Release1.5

bin/lcs_bar_plot.R

@@ -6,13 +6,15 @@ library(ggplot2)
 library(dplyr)
 
 args <- commandArgs(TRUE)
-proportion_cutoff <- eval( parse(text=args[1]) )[1] 
+tsv <- args[1]
+name <- parse(text=args[2])
+proportion_cutoff <- eval( parse(text=args[3]) )
 
-input <- read.csv("lcs_results.tsv", sep='\t')
+input <- read.csv(tsv, sep='\t')
 
 filter(input, proportion>=proportion_cutoff) %>% ggplot(aes(x=variant_group, y=proportion)) + geom_col(position='dodge') + 
 geom_errorbar(width=0.4,aes(ymin=proportion-std_error, ymax=proportion+std_error)) + facet_wrap(~sample) +
-theme(axis.text.x=element_text(angle=90,vjust=.5)) + coord_flip() + ggsave("lcs_bar_plot.png")
+theme(axis.text.x=element_text(angle=90,vjust=.5)) + coord_flip() + ggsave(paste0('lcs_barplot_', name, '.png'))
 
 # for ggplot2 versions > 3.3.0:
 # ggplot aes flip x and y

bin/summary_report.py

@@ -38,7 +38,7 @@ class SummaryReport():
     scorpio_constellations_version = None
     variants_table = None
     pangolin_version = None
-    pangolearn_version = None
+    pangolindata_version = None
     nextclade_version = None
     nextcladedata_version = None
     tabledata = None
@@ -110,20 +110,17 @@ def add_poreCov_version_param(self, porecov_version):
 
 
     def add_pangolin_version_param(self):
-        if self.pangolearn_version is None:
-            error('add_pangolin_version_param() called before parse_pangolin_version()')
-        warning_msg = f' - <font color="{self.color_error_red}"><b>Warning</b>: A rather old version of PangoLEARN was used ({self.pangolearn_version}). Use parameter \'--update\' to force the use of the most recent Pangolin container!</font>'
+        if self.pangolindata_version is None:
+            error('add_pangolin_version_param() called before pangolin version was set')
+        warning_msg = f' - <font color="{self.color_error_red}"><b>Warning</b>: A rather old version of pangolin-data was used ({self.pangolindata_version}). Use parameter \'--update\' to force the use of the most recent Pangolin container!</font>'
 
-        # pa_param = f'<a href="https://cov-lineages.org/pangolin.html"><b>Pangolin</b></a> version'
-        # pa_val =  f'{self.pangolin_version}'
-        pl_param = f'<a href="https://cov-lineages.org/resources/pangolin/pangolearn.html"><b>PangoLEARN</b></a> version'
-        pl_val = f'{self.pangolearn_version}'
+        pl_param = f'<a href="https://cov-lineages.org/resources/pangolin/requirements.html"><b>pangolin-data</b></a> version'
+        pl_val = f'{self.pangolindata_version}'
 
-        year, month, day = self.pangolearn_version.split('-')
-        if int(year) <= 2021 and int(month) <= 10:
+        v1, v2, v3 = self.pangolindata_version.split('.')
+        if int(v1) <= 1 and int(v2) <= 2 and int(v3) <= 132:
             pl_val += warning_msg
 
-        # self.add_param(pa_param, pa_val)
         self.add_param(pl_param, pl_val)
 
 
@@ -162,22 +159,6 @@ def parse_version_config(self, version_config_file):
         log('Parsed version config file.')
 
 
-    def parse_scorpio_versions(self, scorpio_version, sc_constell_version):
-        # e.g. 'scorpio 0.3.14'
-        name, vers = scorpio_version.split(' ')
-        assert name == 'scorpio'
-        self.scorpio_version = vers.lstrip('v')
-
-        # e.g. 'constellations v0.0.24'
-        name, vers = sc_constell_version.split(' ')
-        assert name == 'constellations'
-        self.scorpio_constellations_version = vers.lstrip('v')
-
-
-    def parse_pangolin_version(self, pangolin_docker):
-        # e.g. nanozoo/pangolin:2.3.8--2021-04-21
-        self.pangolin_version, self.pangolearn_version = pangolin_docker.split(':',1)[-1].split('--')
-
     def parse_nextclade_version(self, nextclade_docker):
         # e.g. nanozoo/nextclade:1.3.0--2021-06-25
         self.nextclade_version, self.nextcladedata_version = nextclade_docker.split(':',1)[-1].split('--')
@@ -377,10 +358,20 @@ def add_pangolin_results(self, pangolin_results):
         self.force_index_dtype_string(res_data)
         self.check_and_init_tabledata(res_data.index)
 
