Merge pull request #95 from UPHL-BioNGS/edits

Edits

bin/.tests.notower.sh

@@ -0,0 +1,99 @@
+#/bin/bash
+#nextflow ~/sandbox/Cecret/Cecret.nf -profile singularity --reads /home/eriny/sandbox/test_files/cecret/reads --outdir tests -with-tower -resume
+
+test=$1
+
+if [ -z "$test" ]; then test="small" ; fi
+
+if [ "$test" == "small" ]
+then
+  options=("reads" "single_reads" "fastas")
+
+  for option in ${options[@]}
+  do
+    # defaults
+    nextflow ~/sandbox/Cecret/Cecret.nf \
+      -profile singularity,artic_V3 \
+      --$option /home/eriny/sandbox/test_files/cecret/$option \
+      --outdir singularity_defaults_$option
+
+    # removed test for bamsnap and rename because of lack of interest
+    # attempted bcftools and filter
+    nextflow ~/sandbox/Cecret/Cecret.nf \
+      -profile singularity,artic_V3 \
+      --$option /home/eriny/sandbox/test_files/cecret/$option \
+      --outdir all_on_$option \
+      --bcftools_variants true \
+      --filter true \
+      -resume
+
+    # removing primer trimming
+    nextflow ~/sandbox/Cecret/Cecret.nf \
+      -profile singularity,artic_V3 \
+      --$option /home/eriny/sandbox/test_files/cecret/$option \
+      --outdir nontrimmed_$option \
+      --trimmer 'none' \
+      -resume
+
+    # changing the cleaner, aligner, and trimmer
+    nextflow ~/sandbox/Cecret/Cecret.nf \
+      -profile singularity,artic_V3 \
+      --$option /home/eriny/sandbox/test_files/cecret/$option \
+      --outdir toggled_$option \
+      --cleaner 'fastp' \
+      --trimmer 'samtools' \
+      --aligner 'minimap2' \
+      -resume
+
+    # with UPHL's config
+    nextflow ~/sandbox/Cecret/Cecret.nf \
+      -profile uphl,artic_V3 \
+      --$option /home/eriny/sandbox/test_files/cecret/$option \
+      --outdir uphl_$option \
+      -resume
+  done
+
+  # multifasta
+  nextflow ~/sandbox/Cecret/Cecret.nf \
+    -profile singularity,artic_V3 \
+    --reads /home/eriny/sandbox/test_files/cecret/reads \
+    --single-reads /home/eriny/sandbox/test_files/cecret/single-reads \
+    --fastas /home/eriny/sandbox/test_files/cecret/fastas \
+    --multifastas /home/eriny/sandbox/test_files/cecret/multifasta \
+    --outdir kitchen_sink
+
+  # empty
+  nextflow ~/sandbox/Cecret/Cecret.nf \
+    -profile singularity,artic_V3 \
+    --reads doesntexit \
+    --single-reads willnotexist \
+    --fastas shouldntexit \
+    --outdir empty
+
+else
+  # CDC's test data with relatedness
+  nextflow ~/sandbox/Cecret/Cecret.nf \
+    -profile singularity,artic_V3 \
+    --reads /home/eriny/sandbox/sars-cov-2-datasets/reads \
+    --outdir default_datasets \
+    --relatedness true
+
+  nextflow ~/sandbox/Cecret/Cecret.nf \
+    -profile uphl,artic_V3 \
+    --reads /home/eriny/sandbox/sars-cov-2-datasets/reads \
+    --outdir uphl_datasets \
+    -resume \
+    --relatedness true
+
+  # CDC's test data with relatedness using nextalign
+  nextflow ~/sandbox/Cecret/Cecret.nf \
+    -profile singularity,artic_V3 \
+    --reads /home/eriny/sandbox/sars-cov-2-datasets/reads \
+    --outdir toggled_datasets \
+    --cleaner 'fastp' \
+    --trimmer 'samtools' \
+    --aligner 'minimap2' \
+    --relatedness true \
+    --msa 'nextalign' \
+    -resume
+fi

bin/combine_results.py

@@ -6,6 +6,7 @@
 pangolin_file='lineage_report.csv'
 nextclade_file='nextclade.csv'
 vadr_file='vadr.csv'
+freyja_file='aggregated-freyja.tsv'
 summary_file='combined_summary.csv'
 
 summary_df = pd.read_csv(summary_file, dtype = str)
@@ -41,7 +42,7 @@
     columns = ['nextclade_clade'] + columns + nextclade_columns
 
 if exists(pangolin_file) :
-    pangolin_df = pd.read_csv(pangolin_file, dtype = str, usecols = ['taxon', 'lineage', 'status', 'scorpio_call', 'version', 'pangolin_version', 'pango_version', 'pangoLEARN_version'])
+    pangolin_df = pd.read_csv(pangolin_file, dtype = str)
     pangolin_df=pangolin_df.add_prefix('pangolin_')
     pangolin_columns = list(pangolin_df.columns)
     pangolin_columns.remove('pangolin_taxon')
@@ -53,4 +54,17 @@
     summary_df.drop('pangolin_taxon', axis=1, inplace=True)
     columns = ['pangolin_lineage'] + columns + pangolin_columns
 
