feat(IPVC-2283): mitochondrial transcript workflow

README.md

@@ -289,56 +289,72 @@ To develop UTA, follow these steps.
 4. Testing
 
         $ docker build --target uta-test -t uta-test .
-        $ docker run -it --rm uta-test python -m unittest
+        $ docker run --rm uta-test python -m unittest
 
 ## UTA update procedure
 
-### 1. Download files from NCBI
+Requires docker.
 
-Run `sbin/ncbi-download-docker`. Requires bash and docker.
+### 0. Setup
 
-Example:
+Make directories:
 ```
-sbin/ncbi-download-docker $(pwd)/ncbi-data
+mkdir -p $(pwd)/ncbi-data
+mkdir -p $(pwd)/output/artifacts
+mkdir -p $(pwd)/output/logs
 ```
 
-The specified directory will have the following structure:
-
-    ├── gene
-    │   └── DATA
-    │       ├── GENE_INFO
-    │       │   └── Mammalia
-    │       │       └── Homo_sapiens.gene_info.gz
-    │       └── gene2accession.gz
-    ├── genomes
-    │   └── refseq
-    │       └── vertebrate_mammalian
-    │           └── Homo_sapiens
-    │               └── all_assembly_versions
-    │                   └── GCF_000001405.25_GRCh37.p13
-    │                       ├── GCF_000001405.25_GRCh37.p13_genomic.fna.gz
-    │                       └── GCF_000001405.25_GRCh37.p13_genomic.gff.gz
-    └── refseq
-        └── H_sapiens
-            └── mRNA_Prot
-                ├── human.1.protein.faa.gz
-                ├── human.1.rna.fna.gz
-                └── human.1.rna.gbff.gz
-
-### 2. Download SeqRepo data
-
-Run `sbin/seqrepo-download`. Requires bash and docker.
-
-Example:
+Set variables:
 ```
-sbin/seqrepo-download 2024-02-20 $(pwd)/seqrepo-data
+export UTA_ETL_OLD_SEQREPO_VERSION=2024-02-20
+export UTA_ETL_OLD_UTA_VERSION=uta_20210129b
+export UTA_ETL_NCBI_DIR=./ncbi-data
+export UTA_ETL_SEQREPO_DIR=./seqrepo-data
+export UTA_ETL_WORK_DIR=./output/artifacts
+export UTA_ETL_LOG_DIR=./output/logs
 ```
 
-### 3. Update UTA and SeqRepo
+Build the UTA image:
+```
+docker build --target uta -t uta-update .
+```
+
+### 1. Download SeqRepo data
+```
+docker pull biocommons/seqrepo:$UTA_ETL_OLD_SEQREPO_VERSION
 
-Run `sbin/uta-update`. Requires bash and docker.
+# download seqrepo. can skip if container already exists.
+docker run --name seqrepo biocommons/seqrepo:$UTA_ETL_OLD_SEQREPO_VERSION
 
-Example:
+# copy seqrepo data into a local directory
+docker run -v $UTA_ETL_SEQREPO_DIR:/output-dir --volumes-from seqrepo ubuntu bash -c 'cp -R /usr/local/share/seqrepo/* /output-dir'
+
+# allow seqrepo to be modified
+docker run -it -v $UTA_ETL_SEQREPO_DIR:/output-dir ubuntu bash -c 'chmod -R +w /output-dir'
 ```
-sbin/uta-update $(pwd)/ncbi-data $(pwd)/seqrepo-data $(pwd)/uta-build uta_20210129b 2024-02-20
+
+Note: pulling data takes ~30 minutes and requires ~13 GB.
+Note: a container called seqrepo will be left behind.
+
+### 2. Extract and transform data from NCBI
+
+Download files from NCBI, extract into intermediate files, and load into UTA and SeqRepo.
+
+See 2A for nuclear transcripts and 2B for mitochondrial transcripts.
+
+#### 2A. Nuclear transcripts
 ```
+docker compose run ncbi-download
+docker compose run uta-extract
+docker compose run seqrepo-load
+UTA_ETL_SKIP_GENE_LOAD=false docker compose run uta-load
+```
+
+#### 2B. Mitochondrial transcripts
+```
+docker compose run mito-extract
+docker compose run seqrepo-load
+UTA_ETL_SKIP_GENE_LOAD=true docker compose run uta-load
+```
+
+UTA has updated and the database has been dumped into a pgd file in `UTA_ETL_WORK_DIR`. SeqRepo has been updated in place.

