Merge pull request #38 from CFIA-NCFAD/dev

Release 3.3.2

.github/workflows/ci.yml

@@ -154,6 +154,14 @@ jobs:
  mkdir reads
  echo "Downloading ERR6359501 from EBI ENA"
  curl -SLk --silent ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR635/001/ERR6359501/ERR6359501.fastq.gz > reads/ERR6359501.fastq.gz
+ - name: Fetch IBV test seq
+ run: |
+ curl -SLk --silent https://github.com/CFIA-NCFAD/nf-test-datasets/raw/nf-flu/nanopore/fastq/SRR24826962.sampled.fastq.gz > reads/SRR24826962.fastq.gz
+ - name: Check IBV data
+ run: |
+ file reads/SRR24826962.fastq.gz
+ md5sum reads/SRR24826962.fastq.gz
+ sha256sum reads/SRR24826962.fastq.gz
  - name: Prepare samplesheet.csv
  run: |
  echo "Subsample reads from ERR6359501.fastq.gz with seqtk to mock different runs and ways of specifying input"
@@ -168,6 +176,7 @@ jobs:
  echo "ERR6359501-10k,$(realpath reads/ERR6359501-10k.fastq)" | tee -a samplesheet.csv
  echo "ERR6359501,$(realpath run1)" | tee -a samplesheet.csv
  echo "ERR6359501,$(realpath run2)" | tee -a samplesheet.csv
+ echo "SRR24826962,$(realpath reads/SRR24826962.fastq.gz)" | tee -a samplesheet.csv
  - name: Cache subsampled influenza.fna
  uses: actions/cache@v3
  id: cache-influenza-fna

CHANGELOG.md

@@ -3,6 +3,10 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [[3.3.2](https://github.com/CFIA-NCFAD/nf-flu/releases/tag/3.3.2)] - 2023-08-03
+
+This patch release fixes an IBV subtype/genotype parsing issue when generating subtyping report using the new metadata format introduced in 3.3.0 ([#32](https://github.com/CFIA-NCFAD/nf-flu/issues/32)).
+
 ## [[3.3.1](https://github.com/CFIA-NCFAD/nf-flu/releases/tag/3.3.1)] - 2023-08-02
 
 ### Fixes

bin/parse_influenza_blast_results.py

@@ -60,6 +60,7 @@
  ("sample_segment", "Sample Genome Segment Number"),
  ("#Accession", "Reference NCBI Accession"),
  ("Genotype", "Reference Subtype"),
+ ("Genus", "Genus"),
  ("pident", "BLASTN Percent Identity"),
  ("length", "BLASTN Alignment Length"),
  ("mismatch", "BLASTN Mismatches"),
@@ -245,7 +246,18 @@ def parse_blast_result(
  df_top_seg_matches = df_top_seg_matches.select(pl.col(cols))
  subtype_results_summary = {"sample": sample_name}
  if not get_top_ref:
- is_iav = not df_top_seg_matches.select(pl.col("Genotype").is_null().all())[0, 0]
+ df_genotype_genus = df_top_seg_matches.select(pl.col(["Genotype", "Genus"]))
+ # where the genus is not IAV, set the genotype to "Not IAV"
+ df_genotype_genus = df_genotype_genus.with_columns(
+ pl.when(pl.col("Genus") == "Alphainfluenzavirus")
+ .then(pl.col("Genotype"))
+ .otherwise(pl.lit("Not IAV"))
+ .alias("Genotype")
+ )
+ genotypes = df_genotype_genus["Genotype"]
+ genotype_counts = genotypes.value_counts(sort=True)
+ # if the top genotype is "Not IAV", then the sample is not IAV
+ is_iav = genotype_counts['Genotype'][0] != "Not IAV"
  H_results = None
  N_results = None
  if "4" in segments:
@@ -290,8 +302,7 @@ def find_h_or_n_type(df_merge, seg, is_iav):
  "4",
  "6",
  ], "Can only determine H or N type from segments 4 or 6, respectively!"
- type_name = "H_type" if seg == "4" else "N_type"
- h_or_n = type_name[0]
+ h_or_n, type_name = ("H", "H_type") if seg == "4" else ("N", "N_type")
  df_segment = df_merge.filter(pl.col("sample_segment") == seg)
  if is_iav:
  type_counts = df_segment["Genotype"].value_counts(sort=True)

nextflow.config

@@ -151,7 +151,7 @@ manifest {
  description = 'Influenza A virus genome assembly pipeline'
  homePage = 'https://github.com/CFIA-NCFAD/nf-flu'
  author = 'Peter Kruczkiewicz, Hai Nguyen'
- version = '3.3.1'
+ version = '3.3.2'
  nextflowVersion = '!>=22.10.1'
  mainScript = 'main.nf'
  doi = '10.5281/zenodo.7011213'