Merge pull request #237 from bioinfo-chru-strasbourg/0.10.0

0.10.0
bioinfo-chru-strasbourg · May 8, 2024 · 0726681 · 0726681
2 parents c9b98a8 + 7b133ed
commit 0726681
Show file tree

Hide file tree

Showing 410 changed files with 394,926 additions and 27,320 deletions.
diff --git a/.dockerignore b/.dockerignore
@@ -0,0 +1,19 @@
+__pycache__/
+howard.egg-info/
+.pytest_cache/
+.cache
+.vscode
+.coverage
+.tmp
+tests/databases/annovar/
+tests/databases/snpeff/
+tests/databases/genomes/
+tests/databases/refseq/
+tests/databases/hg19.fa
+tests/databases/hg19.fa.fai
+tests/databases/.DS_Store
+tests/data/TEM*
+misc/
+**.DS_Store
+snpEff_*
+.gitignore
diff --git a/.env b/.env
@@ -24,7 +24,7 @@ DOCKER_COMPOSE_ENV=.env
 # Docker HOWARD image including HOWARD tool and configuration
 # This image will be build if needed (using Docker HOWARD context)
 #DOCKER_HOWARD_IMAGE=howard:latest
-DOCKER_HOWARD_IMAGE=howard:0.9.15.6
+DOCKER_HOWARD_IMAGE=howard:0.10.0
 
 
 ### DOCKER HOWARD CONTEXT
@@ -41,7 +41,7 @@ DOCKER_HOWARD_NETWORK=howard_howard
 
 
 ### DOCKER HOWARD HOME
-DOCKER_HOWARD_HOME=${HOME}/HOWARD
+DOCKER_HOWARD_HOME=${HOME}/howard
 
 
 # SERVICE CLI
@@ -84,49 +84,51 @@ DOCKER_HOWARD_SETUP_IMAGE=${DOCKER_HOWARD_IMAGE}
 DOCKER_HOWARD_SETUP_CONTAINER_NAME=HOWARD-setup
 
 ### Databases folders
+DOCKER_HOWARD_SETUP_GENOMES=${DOCKER_HOWARD_CLI_FOLDER_INNER_DATABASES}/genomes/current
 DOCKER_HOWARD_SETUP_ANNOVAR_DATABASES=${DOCKER_HOWARD_CLI_FOLDER_INNER_DATABASES}/annovar/current
 DOCKER_HOWARD_SETUP_SNPEFF_DATABASES=${DOCKER_HOWARD_CLI_FOLDER_INNER_DATABASES}/snpeff/current
+DOCKER_HOWARD_SETUP_REFSEQ_DATABASES=${DOCKER_HOWARD_CLI_FOLDER_INNER_DATABASES}/refseq/current
+DOCKER_HOWARD_SETUP_DBNSFP_DATABASES=${DOCKER_HOWARD_CLI_FOLDER_INNER_DATABASES}/dbnsfp/current
+DOCKER_HOWARD_SETUP_ALPHAMISSENSE_DATABASES=${DOCKER_HOWARD_CLI_FOLDER_INNER_DATABASES}/annotations/current
+DOCKER_HOWARD_SETUP_EXOMISER_DATABASES=${DOCKER_HOWARD_CLI_FOLDER_INNER_DATABASES}/exomiser/current
+DOCKER_HOWARD_SETUP_DBSNP_DATABASES=${DOCKER_HOWARD_CLI_FOLDER_INNER_DATABASES}/dbsnp/current
 
 ### Databases annotation options
 
 # Assembly
 DOCKER_HOWARD_SETUP_ASSEMBLY=hg19
 
-# Annotation
-# Use "ALL" to annotate, test and download all available databases (defined in the HOWARD configuration annotation file)
-# Use "core" to annotate, test and download only core databases (symbol, outcom, location, hgvs, dbSNP... see HOWARD doc)
-# Use "<annovar_code>" to annotate, test and download a custom annovar database (see code on annovar website)
-# Use "symbol" to annotate, test and download only symbol annotation
-# Use "snpeff" to annotate, test and download snpEff databases
-DOCKER_HOWARD_SETUP_ANNOTATION="core,CLINVAR,COSMIC,snpeff"
+# Genomes
+DOCKER_HOWARD_SETUP_GENOMES_PROVIDER="UCSC"
+DOCKER_HOWARD_SETUP_GENOMES_CONTIG_REGEX='chr[0-9XYM]+$'
 
+# Annovar Annotation databases
+DOCKER_HOWARD_SETUP_ANNOTATION="refGene,cosmic70,nci60"
 
-### setup command
-# Annotation trough HOWARD annotation
-# All daabases can be downloaded independently, see ANNOVAR and snpEff doc
-
-# This simple command actually does not work for snpEff 5.0e (due to snpEff bug)
-#DOCKER_HOWARD_SETUP_CONTAINER_COMMAND='-c "mkdir -p ${DOCKER_HOWARD_SETUP_ANNOVAR_DATABASES} ${DOCKER_HOWARD_SETUP_SNPEFF_DATABASES} && HOWARD --input=/tool/docs/example.vcf --output=/tmp/example.howard.vcf.gz --annotation=symbol,snpeff --calculation=BARCODE --prioritization=default --translation=TSV --compress=5 --index --verbose --threads=1 && bcftools view /tmp/example.howard.vcf.gz && echo \"# HOWARD setup and test checked!\""'
+# refSeq format to BED
+DOCKER_HOWARD_SETUP_REFSEQ_TO_BED="ncbiRefSeq.txt"
 
