Merge pull request #88 from sanger-bentley-group/dev

Dev

.github/workflows/test.yml

@@ -11,13 +11,13 @@ on:
 jobs:
   test:
 
-    runs-on: ubuntu-18.04
+    runs-on: ubuntu-22.04
 
     steps:
     - uses: actions/checkout@v2
-    - uses: actions/setup-python@v2
+    - uses: actions/setup-python@v4
       with:
-        python-version: 3.6
+        python-version: 3.9
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip

README.md

@@ -87,9 +87,9 @@ Sample_id | Serotype | 23S1 | 23S3 | CAT | ermB | ermT | FOSA | GYRA | lnuB | ls
 Gives the SNP variants for GBS-specific resistance genes
 e.g. Isolate Strep B sample 25292_2#105 have common variants 23S1, 23S3 and GYRA (shown with *), but replacement of amino acid S by Q in position 17 of the PARC protein sequence
 
-Sample_id | 23S1 | 23S3 | GYRA | PARC | RPOBGBS-1 | RPOBGBS-2 | RPOBGBS-3 | RPOBGBS-4
-:---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---:
-25292_2#105 | * | * | * | Q17S | | | | |
+Sample_id | 23S1 | 23S3 | GYRA | PARC
+:---: | :---: | :---: | :---: | :---:
+25292_2#105 | * | * | * | Q17S
 
 3. **drug_cat_alleles_variants.txt**
 
@@ -141,14 +141,13 @@ Sample_id | ALPH | hvgA | PILI | SRR
     --other_res_min_coverage        Minimum coverage for mapping to other resistance reference database(s). (Default: 70)
     --other_res_max_divergence      Maximum divergence for mapping to other resistance reference database. (Default: 30, i.e. report only hits with <30% divergence)
     --restyper_min_read_depth       Minimum read depth where mappings to antibiotic resistance genes with fewer reads are excluded. (Default: 30)
-    --serotyper_min_read_depth      Minimum read depth where mappings to serotyping genes with fewer reads are excluded. (Default: 30)
+    --serotyper_min_read_depth      Minimum read depth where mappings to serotyping genes with fewer reads are excluded. (Default: 0)
 
 ### Other Workflow Options
     --run_sero_res                  Run the main serotyping and resistance workflows. (Default: true)
-                                    Use '--run_sero_res false' to override the default.
-    --run_surfacetyper              Run the surface protein typing workflow. (Default: false)
+    --run_surfacetyper              Run the surface protein typing workflow. (Default: true)
     --run_mlst                      Run the MLST workflow to query existing sequence types and new MLST alleles. (Default: true)
-    --run_pbptyper                  Run the PBP (Penicillin binding protein) allele typer workflow. Must also specify --contigs input. (Default: true)
+    --run_pbptyper                  Run the PBP (Penicillin binding protein) allele typer workflow. Must also specify --contigs input. (Default: false)
 
 ### Other Parameters
     --mlst_min_read_depth           Minimum read depth where mappings to alleles in MLST with fewer reads are excluded. Only operational with --run_mlst. (Default: 30)

bin/process_serotyper_results.py

@@ -58,8 +58,8 @@ def get_arguments():
                         help='Input fullgenes results tab file.')
     parser.add_argument('--output', '-o', dest='output', required=True,
                         help='Output filename.')
-    parser.add_argument('--min_read_depth', '-d', dest='depth', default = 30, type=float,
-                        help='Minimum read depth where mappings with fewer reads are excluded. Default: 30.')
+    parser.add_argument('--min_read_depth', '-d', dest='depth', default = 0, type=float, required=False,
+                        help='Minimum read depth where mappings with fewer reads are excluded. Default: 0.')
 
     return parser
 

modules/serotyping.nf

@@ -19,18 +19,9 @@ process serotyping {
     git clone https://github.com/swainechen/GBS-SBG
     mv GBS-SBG/${sero_gene_db} .
 
-    srst2 --samtools_args '\\-A' --input_pe ${reads[0]} ${reads[1]} --output SERO_${pair_id} --log --save_scores --min_coverage 99.0 --max_divergence 7 --gene_db ${sero_gene_db}
+    srst2 --samtools_args '\\-A' --input_pe ${reads[0]} ${reads[1]} --output SERO_${pair_id} --log --save_scores --gene_db ${sero_gene_db}
     process_serotyper_results.py --srst2_output SERO_${pair_id} --sero_db ${sero_gene_db} --output ${pair_id}_SeroType_Results.txt --min_read_depth ${min_read_depth}
 
     touch ${output_file}
-
-    # Clean directory
-    mkdir output
-    mv ${output_file} output
-    find . -maxdepth 1 -type f -delete
-    unlink ${reads[0]}
-    unlink ${reads[1]}
-    mv output/${output_file} .
-    rm -d output
     """
 }

nextflow.config

@@ -17,7 +17,7 @@ params {
     results_dir = ""
     config = "./headers.json"
     contigs = ""
-    serotyper_min_read_depth = 30
+    serotyper_min_read_depth = 0
     gbs_blactam_db = "$db_dir/GBS_bLactam-DB/GBS_bLactam_Ref.fasta"
     gbs_blactam_1A_db = "$db_dir/GBS_bLactam-DB/GBS_bLactam_1A-DB.faa"
     gbs_blactam_2B_db = "$db_dir/GBS_bLactam-DB/GBS_bLactam_2B-DB.faa"

requirements.txt

@@ -8,3 +8,4 @@ py==1.10.0
 pyparsing==2.4.7
 pytest==6.2.4
 toml==0.10.2
+pandas==1.5.3

tests/process_serotyper_results_test.py

@@ -48,4 +48,4 @@ def test_arguments_short_options(self):
     def test_arguments_without_depth_threshold(self):
         actual = get_arguments().parse_args(['-s', 'srst2_output_name', '-b', 'sero_db', '-o', 'outfile'])
         self.assertEqual(actual,
-                        argparse.Namespace(id='srst2_output_name', db='sero_db', output='outfile', depth=30.0))
+                        argparse.Namespace(id='srst2_output_name', db='sero_db', output='outfile', depth=0))