nf-core · jscgh · Mar 12, 2026 · Mar 12, 2026 · Mar 12, 2026 · Mar 12, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -121,7 +121,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [[#503](https://github.com/nf-core/proteinfold/issues/503)] - Add checkIfExists validation to user-provided database paths across all prepare DB subworkflows.
 - [[#507](https://github.com/nf-core/proteinfold/issues/507)] - Implement missing full tests and check that the others work before release 2.0.0.
 - [[PR #509](https://github.com/nf-core/proteinfold/pulls/509)] - Setup gpu environment for AWS full tests.
+- [[PR #527](https://github.com/nf-core/proteinfold/pulls/527)] - Auto-detect multimer vs monomer and validate unique split.
 - [[PR #538](https://github.com/nf-core/proteinfold/pulls/538)] - Fix alphafold2_random_seed type.
+- [[PR #549](https://github.com/nf-core/proteinfold/pulls/549)] - Create `EXTRACT_METRICS` module and remove extract_metrics.py from AlphaFold2 module.
+- [[PR #554](https://github.com/nf-core/proteinfold/pulls/554)] - Remove extract_metrics.py from RoseTTAFold_All_Atom module.
 
 ### Parameters
 

diff --git a/conf/dbs.config b/conf/dbs.config
@@ -11,12 +11,13 @@ params {
 
     // Dated prefixes, can be modified for alternate versions
     alphafold2_params_prefix   = "alphafold_params_2022-12-06"
+    colabfold_params_prefix    = "alphafold_params_2022-12-06"
     uniref30_prefix            = "UniRef30_2023_02"
 
     // AlphaFold2 links
     alphafold2_bfd_link             = 'https://storage.googleapis.com/alphafold-databases/casp14_versions/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt.tar.gz'
     alphafold2_small_bfd_link       = 'https://storage.googleapis.com/alphafold-databases/reduced_dbs/bfd-first_non_consensus_sequences.fasta.gz'
-    alphafold2_params_link          = 'https://storage.googleapis.com/alphafold/alphafold_params_2022-12-06.tar'
+    alphafold2_params_link          = "https://storage.googleapis.com/alphafold/${params.alphafold2_params_prefix}.tar"
     alphafold2_mgnify_link          = 'https://ftp.ebi.ac.uk/pub/databases/metagenomics/peptide_database/2024_04/mgy_clusters.fa.gz'
     alphafold2_pdb70_link           = 'https://wwwuser.gwdguser.de/~compbiol/data/hhsuite/databases/hhsuite_dbs/pdb70_from_mmcif_220313.tar.gz'
     alphafold2_pdb_mmcif_link       = 'rsync.rcsb.org::ftp_data/structures/divided/mmCIF/' //Other sources available: 'rsync.rcsb.org::ftp_data/structures/divided/mmCIF/' ftp.pdbj.org::ftp_data/structures/divided/mmCIF/ rsync.ebi.ac.uk::pub/databases/pdb/data/structures/divided/mmCIF/
@@ -78,19 +79,14 @@ params {
     boltz2_mols_path         = "${params.boltz_db}/params/mols/"
 
     // Colabfold links
-    colabfold_db_link       = 'https://opendata.mmseqs.org/colabfold/colabfold_envdb_202108.db.tar.gz'
-    colabfold_uniref30_link = 'https://opendata.mmseqs.org/colabfold/uniref30_2302.db.tar.gz'
+    colabfold_db_link                 = 'https://opendata.mmseqs.org/colabfold/colabfold_envdb_202108.db.tar.gz'
+    colabfold_uniref30_link           = 'https://opendata.mmseqs.org/colabfold/uniref30_2302.db.tar.gz'
+    colabfold_alphafold2_params_link  = "https://storage.googleapis.com/alphafold/${params.colabfold_params_prefix}.tar"
 
