Simplify Alignment Job and Resolve SAM Flag Issue in CRAM to FASTQ Conversion

configs/defaults/large_cohort.toml

@@ -6,10 +6,24 @@ status_reporter = 'metamist'
 # define reference fasta. If not specified here, the reference file is pulled from [references.broad][ref_fasta]
 ref_fasta='gs://cpg-common-main/references/hg38/v0/dragen_reference/Homo_sapiens_assembly38_masked.fasta'
 highmem_workers = true
-# Realign CRAM when available, instead of using FASTQ.
-# The parameter value should correspond to CRAM version
-# (e.g. v0 in gs://cpg-fewgenomes-main/cram/v0/CPGaaa.cram
-#realign_from_cram_version = 'v0'
+# Realign CRAM instead of using FASTQ.
+# The parameter value should correspond to CRAM version.
+# For example, to realign from CRAM version 'v0', ensure the following configuration is set:
+# ["workflow"]["align"]["realign_from_cram"]["version"] = "v0"
+# E.g.
+# [align.realign_from_cram]
+# version = "v0"
+# This will use the CRAM file located at gs://<dataset-prefix>/cram/v0/<SequencingGroupID>.cram
+# and realign it using the reference specified in ["workflow"]["align"]["realign_from_cram"][<new_version_id>].
+# A new CRAM file will be created at gs://<dataset-prefix>/cram/<new_version_id>/<SequencingGroupID>.cram after realignment.
+# Ensure the correct reference is configured for the current version of the cram in ["workflow"]["align"]["realign_from_cram"]["cram_version_map"]
+# as well as the new version.
+# [align.realign_from_cram]
+# version = 'v1'
+# new_version = 'v2'
+# [align.realign_from_cram.cram_version_map]
+# v1 = 'gs://cpg-common-main/references/hg38/v0/dragen_reference/Homo_sapiens_assembly38_masked.fasta'
+# v2 = 'gs://<path-to-new/updated/alternative-reference'
 
 # Calling intervals (defauls to whole genome intervals)
 #intervals_path =