sanger-tol · DLBPointon · May 25, 2026 · May 25, 2026 · May 25, 2026 · Jun 2, 2026
diff --git a/.github/workflows/workflowhub_update.yml b/.github/workflows/workflowhub_update.yml
@@ -0,0 +1,18 @@
+name: Publish workflows on WorkflowHub
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  wfh-submit:
+    name: WorkflowHub submission
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Submit workflows
+        uses: workflowhub-eu/submission-action@v0
+        env:
+          API_TOKEN: ${{ secrets.WORKFLOWHUB_API_TOKEN }}
+        with:
+          team_id: 204
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -14,6 +14,9 @@ Release 11 of sanger-tol/ascc
 - `KMER_COUNTER` has been replaced with `COBIONTID_KMERCOUNTER` to increase efficiency.
   - This required the addition of `REFORMAT_NPY_2_CSV` to generate the kmer table.
 - `FCSGX_RUNGX` has been updated to not depend on `modulecmd` instead, production profiles will instead default to a local installation of fcs_gx. Avoiding containerised options provided in the module.
+- Samtools modules have been updated to `1.23.1`.
+- `ORGANELLAR` and `GENOMIC` subworkflows have been merged into a single `ASCC` workflow.
+  - This was an artifact from when the two would have been doing significantly different processes.
 
 ### `Dependencies`
 
@@ -24,6 +27,7 @@ Release 11 of sanger-tol/ascc
 | `REFORMAT_NPY_2_CSV`    | npy_2_csv.py        | NA          | 1.0.0         |
 | `SAMTOOLS_DICT`         | samtools            | 1.22.1      | 1.23.1        |
 | `SAMTOOLS_FAIDX`        | samtools            | 1.22.1      | 1.23.1        |
+| `SAMTOOLS_SORT`         | samtools            | 1.22.1      | 1.23.1        |
 | `MINIMAP2_ALIGN2`       | minimap2 + samtools | 2.29 + 1.21 | 2.30 + 1.23.1 |
 
 ## [0.6.0] - Red Notebook [28/01/2025]

diff --git a/assets/farm_testing/samplesheet.csv b/assets/farm_testing/samplesheet.csv
@@ -1,4 +1,2 @@
 sample,assembly_type,assembly_file
-odCymConc1,PRIMARY,/lustre/scratch122/tol/data/d/8/a/6/e/b/Cymbastela_concentrica/assembly/draft/odCymConc1.20241101/odCymConc1.20241101.fa.gz
-odCymConc1,HAPLO,/lustre/scratch122/tol/data/d/8/a/6/e/b/Cymbastela_concentrica/assembly/draft/odCymConc1.20241101/odCymConc1.20241101.haplotigs.decontaminated.fa.gz
-odCymConc1,MITO,/lustre/scratch122/tol/data/d/8/a/6/e/b/Cymbastela_concentrica/assembly/draft/odCymConc1.20241101/odCymConc1-MT.fa.gz
+odCymConc1,PRIMARY,/nfs/treeoflife-01/resources/nextflow/test-data/Laetiporus_sulphureus/assembly/release/gfLaeSulp1.1/insdc/GCA_927399515.1.fasta.gz
diff --git a/bin/abnormal_contamination_check.py b/bin/abnormal_contamination_check.py
@@ -1,12 +1,13 @@
 #!/usr/bin/env python
 
-import general_purpose_functions as gpf
-import sys
+import argparse
 import os.path
 import pathlib
-import argparse
+import sys
 import textwrap
 
+import general_purpose_functions as gpf
+
 VERSION = "V1.2.0"
 