     // Colabfold paths
     colabfold_envdb_path             = "${params.colabfold_db}/colabfold_envdb/*"
     colabfold_uniref30_path          = "${params.colabfold_db}/colabfold_uniref30/*"
-    // Are all these params options needed?
-    colabfold_alphafold2_params_tags = [
-        "alphafold2_multimer_v1" : "alphafold_params_colab_2021-10-27",
-        "alphafold2_multimer_v2" : "alphafold_params_colab_2022-03-02",
-        "alphafold2_multimer_v3" : "alphafold_params_colab_2022-12-06",
-        "alphafold2_ptm"         : "alphafold_params_2021-07-14"
-    ]
+    colabfold_alphafold2_params_path = "${params.colabfold_db}/params/${params.colabfold_params_prefix}"
 
     // RoseTTAFold_All_Atom links
     rosettafold_all_atom_uniref30_link      = 'https://wwwuser.gwdguser.de/~compbiol/uniclust/2023_02/UniRef30_2023_02_hhsuite.tar.gz'

diff --git a/conf/modules_alphafold2.config b/conf/modules_alphafold2.config
@@ -102,16 +102,6 @@ process {
             params.alphafold2_random_seed ? "--random_seed=${params.alphafold2_random_seed}" : ''
         ].join(' ').trim()
         publishDir = [
-            [
-                path: { "${params.outdir}/alphafold2/${params.alphafold2_mode}/${meta.id}" },
-                mode: 'copy',
-                saveAs: { filename ->
-                    if(filename.endsWith('_pae.tsv')){
-                        "paes/$filename"
-                    } else { filename }
-                },
-                pattern: '*.tsv'
-            ],
             [
                 enabled: params.save_intermediates,
                 path: { "${params.outdir}/alphafold2/${params.alphafold2_mode}/${meta.id}/" },
@@ -163,16 +153,6 @@ process {
             params.alphafold2_random_seed ? "--random_seed=${params.alphafold2_random_seed}" : ''
         ].join(' ').trim()
         publishDir = [
-            [
-                path: { "${params.outdir}/alphafold2/${params.alphafold2_mode}/${meta.id}" },
-                mode: 'copy',
-                saveAs: { filename ->
-                    if(filename.endsWith('_pae.tsv')){
-                        "paes/$filename"
-                    } else { filename }
-                },
-                pattern: '*.tsv'
-            ],
             [
                 enabled: params.save_intermediates,
                 path: { "${params.outdir}/alphafold2/${params.alphafold2_mode}/${meta.id}/" },
@@ -187,4 +167,27 @@ process {
             ]
         ]
     }
+
+    withName: 'EXTRACT_METRICS_AF2_STANDARD' {
+        container = 'nf-core/proteinfold_alphafold2_standard:2.0.0'
+    }
+
+    withName: 'EXTRACT_METRICS_AF2_PRED' {
+        container = 'nf-core/proteinfold_alphafold2_pred:2.0.0'
+    }
+
+    withName: 'EXTRACT_METRICS_AF2_STANDARD|EXTRACT_METRICS_AF2_PRED|EXTRACT_METRICS' {
+        publishDir = [
+            [
+                path: { "${params.outdir}/alphafold2/${params.alphafold2_mode}/${meta.id}" },
+                mode: 'copy',
+                saveAs: { filename ->
+                    if(filename.endsWith('_pae.tsv')){
+                        "paes/$filename"
+                    } else { filename }
+                },
+                pattern: '*.tsv'
+            ]
+        ]
+    }
 }
diff --git a/conf/modules_boltz.config b/conf/modules_boltz.config
@@ -14,7 +14,7 @@ process {
     // Provide args plus configure processes to use correct directory names
     // for Boltz parameters and models, which are downloaded as part of the workflow
     withName: '.*ARIA2_COLABFOLD_PARAMS:UNTAR' {
-        ext.prefix = { "${params.colabfold_alphafold2_params_tags[params.colabfold_model_preset] }" }
+        ext.prefix = { "${params.colabfold_params_prefix}" }
         publishDir = [
             path: {"${params.outdir}/DBs/${params.mode}/params"},
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },

diff --git a/conf/modules_colabfold.config b/conf/modules_colabfold.config
@@ -21,7 +21,7 @@ process {
 
