BioBB WF protein MD analysis

biobb_wf_pmx_tutorial/README.md

@@ -46,8 +46,8 @@ The tutorial calculates the **free energy difference** in the folded state of a
 ## Copyright & Licensing
 This software has been developed in the [MMB group](http://mmb.irbbarcelona.org) at the [BSC](http://www.bsc.es/) & [IRB](https://www.irbbarcelona.org/) for the [European BioExcel](http://bioexcel.eu/), funded by the European Commission (EU H2020 [823830](http://cordis.europa.eu/projects/823830), EU H2020 [675728](http://cordis.europa.eu/projects/675728)).
 
-* (c) 2015-2024 [Barcelona Supercomputing Center](https://www.bsc.es/)
-* (c) 2015-2024 [Institute for Research in Biomedicine](https://www.irbbarcelona.org/)
+* (c) 2015-2025 [Barcelona Supercomputing Center](https://www.bsc.es/)
+* (c) 2015-2025 [Institute for Research in Biomedicine](https://www.irbbarcelona.org/)
 
 Licensed under the
 [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0), see the file LICENSE for details.

biobb_wf_pmx_tutorial/python/workflow.py

@@ -4,23 +4,15 @@
 import argparse
 import os
 import zipfile
-
-# biobb common modules
 from biobb_common.configuration import settings
 from biobb_common.tools import file_utils as fu
-
-# biobb pmx modules
 from biobb_pmx.pmxbiobb.pmxmutate import pmxmutate
 from biobb_pmx.pmxbiobb.pmxgentop import pmxgentop
 from biobb_pmx.pmxbiobb.pmxanalyse import pmxanalyse
-
-# biobb md modules
 from biobb_gromacs.gromacs.pdb2gmx import pdb2gmx
 from biobb_gromacs.gromacs.make_ndx import make_ndx
 from biobb_gromacs.gromacs.grompp import grompp
 from biobb_gromacs.gromacs.mdrun import mdrun
-
-# biobb analysis module
 from biobb_analysis.gromacs.gmx_trjconv_str_ens import gmx_trjconv_str_ens
 
 
@@ -33,14 +25,15 @@ def main(config, system=None):
     dhdl_paths_listA = []
     dhdl_paths_listB = []
 
-    for ensemble, mutation in conf.properties['mutations'].items():
+    for ensemble, mutation in conf.properties['global_properties']['mutations'].items():
         ensemble_prop = conf.get_prop_dic(prefix=ensemble, global_log=global_log)
         ensemble_paths = conf.get_paths_dic(prefix=ensemble)
 
         # Create and launch bb
         global_log.info(ensemble+" Step 0: gmx trjconv: Extract snapshots from equilibrium trajectories")
-        ensemble_paths['step0_trjconv']['input_traj_path'] = conf.properties['input_trajs'][ensemble]['input_traj_path']
-        ensemble_paths['step0_trjconv']['input_top_path'] = conf.properties['input_trajs'][ensemble]['input_tpr_path']
+        ensemble_paths['step0_trjconv']['input_traj_path'] = conf.properties['global_properties']['input_trajs'][ensemble]['input_traj_path']
+        ensemble_paths['step0_trjconv']['input_top_path'] = conf.properties['global_properties']['input_trajs'][ensemble]['input_tpr_path']
+
         gmx_trjconv_str_ens(**ensemble_paths["step0_trjconv"], properties=ensemble_prop["step0_trjconv"])
 
         with zipfile.ZipFile(ensemble_paths["step0_trjconv"]["output_str_ens_path"], 'r') as zip_f:
@@ -56,18 +49,21 @@ def main(config, system=None):
             global_log.info("Step 1: pmx mutate: Generate Hybrid Structure")
             paths['step1_pmx_mutate']['input_structure_path'] = pdb_path
             prop['step1_pmx_mutate']['mutation_list'] = mutation
+            prop['step1_pmx_mutate']['gmx_lib'] = os.getenv('CONDA_PREFIX') + '/lib/python3.10/site-packages/pmx/data/mutff'
             pmxmutate(**paths["step1_pmx_mutate"], properties=prop["step1_pmx_mutate"])
 