 DESCRIPTION = """
@@ -38,11 +39,33 @@ def parse_args():
     parser.add_argument("assembly", type=str, help="Path to the fasta assembly file")
     parser.add_argument("summary_path", type=str, help="Path to the tiara summary file")
     parser.add_argument("-q", "--out_prefix", type=str, help="Output file prefix for the report")
-    parser.add_argument("-o", "--output", type=str, help="Path to output file", default="fcs-gx_alarm_indicator_file.txt")
-    parser.add_argument("-p", "--alarm_percentage", type=int, help="Percentage of putative contaminant sequence in genomic assembly that will trip the alarm", default=3)
-    parser.add_argument("-l", "--alarm_length_removed", type=int, help="Length of removed sequence is greater than default, greater than this will trip the alarm.", default=1e7)
-    parser.add_argument("-s", "--alarm_scaff_length", type=int, help="Length of largest scaffold removed to trip alarm.", default=1.8e6)
-    parser.add_argument("-t", "--alarm_scaff_percent_removed", type=float, help="Percentage of Scaffolds set for removal from assembly to trip the alarm.", default=10.0)
+    parser.add_argument(
+        "-o", "--output", type=str, help="Path to output file", default="fcs-gx_alarm_indicator_file.txt"
+    )
+    parser.add_argument(
+        "-p",
+        "--alarm_percentage",
+        type=int,
+        help="Percentage of putative contaminant sequence in genomic assembly that will trip the alarm",
+        default=3,
+    )
+    parser.add_argument(
+        "-l",
+        "--alarm_length_removed",
+        type=int,
+        help="Length of removed sequence is greater than default, greater than this will trip the alarm.",
+        default=1e7,
+    )
+    parser.add_argument(
+        "-s", "--alarm_scaff_length", type=int, help="Length of largest scaffold removed to trip alarm.", default=1.8e6
+    )
+    parser.add_argument(
+        "-t",
+        "--alarm_scaff_percent_removed",
+        type=float,
+        help="Percentage of Scaffolds set for removal from assembly to trip the alarm.",
+        default=10.0,
+    )
     parser.add_argument("-r", "--review_info", type=int, help="Number of REVIEW/INFO to the trigger alarm", default=0)
     parser.add_argument("-v", "--version", action="version", version=VERSION)
     return parser.parse_args()
@@ -66,9 +89,7 @@ def load_fcs_gx_results(seq_dict, fcs_gx_and_tiara_summary_path):
     Loads FCS-GX actions from the FCS-GX and Tiara results summary file, adds them to the dictionary that contains sequence lengths
     """
     fcs_gx_and_tiara_summary_data = gpf.l(fcs_gx_and_tiara_summary_path)
-    fcs_gx_and_tiara_summary_data = fcs_gx_and_tiara_summary_data[
-        1 : len(fcs_gx_and_tiara_summary_data)
-    ]
+    fcs_gx_and_tiara_summary_data = fcs_gx_and_tiara_summary_data[1 : len(fcs_gx_and_tiara_summary_data)]
     for line in fcs_gx_and_tiara_summary_data:
         split_line = line.split(",")
         assert len(split_line) == 5
@@ -87,9 +108,7 @@ def main():
         sys.exit(1)
 
     if os.path.isfile(args.assembly) is False:
-        sys.stderr.write(
-            f"The assembly FASTA file was not found at the expected location ({args.assembly})\n"
-        )
+        sys.stderr.write(f"The assembly FASTA file was not found at the expected location ({args.assembly})\n")
         sys.exit(1)
 
     seq_dict = get_sequence_lengths(args.assembly)
@@ -115,7 +134,7 @@ def main():
         "PERCENTAGE_LENGTH_REMOVED": args.alarm_percentage,
         "LARGEST_SCAFFOLD_REMOVED": args.alarm_scaff_length,
         "PERCENTAGE_SCAFFOLDS_REMOVED": args.alarm_scaff_percent_removed,
-        "REVIEW_OR_INFO": args.review_info
+        "REVIEW_OR_INFO": args.review_info,
     }
 
     report_dict = {
@@ -124,7 +143,7 @@ def main():
         "LARGEST_SCAFFOLD_REMOVED": max(lengths_removed, default=0),
         "SCAFFOLDS_REMOVED": scaffolds_removed,
         "PERCENTAGE_SCAFFOLDS_REMOVED": 100 * scaffolds_removed / scaffold_count,
-        "REVIEW_OR_INFO": review_info
+        "REVIEW_OR_INFO": review_info,
     }
 
     # Seperated out to ensure that the file is written in one go and doesn't confuse Nextflow

diff --git a/bin/general_purpose_functions.py b/bin/general_purpose_functions.py
@@ -7,8 +7,7 @@
 #
 # Copyright (c) 2020-2021 Genome Research Ltd.
 #
-# Author: Eerik Aunin (eeaunin@gmail.com)
-#
+# Author: Eerik Aunin (eeaunin@gmail.com
 # This file is a part of the Genome Decomposition Analysis (GDA) pipeline.
 #
 # Permission is hereby granted, free of charge, to any person obtaining a copy
@@ -29,13 +28,13 @@
 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 # SOFTWARE.
 
