tabix --only-header $VCF $REGIONS; \
+  tabix $VCF $REGIONS \
+  | sort -k1,1V -k2,2n \
+  | uniq; \
+) \
+| bgzip -c \
+> Case_1_index.gatk_hc.vcf.gz
+tabix -f Case_1_index.gatk_hc.vcf.gz
+
+VCF=$BASEDIR/wgs_sv_calling/output/bwa.delly2.Case_1_index-N1-DNA1-WGS1/out/bwa.delly2.Case_1_index-N1-DNA1-WGS1.vcf.gz
+
+( \
+  tabix --only-header $VCF $REGIONS; \
+  tabix $VCF $REGIONS \
+  | sort -k1,1V -k2,2n \
+  | uniq; \
+) \
+| bgzip -c \
+> Case_1_index.delly2.vcf.gz
+tabix -f Case_1_index.delly2.vcf.gz

tests/hg19-chr22/db-info.txt-expected

@@ -0,0 +1,12 @@
+Table clinvar_var
+TABLE	RELEASE	CHROM	COUNT
+clinvar_var	GRCh37	22	124
+Table hgmd_locus
+TABLE	RELEASE	CHROM	COUNT
+hgmd_locus	GRCh37	22	11
+Table gnomad_exome_var
+TABLE	RELEASE	CHROM	COUNT
+gnomad_exome_var	GRCh37	22	1437
+Table gnomad_genome_var
+TABLE	RELEASE	CHROM	COUNT
+gnomad_genome_var	GRCh37	22	6072

tests/hg19-chr22/run-tests.sh

@@ -0,0 +1,90 @@
+#!/usr/bin/bash
+
+set -euo pipefail
+set -x
+
+JAR=$(ls ../../varfish-annotator-cli/target/varfish-annotator-cli-*.jar | grep -v sources | tail -n 1)
+
+## step 0: help
+
+java -jar $JAR --help >/tmp/the-output
+test -s /tmp/the-output
+
+set +e
+java -jar $JAR > /tmp/the-output
+retcode=$?
+set -e
+test 1 -eq $retcode
+test -s /tmp/the-output
+
+## step 1: init-db
+
+java -jar $JAR init-db \
+  --release GRCh37 \
+  --db-release-info varfish-annotator:main \
+  --db-release-info varfish-annotator-db:for-testing \
+  --db-path /tmp/out \
+  \
+  --ref-path chr22_part.fa \
+  \
+  --db-release-info exac:r1.0 \
+  --exac-path ExAC.r1.sites.vep.vcf.gz \
+  \
+  --db-release-info thousand_genomes:v3.20101123 \
+  --thousand-genomes-path ALL.chr22.phase3_shapeit2_mvncall_integrated_v5b.20130502.sites.vcf.gz \
+  \
+  --db-release-info clinvar:for-testing \
+  --clinvar-path Clinvar.tsv.gz \
+  \
+  --db-release-info gnomad_exomes:r2.1.1 \
+  --gnomad-exomes-path gnomad.exomes.r2.1.1.sites.chr22.vcf.bgz \
+  \
+  --db-release-info gnomad_genomes:r2.1.1 \
+  --gnomad-genomes-path gnomad.genomes.r2.1.1.sites.chr22.vcf.bgz \
+  \
+  --db-release-info hgmd_public:for-testing \
+  --hgmd-public HgmdPublicLocus.tsv.gz
+
+## step 2: db-info
+
+java -jar $JAR db-stats --db-path /tmp/out.h2.db --parseable \
+> /tmp/db-info.txt
+diff /tmp/db-info.txt db-info.txt-expected
+
+## step 3: annotate
+
+java -jar $JAR annotate \
+  --release GRCh37 \
+  --input-vcf Case_1_index.gatk_hc.vcf.gz \
+  --output-gts /tmp/Case_1_index.gatk_hc.gts.tsv \
+  --output-db-info /tmp/Case_1_index.gatk_hc.db-info.tsv \
+  --ref-path chr22_part.fa \
+  --refseq-ser-path hg19_refseq.ser \
+  --ensembl-ser-path hg19_ensembl.ser \
+  --db-path /tmp/out.h2.db \
+  --self-test-chr22-only
+
+diff /tmp/Case_1_index.gatk_hc.gts.tsv Case_1_index.gatk_hc.gts.tsv-expected
+diff /tmp/Case_1_index.gatk_hc.db-info.tsv Case_1_index.gatk_hc.db-info.tsv-expected
+
+## step 4: annotate-svs
+
+java -jar $JAR annotate-svs \
+  --release GRCh37 \
+  --input-vcf Case_1_index.delly2.vcf.gz \
+  --output-gts /tmp/Case_1_index.delly2.gts.tsv \
+  --output-feature-effects /tmp/Case_1_index.delly2.feature-effects.tsv \
+  --output-db-info /tmp/Case_1_index.delly2.db-info.tsv \
+  --refseq-ser-path hg19_refseq.ser \
+  --ensembl-ser-path hg19_ensembl.ser \
+  --db-path /tmp/out.h2.db \
+  --self-test-chr22-only
+
+diff /tmp/Case_1_index.delly2.gts.tsv Case_1_index.delly2.gts.tsv-expected
+diff /tmp/Case_1_index.delly2.db-info.tsv Case_1_index.delly2.db-info.tsv-expected
+diff /tmp/Case_1_index.delly2.feature-effects.tsv Case_1_index.delly2.feature-effects.tsv-expected
+
+## if we reach here, everything is fine
+
+echo "-- ALL TESTS PASSED --"
+exit 0

varfish-annotator-cli/src/main/java/com/github/bihealth/varfish_annotator/VarfishAnnotatorCli.java

@@ -30,6 +30,9 @@ public static void main(String[] args) {
     if ((args == null || args.length == 0)) {
       jc.usage();
       System.exit(1);
+    } else if (args.length == 1 && "--help".equals(args[0])) {
+      jc.usage();
+      System.exit(0);
     }
 
     try {