describe check-transcripts step in readme/sbin/src

README.md

@@ -339,6 +339,7 @@ See 2A for nuclear transcripts and 2B for mitochondrial transcripts.
 ```
 docker compose run ncbi-download
 docker compose run uta-extract
+[OPTIONAL] docker compose run uta-check-transcripts
 docker compose run seqrepo-load
 docker compose run uta-load
 ```
@@ -351,7 +352,7 @@ docker compose run uta-load
 ```
 
 #### 2C. Manual splign transcripts
-To load splign-manual transcripts, the workflow expects an input txdata.yaml file and splign alignments. Define this path 
+To load splign-manual transcripts, the workflow expects an input txdata.yaml file and splign alignments. Define this path
 using the environment variable $UTA_SPLIGN_MANUAL_DIR. These file paths should exist:
 - `$UTA_SPLIGN_MANUAL_DIR/splign-manual/txdata.yaml`
 - `$UTA_SPLIGN_MANUAL_DIR/splign-manual/alignments/*.splign`

docker-compose.yml

@@ -46,6 +46,16 @@ services:
       interval: 10s
       retries: 80
     network_mode: host
+  uta-check-transcripts:
+    image: uta-update
+    command: sbin/uta-check-transcripts ${UTA_ETL_OLD_UTA_VERSION} /uta-check-transcripts/work /uta-check-transcripts/logs
+    depends_on:
+      uta:
+        condition: service_healthy
+    volumes:
+      - ${UTA_ETL_WORK_DIR}:/uta-check-transcripts/work
+      - ${UTA_ETL_LOG_DIR}:/uta-check-transcripts/logs
+    network_mode: host
   uta-load:
     image: uta-update
     command: sbin/uta-load ${UTA_ETL_OLD_UTA_VERSION} ${UTA_ETL_NEW_UTA_VERSION} /ncbi-dir /uta-load/work /uta-load/logs

sbin/uta-check-transcripts

@@ -1,8 +1,12 @@
 #!/usr/bin/env bash
 
-# This script ...
+# Find transcripts in the current UTA database version which are not in the txinfo file,
+# and write those transcripts to the check-transcripts.txt file.
 #
-# source_uta_v is the UTA version before the update procedure.
+# uta-extract, which produces the needed txinfo file, must run before this script.
+# Any action taken with respect to the identified transcripts is case-dependent and optional.
+#
+# source_uta_v is the current UTA database version.
 # working_dir stores input and output files.
 # log_dir stores log files.
 
@@ -20,7 +24,5 @@ fi
 
 mkdir -p "$log_dir"
 
-# Report transcripts which have already loaded into UTA but are not part of the incoming transcript set.
-# These transcripts are at risk of missing updates to information such as transl_except. ???
 UTA_USE_SCHEMA=false uta --conf=etc/global.conf --conf=etc/[email protected] check-transcripts --prefixes=NM,NR "$working_dir/txinfo.gz" "$source_uta_v" "$working_dir/check-transcripts.txt" 2>&1 | \
     tee "$log_dir/check-transcripts.log"

src/uta/loading.py

@@ -169,7 +169,8 @@ def analyze(session, opts, cf):
 
 def check_transcripts(session: Session, opts: Dict, cf: ConfigParser):
     """
-
+    Find transcripts in the given UTA database version which are not in the given txinfo file,
+    and write those transcripts to the specified file.
     """
     # required opts
     txinfo_file = opts['TXINFO_FILE']