Merge pull request #82 from davidkastner/submit-clustering

Adding a script for submitting clustering calculations

Author: davidkastner

pyqmmm/cli.py

@@ -42,13 +42,15 @@ def cli():
 @click.option("--translate_pdb_to_center", "-tc", is_flag=True, help="Translates PDB traj to new center.")
 @click.option("--xyz2pdb", "-x2p", is_flag=True, help="Converts an xyz file or traj to a PDB.")
 @click.option("--repo2markdown", "-r2m", is_flag=True, help="Converts python package to markdown file.")
+@click.option("--submit_clustering", "-sc", is_flag=True, help="Submits clustering jobs to queue.")
 def io(
     ppm2png,
     delete_xyz_atoms,
     delete_pdb_atoms,
     translate_pdb_to_center,
     xyz2pdb,
-    repo2markdown
+    repo2markdown,
+    submit_clustering
     ):
     """
     Tools for useful manipulations of common file types.
@@ -122,6 +124,12 @@ def io(
         import pyqmmm.io.repo2markdown
         pyqmmm.io.repo2markdown.main()
 
+    elif submit_clustering:
+        click.echo("Submits clustering calculations to queue")
+        click.echo("Loading...")
+        import pyqmmm.io.submit_clustering
+        pyqmmm.io.submit_clustering.main()
+
 
 @cli.command()
 @click.option("--gbsa_submit", "-gs", is_flag=True, help="Prepares and submits a mmGBSA job.")

pyqmmm/io/submit_clustering.py

@@ -0,0 +1,63 @@
+import os
+import subprocess
+
+# Get the current working directory
+cwd = os.getcwd()
+
+# Function to check if a directory contains any .out file
+def has_out_file(dir_path):
+    for file in os.listdir(dir_path):
+        if file.endswith('.out'):
+            return True
+    return False
+
+# Iterate over all items in the cwd
+for item in os.listdir(cwd):
+    item_path = os.path.join(cwd, item)
+    
+    # Check if it's a directory and not "1_cluster"
+    if os.path.isdir(item_path) and item != "1_cluster":
+        # Path to 2_analysis
+        analysis_dir = os.path.join(item_path, "2_analysis")
+        
+        # Check if 2_analysis exists
+        if os.path.exists(analysis_dir) and os.path.isdir(analysis_dir):
+            # Path to 1_cluster inside 2_analysis
+            cluster_dir = os.path.join(analysis_dir, "1_cluster")
+            
+            # Check if 1_cluster exists
+            if os.path.exists(cluster_dir) and os.path.isdir(cluster_dir):
+                # Iterate over subdirectories in 1_cluster
+                for sub_item in os.listdir(cluster_dir):
+                    sub_item_path = os.path.join(cluster_dir, sub_item)
+                    
+                    # Check if it's a directory
+                    if os.path.isdir(sub_item_path):
+                        # Path to cluster.sh
+                        sh_file = os.path.join(sub_item_path, "cluster.sh")
+                        
+                        # Check if cluster.sh exists
+                        if os.path.exists(sh_file):
+                            # Check for .out files
+                            if has_out_file(sub_item_path):
+                                # Prompt user
+                                response = input(f"Job might be running in {sub_item_path}. Resubmit? (y/N): ").strip().lower()
+                                if response != 'y':
+                                    print(f"Skipping resubmission for {sub_item_path}")
+                                    continue
+                            
+                            # Submit the job
+                            try:
+                                result = subprocess.run(['sbatch', sh_file], capture_output=True, text=True, cwd=sub_item_path)
+                                if result.returncode == 0:
+                                    print(f"Submitted job for {sub_item_path}: {result.stdout.strip()}")
+                                else:
+                                    print(f"Error submitting job for {sub_item_path}: {result.stderr.strip()}")
+                            except Exception as e:
+                                print(f"Exception submitting job for {sub_item_path}: {str(e)}")
+                        else:
+                            print(f"cluster.sh not found in {sub_item_path}")
+            else:
+                print(f"1_cluster not found in {analysis_dir}")
+        else:
+            print(f"2_analysis not found in {item_path}")