+import argparse
 import os
-from os.path import isfile
-import sys
-import subprocess
 import signal
+import subprocess
+import sys
 from datetime import datetime
-import argparse
+from os.path import isfile
 
 
 def l(path):
@@ -172,17 +171,15 @@ def string_to_chunks(line, n):
     return [line[i : i + n] for i in range(0, len(line), n)]
 
 
-def run_system_command(
-    system_command, verbose=True, dry_run=False, tries=1, expected_exit_code=0
-):
+def run_system_command(system_command, verbose=True, dry_run=False, tries=1, expected_exit_code=0):
     """
     Executes a system command and checks its exit code
     """
     triggering_script_name = sys.argv[0].split("/")[-1]
     try_counter_string = ""
-    if dry_run == False:
+    if not dry_run:
         for i in range(0, tries):
-            if verbose == True:
+            if verbose:
                 time_now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
                 if i > 0:
                     try_counter_string = ", try {}".format(i + 1)
@@ -201,11 +198,7 @@ def run_system_command(
                 break
             except subprocess.CalledProcessError as exc:
                 out_errormessage = (
-                    "<"
-                    + triggering_script_name
-                    + "> "
-                    + " exited with error code "
-                    + str(exc.returncode)
+                    "<" + triggering_script_name + "> " + " exited with error code " + str(exc.returncode)
                 )
                 if exc.output.isspace() == False:
                     out_errormessage += ". Error message: " + exc.output
@@ -234,11 +227,7 @@ def get_file_paths(in_folder_path, extension):
     onlyfiles = list()
     selected_file_paths = list()
     if os.path.isdir(in_folder_path):
-        onlyfiles = [
-            f
-            for f in os.listdir(in_folder_path)
-            if os.path.isfile(os.path.join(in_folder_path, f))
-        ]
+        onlyfiles = [f for f in os.listdir(in_folder_path) if os.path.isfile(os.path.join(in_folder_path, f))]
         for file_item in onlyfiles:
             if "." + extension in file_item:
                 file_item_split = file_item.split(".")

diff --git a/conf/modules.config b/conf/modules.config
@@ -155,8 +155,8 @@ process {
         ]
     }
 
-    withName: ".*:ASCC_ORGANELLAR:RUN_DECONTAMINATE_FASTA:DECONTAMINATE_GENERATE_BED" {
-        ext.args = "--is_organelle True"
+    withName: ".*:ASCC_ASSEMBLY:RUN_DECONTAMINATE_FASTA:DECONTAMINATE_GENERATE_BED" {
+        ext.args = { meta.assembly_type == "organellar" ? "--is_organelle True" : "" }
     }
 
     withName: "ASCC_MERGE_TABLES|DECONTAMINATE_GENERATE_BED|GZIP" {

diff --git a/conf/production.config b/conf/production.config
@@ -20,8 +20,6 @@ process {
     // Allowing it to use default resources, stops it showing up in LSF?
     withName: FCSGX_RUNGX {
         container   = ""
-        module      = ""
-        //module      = "fcs-gx/farm/0.5.5"
         cpus        = { 32      }
         memory      = { 520.GB  }
         time        = { 12.h    }
@@ -67,13 +65,13 @@ params {
     // for sanger decontamination.
 
     run_essentials                      = "both"
-    run_kmers                           = "off"         //genomic
+    run_kmers                           = "genomic"         //genomic
     run_tiara                           = "both"
     run_coverage                        = "both"
-    run_nt_blast                        = "off"         //both
-    run_nr_diamond                      = "off"         //both
-    run_uniprot_diamond                 = "off"         //both
-    run_kraken                          = "off"         //both
+    run_nt_blast                        = "both"         //both
+    run_nr_diamond                      = "both"         //both
+    run_uniprot_diamond                 = "both"         //both
+    run_kraken                          = "both"         //both
     run_fcsgx                           = "both"        //both
     run_fcs_adaptor                     = "both"        //both
     run_vecscreen                       = "both"        //both

diff --git a/conf/test.config b/conf/test.config
@@ -10,14 +10,33 @@
 ----------------------------------------------------------------------------------------
 */
 
+
 process {
-    resourceLimits = [
-        cpus: 4,
-        memory: '15.GB',
-        time: '1.h'
-    ]
+    // Adding the module info here
+    // stopped the resources from base.config
+    // from being used, and causes the job
+    // to only use the defaulted process_* tag
+    // which is just not enough for FCS_GX
+    // TODO
+    // Allowing it to use default resources, stops it showing up in LSF?
+    withName: FCSGX_RUNGX {
+        container   = ""
+        cpus        = { 32      }
+        memory      = { 520.GB  }
+        time        = { 12.h    }
+    }
+
+    withName: SANGER_TOL_BTK {
+        clusterOptions  = {"-J NF_ASCC::BLOBTOOLKIT(${meta.id})"}
+        queue           = "oversubscribed"
+        cpus            = { 2 }
+        memory          = { 1200.MB * task.attempt  }
+        time            = { 96.h    * task.attempt  }
+    }
 }
 
