Updated rosettafold_all_atom files

Australian-Structural-Biology-Computing · Nov 15, 2024 · 8cc32e1 · 8cc32e1
1 parent a19d4d4
commit 8cc32e1
Show file tree

Hide file tree

Showing 3 changed files with 29 additions and 15 deletions.
diff --git a/conf/dbs.config b/conf/dbs.config
@@ -49,14 +49,26 @@ params {
     ]
 
     // RoseTTAFold links
-    uniref30              = 'http://wwwuser.gwdg.de/~compbiol/uniclust/2020_06/UniRef30_2020_06_hhsuite.tar.gz'
+	uniref30              = 'http://wwwuser.gwdg.de/~compbiol/uniclust/2020_06/UniRef30_2020_06_hhsuite.tar.gz'
     pdb100                = 'https://files.ipd.uw.edu/pub/RoseTTAFold/pdb100_2021Mar03.tar.gz'
 
     // RoseTTAFold paths
     uniref30_rosettafold_all_atom_path  = "${params.rosettafold_all_atom_db}/uniref30/UniRef30_2020_06/*"
     pdb100_path                         = "${params.rosettafold_all_atom_db}/pdb100_2021Mar03/*"
     bfd_rosettafold_all_atom_path       = "${params.rosettafold_all_atom_db}/bfd/*"
 
+    // Helixfold3 links
+    uniclust30_link             = 'https://storage.googleapis.com/alphafold-databases/casp14_versions/uniclust30_2018_08_hhsuite.tar.gz'
+    ccd_preprocessed_link       = 'https://paddlehelix.bd.bcebos.com/HelixFold3/CCD/ccd_preprocessed_etkdg.pkl.gz'
+    rfam_link                   = 'https://paddlehelix.bd.bcebos.com/HelixFold3/MSA/Rfam-14.9_rep_seq.fasta'
+    helixfold3_init_models_link = 'https://paddlehelix.bd.bcebos.com/HelixFold3/params/HelixFold3-params-240814.zip'
+
+    // Helixfold3 paths
+    uniclust30_path             = "${params.helixfold3_db}/uniclust30/*"
+    ccd_preprocessed_path       = "${params.helixfold3_db}/ccd_preprocessed_etkdg.pkl.gz"
+    rfam_path                   = "${params.helixfold3_db}/Rfam-14.9_rep_seq.fasta"
+    helixfold3_init_models_path = "${params.helixfold3_db}"
+
     // Esmfold links
     esmfold_3B_v1                        = 'https://dl.fbaipublicfiles.com/fair-esm/models/esmfold_3B_v1.pt'
     esm2_t36_3B_UR50D                    = 'https://dl.fbaipublicfiles.com/fair-esm/models/esm2_t36_3B_UR50D.pt'

diff --git a/modules/local/run_rosettafold_all_atom.nf b/modules/local/run_rosettafold_all_atom.nf
@@ -1,10 +1,10 @@
 /*
- * Run RoseTTAFold_All_Atom
+ * Run RoseTTAFold_All_Atom 
  */
 process RUN_ROSETTAFOLD_ALL_ATOM {
     tag "$meta.id"
-    label 'process_medium'
     label 'gpu_compute'
+    label 'process_medium'
 
     // Exit if running this module with -profile conda / -profile mamba
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
@@ -18,11 +18,12 @@ process RUN_ROSETTAFOLD_ALL_ATOM {
     path ('bfd/*')
     path ('UniRef30_2020_06/*')
     path ('pdb100_2021Mar03/*')
-
+    
     output:
     path ("${fasta.baseName}*")
-    tuple val(meta), path ("*pdb"), emit: pdb
-    tuple val(meta), path ("*_mqc.tsv"), emit: multiqc
+    tuple val(meta), path ("${meta.id}_rosettafold_all_atom.pdb")   , emit: main_pdb
+    tuple val(meta), path ("*pdb")                                  , emit: pdb
+    tuple val(meta), path ("*_mqc.tsv")                             , emit: multiqc
     path "versions.yml", emit: versions
 
     when:
@@ -33,14 +34,15 @@ process RUN_ROSETTAFOLD_ALL_ATOM {
     ln -s /app/RoseTTAFold-All-Atom/* .
 
     mamba run --name RFAA python -m rf2aa.run_inference \
-    --config-dir $PWD \
-    --config-path $PWD \
+    loader_params.MAXCYCLE=1 \
+    checkpoint_path="/srv/scratch/sbf/rfaa/RFAA_paper_weights.pt" \
+    --config-dir /app/RoseTTAFold-All-Atom/rf2aa/config/inference \
     --config-name "${fasta}"
 
-    cp "${fasta.baseName}".pdb ./"${fasta.baseName}".rosettafold_all_atom.pdb
-    awk '{print \$6"\\t"\$11}' "${fasta.baseName}".rosettafold_all_atom.pdb | uniq > plddt.tsv
-    echo -e Positions"\\t" > header.tsv
-    cat header.tsv plddt.tsv > "${fasta.baseName}"_plddt_mqc.tsv
+    cp "${fasta.baseName}".pdb ./"${meta.id}"_rosettafold_all_atom.pdb
+    awk '{print \$6"\\t"\$11}' "${meta.id}"_rosettafold_all_atom.pdb | uniq > plddt.tsv
+    echo -e Positions"\\t""${meta.id}"_rosettafold_all_atom.pdb > header.tsv
+    cat header.tsv plddt.tsv > "${meta.id}"_plddt_mqc.tsv
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -50,8 +52,8 @@ process RUN_ROSETTAFOLD_ALL_ATOM {
 
     stub:
     """
-    touch ./"${fasta.baseName}".rosettafold_all_atom.pdb
-    touch ./"${fasta.baseName}"_mqc.tsv
+    touch ./"${meta.id}"_rosettafold_all_atom.pdb
+    touch ./"${meta.id}"_mqc.tsv
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

diff --git a/workflows/rosettafold_all_atom.nf b/workflows/rosettafold_all_atom.nf
@@ -45,7 +45,7 @@ workflow ROSETTAFOLD_ALL_ATOM {
 
     main:
     ch_multiqc_files = Channel.empty()
-
+    
     //
     // SUBWORKFLOW: Run Rosettafold_All_Atom
     //
-Original file line number
+Diff line change
@@ Expand Up / @@ -45,7 +45,7 @@ workflow ROSETTAFOLD_ALL_ATOM { @@
         main:
         ch_multiqc_files = Channel.empty()
         //
         // SUBWORKFLOW: Run Rosettafold_All_Atom
         //
@@ Expand Down @@