From 89f5a13966fa13e8c321ba89b0b08c3313db2e48 Mon Sep 17 00:00:00 2001
From: vagkaratzas <vagelaros.gee@gmail.com>
Date: Tue, 2 Dec 2025 09:59:36 +0000
Subject: [PATCH 1/3] added s4pred module to pipeline

---
 CITATIONS.md                                  |  4 +
 conf/modules.config                           | 10 ++
 docs/output.md                                | 19 ++++
 modules.json                                  |  5 +
 .../nf-core/s4pred/runmodel/environment.yml   |  7 ++
 modules/nf-core/s4pred/runmodel/main.nf       | 52 ++++++++++
 modules/nf-core/s4pred/runmodel/meta.yml      | 52 ++++++++++
 .../s4pred/runmodel/tests/main.nf.test        | 58 +++++++++++
 .../s4pred/runmodel/tests/main.nf.test.snap   | 98 +++++++++++++++++++
 nextflow.config                               |  4 +
 nextflow_schema.json                          | 23 +++++
 .../main.nf                                   |  6 ++
 workflows/proteinannotator.nf                 |  4 +
 13 files changed, 342 insertions(+)
 create mode 100644 modules/nf-core/s4pred/runmodel/environment.yml
 create mode 100644 modules/nf-core/s4pred/runmodel/main.nf
 create mode 100644 modules/nf-core/s4pred/runmodel/meta.yml
 create mode 100644 modules/nf-core/s4pred/runmodel/tests/main.nf.test
 create mode 100644 modules/nf-core/s4pred/runmodel/tests/main.nf.test.snap

diff --git a/CITATIONS.md b/CITATIONS.md
index 0190458..02178b9 100644
--- a/CITATIONS.md
+++ b/CITATIONS.md
@@ -22,6 +22,10 @@
 
 > Zdobnov, Evgeni M., and Rolf Apweiler. “InterProScan – an Integration Platform for the Signature-Recognition Methods in InterPro.” Bioinformatics 17, no. 9 (September 1, 2001): 847–48. https://doi.org/10.1093/bioinformatics/17.9.847.
 
+- [s4pred](https://pubmed.ncbi.nlm.nih.gov/34213528/)
+
+> Moffat L, Jones DT. Increasing the accuracy of single sequence prediction methods using a deep semi-supervised learning framework. Bioinformatics. 2021 Nov 1;37(21):3744-51. doi: 10.1093/bioinformatics/btab491. PubMed PMID: 34213528; PubMed Central PMCID: PMC8570780.
+
 <!-- - [MMseqs2](https://www.nature.com/articles/nbt.3988)
 
 > Zdobnov, Evgeni M., and Rolf Apweiler. “InterProScan – an Integration Platform for the Signature-Recognition Methods in InterPro.” Bioinformatics 17, no. 9 (September 1, 2001): 847–48. https://doi.org/10.1093/bioinformatics/17.9.847.
diff --git a/conf/modules.config b/conf/modules.config
index 62ee119..e29e243 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -74,6 +74,16 @@ process {
         ]
     }
 
+    withName: 'NFCORE_PROTEINANNOTATOR:PROTEINANNOTATOR:S4PRED_RUNMODEL' {
+        ext.prefix = { params.s4pred_outfmt }
+        ext.args   = { "--outfmt ${params.s4pred_outfmt}" }
+        publishDir = [
+            path: { "${params.outdir}/s4pred/${meta.id}/" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: 'MULTIQC' {
         ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [
diff --git a/docs/output.md b/docs/output.md
index 2639d3e..274b4f6 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -18,6 +18,9 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 - [Functional Annotation](#functional-annotation) Annotate proteins with functional domains
   - [InterProScan](#Interproscan) - Search the InterPro database for functional domains
+
+- [s4pred](#s4pred) - Predict secondary structures of sequences, producing per amino acid probabilities of being an α-helix, a β-strand or a coil.
+
 - [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
 - [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
 
@@ -307,6 +310,22 @@ The XML Schema Definition (XSD) is available [here](http://ftp.ebi.ac.uk/pub/sof
 