+if exists(freyja_file) :
+    freyja_df = pd.read_table(freyja_file, dtype = str, sep="\t")
+    freyja_df = freyja_df.add_prefix('freyja_')
+    freyja_df['freyja_Unnamed: 0'] = freyja_df['freyja_Unnamed: 0'].str.replace("_variants.tsv", "")
+    freyja_columns = list(freyja_df.columns)
+    freyja_columns.remove('freyja_Unnamed: 0')
+
+    summary_df = pd.merge(summary_df, freyja_df, left_on = 'sample_id', right_on = 'freyja_Unnamed: 0', how = 'outer')
+    summary_df['sample_id'].fillna(summary_df['freyja_Unnamed: 0'], inplace=True)
+    summary_df['fasta_line'].fillna(summary_df['freyja_Unnamed: 0'], inplace=True)
+    summary_df.drop('freyja_Unnamed: 0', axis=1, inplace=True)
+    columns = columns + freyja_columns
+
 summary_df.to_csv('cecret_results.csv', columns = ['sample_id','sample'] + columns, index=False)

configs/cecret_config_template.config

@@ -88,6 +88,8 @@ nextalign_container = 'nextstrain/nextalign:latest'
 snp_dists_container = 'staphb/snp-dists:latest'
 iqtree2_container = 'staphb/iqtree2:latest'
 pandas_container = 'quay.io/biocontainers/pandas:1.1.5'
+multiqc_container = 'ewels/multiqc:latest'
+freyja_container = 'staphb/freyja:latest'
 
 //# Workflow parameters --------------------------------------
 
@@ -120,15 +122,15 @@ pandas_container = 'quay.io/biocontainers/pandas:1.1.5'
 //params.filter = true
 
 //# For process ivar_trim
-//params.trimmer == 'ivar'
+//params.trimmer = 'ivar'
 //params.ivar_trim_options = ''
 
 //# For process samtools_ampliconclip
-//params.trimmer == 'samtools'
+//params.trimmer = 'samtools'
 //params.samtools_ampliconclip_options = ''
 
 //# trimming can also be skipped with
-//params.trimmer == 'none'
+//params.trimmer = 'none'
 
 //# For process ivar_variants
 //params.ivar_variants = true
@@ -197,6 +199,15 @@ pandas_container = 'quay.io/biocontainers/pandas:1.1.5'
 //params.pangolin_options = ''
 //params.pangolin = true
 
+//# For process freyja
+//params.freyja = true
+//params.freyja_variants_options=''
+//params.freyja_demix_options=''
+//params.freyja_boot_options='--nb 1000'
+//params.freyja_aggregate_options=''
+//params.freyja_plot_options=''
+//params.freyja_plot_filetype='png'
+
 //# For process nextclade
 //params.nextclade_dataset = 'sars-cov-2'
 //params.nextclade_options = ''
@@ -214,13 +225,17 @@ pandas_container = 'quay.io/biocontainers/pandas:1.1.5'
 //# params.minimum_depth is shared with ivar_variants, ivar_consensus, and samtools_depth
 //params.minimum_depth = 100
 
+//# For process multiqc
+//params.multiqc = true
+//params.multiqc_options = ''
+
 //# For process mafft
-//params.msa == 'mafft'
+//params.msa = 'mafft'
 //params.mafft_options = '--maxambiguous 0.5'
 //params.relatedness = true
 
 //# For process nextalign
-//params.msa == 'nextalign'
+//params.msa = 'nextalign'
 //params.nextalign_options = '--genes E,M,N,ORF1a,ORF1b,ORF3a,ORF6,ORF7a,ORF7b,ORF8,ORF9b,S --include-reference'
 //params.relatedness = true
 
@@ -348,8 +363,17 @@ process {
     container = pangolin_container
   }
 
+  withName:freyja{
+    container = freyja_container
+  }
+
+  withName:freyja_aggregate{
+    container = freyja_container
+  }
+
   withName:nextclade{
     cpus = params.medcpus
+    memory = '4 GB'
     container = nextclade_container
   }
 
@@ -367,6 +391,10 @@ process {
     container = pandas_container
   }
 
+  withName:multiqc{
+    container = multiqc_container
+  }
+
   withName:mafft{
     cpus = params.maxcpus
     container = mafft_container