Update ichorCNA to the nf-core upstream versions

CHANGELOG.md

@@ -3,6 +3,29 @@
 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).
 
+## Unreleased
+
+### Breaking changes
+
+- A new **mandatory** column has been added in the samplesheet, `status`, which can be either `normal` or `tumor` (@lbeltrame, issue #13)
+- Option `--pon_path` has been **removed**. Instead, add your normal samples to the samplesheet (same rules as case samples) with the `normal` status
+- Due to a bug in ichorCNA with security implications, the syntax of all options regarding ichorCNA chromosome handling (but not the `readcounter` parameters) has changed:
+  - Specify chromosomes with _identifier only_ (without `chr`)
+  - Valid values are individual chromosomes, separated by comma (e.g. `1` or `1,2`), ranges using `:` (`1:22`) or a combination of the above (`1:22, X`). If you set `ichorcna_genomestyle`, the right prefix will be appended for you when running the analysis
+  - `ichorcna_plotylim` now takes a min and max value separated by comma (e.g. `-2,4`)
+  - All the ichorCNA options that require `TRUE` or `FALSE` now take a boolean `true` or `false`
+  - Raw R in any ichorCNA option (e.g. `c(1,2)`) is no longer supported and will raise an error.
+
+### New features
+
+- Support the latest version of ichorCNA (@lbeltrame and @SaraPotente, PR #57)
+- Update the ichorCNA modules to the latest upstream nf-core versions (@lbeltrame, PR #57)
+- PoN support in the samplesheet (@lbeltrame, #13, PR #57)
+
+### Bug fixes
+
+- Don't raise an error if in CIN quantification there is only one sample (#59, @lbeltrame)
+
 ## v1.3.1 - "Mori Ranmaru" (2025-11-17)
 
 This release is a hotfix for a regression in size selection that somehow slipped under the radar.

assets/schema_input.json

@@ -63,8 +63,22 @@
                     }
                 ],
                 "meta": ["gender"]
+            },
+            "status": {
+                "errorMessage": "Status must be either tumor or normal",
+                "anyOf": [
+                    {
+                        "type": "string",
+                        "enum": ["tumor", "normal"]
+                    },
+                    {
+                        "type": "string",
+                        "maxLength": 0
+                    }
+                ],
+                "meta": ["status"]
             }
         },
-        "anyOf": [{ "required": ["sample", "fastq_1"] }, { "required": ["sample", "bam"] }]
+        "anyOf": [{ "required": ["sample", "fastq_1", "status"] }, { "required": ["sample", "bam", "status"] }]
     }
 }

bin/compute_signatures.R

@@ -50,8 +50,12 @@ df_activity <- df_activity %>%
 readr::write_tsv(df_activity, file = paste0(args$projectname, "_activity.txt"),
     quote = "needed")
 
-png(filename="ascat_sc_plot_by_component.png")
-plotSampleByComponent(object = cnobj)
+# Only plot if samples are > 1
+total_samples <- segments %>% pull(sample) %>% unique() %>% length()
+png(filename = "ascat_sc_plot_by_component.png")
+if (total_samples > 1) {
+    plotSampleByComponent(object = cnobj)
+}
 dev.off()
 
 

bin/correct_logr_ichorcna.py

@@ -31,12 +31,16 @@ def main(
     ),
 ):
 
-    segments = pl.scan_csv(seg, separator="\t")
+    segments = pl.scan_csv(seg, separator="\t").rename(
+        {"ID": "sample", "chrom": "chromosome"}
+    )
     ploidy_df = pl.scan_csv(ploidy, separator="\t")
 
     result = (
         segments.join(
-            ploidy_df.select("sample", "Ploidy"), on="sample", how="left"
+            ploidy_df.select(pl.col("samplename").alias("sample"), "Ploidy"),
+            on="sample",
+            how="left",
         )
         .with_columns(
             pl.col("logR_Copy_Number")

conf/modules.config

@@ -262,50 +262,51 @@ process {
         }
     }
 
-    withName: ICHORCNA_GENERATE_PON {
+    withName: ICHORCNA_CREATEPON {
         publishDir = [
             path: { "${params.outdir}/ichorcna/PoN/" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
         ]
         ext.args   = [
-            "--genomeStyle ${params.ichorcna_genome_style}",
-            "--genomeBuild ${params.genome}",
-            "--chrs \"${params.ichorcna_chrs_to_use}\"",
-            "--maleChrXLogRThres \"${params.ichorcna_male_chrX_logR}\"",
-        ].join(' ')
-        ext.prefix = { params.pon_name ? "${params.pon_name}" : "PoN" }
+            "genomeStyle='${params.ichorcna_genome_style}'",
+            "chrs=\"${params.ichorcna_chrs_to_use}\"",
+            "minMapScore=${params.ichorcna_min_map_score}",
+            "fracReadsInChrYForMale=${params.ichorcna_fraction_reads_male}",
+            "maleChrXLogRThres=${params.ichorcna_male_chrX_logR}",
+        ].join(",\n")
     }
 