 </details>
 
+#### s4pred
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `s4pred/`
+  - `<samplename>/`
+    - `<s4pred_outfmt>/`
+      - `<samplename>.<s4pred_outfmt>`: The probability of each amino acid to be an α-helix, a β-strand or a coil, in the chosen output format (i.e., 'ss2', 'fas', or 'horiz').
+
+</details>
+
+The `s4pred` module is used to predict secondary structures of amino acid sequences.
+
+[s4pred](https://github.com/psipred/s4pred) is a tool for accurate prediction of a protein's secondary structure from only it's amino acid sequence.
+
 ### MultiQC
 
 <details markdown="1">
diff --git a/modules.json b/modules.json
index 29cf403..132450a 100644
--- a/modules.json
+++ b/modules.json
@@ -20,6 +20,11 @@
                         "git_sha": "af27af1be706e6a2bb8fe454175b0cdf77f47b49",
                         "installed_by": ["modules"]
                     },
+                    "s4pred/runmodel": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"]
+                    },
                     "seqfu/stats": {
                         "branch": "master",
                         "git_sha": "e753770db613ce014b3c4bc94f6cba443427b726",
diff --git a/modules/nf-core/s4pred/runmodel/environment.yml b/modules/nf-core/s4pred/runmodel/environment.yml
new file mode 100644
index 0000000..83e4fb2
--- /dev/null
+++ b/modules/nf-core/s4pred/runmodel/environment.yml
@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - "bioconda::s4pred=1.2.1"
diff --git a/modules/nf-core/s4pred/runmodel/main.nf b/modules/nf-core/s4pred/runmodel/main.nf
new file mode 100644
index 0000000..d96ea5b
--- /dev/null
+++ b/modules/nf-core/s4pred/runmodel/main.nf
@@ -0,0 +1,52 @@
+process S4PRED_RUNMODEL {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/s4pred:1.2.1--pyhdfd78af_1':
+        'biocontainers/s4pred:1.2.1--pyhdfd78af_1' }"
+
+    input:
+    tuple val(meta), path(fasta)
+
+    output:
+    tuple val(meta), path("${prefix}"), emit: preds
+    path "versions.yml"               , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args    = task.ext.args   ?: ''
+    prefix      = task.ext.prefix ?: "${meta.id}"
+    def VERSION = '1.2.1' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+    """
+    mkdir ${prefix}
+
+    run_model \\
+        $args \\
+        --threads $task.cpus \\
+        --save-files \\
+        --outdir ${prefix} \\
+        ${fasta}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        s4pred: $VERSION
+    END_VERSIONS
+    """
+
+    stub:
+    prefix      = task.ext.prefix ?: "${meta.id}"
+    def VERSION = '1.2.1' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+    """
+    mkdir -p ${prefix}
+    touch ${prefix}/test.ss2
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        s4pred: $VERSION
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/s4pred/runmodel/meta.yml b/modules/nf-core/s4pred/runmodel/meta.yml
new file mode 100644
index 0000000..638ce67
--- /dev/null
+++ b/modules/nf-core/s4pred/runmodel/meta.yml
@@ -0,0 +1,52 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "s4pred_runmodel"
+description: Prediction of a protein's secondary structure from its amino acid sequence
+keywords:
+  - protein
+  - secondary structure
+  - prediction
+tools:
+  - "s4pred":
+      description: "Accurate prediction of a protein's secondary structure from its
+        amino acid sequence"
+      homepage: "https://github.com/psipred/s4pred"
+      documentation: "https://github.com/psipred/s4pred"
+      tool_dev_url: "https://github.com/psipred/s4pred"
+      doi: "10.1093/bioinformatics/btab491"
+      licence: ["GPL v3-or-later"]
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
+    - fasta:
+        type: file
+        description: protein FASTA file containing one or more amino acid sequences
+          to predict their respective secondary structures
+        pattern: "*.{fasta,fa,fas,fna,faa}"
+        ontologies:
+          - edam: http://edamontology.org/format_1929 # FASTA
+output:
+  preds:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - ${prefix}:
+          type: directory
+          description: A folder with all the prediction outputs
+          pattern: "${prefix}"
+  versions:
+    - versions.yml:
+        type: file
+        description: File containing software versions
+        pattern: "versions.yml"
+        ontologies:
+          - edam: http://edamontology.org/format_3750 # YAML
+authors:
+  - "@vagkaratzas"
+maintainers:
+  - "@vagkaratzas"