             # Step 2: gmx pdb2gmx: Generate Topology
             # From pmx tutorial:
             # gmx pdb2gmx -f mut.pdb -ff amber99sb-star-ildn-mut -water tip3p -o pdb2gmx.pdb
             global_log.info("Step 2: gmx pdb2gmx: Generate Topology")
+            prop['step2_gmx_pdb2gmx']['gmx_lib'] = os.getenv('CONDA_PREFIX') + '/lib/python3.10/site-packages/pmx/data/mutff'
             pdb2gmx(**paths["step2_gmx_pdb2gmx"], properties=prop["step2_gmx_pdb2gmx"])
 
             # Step 3: pmx gentop: Generate Hybrid Topology
             # From pmx tutorial:
             # python generate_hybrid_topology.py -itp topol_Protein.itp -o topol_Protein.itp -ff amber99sb-star-ildn-mut
             global_log.info("Step 3: pmx gentop: Generate Hybrid Topology")
+            prop['step3_pmx_gentop']['gmx_lib'] = os.getenv('CONDA_PREFIX') + '/lib/python3.10/site-packages/pmx/data/mutff'
             pmxgentop(**paths["step3_pmx_gentop"], properties=prop["step3_pmx_gentop"])
 
             # Step 4: gmx make_ndx: Generate Gromacs Index File to select atoms to freeze
@@ -88,6 +84,7 @@ def main(config, system=None):
                 # From pmx tutorial:
                 # gmx grompp -c pdb2gmx.pdb -p topol.top -f ../../mdp/em_FREEZE.mdp -o em.tpr -n ../index.ndx
                 global_log.info("Step 5: gmx grompp: Creating portable binary run file for energy minimization")
+                prop['step5_gmx_grompp']['gmx_lib'] = os.getenv('CONDA_PREFIX') + '/lib/python3.10/site-packages/pmx/data/mutff'
                 grompp(**paths["step5_gmx_grompp"], properties=prop["step5_gmx_grompp"])
 
                 # Step 6: gmx mdrun: Running energy minimization
@@ -100,6 +97,7 @@ def main(config, system=None):
             # From pmx tutorial:
             # gmx grompp -c emout.gro -p topol.top -f ../../mdp/eq_20ps.mdp -o eq_20ps.tpr -maxwarn 1
             global_log.info(ensemble+" Step 7: gmx grompp: Creating portable binary run file for system equilibration")
+            prop['step7_gmx_grompp']['gmx_lib'] = os.getenv('CONDA_PREFIX') + '/lib/python3.10/site-packages/pmx/data/mutff'
             grompp(**paths["step7_gmx_grompp"], properties=prop["step7_gmx_grompp"])
 
             # Step 8: gmx mdrun: Running system equilibration
@@ -112,6 +110,7 @@ def main(config, system=None):
             # From pmx tutorial:
             # gmx grompp -c eqout.gro -p topol.top -f ../../mdp/ti.mdp -o ti.tpr -maxwarn 1
             global_log.info(ensemble+" Step 9: Creating portable binary run file for thermodynamic integration (ti)")
+            prop['step9_gmx_grompp']['gmx_lib'] = os.getenv('CONDA_PREFIX') + '/lib/python3.10/site-packages/pmx/data/mutff'
             grompp(**paths["step9_gmx_grompp"], properties=prop["step9_gmx_grompp"])
 
             # Step 10: gmx mdrun: Running thermodynamic integration

biobb_wf_pmx_tutorial/python/workflow.yml

@@ -1,18 +1,16 @@
 global_properties:
   working_dir_path: biobb_wf_pmx_tutorial
   can_write_console_log: False
-
-mutations:
-  stateA: 10Ala
-  stateB: 10Ile
-
-input_trajs:
-  stateA:
-    input_tpr_path: file:pmx_tutorial/stateA.tpr
-    input_traj_path: file:pmx_tutorial/stateA_1ns.xtc
-  stateB:
-    input_tpr_path: file:pmx_tutorial/stateB.tpr
-    input_traj_path: file:pmx_tutorial/stateB_1ns.xtc
+  mutations:
+    stateA: 10Ala
+    stateB: 10Ile
+  input_trajs:
+    stateA:
+      input_tpr_path: pmx_tutorial/stateA.tpr
+      input_traj_path: pmx_tutorial/stateA_1ns.xtc
+    stateB:
+      input_tpr_path: pmx_tutorial/stateB.tpr
+      input_traj_path: pmx_tutorial/stateB_1ns.xtc
 
