Merge pull request #128 from cyenyxe/feature/annotation-collection

Versioned VEP annotation + new collection

README.md

@@ -126,7 +126,7 @@ Database name and collection names can be specified with these parameters. To se
 * `db.collections.variants.name`: Main collection. Has variant coordinates, sample information, and some statistics and annotation.
 * `db.collections.files.name`: File (and study) metadata information.
 * `db.collections.stats.name`: Main collection for statistics. The variants collection might contain a subset of this.
-* `db.collections.annotation.metadata.name`: Main collection for annotation. The variants collection might contain a subset of this.
+* `db.collections.annotation-metadata.name`: Main collection for annotation. The variants collection might contain a subset of this.
 
 #### Configuration of third party applications
 

examples/annotate-variants-job.properties

@@ -0,0 +1,35 @@
+# JOB
+spring.batch.job.names=annotate-variants-job
+
+# SUBMISSION FIELDS
+input.vcf.id=1234
+input.study.id=2345
+
+input.fasta=/path/to/homo_sapiens/sequence.fa
+
+output.dir.annotation=/path/to/annotation-files/
+
+
+# VEP
+app.vep.path=/path/to/variant_effect_predictor.pl
+app.vep.cache.path=/path/to/vep/cache_folder
+app.vep.cache.version=82
+app.vep.version=82
+app.vep.cache.species=homo_sapiens
+app.vep.num-forks=4
+app.vep.timeout=600
+
+# STEPS MANAGEMENT
+config.chunk.size=1000
+
+## Skip steps
+annotation.overwrite=false
+
+# Database configuration
+spring.data.mongodb.database=
+# TODO The following 2 properties will be used exclusive after removing readers and writers dependency
+# on OpenCGA. At the moment they need to be specified in both.
+db.collections.files.name=files
+db.collections.variants.name=variants
+db.collections.annotation-metadata.name=annotationMetadata
+db.collections.annotations.name=annotations

examples/application.properties

@@ -1,7 +1,7 @@
 # EXECUTION PROFILE
 ## "production" to keep track of half-executed jobs using a job repository database
 ## "test" to use an in-memory database that will record a single run
-spring.profiles.active=production
+spring.profiles.active=production,mongo
 
 
 # OpenCGA

examples/drop-study-job.properties

@@ -9,4 +9,5 @@ spring.data.mongodb.database=your_db
 
 db.collections.variants.name=variants
 db.collections.files.name=files
+db.collections.annotations.name=annotations
 

examples/load-aggregated-vcf.properties

@@ -31,11 +31,13 @@ config.chunk.size=1000
 ## Skip steps
 statistics.skip=false
 annotation.skip=false
+annotation.overwrite=false
 
 # Database configuration
 spring.data.mongodb.database=
 # TODO The following 2 properties will be used exclusive after removing readers and writers dependency
 # on OpenCGA. At the moment they need to be specified in both.
 db.collections.files.name=files
 db.collections.variants.name=variants
-db.collections.annotation.metadata.name=annotationMetadata
+db.collections.annotation-metadata.name=annotationMetadata
+db.collections.annotations.name=annotations

examples/load-genotyped-vcf.properties

@@ -33,11 +33,13 @@ config.chunk.size=1000
 ## Skip steps
 statistics.skip=false
 annotation.skip=false
+annotation.overwrite=false
 
 # Database configuration
 spring.data.mongodb.database=
 # TODO The following 2 properties will be used exclusive after removing readers and writers dependency
 # on OpenCGA. At the moment they need to be specified in both.
 db.collections.files.name=files
 db.collections.variants.name=variants
-db.collections.annotation.metadata.name=annotationMetadata
+db.collections.annotation-metadata.name=annotationMetadata
+db.collections.annotations.name=annotations