docker-compose.yml

@@ -3,24 +3,60 @@
 version: '3'
 
 services:
+  ncbi-download:
+    image: uta-update
+    command: sbin/ncbi-download /ncbi-dir
+    volumes:
+      - .:/opt/repos/uta
+      - ${UTA_ETL_NCBI_DIR}:/ncbi-dir
+    working_dir: /opt/repos/uta
+    network_mode: host
+  uta-extract:
+    image: uta-update
+    command: sbin/uta-extract /ncbi-dir /uta-extract/work /uta-extract/logs
+    volumes:
+      - ${UTA_ETL_NCBI_DIR}:/ncbi-dir
+      - ${UTA_ETL_SEQREPO_DIR}:/usr/local/share/seqrepo
+      - ${UTA_ETL_WORK_DIR}:/uta-extract/work
+      - ${UTA_ETL_LOG_DIR}:/uta-extract/logs
+    working_dir: /opt/repos/uta
+    network_mode: host
+  seqrepo-load:
+    image: uta-update
+    command: sbin/seqrepo-load /usr/local/share/seqrepo 2024-02-20 /seqrepo-load/work /seqrepo-load/logs
+    volumes:
+      - ${UTA_ETL_SEQREPO_DIR}:/usr/local/share/seqrepo
+      - ${UTA_ETL_WORK_DIR}:/seqrepo-load/work
+      - ${UTA_ETL_LOG_DIR}:/seqrepo-load/logs
+    working_dir: /opt/repos/uta
+    network_mode: host
   uta:
     container_name: uta
-    image: biocommons/uta:${UTA_VERSION}
+    image: biocommons/uta:${UTA_ETL_OLD_UTA_VERSION}
     environment:
       - POSTGRES_HOST_AUTH_METHOD=trust
     healthcheck:
-      test: psql -h localhost -U anonymous -d uta -c "select * from ${UTA_VERSION}.meta"
+      test: psql -h localhost -U anonymous -d uta -c "select * from ${UTA_ETL_OLD_UTA_VERSION}.meta"
       interval: 10s
       retries: 60
     network_mode: host
-  uta-update:
+  uta-load:
     image: uta-update
-    command: etc/scripts/run-uta-build.sh ${UTA_VERSION} ${SEQREPO_VERSION} /ncbi-dir /workdir
+    command: sbin/uta-load ${UTA_ETL_OLD_UTA_VERSION} /ncbi-dir /uta-load/work /uta-load/logs ${UTA_ETL_SKIP_GENE_LOAD}
     depends_on:
       uta:
         condition: service_healthy
     volumes:
-      - ${NCBI_DIR}:/ncbi-dir
-      - ${SEQREPO_DIR}:/usr/local/share/seqrepo
-      - ${WORKING_DIR}:/workdir
+      - ${UTA_ETL_NCBI_DIR}:/ncbi-dir
+      - ${UTA_ETL_SEQREPO_DIR}:/usr/local/share/seqrepo
+      - ${UTA_ETL_WORK_DIR}:/uta-load/work
+      - ${UTA_ETL_LOG_DIR}:/uta-load/logs
+    network_mode: host
+  mito-extract:
+    image: uta-update
+    command: sbin/ncbi_process_mito.py NC_012920.1 --output-dir /mito-extract/work | tee /mito-extract/logs/mito.log
+    volumes:
+      - ${UTA_ETL_WORK_DIR}:/mito-extract/work
+      - ${UTA_ETL_LOG_DIR}:/mito-extract/logs
+    working_dir: /opt/repos/uta
     network_mode: host

sbin/ncbi-download

@@ -1,6 +1,29 @@
 #!/usr/bin/env bash
 
 # This script downloads the files needed for a UTA+SeqRepo update into to the given directory.
+#
+# DONWLOAD_DIR will have the following structure:
+#
+#    ├── gene
+#    │   └── DATA
+#    │       ├── GENE_INFO
+#    │       │   └── Mammalia
+#    │       │       └── Homo_sapiens.gene_info.gz
+#    │       └── gene2accession.gz
+#    ├── genomes
+#    │   └── refseq
+#    │       └── vertebrate_mammalian
+#    │           └── Homo_sapiens
+#    │               └── all_assembly_versions
+#    │                   └── GCF_000001405.25_GRCh37.p13
+#    │                       ├── GCF_000001405.25_GRCh37.p13_genomic.fna.gz
+#    │                       └── GCF_000001405.25_GRCh37.p13_genomic.gff.gz
+#    └── refseq
+#        └── H_sapiens
+#            └── mRNA_Prot
+#                ├── human.1.protein.faa.gz
+#                ├── human.1.rna.fna.gz
+#                └── human.1.rna.gbff.gz
 
 set -e
 
@@ -26,6 +49,7 @@ do
     DOWNLOAD_MODULE="${DOWNLOAD_PATH%%/*}"
     DOWNLOAD_SRC="ftp.ncbi.nlm.nih.gov::$DOWNLOAD_PATH"
     DOWNLOAD_DST="$DOWNLOAD_DIR/$DOWNLOAD_MODULE"
+    mkdir -p $DOWNLOAD_DST
     echo "Downloading $DOWNLOAD_SRC to $DOWNLOAD_DST"
     rsync --no-motd -DHPRprtv "$DOWNLOAD_SRC" "$DOWNLOAD_DST"
 done