Wire ModelPDB generation into Nextflow workflow

Author: mitsenkov

README.md

@@ -619,6 +619,8 @@ AF-0001234567890125
 AF-0001234567890126
 ```
 
+The ModelPDB step also requires provider metadata. By default the workflow reads this from `input/provider.json`; override it with `--provider_json <path>` if your provider file is elsewhere.
+
 **Example input.txt:**
 ```bash
 # Create the input list file

workflow/workflow.nf

@@ -93,9 +93,35 @@ process runDSSP {
     """
 }
 
+/*
+    Add AFDB-specific PDB headers from the DSSP-annotated CIF for each entry
+*/
+process runModelPdbGenerator {
+
+    publishDir "${params.output_dir}/${getEntryDir(entry)}", mode: 'copy'
+
+    input:
+        path cif_file
+        val entry
+
+    output:
+        path "${entry}-model-${params.version}.pdb"
+
+    script:
+    """
+    echo "Generating enriched model PDB for entry: ${entry}"
+    ${params.python_cmd} run-modelpdb-gen \
+        -c "${cif_file}" \
+        -p "${params.input_dir}/${getEntryDir(entry)}/${entry}-model-${params.version}.pdb" \
+        -r "${params.provider_json}" \
+        -o "${entry}-model-${params.version}.pdb"
+    """
+}
+
 params.input_dir = "/input"
 params.output_dir = "/output"
 params.input_list = "${params.input_dir}/input.txt"
+params.provider_json = "${params.input_dir}/provider.json"
 params.version = "v1"
 params.results_dir = "${params.output_dir}/results"
 params.python_cmd = "uv run /app/main.py"
@@ -112,9 +138,10 @@ workflow {
 
     createEntryOutDir(input_channel)
 
-    runModelCifGenerator(input_channel)
+    model_cif = runModelCifGenerator(input_channel)
 
-    runDSSP(runModelCifGenerator.out)
+    dssp = runDSSP(model_cif.cif_file, model_cif.entry)
 
-    runCif2Bcif(runDSSP.out)
+    runModelPdbGenerator(dssp.cif_file, dssp.entry)
+    runCif2Bcif(dssp.cif_file, dssp.entry)
 }