Address review comments and update documentation

.github/CONTRIBUTING.md

@@ -29,7 +29,7 @@ If you're not used to this workflow with git, you can start with some [docs from
 You have the option to test your changes locally by running the pipeline. For receiving warnings about process selectors and other `debug` information, it is recommended to use the debug profile. Execute all the tests with the following command:
 
 ```bash
-nf-test test --profile debug,test,docker --verbose
+nextflow run . --profile debug,test,docker --outdir <OUTDIR>
 ```
 
 When you create a pull request with changes, [GitHub Actions](https://github.com/features/actions) will run automatic tests.

.github/workflows/ci.yml

@@ -26,6 +26,15 @@ jobs:
         NXF_VER:
           - "23.04.0"
           - "latest-everything"
+        parameters:
+          - "test"
+          - "test_alphafold2_split"
+          - "test_alphafold2_download"
+          - "test_colabfold_local"
+          - "test_colabfold_webserver"
+          - "test_colabfold_download"
+          - "test_esmfold"
+
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
@@ -38,102 +47,6 @@ jobs:
       - name: Disk space cleanup
         uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
 
-      - name: Run pipeline with test data
-        run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results
-
-  test_alphafold2_split:
-    name: Test alphafold2 split workflow
-    if: ${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/proteinfold') }}
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out pipeline code
-        uses: actions/checkout@v2
-
-      - name: Install Nextflow
-        run: |
-          wget -qO- get.nextflow.io | bash
-          sudo mv nextflow /usr/local/bin/
-      - name: Run pipeline with stub-run in alphafold2 split mode
-        run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test_alphafold2_split,docker --outdir ./results
-
-  test_alphafold2_download:
-    name: Test alphafold2 download workflow
-    if: ${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/proteinfold') }}
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out pipeline code
-        uses: actions/checkout@v2
-
-      - name: Install Nextflow
-        run: |
-          wget -qO- get.nextflow.io | bash
-          sudo mv nextflow /usr/local/bin/
-      - name: Run pipeline with stub-run in alphafold2 standard mode (download)
-        run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test_alphafold2_download,docker --outdir ./results
-
-  test_colabfold_local:
-    name: Test Colabfold local workflow
-    if: ${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/proteinfold') }}
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out pipeline code
-        uses: actions/checkout@v2
-
-      - name: Install Nextflow
-        run: |
-          wget -qO- get.nextflow.io | bash
-          sudo mv nextflow /usr/local/bin/
-      - name: Run pipeline with stub-run in colabfold_local mode
-        run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test_colabfold_local,docker --outdir ./results
-
-  test_colabfold_webserver:
-    name: Test Colabfold webserver workflow
-    if: ${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/proteinfold') }}
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out pipeline code
-        uses: actions/checkout@v2
-
-      - name: Install Nextflow
-        run: |
-          wget -qO- get.nextflow.io | bash
-          sudo mv nextflow /usr/local/bin/
-      - name: Run pipeline with stub-run in colabfold_webserver mode
-        run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test_colabfold_webserver,docker --outdir ./results
-
-  test_colabfold_download:
-    name: Test colabfold download workflow
-    if: ${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/proteinfold') }}
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out pipeline code
-        uses: actions/checkout@v2
-
-      - name: Install Nextflow
-        run: |
-          wget -qO- get.nextflow.io | bash
-          sudo mv nextflow /usr/local/bin/
-      - name: Run pipeline with stub-run in colabfold webserver (download)
-        run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test_colabfold_download,docker --outdir ./results
-
-  test_esmfold:
-    name: Test ESMFold workflow
-    if: ${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/proteinfold') }}
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out pipeline code
-        uses: actions/checkout@v2
-
-      - name: Install Nextflow
-        run: |
-          wget -qO- get.nextflow.io | bash
-          sudo mv nextflow /usr/local/bin/
-      - name: Run pipeline with stub-run in esmfold mode
+      - name: Run pipeline with test data ${{ matrix.parameters }} profile
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test_esmfold,docker --outdir ./results
+          nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.parameters }},docker --outdir ./results_${{ matrix.parameters }}

.nf-core.yml

@@ -2,6 +2,5 @@ repository_type: pipeline
 nf_core_version: "2.14.1"
 lint:
   files_unchanged:
-    - .github/ISSUE_TEMPLATE/bug_report.yml
-    - pyproject.toml
+    - .github/CONTRIBUTING.md
   multiqc_config: false

CHANGELOG.md

@@ -35,12 +35,35 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [[#130](https://github.com/nf-core/proteinfold/issues/130)] - Add `--skip_multiqc` parameter.
 - [[PR #154](https://github.com/nf-core/proteinfold/pull/154)] - Update pipeline template to [nf-core/tools 2.14.1](https://github.com/nf-core/tools/releases/tag/2.14.1).
 - [[#148](https://github.com/nf-core/proteinfold/issues/148)] - Update Colabfold DBs.
+- [[PR #159](https://github.com/nf-core/proteinfold/pull/159)] - Update `mgnify` paths to new available version.
 