+        # pangolin and scorpio versions
+        # column names used:
+        # version,pangolin_version,scorpio_version,constellation_version
+        assert res_data.shape[0] > 0
+        self.pangolin_version = res_data.iloc[0]['pangolin_version']
+        self.pangolindata_version = res_data.iloc[0]['version'].split('-',1)[-1].split('v',1)[-1]
+        self.scorpio_version = res_data.iloc[0]['scorpio_version']
+        self.scorpio_constellations_version = res_data.iloc[0]['constellation_version']
+
+
+        # get data
         self.add_column_raw('pangolin_lineage', res_data['lineage'])
         self.add_column_raw('pangolin_conflict', res_data['conflict'])
 
-
         res_data['lineage_conflict'] = [f'<b>{l}</b><br>({p if pd.notnull(p) else "-"})' for l,p in zip(res_data['lineage'], res_data['conflict'])]
         colname = 'Lineage<br>(conflict)'
 
@@ -399,13 +390,16 @@ def add_pangolin_results(self, pangolin_results):
                     res_data.at[row, 'lineage_conflict'] += f'<br><font color="{color}"><b>{var_status}</b></font>'
 
             self.add_column_raw('variant_status', res_data['variant_status'])
-            self.add_col_description(f'Variant type (VOC, VOI, etc.) was determined from the <a href="{args.variants_table}">variants table</a> of <a href="https://github.com/3dgiordano/SARS-CoV-2-Variants">SARS-CoV-2-Variants</a>.')
+            self.add_col_description(f'Variant type (VOC, VOI, etc.) was determined from the <a href="{args.variants_table}">variants table</a> ' + \
+                'of <a href="https://github.com/3dgiordano/SARS-CoV-2-Variants">SARS-CoV-2-Variants</a>.')
 
 
         self.add_column(colname, res_data['lineage_conflict'])
-        if self.pangolin_version is None or self.pangolearn_version is None:
-            error('No pangolin/pangoLEARN versions were added before adding pangolin results.')
-        self.add_col_description(f'Lineage and the corresponding tree resolution conflict measure were determined with <a href="https://cov-lineages.org/pangolin.html">Pangolin</a> (v{self.pangolin_version} using <a href="https://cov-lineages.org/resources/pangolin/pangolearn.html">PangoLEARN</a> data release {self.pangolearn_version}).')
+        if self.pangolin_version is None or self.pangolindata_version is None:
+            error('No pangolin/pangolin-data versions were added before adding pangolin results.')
+        self.add_col_description(f'Lineage and the corresponding tree resolution conflict measure were determined with ' + \
+            f'<a href="https://cov-lineages.org/pangolin.html">Pangolin</a> (v{self.pangolin_version} using ' + \
+            f'<a href="https://cov-lineages.org/resources/pangolin/requirements.html">pangolin-data</a> v{self.pangolindata_version}).')
 
         # Add scorpio info if any is present
         if res_data['scorpio_call'].notna().any():
@@ -419,7 +413,10 @@ def add_pangolin_results(self, pangolin_results):
             self.add_column('Constellation<br>(conflict)', res_data['scorpio_conflict'])
             if self.scorpio_version is None or self.scorpio_constellations_version is None:
                 error('No Scorpio/constellations versions were added before adding Pangolin results.')
-            self.add_col_description(f'Constellation and the corresponding tree resolution conflict measure were determined with <a href="https://github.com/cov-lineages/scorpio">Scorpio</a> (v{self.scorpio_version} using <a href="https://cov-lineages.org/constellations.html">Constellations</a> version {self.scorpio_constellations_version}).')
+            self.add_col_description(f'Constellation and the corresponding tree resolution conflict measure were determined with ' + \
+                f'<a href="https://github.com/cov-lineages/scorpio">Scorpio</a> (v{self.scorpio_version} using ' + \
+                f'<a href="https://cov-lineages.org/constellations.html">Constellations</a> version {self.scorpio_constellations_version}).')
+
 
 
     def add_president_results(self, president_results):
@@ -505,6 +502,13 @@ def add_nextclade_results(self, nextclade_results):
         self.add_column_raw('nextclade_insertions', res_data['aaInsertions'])
         self.add_column_raw('nextclade_frameshifts', res_data['frameShifts'])
 