diff --git a/modules/nf-core/s4pred/runmodel/tests/main.nf.test b/modules/nf-core/s4pred/runmodel/tests/main.nf.test
new file mode 100644
index 0000000..0879036
--- /dev/null
+++ b/modules/nf-core/s4pred/runmodel/tests/main.nf.test
@@ -0,0 +1,58 @@
+nextflow_process {
+
+    name "Test Process S4PRED_RUNMODEL"
+    script "../main.nf"
+    process "S4PRED_RUNMODEL"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "s4pred"
+    tag "s4pred/runmodel"
+
+    test("sarscov2 - proteome - fasta") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("sarscov2 - proteome - fasta - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}
diff --git a/modules/nf-core/s4pred/runmodel/tests/main.nf.test.snap b/modules/nf-core/s4pred/runmodel/tests/main.nf.test.snap
new file mode 100644
index 0000000..8b3d57a
--- /dev/null
+++ b/modules/nf-core/s4pred/runmodel/tests/main.nf.test.snap
@@ -0,0 +1,98 @@
+{
+    "sarscov2 - proteome - fasta": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            "ENSSASP00005000002.1.ss2:md5,ca1ecb796927219ab1bd2408e17d94d6",
+                            "ENSSASP00005000003.1.ss2:md5,ad37a8ec4cef27c91c9958bcb652903f",
+                            "ENSSASP00005000004.1.ss2:md5,dae6e305856d12c20c97b86492c937cd",
+                            "ENSSASP00005000005.1.ss2:md5,f3e72765229ac89063633f6d4e40c4fe",
+                            "ENSSASP00005000006.1.ss2:md5,731586e1e6176ada900c181edb17e3c9",
+                            "ENSSASP00005000007.1.ss2:md5,2f7459999558834d339b781c96da1482",
+                            "ENSSASP00005000008.1.ss2:md5,c620bbff5f073089df9554ca439933eb",
+                            "ENSSASP00005000009.1.ss2:md5,19f317c1b3d468ec2e876ecce4d4b60a",
+                            "ENSSASP00005000010.1.ss2:md5,020604f0e037a104983e7ba325821c0a",
+                            "ENSSASP00005000011.1.ss2:md5,ee9dc69931be3ec7eeed88e42f7b90e7",
+                            "ENSSASP00005000012.1.ss2:md5,f08bffd8ce8031fb7bb658f8e2408626",
+                            "ENSSASP00005000013.1.ss2:md5,445e88597dc8fc0f40e21d95d148ced1"
+                        ]
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,408e5584371b73bd5dd0a53096ed2d14"
+                ],
+                "preds": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            "ENSSASP00005000002.1.ss2:md5,ca1ecb796927219ab1bd2408e17d94d6",
+                            "ENSSASP00005000003.1.ss2:md5,ad37a8ec4cef27c91c9958bcb652903f",
+                            "ENSSASP00005000004.1.ss2:md5,dae6e305856d12c20c97b86492c937cd",
+                            "ENSSASP00005000005.1.ss2:md5,f3e72765229ac89063633f6d4e40c4fe",
+                            "ENSSASP00005000006.1.ss2:md5,731586e1e6176ada900c181edb17e3c9",
+                            "ENSSASP00005000007.1.ss2:md5,2f7459999558834d339b781c96da1482",
+                            "ENSSASP00005000008.1.ss2:md5,c620bbff5f073089df9554ca439933eb",
+                            "ENSSASP00005000009.1.ss2:md5,19f317c1b3d468ec2e876ecce4d4b60a",
+                            "ENSSASP00005000010.1.ss2:md5,020604f0e037a104983e7ba325821c0a",
+                            "ENSSASP00005000011.1.ss2:md5,ee9dc69931be3ec7eeed88e42f7b90e7",
+                            "ENSSASP00005000012.1.ss2:md5,f08bffd8ce8031fb7bb658f8e2408626",
+                            "ENSSASP00005000013.1.ss2:md5,445e88597dc8fc0f40e21d95d148ced1"
+                        ]
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,408e5584371b73bd5dd0a53096ed2d14"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.6"
+        },
+        "timestamp": "2025-05-07T10:09:40.552710868"
+    },
+    "sarscov2 - proteome - fasta - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            "test.ss2:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        ]
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,408e5584371b73bd5dd0a53096ed2d14"
+                ],
+                "preds": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            "test.ss2:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        ]
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,408e5584371b73bd5dd0a53096ed2d14"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.6"
+        },
+        "timestamp": "2025-05-07T10:09:46.65000795"
+    }
+}
\ No newline at end of file
diff --git a/nextflow.config b/nextflow.config
index 1446dca..f331479 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -24,6 +24,10 @@ params {
     interproscan_database = null
     interproscan_database_version = null
 