 ### Parameters
 
-| Old parameter | New parameter    |
-| ------------- | ---------------- |
-|               | `--skip_multiqc` |
+| Old parameter         | New parameter                            |
+| --------------------- | ---------------------------------------- |
+| `--uniclust30`        |                                          |
+| `--bfd`               | `--bfd_link`                             |
+| `--small_bfd`         | `--small_bfd_link`                       |
+| `--alphafold2_params` | `--alphafold2_params_link`               |
+| `--mgnify`            | `--mgnify_link`                          |
+| `--pdb70`             | `--pdb70_link`                           |
+| `--pdb_mmcif`         | `--pdb_mmcif_link`                       |
+| `--pdb_obsolete`      | `--pdb_obsolete_link`                    |
+| `--uniref90`          | `--uniref90_link`                        |
+| `--pdb_seqres`        | `--pdb_seqres_link`                      |
+| `--uniprot_sprot`     | `--uniprot_sprot_link`                   |
+| `--uniprot_trembl`    | `--uniprot_trembl_link`                  |
+| `--uniclust30_path`   | `--uniref30_alphafold2_path`             |
+| `--uniref30`          | `--uniref30_colabfold_link`              |
+| `--uniref30_path`     | `--uniref30_colabfold_path`              |
+|                       | `--uniref30_alphafold2_link`             |
+|                       | `--esmfold_db`                           |
+|                       | `--esmfold_model_preset`                 |
+|                       | `--esmfold_3B_v1`                        |
+|                       | `--esm2_t36_3B_UR50D`                    |
+|                       | `--esm2_t36_3B_UR50D_contact_regression` |
+|                       | `--esmfold_params_path`                  |
+|                       | `--skip_multiqc`                         |
 
 > **NB:** Parameter has been **updated** if both old and new parameter information is present.
 > **NB:** Parameter has been **added** if just the new parameter information is present.

README.md

@@ -31,15 +31,15 @@ On release, automated continuous integration tests run the pipeline on a full-si
 
 1. Choice of protein structure prediction method:
 
-   i. [AlphaFold2](https://github.com/deepmind/alphafold)
+   i. [AlphaFold2](https://github.com/deepmind/alphafold) - Regular AlphaFold2 (MSA computation and model inference in the same process)
 
    ii. [AlphaFold2 split](https://github.com/luisas/alphafold_split) - AlphaFold2 MSA computation and model inference in separate processes
 
    iii. [ColabFold](https://github.com/sokrypton/ColabFold) - MMseqs2 API server followed by ColabFold
 
    iv. [ColabFold](https://github.com/sokrypton/ColabFold) - MMseqs2 local search followed by ColabFold
 
-   v. [ESMFold](https://github.com/facebookresearch/esm)
+   v. [ESMFold](https://github.com/facebookresearch/esm) - Regular ESM
 
 ## Usage
 
@@ -55,9 +55,9 @@ nextflow run nf-core/proteinfold \
    --outdir <OUTDIR>
 ```
 
-The pipeline takes care of downloading the databases and parameters required by AlphaFold2, Colabfold or ESMFold. In case you have already downloaded the required files, you can skip this step by providing the path to the databases in parameters using the corresponding parameter [`--alphafold2_db`], [`--colabfold_db`] or [`--esmfold_db`]
+The pipeline takes care of downloading the databases and parameters required by AlphaFold2, Colabfold or ESMFold. In case you have already downloaded the required files, you can skip this step by providing the path to the databases using the corresponding parameter [`--alphafold2_db`], [`--colabfold_db`] or [`--esmfold_db`]. Please refer to the [usage documentation](https://nf-co.re/proteinfold/usage) to check the directory structure you need to provide for each of the databases.
 
-- Typical command to run AlphaFold2 mode:
+- The typical command to run AlphaFold2 mode is shown below:
 
   ```console
   nextflow run nf-core/proteinfold \
@@ -71,7 +71,7 @@ The pipeline takes care of downloading the databases and parameters required by
       -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
   ```
 
-- Typical command to run AlphaFold2 splitting the MSA from the prediction execution:
+- Here is the command to run AlphaFold2 splitting the MSA from the prediction execution:
 
   ```console
   nextflow run nf-core/proteinfold \
@@ -86,7 +86,7 @@ The pipeline takes care of downloading the databases and parameters required by
       -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
   ```
 
-- Typical command to run colabfold_local mode:
+- Below, the command to run colabfold_local mode:
 
   ```console
   nextflow run nf-core/proteinfold \
@@ -103,7 +103,7 @@ The pipeline takes care of downloading the databases and parameters required by
       -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
   ```
 
-- Typical command to run colabfold_webserver mode:
+- The typical command to run colabfold_webserver mode would be:
 
   ```console
   nextflow run nf-core/proteinfold \
@@ -120,10 +120,11 @@ The pipeline takes care of downloading the databases and parameters required by
       -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
   ```
 
-  > **Warning**
+  [!WARNING]
+
   > If you aim to carry out a large amount of predictions using the colabfold_webserver mode, please setup and use your own custom MMSeqs2 API Server. You can find instructions [here](https://github.com/sokrypton/ColabFold/tree/main/MsaServer).
 
-- Typical command to run esmfold mode:
+- The esmfold mode can be run using the command below:
 
   ```console
   nextflow run nf-core/proteinfold \