     // Configure UNTAR processes to use correct directory names
     withName: '.*ARIA2_COLABFOLD_PARAMS:UNTAR' {
-        ext.prefix = { "${params.colabfold_alphafold2_params_tags[params.colabfold_model_preset] }" }
+        ext.prefix = { "${params.colabfold_params_prefix}" }
         publishDir = [
             path: {"${params.outdir}/DBs/${params.mode}/params"},
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },

diff --git a/conf/modules_rosettafold_all_atom.config b/conf/modules_rosettafold_all_atom.config
@@ -25,33 +25,39 @@ process {
         }
         publishDir  = [
             [
-                path: { "${params.outdir}/rosettafold_all_atom/${meta.id}" },
+                enabled: params.save_intermediates,
+                path: { "${params.outdir}/rosettafold_all_atom/${meta.id}/raw" },
                 mode: 'copy',
-                pattern: '*_plddt.tsv'
+                pattern: 'raw/**',
+                saveAs: { filename -> filename.toString().replaceFirst(/^raw\//, '') }
             ],
             [
-                path: { "${params.outdir}/rosettafold_all_atom/${meta.id}" },
+                path: { "${params.outdir}/rosettafold_all_atom/top_ranked_structures" },
                 mode: 'copy',
-                saveAs: { filename -> "paes/$filename" },
-                pattern: '*_[0-5]_pae.tsv'
-            ],
+                saveAs: { "${meta.id}.pdb" },
+                pattern: '*_rosettafold_all_atom.pdb'
+            ]
+        ]
+    }
+
+    withName: 'EXTRACT_METRICS_RFAA' {
+        container = 'nf-core/proteinfold_rosettafold_all_atom:2.0.0'
+        publishDir = [
             [
                 path: { "${params.outdir}/rosettafold_all_atom/${meta.id}" },
                 mode: 'copy',
-                pattern: '*_rosettafold_all_atom_msa.tsv'
+                pattern: '*_plddt.tsv'
             ],
             [
-                enabled: params.save_intermediates,
-                path: { "${params.outdir}/rosettafold_all_atom/${meta.id}/raw" },
+                path: { "${params.outdir}/rosettafold_all_atom/${meta.id}" },
                 mode: 'copy',
-                pattern: 'raw/**',
-                saveAs: { filename -> filename.toString().replaceFirst(/^raw\//, '') }
+                saveAs: { filename -> "paes/$filename" },
+                pattern: '*_[0-9]_pae.tsv'
             ],
             [
-                path: { "${params.outdir}/rosettafold_all_atom/top_ranked_structures" },
+                path: { "${params.outdir}/rosettafold_all_atom/${meta.id}" },
                 mode: 'copy',
-                saveAs: { "${meta.id}.pdb" },
-                pattern: '*_rosettafold_all_atom.pdb'
+                pattern: '*_rosettafold_all_atom_msa.tsv'
             ]
         ]
     }

diff --git a/conf/test.config b/conf/test.config
@@ -28,7 +28,7 @@ params {
     // Input data to test alphafold2 analysis
     mode            = 'alphafold2'
     alphafold2_mode = 'standard'
-    input           = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
+    input           = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet.csv'
     alphafold2_db   = "${projectDir}/assets/dummy_db_dir"
 }
 

diff --git a/conf/test_alphafold3_download.config b/conf/test_alphafold3_download.config
@@ -27,7 +27,7 @@ params {
 
     // Input data to test alphafold2 analysis
     mode                   = 'alphafold3'
-    input                  = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
+    input                  = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet.csv'
     alphafold3_params_path = "${projectDir}/assets/dummy_db_dir"
 }
 

diff --git a/conf/test_alphafold3_standard.config b/conf/test_alphafold3_standard.config
@@ -27,7 +27,7 @@ params {
 