-# This command actually does not work for snpEff 5.0e (due to snpEff bug)
-#DOCKER_HOWARD_SETUP_CONTAINER_COMMAND='-c "mkdir -p ${DOCKER_HOWARD_SETUP_ANNOVAR_DATABASES} ${DOCKER_HOWARD_SETUP_SNPEFF_DATABASES} && if [ ! -d ${DOCKER_HOWARD_SETUP_SNPEFF_DATABASES}/${DOCKER_HOWARD_SETUP_ASSEMBLY} ]; then $JAVA -jar -Xmx4g -jar $SNPEFF download ${DOCKER_HOWARD_SETUP_ASSEMBLY}; fi && HOWARD --input=/tool/docs/example.vcf --output=/tmp/example.howard.vcf.gz --annotation=symbol,snpeff --calculation=BARCODE --prioritization=default --translation=TSV --compress=5 --index --verbose --threads=1 && bcftools view /tmp/example.howard.vcf.gz && echo \"# HOWARD setup and test checked!\""'
-
-# This command is more manual, but works (only for snpEff 5.0 and the indicated assembly)
-DOCKER_HOWARD_SETUP_CONTAINER_COMMAND='-c "mkdir -p ${DOCKER_HOWARD_SETUP_ANNOVAR_DATABASES} ${DOCKER_HOWARD_SETUP_SNPEFF_DATABASES} && if [ ! -d ${DOCKER_HOWARD_SETUP_SNPEFF_DATABASES}/${DOCKER_HOWARD_SETUP_ASSEMBLY} ]; then wget --progress=bar -O ${DOCKER_HOWARD_SETUP_SNPEFF_DATABASES}/snpEff_v5_0_${DOCKER_HOWARD_SETUP_ASSEMBLY}.zip https://snpeff.blob.core.windows.net/databases/v5_0/snpEff_v5_0_${DOCKER_HOWARD_SETUP_ASSEMBLY}.zip ; unzip -o ${DOCKER_HOWARD_SETUP_SNPEFF_DATABASES}/snpEff_v5_0_${DOCKER_HOWARD_SETUP_ASSEMBLY}.zip -d ${DOCKER_HOWARD_SETUP_SNPEFF_DATABASES}/; mv ${DOCKER_HOWARD_SETUP_SNPEFF_DATABASES}/data/* ${DOCKER_HOWARD_SETUP_SNPEFF_DATABASES}/; fi && HOWARD --input=/tool/docs/example.vcf --output=/tmp/example.howard.tsv --annotation=${DOCKER_HOWARD_SETUP_ANNOTATION} --calculation=BARCODE,NOMEN --prioritization=default --translation=TSV --verbose --threads=1 && cat /tmp/example.howard.tsv && echo \"# HOWARD setup and test checked!\""'
+# Threads
+DOCKER_HOWARD_SETUP_THREADS=-1
 
+### setup command
+# Download Annovar and snpEff databases
+DOCKER_HOWARD_SETUP_CONTAINER_COMMAND='-c "howard databases --config=/tool/config/config.json --assembly=${DOCKER_HOWARD_SETUP_ASSEMBLY} --download-genomes=${DOCKER_HOWARD_SETUP_GENOMES} --download-genomes-provider=${DOCKER_HOWARD_SETUP_GENOMES_PROVIDER} --download-genomes-contig-regex=${DOCKER_HOWARD_SETUP_GENOMES_CONTIG_REGEX} --download-annovar=${DOCKER_HOWARD_SETUP_ANNOVAR_DATABASES} --download-annovar-files=${DOCKER_HOWARD_SETUP_ANNOTATION} --download-snpeff=${DOCKER_HOWARD_SETUP_SNPEFF_DATABASES} --download-refseq=${DOCKER_HOWARD_SETUP_REFSEQ_DATABASES} --download-refseq-format-file=${DOCKER_HOWARD_SETUP_REFSEQ_TO_BED} --download-dbnsfp=${DOCKER_HOWARD_SETUP_DBNSFP_DATABASES} --download-dbnsfp-subdatabases --download-alphamissense=${DOCKER_HOWARD_SETUP_ALPHAMISSENSE_DATABASES} --download-exomiser=${DOCKER_HOWARD_SETUP_EXOMISER_DATABASES} --download-dbsnp=${DOCKER_HOWARD_SETUP_DBSNP_DATABASES} --download-dbsnp-vcf --threads=${DOCKER_HOWARD_SETUP_THREADS}" --genomes-folder=${DOCKER_HOWARD_SETUP_GENOMES}'
 
+###########
+# NETWORK #
+###########
 
-#########
-# PROXY #
-#########
+# Docker subnet
+DOCKER_HOWARD_SUBNET=172.42.2.0/24
 
 # Enable/Disable proxy to connect services behind proxy
-HTTP_PROXY=
-HTTPS_PROXY=
-FTP_PROXY=
-http_proxy=
-https_proxy=
-ftp_proxy=
+# HTTP_PROXY=
+# HTTPS_PROXY=
+# FTP_PROXY=
+# http_proxy=
+# https_proxy=
+# ftp_proxy=
 
 
 

diff --git a/.gitignore b/.gitignore
@@ -0,0 +1,23 @@
+__pycache__/
+howard.egg-info/
+.pytest_cache/
+.cache
+.vscode
+.coverage
+.tmp
+.obsidian
+.benchmarks
+tests/databases/annovar/
+tests/databases/snpeff/
+tests/databases/genomes/
+tests/databases/refseq/
+tests/databases/hg19.fa
+tests/databases/hg19.fa.fai
+tests/databases/.DS_Store
+tests/data/TEM*
+benchmark
+misc/
+*.DS_Store
+snpEff_*
+.gitignore
+tests/tmp*