Add support for foldmason Guidetree and visualization

.params_2024-12-02_11-11-58.json

@@ -0,0 +1,50 @@
+{
+    "input": "https://raw.githubusercontent.com/nf-core/test-datasets/multiplesequencealign/samplesheet/v1.0/samplesheet_test_af2.csv",
+    "tools": "https://raw.githubusercontent.com/nf-core/test-datasets/multiplesequencealign/toolsheet/v1.0/toolsheet_small.csv",
+    "templates_suffix": ".pdb",
+    "optional_data_dir": null,
+    "build_consensus": true,
+    "skip_stats": false,
+    "calc_sim": true,
+    "calc_seq_stats": true,
+    "extract_plddt": true,
+    "skip_eval": false,
+    "calc_sp": true,
+    "calc_tc": true,
+    "calc_irmsd": true,
+    "calc_gaps": true,
+    "calc_tcs": true,
+    "skip_compression": false,
+    "multiqc_config": null,
+    "multiqc_title": null,
+    "multiqc_logo": null,
+    "max_multiqc_email_size": "25.MB",
+    "multiqc_methods_description": null,
+    "skip_multiqc": false,
+    "outdir": "results",
+    "publish_dir_mode": "copy",
+    "email": null,
+    "email_on_fail": null,
+    "plaintext_email": false,
+    "monochrome_logs": false,
+    "hook_url": null,
+    "help": false,
+    "help_full": false,
+    "show_hidden": false,
+    "version": false,
+    "pipelines_testdata_base_path": "https://raw.githubusercontent.com/nf-core/test-datasets/",
+    "shiny_app": "/home/luisasantus/Desktop/multiplesequencealign/bin/shiny_app",
+    "skip_shiny": false,
+    "shiny_trace_mode": "latest",
+    "config_profile_name": "Full test profile",
+    "config_profile_description": "Full test dataset to check pipeline function",
+    "custom_config_version": "master",
+    "custom_config_base": "https://raw.githubusercontent.com/nf-core/configs/master",
+    "config_profile_contact": null,
+    "config_profile_url": null,
+    "validate_params": true,
+    "igenomes_ignore": true,
+    "genomes": {
+
+    }
+}

assets/samplesheet.csv

@@ -0,0 +1,3 @@
+id,fasta,reference,optional_data
+seatoxin-ref,https://raw.githubusercontent.com/nf-core/test-datasets/multiplesequencealign/testdata/setoxin-ref.fa,https://raw.githubusercontent.com/nf-core/test-datasets/multiplesequencealign/testdata/setoxin.ref,https://raw.githubusercontent.com/nf-core/test-datasets/multiplesequencealign/testdata/structures/seatoxin-ref.tar.gz
+toxin-ref,https://raw.githubusercontent.com/nf-core/test-datasets/multiplesequencealign/testdata/toxin-ref.fa,https://raw.githubusercontent.com/nf-core/test-datasets/multiplesequencealign/testdata/toxin.ref,

assets/toolsheet.csv

@@ -0,0 +1,4 @@
+tree,args_tree,aligner,args_aligner
+,,FOLDMASON,
+FAMSA,,FAMSA,
+FAMSA,,FOLDMASON,

bin/pdbs_to_fasta.py

@@ -0,0 +1,35 @@
+#!/usr/bin/env python
+
+# read in multiple pdb files, extract the sequence and write to a fasta file
+import sys
+from Bio import PDB
+from Bio.SeqUtils import seq1
+
+
+def pdb_to_fasta(pdb_file):
+    """
+    Extract the sequence from a PDB file and format it in FASTA.
+    """
+    parser = PDB.PDBParser(QUIET=True)
+    structure = parser.get_structure(pdb_file, pdb_file)
+    fasta_sequences = []
+    file_id = pdb_file.rsplit(".", 1)[0]  # Use the file name without extension as ID
+
+    for model in structure:
+        for chain in model:
+            sequence = []
+            for residue in chain:
+                if PDB.is_aa(residue, standard=True):
+                    sequence.append(seq1(residue.resname))
+            if sequence:
+                fasta_sequences.append(f">{file_id}\n{''.join(sequence)}")
+            return "\n".join(fasta_sequences)
+
+def main():
+    pdb_files = sys.argv[1:]
+    for pdb_file in pdb_files:
+        fasta = pdb_to_fasta(pdb_file)
+        print(f"{fasta}")
+
+if __name__ == "__main__":
+    main()

bin/shiny_app/shiny_app.py

@@ -30,9 +30,9 @@
     sys.exit(1)
 