-    withName: RUN_ICHORCNA {
+    withName: ICHORCNA_RUN {
         publishDir = [
             path: { "${params.outdir}/ichorcna" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
         ]
         ext.args   = [
-            "--maxCN ${params.ichorcna_max_cn}",
-            "--chrTrain \"${params.ichorcna_chrs_to_train}\"",
-            "--chrs \"${params.ichorcna_chrs_to_use}\"",
-            "--txnE ${params.ichorcna_txne}",
-            "--txnStrength ${params.ichorcna_trx_strength}",
-            "--minMapScore ${params.ichorcna_min_map_score}",
-            "--fracReadsInChrYForMale ${params.ichorcna_fraction_reads_male}",
-            "--minSegmentBins ${params.ichorcna_min_segment_bins}",
-            "--maxFracGenomeSubclone ${params.ichorcna_max_frac_genome_subclone}",
-            "--maxFracCNASubclone ${params.ichorcna_max_frac_cna_subclone}",
-            "--includeHOMD ${params.ichorcna_include_homd}",
-            "--altFracThreshold ${params.ichorcna_alt_frac_threshold}",
-            "--genomeStyle ${params.ichorcna_genome_style}",
-            "--plotFileType ${params.ichorcna_plotfiletype}",
-            "--plotYLim '${params.ichorcna_plotylim}'",
-            "--normal 'c(${params.ichorcna_normal_states})'",
-            "--genomeBuild ${params.genome}",
-            params.ichorcna_estimate_ploidy ? "--ploidy 'c(2, 3, 4, 5)'" : "",
-            params.ichorcna_estimate_ploidy ? "--estimatePloidy TRUE" : "--estimatePloidy FALSE",
-            params.ichorcna_estimate_sc ? "--estimateScPrevalence TRUE" : "--estimateScPrevalence FALSE",
-            params.ichorcna_estimate_sc ? "--scStates 'c(1,3)'" : "--scStates 'c()'",
-        ].join(' ')
+            "maxCN=${params.ichorcna_max_cn}",
+            params.ichorcna_genome_style == "UCSC" ? "chrTrain=\"paste0('chr', c(${params.ichorcna_chrs_to_train}))\"" : "chrTrain='c(${params.ichorcna_chrs_to_train})'",
+            params.ichorcna_genome_style == "UCSC" ? "chrs=\"paste0('chr', c(${params.ichorcna_chrs_to_use}))\"" : "chrs='c(${params.ichorcna_chrs_to_use})'",
+            params.ichorcna_genome_style == "UCSC" ? "chrNormalize=\"paste0('chr', c(${params.ichorcna_chrs_to_normalize}))\"" : "chrNormalize='c(${params.ichorcna_chrs_to_normalize})'",
+            "txnE=${params.ichorcna_txne}",
+            "txnStrength=${params.ichorcna_trx_strength}",
+            "minMapScore=${params.ichorcna_min_map_score}",
+            "fracReadsInChrYForMale=${params.ichorcna_fraction_reads_male}",
+            "minSegmentBins=${params.ichorcna_min_segment_bins}",
+            "maxFracCNASubclone=${params.ichorcna_max_frac_genome_subclone}",
+            params.ichorcna_include_homd ? "includeHOMD=TRUE" : "includeHOMD=FALSE",
+            "altFracThreshold=${params.ichorcna_alt_frac_threshold}",
+            "genomeStyle='${params.ichorcna_genome_style}'",
+            "plotFileType='${params.ichorcna_plotfiletype}'",
+            "plotYLim='c(${params.ichorcna_plotylim})'",
+            "normal='c(${params.ichorcna_normal_states})'",
+            "genomeBuild='${params.genome}'",
+            params.ichorcna_estimate_normal ? "estimateNormal=TRUE" : "estimateNormal=FALSE",
+            params.ichorcna_estimate_ploidy ? "ploidy='c(2, 3, 4, 5)'" : "ploidy='2'",
+            params.ichorcna_estimate_ploidy ? "estimatePloidy=TRUE" : "estimatePloidy=FALSE",
+            params.ichorcna_estimate_sc ? "estimateScPrevalence=TRUE" : "estimateScPrevalence=FALSE",
+            params.ichorcna_estimate_sc ? "scStates='c(1,3)'" : "scStates='c()'",
+        ].join(",\n") + ", "
     }
 
     withName: AGGREGATE_ICHORCNA_TABLE {
@@ -334,7 +335,7 @@ process {
     }
 
     withName: CONCATENATE_QDNASEQ_PLOTS {
-        publishDir       = [
+        publishDir = [
             path: { "${params.outdir}/cn_plots/qdnaseq/" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
@@ -432,23 +433,23 @@ process {
     }
 
     withName: CONCATENATE_BIN_PLOTS {
-        publishDir       = [
+        publishDir = [
             path: { "${params.outdir}/cn_plots/ichorcna" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
         ]
     }
 
     withName: CONCATENATE_ASCATSC_PLOTS {
-        publishDir       = [
+        publishDir = [
             path: { "${params.outdir}/cn_plots/ascat_sc" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
         ]
     }
 
     withName: CONCATENATE_ASCATSC_REFITTED_PLOTS {
-        publishDir       = [
+        publishDir = [
             path: { "${params.outdir}/cn_plots/ascat_sc_refitted" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
@@ -534,5 +535,4 @@ process {
         ].join(' ')
         ext.when   = params.run_gistic
     }
-
 }

conf/test.config

@@ -24,7 +24,7 @@ params {
     config_profile_description = 'Minimal test dataset to check pipeline function with ASCAT.sc caller and solid_biopsy subworkflow.'
 
     // Input data
-    input  = 'https://github.com/DIncalciLab/samurai-test-data/raw/refs/heads/master/samplesheet.csv'
+    input  = 'https://github.com/DIncalciLab/samurai-test-data/raw/refs/heads/new-samplesheet-format/samplesheet.csv'
 
     // Genome references
     genome = 'hg38'

conf/test_ichorcna.config

@@ -24,7 +24,7 @@ params {
     config_profile_description = 'Minimal test dataset to check pipeline function with ichorCNA caller and liquid_biopsy subworkflow.'
 
     // Input data
-    input  = 'https://github.com/DIncalciLab/samurai-test-data/raw/refs/heads/master/samplesheet.csv'
+    input  = 'https://github.com/DIncalciLab/samurai-test-data/raw/refs/heads/new-samplesheet-format/samplesheet.csv'
 
     // Genome references
     genome = 'hg38'