     // Input data to test alphafold2 analysis
     mode            = 'alphafold3'
-    input           = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
+    input           = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet.csv'
     alphafold3_db   = "${projectDir}/assets/dummy_db_dir"
 }
 

diff --git a/conf/test_alphafold_download.config b/conf/test_alphafold_download.config
@@ -28,7 +28,7 @@ params {
     // Input data to test alphafold2 analysis
     mode            = 'alphafold2'
     alphafold2_mode = 'standard'
-    input           = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
+    input           = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet.csv'
 }
 
 process {

diff --git a/conf/test_alphafold_split.config b/conf/test_alphafold_split.config
@@ -28,7 +28,7 @@ params {
     // Input data to test alphafold2 splitting MSA from prediction analysis
     mode            = 'alphafold2'
     alphafold2_mode = 'split_msa_prediction'
-    input           = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
+    input           = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet.csv'
     alphafold2_db   = "${projectDir}/assets/dummy_db_dir"
 }
 

diff --git a/conf/test_boltz.config b/conf/test_boltz.config
@@ -27,7 +27,7 @@ params {
     // Input data for full test of boltz
     mode                    = 'boltz'
     colabfold_model_preset  = 'alphafold2_ptm'
-    input                   = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
+    input                   = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet.csv'
     colabfold_db            = "${projectDir}/assets/dummy_db_dir"
     boltz_db                = "${projectDir}/assets/dummy_db_dir"
 }

diff --git a/conf/test_colabfold_download.config b/conf/test_colabfold_download.config
@@ -28,7 +28,7 @@ params {
     // Input data to test colabfold analysis
     mode             = 'colabfold'
     use_msa_server   = true
-    input            = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
+    input            = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet.csv'
 }
 
 process {

diff --git a/conf/test_colabfold_local.config b/conf/test_colabfold_local.config
@@ -26,7 +26,7 @@ params {
     // Input data to test colabfold with the colabfold webserver analysis
     mode             = 'colabfold'
     colabfold_db     = "${projectDir}/assets/dummy_db_dir"
-    input            = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
+    input            = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet.csv'
 }
 
 process {

diff --git a/conf/test_colabfold_webserver.config b/conf/test_colabfold_webserver.config
@@ -27,7 +27,7 @@ params {
     mode             = 'colabfold'
     use_msa_server   = true
     colabfold_db     = "${projectDir}/assets/dummy_db_dir"
-    input            = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
+    input            = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet.csv'
 }
 
 process {

diff --git a/conf/test_esmfold.config b/conf/test_esmfold.config
@@ -26,7 +26,7 @@ params {
     // Input data to test esmfold
     mode             = 'esmfold'
     esmfold_db       = "${projectDir}/assets/dummy_db_dir"
-    input            = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
+    input            = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet.csv'
 }
 