+        # private mutation information
+        self.add_column_raw('nextclade_privateNucMutations_reversion', res_data["privateNucMutations.reversionSubstitutions"])
+        self.add_column_raw('nextclade_privateNucMutations_labeled', res_data["privateNucMutations.labeledSubstitutions"])
+        self.add_column_raw('nextclade_privateNucMutations_unlabeled', res_data["privateNucMutations.unlabeledSubstitutions"])
+        self.add_column_raw('nextclade_privateNucMutations_qc_status', res_data["qc.privateMutations.status"])
+
+
         res_data['mutations_formatted'] = [m.replace(',', ', ') if type(m) == str else '-' for m in res_data['aaSubstitutions']]
         res_data['deletions_formatted'] = [m.replace(',', ', ') if type(m) == str else '-' for m in res_data['aaDeletions']]
         res_data['insertions_formatted'] = [m.replace(',', ', ') if type(m) == str else '-' for m in res_data['aaInsertions']]
@@ -560,7 +564,8 @@ def get_markup_with_toggle_and_tag(tag):
 
         if self.nextclade_version is None or self.nextcladedata_version is None:
             error('No nextclade/nextcladedata versions were added before adding nextclade results.')
-        self.add_col_description(f'Clade, mutations, deletions, insertions and frameshifts were determined with <a href="https://clades.nextstrain.org/">Nextclade</a> (v{self.nextclade_version} using nextclade data release {self.nextcladedata_version}).')
+        self.add_col_description(f'Clade, mutations, deletions, insertions and frameshifts were determined with ' + \
+            f'<a href="https://clades.nextstrain.org/">Nextclade</a> (v{self.nextclade_version} using nextclade data release {self.nextcladedata_version}).')
 
 
 
@@ -782,16 +787,13 @@ def get_lineage_status(self, lineage):
     log('Started summary_report.py ...')
 
     parser = argparse.ArgumentParser(description='Generate a summary report for multiple samples run with poreCov')
-    parser.add_argument("-v", "--version_config", help="version config", required=True)
-    parser.add_argument("--scorpio_version", help="scorpio version", required=True)
-    parser.add_argument("--scorpio_constellations_version", help="scorpio constellations version", required=True)    
+    parser.add_argument("-v", "--version_config", help="version config", required=True)  
     parser.add_argument("--variants_table", help="variants table with VOCs, VOIs etc.", required=True)    
     parser.add_argument("--porecov_version", help="porecov version", required=True)
     parser.add_argument("--guppy_used", help="guppy used")
     parser.add_argument("--guppy_model", help="guppy model")
     parser.add_argument("--medaka_model", help="medaka model")
     parser.add_argument("--nf_commandline", help="full nextflow command call", required=True)
-    parser.add_argument("--pangolin_docker", help="pangolin/pangoLEARN version", required=True)
     parser.add_argument("--nextclade_docker", help="nextclade/nextcladedata version", required=True)
     parser.add_argument("--primer", help="primer version")
     parser.add_argument("-p", "--pangolin_results", help="pangolin results")
@@ -806,9 +808,7 @@ def get_lineage_status(self, lineage):
     ### build report
     report = SummaryReport()
     report.parse_version_config(args.version_config)
-    report.parse_scorpio_versions(args.scorpio_version, args.scorpio_constellations_version)
     report.parse_variants_table(args.variants_table)
-    report.parse_pangolin_version(args.pangolin_docker)
     report.parse_nextclade_version(args.nextclade_docker)
 
 

nextflow.config

@@ -41,8 +41,8 @@ params {
     update = false
     screen_reads = false
     screen_reads_plot_cutoff = 0.03
-    defaultpangolin = 'nanozoo/pangolin:3.1.20--2022-02-28'
-    defaultnextclade = 'nanozoo/nextclade:1.10.3--2022-02-07'
+    defaultpangolin = 'nanozoo/pangolin-v4:4.0.4--1.2.133'
+    defaultnextclade = 'nanozoo/nextclade:1.11.0--2022-03-31'
 
     // parameters
     primerV = 'V3'

poreCov.nf

@@ -235,7 +235,7 @@ if (params.samples) {
 
 static boolean DockernetIsAvailable() {
     try {
-        final URL url = new URL("https://registry.hub.docker.com/v2/repositories/nanozoo/pangolin/tags/");
+        final URL url = new URL("https://registry.hub.docker.com/v2/repositories/nanozoo/pangolin-v4/tags/");
         final URLConnection conn = url.openConnection();
         conn.connect();
         conn.getInputStream().close();
@@ -252,8 +252,8 @@ def internetcheck = DockernetIsAvailable()
 if (params.update) {
 println "\033[0;33mWarning: Running --update might not be poreCov compatible!\033[0m"
     if ( internetcheck.toString() == "true" ) { 
-        tagname = 'https://registry.hub.docker.com/v2/repositories/nanozoo/pangolin/tags/'.toURL().text.split(',"name":"')[1].split('","')[0]
-        params.pangolindocker = "nanozoo/pangolin:" + tagname
+        tagname = 'https://registry.hub.docker.com/v2/repositories/nanozoo/pangolin-v4/tags/'.toURL().text.split(',"name":"')[1].split('","')[0]
+        params.pangolindocker = "nanozoo/pangolin-v4:" + tagname
         println "\033[0;32mFound latest pangolin container, using: " + params.pangolindocker + " \033[0m" 
 