+
+
 params {
     config_profile_name        = 'Test profile'
     config_profile_description = 'Minimal test dataset to check pipeline function'
@@ -82,7 +101,7 @@ params {
     run_organellar_blast                = "genomic"
     run_autofilter_assembly             = "both"
     run_create_btk_dataset              = "both"
-    run_merge_datasets                  = "genomic"
+    run_merge_datasets                  = "both"
     run_decontaminate_fasta             = "both"
     run_html_report                     = "both"
 }
diff --git a/conf/test_full.config b/conf/test_full.config
@@ -64,21 +64,21 @@ params {
     run_essentials                      = "both"    // both
     run_kmers                           = "genomic" // genomic
     run_tiara                           = "both"    // both
-    run_coverage                        = "both"    // both
-    run_nt_blast                        = "both"    // both
-    run_nr_diamond                      = "both"    // both
-    run_uniprot_diamond                 = "both"    // both
-    run_kraken                          = "both"    // both
+    run_coverage                        = "off"    // both
+    run_nt_blast                        = "off"    // both
+    run_nr_diamond                      = "off"    // both
+    run_uniprot_diamond                 = "off"    // both
+    run_kraken                          = "off"    // both
     run_fcsgx                           = "both"    // both
-    run_fcs_adaptor                     = "both"    // both
-    run_vecscreen                       = "both"    // both
-    run_btk_busco                       = "genomic" // genomic
-    run_pacbio_barcodes                 = "both"    // both
-    run_organellar_blast                = "genomic" // genomic
+    run_fcs_adaptor                     = "off"    // both
+    run_vecscreen                       = "off"    // both
+    run_btk_busco                       = "off" // genomic
+    run_pacbio_barcodes                 = "off"    // both
+    run_organellar_blast                = "off" // genomic
     run_autofilter_assembly             = "both"    // both
-    run_create_btk_dataset              = "both"    // both
-    run_merge_datasets                  = "genomic" // genomic
+    run_create_btk_dataset              = "off"    // both
+    run_merge_datasets                  = "off" // genomic
     run_decontaminate_fasta             = "both"    // both
-    run_html_report                     = "both"    // both
+    run_html_report                     = "off"    // both
 
 }
diff --git a/modules.json b/modules.json
@@ -37,12 +37,6 @@
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/fcs/fcsadaptor/fcs-fcsadaptor.diff"
                     },
-                    "fcsgx/rungx": {
-                        "branch": "master",
-                        "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
-                        "installed_by": ["modules"],
-                        "patch": "modules/nf-core/fcsgx/rungx/fcsgx-rungx.diff"
-                    },
                     "gnu/sort": {
                         "branch": "master",
                         "git_sha": "7ad318b7b2c0ef6a101c01b6083b8acd6a9a63de",
@@ -151,6 +145,16 @@
                         "git_sha": "f919028603ca42cb01a59e45475c19106840372d",
                         "installed_by": ["fastx_map_long_reads"]
                     },
+                    "fcsgx/parseresults": {
+                        "branch": "main",
+                        "git_sha": "17d7d065459873b60bb795714fac19137304b793",
+                        "installed_by": ["modules"]
+                    },
+                    "fcsgx/rungx": {
+                        "branch": "main",
+                        "git_sha": "864e75dc4bf5b4fc50f7a5e568a4cb6236bfb528",
+                        "installed_by": ["modules"]
+                    },
                     "samtools/mergedup": {
                         "branch": "main",
                         "git_sha": "729e9c8cfa83bc64c95ea6024dd5477c936e305e",

diff --git a/modules/local/ascc/merge_tables/main.nf b/modules/local/ascc/merge_tables/main.nf
@@ -34,7 +34,7 @@ process ASCC_MERGE_TABLES {
     script:
     def args                             = task.ext.args                    ?: ""
 
-    def empty_file_size                  = 80
+    def empty_file_size                  = 50
     def coverage_data                    = coverage.size()                   > empty_file_size   ? "-c ${coverage}"                  : ""
     def tiara_data                       = tiara.size()                      > empty_file_size   ? "-t ${tiara}"                     : ""
     def nt_kraken_data                   = nt_kraken.size()                  > empty_file_size   ? "-nk ${nt_kraken}"                : ""