feat: integrate dotty for c./n./g. resolution to SPDI (#16)

bihealth · Oct 4, 2023 · 42e79bd · 42e79bd
1 parent 38aa465
commit 42e79bd
Show file tree

Hide file tree

Showing 5 changed files with 64 additions and 0 deletions.
diff --git a/.env.ci b/.env.ci
@@ -34,6 +34,12 @@ FLOWER_BASIC_AUTH=admin:flower-password
 # Name of the registry server and org to use for our images.
 # image_base=ghcr.io/bihealth
 
+# Name of the dotty image to use.
+# image_dotty_name=dotty
+
+# Version of the dotty image to use.
+# image_dotty_version=latest
+
 # Name of the mehari image to use.
 # image_mehari_name=mehari
 

diff --git a/README.md b/README.md
@@ -291,6 +291,28 @@ tar -C .dev/volumes/reev-static/data/download/annonars \
 ln -sr .dev/volumes/reev-static/data/download/annonars/annonars-clinvar-genes-20230910+0.18.0 \
   .dev/volumes/reev-static/data/annonars/clinvar-genes
 ```
+
+To obtain data for dotty
+
+```bash session
+mkdir -p .dev/volumes/reev-static/data/download/dotty
+pushd .dev/volumes/reev-static/data/download/dotty
+wget \
+    https://github.com/SACGF/cdot/releases/download/v0.2.21/cdot-0.2.21.ensembl.grch37.json.gz \
+    https://github.com/SACGF/cdot/releases/download/v0.2.21/cdot-0.2.21.ensembl.grch38.json.gz \
+    https://github.com/SACGF/cdot/releases/download/v0.2.21/cdot-0.2.21.refseq.grch37.json.gz \
+    https://github.com/SACGF/cdot/releases/download/v0.2.21/cdot-0.2.21.refseq.grch38.json.gz
+wget \
+  https://github.com/bihealth/dotty/releases/download/v0.1.0/seqrepo.tar.gz-00 \
+  https://github.com/bihealth/dotty/releases/download/v0.1.0/seqrepo.tar.gz-01
+cat seqrepo.tar.gz-?? | tar xzf -
+popd
+
+mkdir -p .dev/volumes/reev-static/data/dotty
+ln -sr .dev/volumes/reev-static/data/download/dotty/{*.json.gz,seqrepo} \
+  .dev/volumes/reev-static/data/dotty
+```
+
 ### Setup Configuration
 
 The next step step is to create the configuration files in `.dev/config`.
@@ -320,6 +342,7 @@ These URLs are used by the REEV application.
 - Mehari impact prections: http://127.0.0.1:3002/tx/csq?genome-release=grch37&chromosome=17&position=48275363&reference=C&alternative=A
 - Viguno for TGDS: http://127.0.0.1:3003/hpo/genes?gene_symbol=TGDS
 - Nginx server with browser tracks http://127.0.0.1:3004/
+- Dotty server with c./n./g. to SPDI resolution http://127.0.0.1:3005/api/v1/to-spdi?q=NM_000059.3:c.274G%3EA
 
 Note that the development subset only has variants for a few genes, including BRCA1 (the example above).
 
@@ -344,6 +367,10 @@ We thus summarize some important points here.
 - In the case of using configuration files, you will have to mount them from the host into the container.
 - By default, we use "catch-all" configuration based on regular expressions on the host/domain name.
 
+### Dotty
+
+Dotty (by the REEV authors) provides mapping from c./n./g. notation to SPDI.
+
 ### Mehari
 
 Mehari (by the REEV authors) provides information about variants and their effect on individual transcripts.

diff --git a/docker-compose.override.yml-dev b/docker-compose.override.yml-dev
@@ -11,6 +11,7 @@
 #   - `3002` -- mehari
 #   - `3003` -- viguno
 #   - `3004` -- nginx
+#   - `3005` -- dotty
 #   - `3020` -- postgres
 #   - `3030` -- redis
 #   - `3031` -- rabbitmq
@@ -38,6 +39,11 @@ services:
     ports:
       - "3004:80"
 
+  # map dotty to port 3005
+  nginx:
+    ports:
+      - "3005:8080"
+
   # disable traefik
   traefik:
     deploy:
@@ -67,3 +73,8 @@ services:
   pgadmin:
     ports:
       - "3041:80"
+
+  # no replicas of reev
+  reev:
+    deploy:
+      replicas: 0
diff --git a/docker-compose.yml b/docker-compose.yml
@@ -110,6 +110,20 @@ services:
       - "traefik.http.services.reev.loadbalancer.server.port=8080"
       - "traefik.http.routers.reev.tls=true"
 
+  # -- Dotty -----------------------------------------------------------------
+  #
+  # Dotty provides translation from c./n./g. notation to SPDI.
+
+  dotty:
+    <<: *service_reev_default
+    container_name: dotty
+    hostname: dotty
+    image: "${image_base:-ghcr.io/bihealth}/${image_dotty_name:-dotty}:\
+      ${image_dotty_version:-latest}"
+    environment:
+      DATA_DIR: /data/dotty
+
+
   # -- Mehari ----------------------------------------------------------------
   #
   # Mehari provides the transcript-related information.

diff --git a/env.tpl b/env.tpl
@@ -34,6 +34,12 @@ FLOWER_BASIC_AUTH=admin:flower-password
 # Name of the registry server and org to use for our images.
 # image_base=ghcr.io/bihealth
 
+# Name of the dotty image to use.
+# image_dotty_name=dotty
+
+# Version of the dotty image to use.
+# image_dotty_version=latest
+
 # Name of the mehari image to use.
 # image_mehari_name=mehari