         tagname = 'https://registry.hub.docker.com/v2/repositories/nanozoo/nextclade/tags/'.toURL().text.split(',"name":"')[1].split('","')[0]

workflows/create_summary_report.nf

@@ -1,8 +1,7 @@
 include { summary_report; summary_report_fasta; summary_report_default } from './process/summary_report'
 include { plot_coverages } from '../modules/plot_coverages.nf'
-include { get_scorpio_version } from '../modules/get_scorpio_version.nf'
 include { get_variants_classification } from '../modules/get_variants_classification.nf'
-include { lcs_plot } from './process/lcs_sc2'
+include { lcs_plot as lcs_plot; lcs_plot as lcs_plot_control  } from './process/lcs_sc2'
 
 workflow create_summary_report_wf {
     take: 
@@ -16,7 +15,6 @@ workflow create_summary_report_wf {
 
         main:
         version_ch = Channel.fromPath(workflow.projectDir + "/configs/container.config")
-        scorpio_ver_ch = get_scorpio_version()
         variants_table_ch = get_variants_classification()
 
         pangolin_results = pangolin.map {it -> it[1]}.collectFile(name: 'pangolin_results.csv', skip: 1, keepHeader: true)
@@ -27,21 +25,23 @@ workflow create_summary_report_wf {
         alignment_files = alignments.map {it -> it[0]}.collect()
         if (params.fasta || workflow.profile.contains('test_fasta')) {
 
-            summary_report_fasta(version_ch, scorpio_ver_ch, variants_table_ch, pangolin_results, president_results, nextclade_results)
+            summary_report_fasta(version_ch, variants_table_ch, pangolin_results, president_results, nextclade_results)
 
         } else {
             kraken2_results = kraken2.map {it -> it[2]}.collect()
             // sort by sample name, group in lists of 6, collect the grouped plots
             coverage_plots = plot_coverages(alignments.map{it -> it[0]}.toSortedList({ a, b -> a.simpleName <=> b.simpleName }).flatten().collate(6), \
                                             alignments.map{it -> it[1]}.toSortedList({ a, b -> a.simpleName <=> b.simpleName }).flatten().collate(6)).collect()
 
-            if (params.samples) { summary_report(version_ch, scorpio_ver_ch, variants_table_ch, pangolin_results, president_results, nextclade_results, kraken2_results, coverage_plots, samples_table) }
-            else { summary_report_default(version_ch, scorpio_ver_ch, variants_table_ch, pangolin_results, president_results, nextclade_results, kraken2_results, coverage_plots) }
+            if (params.samples) { summary_report(version_ch, variants_table_ch, pangolin_results, president_results, nextclade_results, kraken2_results, coverage_plots, samples_table) }
+            else { summary_report_default(version_ch, variants_table_ch, pangolin_results, president_results, nextclade_results, kraken2_results, coverage_plots) }
 
         }
 
         if (params.screen_reads){
-            lcs_plot(lcs_results, params.screen_reads_plot_cutoff)
+            lcs_plot(lcs.filter({ !it[0].contains("negativ") }).map {it -> it[1]}.collectFile(name: 'lcs_results.tsv', skip: 1, keepHeader: true).map{ it -> ['samples', it] }, params.screen_reads_plot_cutoff)
+
+            lcs_plot_control(lcs.filter({ it[0].contains("negativ") }), params.screen_reads_plot_cutoff)
         }
 
 } 

workflows/process/lcs_sc2.nf

@@ -36,14 +36,14 @@ process lcs_plot {
   publishDir "${params.output}/${params.lineagedir}/", mode: 'copy'
 
   input:
-  path(tsv)
+  tuple val(name), path(tsv)
   val(cutoff)
 
   output:
-  path("lcs_bar_plot.png")
+  path("*.png")
 
   script:
   """
-  lcs_bar_plot.R ${cutoff}
+  lcs_bar_plot.R '${tsv}' '${name}' ${cutoff}
   """
 }