Move to 2.2.0

.nf-core.yml

@@ -10,4 +10,4 @@ template:
   name: hic
   org: nf-core
   outdir: .
-  version: 2.2.0dev
+  version: 2.2.0

.vscode/settings.json

@@ -1,3 +1,4 @@
 {
-    "markdown.styles": ["public/vscode_markdown.css"]
+    "markdown.styles": ["public/vscode_markdown.css"],
+    "nextflow.telemetry.enabled": false
 }

CHANGELOG.md

@@ -3,14 +3,53 @@
 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).
 
+## Version 2.2.0 2026-03-02
+
+### `Added`
+
+- Subworkflows meta.yml
+- Module FAIDX for chromosomes sizes calculation
+- TRIMGALORE module for 5' clipping (see #225)
+- CALDER2 compartments calling (see '--compartments_caller' option)
+- Local FILTER_CHROMSIZE module (in order to apply CALDER2 without error)
+- Optional '--min_size' parameter for chromosome selection
+- Default MIN_FRAG_SIZE, MAX_FRAG_SIZE, MIN_INSERT_SIZE and MAX_INSERT_SIZE values for Arima and ArimV2 protocols
+
+### `Removed`
+
+- Module GETCHROMSIZES (replaced by FAIDX)
+- Version channels from subworkflows (tools versions gathering still a WIP)
+
+### `Fixed`
+
+- #227: MPLCONFIGDIR is set to "${baseDir}/mplconfig"
+- #62: a single number can be given as BIN_SIZES without error
+- #225:TRIMGALORE remove the first 5 bases of the 5' end and
+  fragments and inserts size min/max settings are set to recommended values if Arima/ArimaV2 is used
+- Bug from COOLER_CLOAD deprecated "pairs" ext.args calling
+- Bug on the cooler "add resolution" step caused by module COOLER_CLOAD update
+- Logo matching template
+
+### `Updated`
+
+- All nf-core modules (including topics channel)
+- Modules path
+- "channel" syntax with lowercase c
+- Components names in subworkflows meta.yml
+- COOLER_CLOAD inputs and outputs
+- BWA_MEM inputs
+- SAMTOOL_SORT inputs
+- UTILS_NFSCHEMA_PLUGIN inputs and outputs
+- Markdown settings
+- Template files
+- nf-core version to 3.5.0
+
 ## v2.2.0dev
 
 ### `Added`
 
 - Parameter `--dnase`is now replaced by `--no_digestion`
 
-- Add CALDER2 compartments calling (see '--compartments_caller' option)
-
 - Add new '--balancing_opts' to update `cooler balance` arguments (#193)
 
 - New subworkflow based on `pairtools` to detect valid pairs. The user

bin/cutsite_trimming.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python3
+
+import argparse
+import gzip
+import ahocorasick
+
+# Open gzip or regular files transparently
+def opengz(path, mode="rt"):
+    return gzip.open(path, mode) if path.endswith(".gz") else open(path, mode)
+
+# Build Aho-Corasick automaton for fast multi-pattern search
+def build_automaton(sites):
+    A = ahocorasick.Automaton()
+    for s in sites:
+        A.add_word(s, s)
+    A.make_automaton()
+    return A
+
+# Find earliest cutsite position in a read
+def cut_position(seq, A):
+    pos = None
+    for end, site in A.iter(seq):
+        start = end - len(site) + 1
+        if pos is None or start < pos:
+            pos = start
+    return pos
+
+# Expand cutsite string (e.g., "A^GCTT") into all IUPAC possibilities
+IUPAC = {
+    "A": ["A"],
+    "T": ["T"],
+    "C": ["C"],
+    "G": ["G"],
+    "N": ["A", "C", "G", "T"],
+}
+
+def expand_cut_sites(site_string):
+    import itertools
+    expanded = []
+    for site in site_string.split(","):
+        site = site.replace("^", "").upper()
+        letters = [IUPAC.get(base, [base]) for base in site]
+        for combo in itertools.product(*letters):
+            expanded.append("".join(combo))
+    return sorted(set(expanded))
+
+def main():
+    p = argparse.ArgumentParser()
+    p.add_argument("--fastq", required=True)
+    p.add_argument("--cutsite", required=True)
+    p.add_argument("--out", required=True)
+    p.add_argument("--rmuntrim", action="store_true")
+    args = p.parse_args()
+
+    # Expand cutsites and build automaton
+    sites = expand_cut_sites(args.cutsite)
+    A = build_automaton(sites)
+
+    total = trimmed = dummy = 0
+
+    with opengz(args.fastq) as fin, open(args.out, "wt") as fout:
+        while True:
+            ID = fin.readline()
+            if not ID:
+                break
+            seq = fin.readline().rstrip()
+            fin.readline()  # skip "+"
+            qual = fin.readline().rstrip()
+
+            total += 1
+
+            cut = cut_position(seq, A)
+
+            if cut is not None:
+                trimmed += 1
+                if cut == 0: # If cutsite is at position 0, replace with length-1 N read
+                    dummy += 1
+                    fout.write(f"{ID}N\n+\n!\n")
+                else:
+                    fout.write(f"{ID}{seq[:cut]}\n+\n{qual[:cut]}\n")
+            elif not args.rmuntrim:
+                fout.write(f"{ID}{seq}\n+\n{qual}\n")
+
+    #print(f"Total reads: {total}")
+    #print(f"Trimmed reads: {trimmed}")
+    #print(f"Dummy reads (site at pos0): {dummy}")
+
+if __name__ == "__main__":
+    main()

conf/modules.config

@@ -10,6 +10,10 @@ process {
         ext.args = '--quiet'
     }
 
+    withName: TRIMGALORE {
+        ext.args = '--clip_R1 5 --clip_R2 5'
+    }
+
     withName: 'MULTIQC' {
         ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [
@@ -37,14 +41,6 @@ process {
         ]
     }
 
-    withName: 'CUSTOM_GETCHROMSIZES' {
-        publishDir = [
-            path: { "${params.outdir}/genome" },
-            mode: 'copy',
-            enabled: params.save_reference
-        ]
-    }
-
     withName: 'GET_RESTRICTION_FRAGMENTS' {
         publishDir = [
             path: { "${params.outdir}/genome" },
@@ -344,7 +340,7 @@ process {
             enabled : params.save_raw_maps
         ]
         ext.prefix = { "${meta.id}.${cool_bin}" }
-        ext.args = "pairs -c1 2 -p1 3 -c2 4 -p2 5"
+        ext.args = "-c1 2 -p1 3 -c2 4 -p2 5"
     }
 
     withName: 'COOLER_BALANCE' {

main.nf

@@ -47,8 +47,6 @@ workflow NFCORE_HIC {
 
     main:
 
-    ch_versions = Channel.empty()
-
     //
     // SUBWORKFLOW: prepare genome annotation
     //
@@ -57,7 +55,6 @@ workflow NFCORE_HIC {
         params.bwt2_index,
         params.bwa_index
     )
-    ch_versions = ch_versions.mix(PREPARE_GENOME.out.versions)
 
     //
     // WORKFLOW: Run pipeline