 process {

diff --git a/conf/test_full.config b/conf/test_full.config
@@ -18,6 +18,14 @@ params {
     mode            = 'alphafold2'
     alphafold2_mode = 'standard'
     use_gpu         = true
-    input           = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
+    input           = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet.csv'
     alphafold2_db   = 's3://proteinfold-dataset/test-data/mini_dbs'
 }
+
+docker.pullStrategy = 'lazy'
+
+process {
+    withName: 'RUN_ALPHAFOLD2' {
+        beforeScript = System.getenv('TOWER_WORKFLOW_ID') ? 'unset LD_LIBRARY_PATH && export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu:/usr/local/nvidia/lib64:/usr/local/nvidia/lib && export OPENMM_CUDA_COMPILER=/opt/conda/bin/nvcc && export TMPDIR=/tmp' : null
+    }
+}
diff --git a/conf/test_full_alphafold_multimer.config b/conf/test_full_alphafold_multimer.config
@@ -19,6 +19,21 @@ params {
     alphafold2_mode         = 'standard'
     alphafold2_model_preset = 'multimer'
     use_gpu                 = true
-    input                   = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet_multimer.csv'
+    input                   = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet_multimer.csv'
     alphafold2_db           = 's3://proteinfold-dataset/test-data/mini_dbs'
 }
+
+docker.pullStrategy = 'lazy'
+
+process {
+    withName: 'RUN_ALPHAFOLD2' {
+        memory = '60 GB'
+        beforeScript = System.getenv('TOWER_WORKFLOW_ID') ? 'unset LD_LIBRARY_PATH && export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu:/usr/local/nvidia/lib64:/usr/local/nvidia/lib && export OPENMM_CUDA_COMPILER=/opt/conda/bin/nvcc && export TMPDIR=/tmp' : null
+    }
+}
+
+process {
+    withName: 'RUN_ALPHAFOLD2_PRED' {
+        ext.args    = "--num_multimer_predictions_per_model 1"
+    }
+}
diff --git a/conf/test_full_alphafold_split.config b/conf/test_full_alphafold_split.config
@@ -18,6 +18,14 @@ params {
     mode            = 'alphafold2'
     alphafold2_mode = 'split_msa_prediction'
     use_gpu         = true
-    input           = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
+    input           = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet.csv'
     alphafold2_db   = 's3://proteinfold-dataset/test-data/mini_dbs'
 }
+
+docker.pullStrategy = 'lazy'
+
+process {
+    withName: 'RUN_ALPHAFOLD2_PRED' {
+        beforeScript = System.getenv('TOWER_WORKFLOW_ID') ? 'unset LD_LIBRARY_PATH && export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu:/usr/local/nvidia/lib64:/usr/local/nvidia/lib && export OPENMM_CUDA_COMPILER=/opt/conda/bin/nvcc && export TMPDIR=/tmp' : null
+    }
+}
diff --git a/conf/test_full_boltz.config b/conf/test_full_boltz.config
@@ -15,9 +15,19 @@ params {
     config_profile_description = 'Minimal test dataset to check pipeline function'
 
     // Input data for full test of boltz
-    mode                    = 'boltz'
-    colabfold_model_preset  = 'alphafold2_ptm'
-    use_gpu                 = true
-    input                   = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
-    colabfold_db            = 's3://proteinfold-dataset/test-data/mini_dbs'
+    mode                   = 'boltz'
+    colabfold_model_preset = 'alphafold2_ptm'
+    use_gpu                = true
+    input                  = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet.csv'
+    colabfold_db           = 's3://proteinfold-dataset/test-data/mini_dbs'
+    boltz_db               = 's3://proteinfold-dataset/test-data/mini_dbs/'
+}
+
+docker.pullStrategy = 'lazy'
+
+process {
+    withName: 'RUN_BOLTZ' {
+        memory = '60 GB'
+        ext.args    = '--output_format "pdb" --write_full_pae --cache ./ --recycling_steps 1'
+    }
 }
diff --git a/conf/test_full_colabfold_local.config b/conf/test_full_colabfold_local.config
@@ -16,15 +16,23 @@ params {
 
 
     // Input data to test colabfold with a local server analysis
-    mode                   = 'colabfold'
-    colabfold_model_preset = 'alphafold2_ptm'
-    use_gpu                = true
-    input                  = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
-    colabfold_db           = 's3://proteinfold-dataset/test-data/mini_dbs'
+    mode                    = 'colabfold'
+    colabfold_model_preset  = 'alphafold2_ptm'
+    use_gpu                 = true
+    input                   = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v2.0/samplesheet.csv'
+    colabfold_db            = 's3://proteinfold-dataset/test-data/mini_dbs'
+    colabfold_use_gpu_relax = false
+    colabfold_use_amber     = false
+    colabfold_use_templates = false
 }
 
+docker.pullStrategy = 'lazy'
+
 process {
     withName:MMSEQS_COLABFOLDSEARCH {
         memory = 16.GB
     }
+    withName: 'COLABFOLD_BATCH' {
+        beforeScript = System.getenv('TOWER_WORKFLOW_ID') ? 'unset LD_LIBRARY_PATH && export LD_LIBRARY_PATH="/usr/lib/x86_64-linux-gnu:/usr/local/nvidia/lib64:/usr/local/nvidia/lib:/usr/local/lib:/usr/local/targets/x86_64-linux/lib:/usr/local/cuda-12.9/targets/x86_64-linux/lib:/opt/conda/lib"' : null
+    }
 }