+    // Secondary structure prediction (s4pred)
+    skip_s4pred   = false
+    s4pred_outfmt = 'ss2'  // ["ss2", "fas", "horiz"]
+
     // MultiQC options
     multiqc_config = null
     multiqc_title = null
diff --git a/nextflow_schema.json b/nextflow_schema.json
index d9d6570..b18e0eb 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -262,6 +262,26 @@
                     "help": "Instead of just removing by similar identifier, the tool also removes duplicate sequences."
                 }
             }
+        },
+        "prediction_params": {
+            "title": "Prediction parameters",
+            "type": "object",
+            "description": "Use these parameters to control the flow of the secondary structure prediction execution.",
+            "properties": {
+                "skip_s4pred": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-ban",
+                    "description": "Skip the secondary structure prediction.",
+                    "help": "Skips the prediction of the secondary structures of sequences with the s4pred software."
+                },
+                "s4pred_outfmt": {
+                    "type": "string",
+                    "default": "ss2",
+                    "description": "Choose the output format (i.e., 'ss2', 'fas', 'horiz') for the s4pred per amino acid probability predictions (i.e., α-helix, β-strand, coil).",
+                    "help_text": "ss2 is the default and it corresponds to the PSIPRED vertical format (PSIPRED VFORMAT). The fas output returns the sequence FASTA file with the predicted secondary structure concatenated on a second line. The horiz option outputs the results in the PSIPRED horizontal format (PSIPRED HFORMAT).",
+                    "enum": ["ss2", "fas", "horiz"]
+                }
+            }
         }
     },
     "allOf": [
@@ -279,6 +299,9 @@
         },
         {
             "$ref": "#/$defs/quality_check_params"
+        },
+        {
+            "$ref": "#/$defs/prediction_params"
         }
     ]
 }
diff --git a/subworkflows/local/utils_nfcore_proteinannotator_pipeline/main.nf b/subworkflows/local/utils_nfcore_proteinannotator_pipeline/main.nf
index 88b9e72..99717b2 100644
--- a/subworkflows/local/utils_nfcore_proteinannotator_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_proteinannotator_pipeline/main.nf
@@ -180,10 +180,13 @@ def toolCitationText() {
         params.skip_preprocessing ? "" : "Input sequences were preprocessed with SeqKit (gap trimming, length filtering, validation, duplicate removal) (Shen et al. 2024)."
     ].join(' ').trim()
 
+    def prediction_text = params.skip_s4pred ? "" : "Secondary structures were predicted via the s4pred software (Moffat et al. 2021)."
+
     def postprocessing_text = "Run statistics were reported using MultiQC (Ewels et al. 2016)."
 
     def citation_text = [
         quality_check_text,
+        prediction_text,
         postprocessing_text
     ].join(' ').trim()
 
@@ -196,10 +199,13 @@ def toolBibliographyText() {
         params.skip_preprocessing ? '' : '<li>Shen, W., Sipos, B., & Zhao, L. (2024). SeqKit2: A Swiss army knife for sequence and alignment processing. Imeta, 3(3), e191. doi: <a href="https://doi.org/10.1002/imt2.191">10.1002/imt2.191</a></li>'
     ].join(' ').trim()
 
+    def prediction_text = params.skip_s4pred ? '' : '<li>Moffat, L., & Jones, D. T. (2021). Increasing the accuracy of single sequence prediction methods using a deep semi-supervised learning framework. Bioinformatics, 37(21), 3744-3751. doi: <a href="https://doi.org/10.1093/bioinformatics/btab491">10.1093/bioinformatics/btab491</a></li>'
+
     def postprocessing_text = '<li>Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics, 32(19), 3047–3048. doi: <a href="https://doi.org/10.1093/bioinformatics/btw354">10.1093/bioinformatics/btw354</a></li>'
 
     def reference_text = [
         quality_check_text,
+        prediction_text,
         postprocessing_text
     ].join(' ').trim()
 