 step0_trjconv:
   paths:
@@ -137,8 +135,8 @@ step10_gmx_mdrun:
 
 step11_pmx_analyse:
   paths:
-    input_a_xvg_zip_path: dhdlA.zip
-    input_b_xvg_zip_path: dhdlB.zip
+    input_a_xvg_zip_path: file:dhdlA.zip
+    input_b_xvg_zip_path: file:dhdlB.zip
     output_result_path: pmx.txt
     output_work_plot_path: pmx.plots.png
   properties:

biobb_wf_protein_md_analysis/README.md

@@ -26,8 +26,8 @@ This workflow computes a set of Quality Control (QC) analyses on top of an uploa
 ## Copyright & Licensing
 This software has been developed in the [MMB group](http://mmb.irbbarcelona.org) at the [BSC](http://www.bsc.es/) & [IRB](https://www.irbbarcelona.org/) for the [European BioExcel](http://bioexcel.eu/), funded by the European Commission (EU H2020 [823830](http://cordis.europa.eu/projects/823830), EU H2020 [675728](http://cordis.europa.eu/projects/675728)).
 
-* (c) 2015-2024 [Barcelona Supercomputing Center](https://www.bsc.es/)
-* (c) 2015-2024 [Institute for Research in Biomedicine](https://www.irbbarcelona.org/)
+* (c) 2015-2025 [Barcelona Supercomputing Center](https://www.bsc.es/)
+* (c) 2015-2025 [Institute for Research in Biomedicine](https://www.irbbarcelona.org/)
 
 Licensed under the
 [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0), see the file LICENSE for details.

biobb_wf_protein_md_analysis/python/workflow.py

@@ -4,7 +4,6 @@
 import argparse
 import csv
 import json
-import shutil
 from Bio.PDB.PDBParser import PDBParser
 from Bio.PDB.PDBIO import PDBIO
 from biobb_common.configuration import settings
@@ -16,6 +15,7 @@
 from biobb_analysis.ambertools.cpptraj_convert import cpptraj_convert
 from biobb_analysis.gromacs.gmx_cluster import gmx_cluster
 
+
 def getBfactorsList(input):
     file = open(input)
     csv_reader = csv.reader(file)
@@ -31,6 +31,7 @@ def getBfactorsList(input):
 
     return bfactors
 
+
 def saveBfactor(input, output, bfactors):
     # load input into BioPython structure
     structure = PDBParser(QUIET=True).get_structure('structure', input)
@@ -43,9 +44,10 @@ def saveBfactor(input, output, bfactors):
 
     # save the structure
     io = PDBIO()
-    io.set_structure(structure) 
+    io.set_structure(structure)
     io.save(output)
 
+
 def saveClusters(input, output):
     file = open(input)
     csv_reader = csv.reader(file)
@@ -54,9 +56,9 @@ def saveClusters(input, output):
     start = False
     for row in csv_reader:
 
-        if start: 
+        if start:
             col = row[0].split('|')
-            if len(col[0].strip()): 
+            if len(col[0].strip()):
                 clusters.append({
                     'cluster': col[0].strip(),
                     'population': col[1].strip().split()[0]
@@ -68,6 +70,7 @@ def saveClusters(input, output):
     with open(output, 'w') as outfile:
         json.dump(clusters, outfile)
 
+
 def main(config, system=None):
     start_time = time.time()
     conf = settings.ConfReader(config, system)
@@ -117,10 +120,10 @@ def main(config, system=None):
     global_log.info('Elapsed time: %.1f minutes' % (elapsed_time/60))
     global_log.info('')
 
+
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description="Protein MD Analysis pipeline using BioExcel Building Blocks")
     parser.add_argument('--config', required=True)
     parser.add_argument('--system', required=False)
     args = parser.parse_args()
     main(args.config, args.system)
-