conf/modules_alphafold2.config

@@ -15,7 +15,7 @@
 //
 
 process {
-    withName: 'GUNZIP|COMBINE_UNIPROT|DOWNLOAD_PDBMMCIF' {
+    withName: 'GUNZIP|COMBINE_UNIPROT|DOWNLOAD_PDBMMCIF|ARIA2_PDB_SEQRES' {
         publishDir = [
             path: {"${params.outdir}/DBs/${params.mode}/${params.alphafold2_mode}"},
             mode: 'symlink',

conf/test_alphafold_download.config

@@ -5,7 +5,7 @@
     Defines input files and everything required to run a fast and simple pipeline test.
 
     Use as follows:
-        nextflow run nf-core/proteinfold -profile test,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/proteinfold -profile test_alphafold2_download,<docker/singularity> --outdir <OUTDIR>
 
 ----------------------------------------------------------------------------------------
 */

conf/test_alphafold_split.config

@@ -5,7 +5,7 @@
     Defines input files and everything required to run a fast and simple pipeline test.
 
     Use as follows:
-        nextflow run nf-core/proteinfold -profile test,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/proteinfold -profile test_alphafold2_split,<docker/singularity> --outdir <OUTDIR>
 
 ----------------------------------------------------------------------------------------
 */

conf/test_colabfold_download.config

@@ -5,7 +5,7 @@
     Defines input files and everything required to run a fast and simple pipeline test.
 
     Use as follows:
-        nextflow run nf-core/proteinfold -profile test,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/proteinfold -profile test_colabfold_download,<docker/singularity> --outdir <OUTDIR>
 
 ----------------------------------------------------------------------------------------
 */

conf/test_colabfold_local.config

@@ -4,7 +4,7 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     Defines input files and everything required to run a fast and simple pipeline test.
     Use as follows:
-        nextflow run nf-core/proteinfold -profile test,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/proteinfold -profile test_colabfold_local,<docker/singularity> --outdir <OUTDIR>
 ----------------------------------------------------------------------------------------
 */
 

conf/test_colabfold_webserver.config

@@ -4,7 +4,7 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     Defines input files and everything required to run a fast and simple pipeline test.
     Use as follows:
-        nextflow run nf-core/proteinfold -profile test,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/proteinfold -profile test_colabfold_webserver,<docker/singularity> --outdir <OUTDIR>
 ----------------------------------------------------------------------------------------
 */
 

conf/test_esmfold.config

@@ -4,7 +4,7 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     Defines input files and everything required to run a fast and simple pipeline test.
     Use as follows:
-        nextflow run nf-core/proteinfold -profile test,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/proteinfold -profile test_esmfold,<docker/singularity> --outdir <OUTDIR>
 ----------------------------------------------------------------------------------------
 */
 

conf/test_full_esmfold.config

@@ -5,7 +5,7 @@
     Defines input files and everything required to run a full size pipeline test.
 
     Use as follows:
-        nextflow run nf-core/proteinfold -profile test_full_colabfold_webserver,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/proteinfold -profile test_full_esmfold,<docker/singularity> --outdir <OUTDIR>
 
 ----------------------------------------------------------------------------------------
 */

conf/test_full_esmfold_multimer.config

@@ -5,7 +5,7 @@
     Defines input files and everything required to run a full size pipeline test.
 
     Use as follows:
-        nextflow run nf-core/proteinfold -profile test_full_colabfold_webserver,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/proteinfold -profile test_full_esmfold_multimer,<docker/singularity> --outdir <OUTDIR>
 
 ----------------------------------------------------------------------------------------
 */