diff --git a/workflows/proteinannotator.nf b/workflows/proteinannotator.nf
index 1334a3d..98b8545 100644
--- a/workflows/proteinannotator.nf
+++ b/workflows/proteinannotator.nf
@@ -5,6 +5,7 @@
 */
 include { FAA_SEQFU_SEQKIT       } from '../subworkflows/nf-core/faa_seqfu_seqkit/main'
 include { FUNCTIONAL_ANNOTATION  } from '../subworkflows/local/functional_annotation'
+include { S4PRED_RUNMODEL        } from '../modules/nf-core/s4pred/runmodel/main'
 include { MULTIQC                } from '../modules/nf-core/multiqc/main'
 include { paramsSummaryMap       } from 'plugin/nf-schema'
 include { paramsSummaryMultiqc   } from '../subworkflows/nf-core/utils_nfcore_pipeline'
@@ -44,6 +45,9 @@ workflow PROTEINANNOTATOR {
     FUNCTIONAL_ANNOTATION( ch_samplesheet_updated )
     ch_versions = ch_versions.mix( FUNCTIONAL_ANNOTATION.out.versions.first() )
 
+    S4PRED_RUNMODEL( ch_samplesheet_updated )
+    ch_versions = ch_versions.mix( S4PRED_RUNMODEL.out.versions.first() )
+
     //
     // Collate and save software versions
     //

From 6ba7d5599050a5dbf133a2d6d741b696cf0dadf8 Mon Sep 17 00:00:00 2001
From: vagkaratzas <vagelaros.gee@gmail.com>
Date: Tue, 2 Dec 2025 10:06:05 +0000
Subject: [PATCH 2/3] nf-test  and changelog updated

---
 CHANGELOG.md               |  1 +
 tests/default.nf.test.snap | 20 ++++++++++++++++----
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 166372a..e396337 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,6 +9,7 @@ Initial release of nf-core/proteinannotator, created with the [nf-core](https://
 
 ### `Added`
 
+- [#60](https://github.com/nf-core/proteinannotator/pull/60) - Added nf-core module `S4PRED_RUNMODEL` for secondary structure prediction (i.e., α-helix, a β-strand or a coil). (by @vagkaratzas). (by @vagkaratzas)
 - [#59](https://github.com/nf-core/proteinannotator/pull/59) - Added nf-core qc and pre-processing subworkflow for amino acid sequences `FAA_SEQFU_SEQKIT`. (by @vagkaratzas). (by @vagkaratzas)
 - [#57](https://github.com/nf-core/proteinannotator/pull/57) - nf-core tools template update to 3.5.1. (by @vagkaratzas)
 - [#52](https://github.com/nf-core/proteinannotator/pull/52) - Add option to turn off InterProScan for testing
diff --git a/tests/default.nf.test.snap b/tests/default.nf.test.snap
index 6eb5308..da16c3c 100644
--- a/tests/default.nf.test.snap
+++ b/tests/default.nf.test.snap
@@ -1,8 +1,11 @@
 {
     "-profile test": {
         "content": [
-            11,
+            13,
             {
+                "S4PRED_RUNMODEL": {
+                    "s4pred": "1.2.1"
+                },
                 "SEQFU_STATS_BEFORE": {
                     "seqfu": "1.22.3"
                 },
@@ -57,7 +60,14 @@
                 "qc/T1026/T1026_after.tsv",
                 "qc/T1026/T1026_after_mqc.txt",
                 "qc/T1026/T1026_before.tsv",
-                "qc/T1026/T1026_before_mqc.txt"
+                "qc/T1026/T1026_before_mqc.txt",
+                "s4pred",
+                "s4pred/T1024",
+                "s4pred/T1024/ss2",
+                "s4pred/T1024/ss2/T1024.ss2",
+                "s4pred/T1026",
+                "s4pred/T1026/ss2",
+                "s4pred/T1026/ss2/T1026.ss2"
             ],
             [
                 "multiqc_T1024_after.txt:md5,f2a552d4750ff8360941b10cec141499",
@@ -76,13 +86,15 @@
                 "T1026_after.tsv:md5,052ba564eabda203298ffc26ef80b7ab",
                 "T1026_after_mqc.txt:md5,3534726223f5a24dedda4446fd202404",
                 "T1026_before.tsv:md5,052ba564eabda203298ffc26ef80b7ab",
-                "T1026_before_mqc.txt:md5,3534726223f5a24dedda4446fd202404"
+                "T1026_before_mqc.txt:md5,3534726223f5a24dedda4446fd202404",
+                "T1024.ss2:md5,6f2467c4e6974e761333bef106809e88",
+                "T1026.ss2:md5,cc788acb2aefe43fea147d9dd2b6c2c9"
             ]
         ],
         "meta": {
             "nf-test": "0.9.3",
             "nextflow": "25.10.2"
         },
-        "timestamp": "2025-12-01T14:53:54.397071161"
+        "timestamp": "2025-12-02T10:01:13.30875032"
     }
 }
\ No newline at end of file

