Merge branch 'CW-4474' into 'dev'

fix run_spoa.py faililng when all reads come from the same strand [CW-4474]

Closes CW-4474

See merge request epi2melabs/workflows/wf-amplicon!89

CHANGELOG.md

@@ -4,6 +4,10 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [v1.1.2]
+### Fixed
+- The workflow failing in _de novo_ mode when all reads for a sample came from the same strand.
+
 ## [v1.1.1]
 ### Changed
 - Updated Medaka to v1.12.0.
@@ -13,8 +17,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - The now redundant `--basecaller_cfg` parameter as its value is now automatically detected from the input data on a per-sample basis.
 
 ### Added
-- `--override_basecaller_cfg` parameter for cases where automatic selection fails or users wishes to override the automatic choice.
-
+- `--override_basecaller_cfg` parameter for cases where automatic selection fails or users wish to override the automatic choice.
 
 ## [v1.1.0]
 ### Fixed

bin/workflow_glue/run_spoa.py

@@ -32,7 +32,7 @@ def get_seqs_from_fastx_and_check_lengths(file, logger, max_len=None):
                     f"{max_len}. This is what assemblers are for. "
                     "Aborting..."
                 )
-                sys.exit()
+                sys.exit(0)
             yield seq
 
 
@@ -95,7 +95,13 @@ def main(args):
     seqs = get_seqs_from_fastx_and_check_lengths(
         args.fastq, logger, args.max_allowed_read_length
     )
-    first_seq = next(seqs)
+    try:
+        first_seq = next(seqs)
+    except StopIteration:
+        # looks like the input file was empty; this shouldn't happen, but we might as
+        # well catch it and exit gracefully
+        logger.error(f"Input file '{args.fastq}' appears to be empty. Aborting...")
+        sys.exit(0)
     for seq in seqs:
         rc = reverse_complement(seq)
         fwd_score = align(seq, first_seq).score
@@ -105,9 +111,15 @@ def main(args):
         else:
             rev.append(rc)
 
-    # uniformly interleave the reads
-    interleaved_reads = interleave_lists(fwd, rev)
-    logger.info("Finished interleaving reads.")
+    # uniformly interleave the reads (as long as we got fwd and rev reads)
+    if fwd and rev:
+        interleaved_reads = interleave_lists(fwd, rev)
+        logger.info("Finished interleaving reads.")
+    else:
+        # we know that we got either fwd or rev reads as otherwise the file must have
+        # been empty (which we checked above)
+        logger.info("Only got reads from one strand; not interleaving...")
+        interleaved_reads = fwd or rev
 
     # determine minimum coverage if param was provided
     min_cov = None

nextflow.config

@@ -76,7 +76,7 @@ manifest {
     description     = 'Amplicon workflow'
     mainScript      = 'main.nf'
     nextflowVersion = '>=23.04.2'
-    version         = 'v1.1.1'
+    version         = 'v1.1.2'
 }
 
 epi2melabs {