 def merge_tree_args(row):
-    if str(row["tree"]) == "nan":
+    if str(row["tree"]) == "DEFAULT":
         return "None"
-    elif str(row["args_tree"]) == "nan":
+    elif str(row["args_tree"]) == "default":
         return str(row["tree"]) + " ()"
     else:
         return str(row["tree"]) + " (" + str(row["args_tree"]) + ")"
@@ -42,7 +42,7 @@ def merge_tree_args(row):
 def merge_aligner_args(row):
     if str(row["aligner"]) == "nan":
         return "None"
-    elif str(row["args_aligner"]) == "nan":
+    elif str(row["args_aligner"]) == "default":
         return str(row["aligner"]) + " ()"
     else:
         return str(row["aligner"]) + " (" + str(row["args_aligner"]) + ")"

conf/modules.config

@@ -74,7 +74,7 @@
                     meta.args_tree ? "args: ${meta.args_tree}" : ""
                 ].join(' ').trim()
             }
-            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.argstree_clean}" }
+            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.args_tree_clean}" }
             ext.args = { "${meta.args_tree}" == "null" ? '' : "${meta.args_tree}" }
             publishDir = [
                 path: { "${params.outdir}/trees/${meta.id}" },
@@ -99,7 +99,7 @@
                     meta.args_aligner ? "args: ${meta.args_aligner}" : ""
                 ].join(' ').trim()
             }
-            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.argstree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}" }
+            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.args_tree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}" }
             ext.args = { "${meta.args_aligner}" == "null" ? '' : "${meta.args_aligner}" }
             if(params.skip_compression){
                 publishDir = [
@@ -119,7 +119,7 @@
                     meta.args_aligner ? "args: ${meta.args_aligner}" : ""
                 ].join(' ').trim()
             }
-            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.argstree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}" }
+            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.args_tree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}" }
             ext.args = { "${meta.args_aligner}" == "null" ? '' : "${meta.args_aligner}" }
             if(params.skip_compression){
                 publishDir = [
@@ -174,21 +174,21 @@
         //
 
         withName: 'PARSE_IRMSD' {
-            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.argstree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}_irmsd" }
+            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.args_tree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}_irmsd" }
         }
 
         withName: 'TCOFFEE_ALNCOMPARE_SP' {
-            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.argstree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}_sp" }
+            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.args_tree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}_sp" }
             ext.args = "-compare_mode sp"
         }
 
         withName: 'TCOFFEE_ALNCOMPARE_TC' {
-            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.argstree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}_tc" }
+            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.args_tree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}_tc" }
             ext.args = "-compare_mode tc"
         }
 
         withName: 'TCOFFEE_IRMSD' {
-            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.argstree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}_irmsd" }
+            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.args_tree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}_irmsd" }
             publishDir = [
                 path: { "${params.outdir}/evaluation/${task.process.tokenize(':')[-1].toLowerCase()}" },
                 mode: params.publish_dir_mode,
@@ -198,7 +198,7 @@
         }
 
         withName: "CALC_GAPS" {
-            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.argstree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}_gaps" }
+            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.args_tree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}_gaps" }
         }
 
         withName: "CONCAT_IRMSD" {
@@ -222,7 +222,7 @@
         }
 
         withName: 'TCOFFEE_TCS' {
-            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.argstree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}_tcs" }
+            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.args_tree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}_tcs" }
             publishDir = [
                 path: { "${params.outdir}/evaluation/${task.process.tokenize(':')[-1].toLowerCase()}" },
                 mode: params.publish_dir_mode,
@@ -269,4 +269,16 @@
                 saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
             ]
         }
+
+        //
+        // Visualization
+        //
+        withName: 'FOLDMASON_MSA2LDDTREPORT' {
+            ext.prefix = { "${meta.id}_${meta.tree}-args-${meta.args_tree_clean}_${meta.aligner}-args-${meta.args_aligner_clean}" }
+            publishDir = [
+                path: { "${params.outdir}/visualization" },
+                mode: params.publish_dir_mode,
+                saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+            ]
+        }
     }

conf/test_pdb.config

@@ -24,12 +24,13 @@ params {
     config_profile_name        = 'Test profile'
     config_profile_description = 'Minimal test dataset to check pipeline function'
 
-    skip_stats = true
-    calc_irmsd = true
-    calc_sp    = false
-    calc_tc    = false
-    calc_gaps  = false
-    calc_tcs   = false
+    skip_preprocessing = false
+    skip_stats         = true
+    calc_irmsd         = true
+    calc_sp            = false
+    calc_tc            = false
+    calc_gaps          = false
+    calc_tcs           = false
 
     // Input data
     input = params.pipelines_testdata_base_path + 'multiplesequencealign/samplesheet/v1.0/samplesheet_test.csv'