From 0269bdd45f3391e833dcd849026e74e2a00b794c Mon Sep 17 00:00:00 2001
From: vagkaratzas <vagelaros.gee@gmail.com>
Date: Tue, 2 Dec 2025 12:31:47 +0000
Subject: [PATCH 3/3] use skip_s4pred flag, removed changelog typos

---
 CHANGELOG.md                  | 4 ++--
 main.nf                       | 3 ++-
 workflows/proteinannotator.nf | 7 +++++--
 3 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index e396337..f9e3ad7 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,8 +9,8 @@ Initial release of nf-core/proteinannotator, created with the [nf-core](https://
 
 ### `Added`
 
-- [#60](https://github.com/nf-core/proteinannotator/pull/60) - Added nf-core module `S4PRED_RUNMODEL` for secondary structure prediction (i.e., α-helix, a β-strand or a coil). (by @vagkaratzas). (by @vagkaratzas)
-- [#59](https://github.com/nf-core/proteinannotator/pull/59) - Added nf-core qc and pre-processing subworkflow for amino acid sequences `FAA_SEQFU_SEQKIT`. (by @vagkaratzas). (by @vagkaratzas)
+- [#60](https://github.com/nf-core/proteinannotator/pull/60) - Added nf-core module `S4PRED_RUNMODEL` for secondary structure prediction (i.e., α-helix, a β-strand or a coil). (by @vagkaratzas)
+- [#59](https://github.com/nf-core/proteinannotator/pull/59) - Added nf-core qc and pre-processing subworkflow for amino acid sequences `FAA_SEQFU_SEQKIT`. (by @vagkaratzas)
 - [#57](https://github.com/nf-core/proteinannotator/pull/57) - nf-core tools template update to 3.5.1. (by @vagkaratzas)
 - [#52](https://github.com/nf-core/proteinannotator/pull/52) - Add option to turn off InterProScan for testing
 - [#51](https://github.com/nf-core/proteinannotator/pull/51) - Update to nf-core/tools v3.3.1
diff --git a/main.nf b/main.nf
index 9e9e9c8..09e045c 100644
--- a/main.nf
+++ b/main.nf
@@ -39,7 +39,8 @@ workflow NFCORE_PROTEINANNOTATOR {
     //
     PROTEINANNOTATOR (
         samplesheet,
-        params.skip_preprocessing
+        params.skip_preprocessing,
+        params.skip_s4pred
     )
     emit:
     multiqc_report = PROTEINANNOTATOR.out.multiqc_report // channel: /path/to/multiqc_report.html
diff --git a/workflows/proteinannotator.nf b/workflows/proteinannotator.nf
index 98b8545..34a48d8 100644
--- a/workflows/proteinannotator.nf
+++ b/workflows/proteinannotator.nf
@@ -25,6 +25,7 @@ workflow PROTEINANNOTATOR {
     take:
     ch_samplesheet      // channel: samplesheet read in from --input
     skip_preprocessing  // boolean
+    skip_s4pred         // boolean
 
     main:
 
@@ -45,8 +46,10 @@ workflow PROTEINANNOTATOR {
     FUNCTIONAL_ANNOTATION( ch_samplesheet_updated )
     ch_versions = ch_versions.mix( FUNCTIONAL_ANNOTATION.out.versions.first() )
 
-    S4PRED_RUNMODEL( ch_samplesheet_updated )
-    ch_versions = ch_versions.mix( S4PRED_RUNMODEL.out.versions.first() )
+    if (!skip_s4pred) {
+        S4PRED_RUNMODEL( ch_samplesheet_updated )
+        ch_versions = ch_versions.mix( S4PRED_RUNMODEL.out.versions.first() )
+    }
 
     //
     // Collate and save software versions