Merge pull request #133 from jvalegre/jv_branch

1. Changing PATH in files and input options, 2. Fixing SUMM in CSEARCH

aqme/cmin.py

@@ -101,9 +101,10 @@
 import time
 from aqme.utils import (
     load_variables,
-    substituted_mol,
     mol_from_sdf_or_mol_or_mol2,
-    add_prefix_suffix
+    add_prefix_suffix,
+    check_files,
+    check_xtb
 )
 from aqme.filter import ewin_filter, pre_E_filter, RMSD_and_E_filter
 from aqme.cmin_utils import creation_of_dup_csv_cmin
@@ -147,10 +148,7 @@ def __init__(self, **kwargs):
             os.chdir(self.args.w_dir_main)
 
         # retrieves the different files to run in CMIN
-        if len(self.args.files) == 0:
-            self.args.log.write('\nx  No files were found! Make sure you use quotation marks if you are using * (i.e. --files "*.sdf")')
-            self.args.log.finalize()
-            sys.exit()
+        _ = check_files(self,'cmin')
 
         # create the dataframe to store the data
         self.final_dup_data = creation_of_dup_csv_cmin(self.args.program.lower())
@@ -277,6 +275,8 @@ def compute_cmin(self, file):
             charge,mult,final_mult,dup_data = self.charge_mult_cmin(dup_data, dup_data_idx)
 
         elif self.args.program.lower() == "xtb":
+            # checks if xTB is installed
+            _ = self.get_cmin_model()
             # sets charge and mult
             file_format = os.path.splitext(file)[1]
             charge_input, mult_input, final_mult = None, None, None
@@ -431,7 +431,7 @@ def compute_cmin(self, file):
     # xTB AND ANI MAIN OPTIMIZATION PROCESS
     def ani_optimize(self, mol, charge, mult):
 
-        # Attempts ANI/xTB imports and exits if the programs are not installed
+        # Attempts ANI imports and exits if the programs are not installed
         try:
             import torch
             import warnings
@@ -527,15 +527,7 @@ def get_cmin_model(self):
             model = getattr(torchani.models,self.args.ani_method)()
 
         elif self.args.program.lower() == "xtb":
-            try:
-                subprocess.run(
-                    ["xtb", "-h"], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL
-                )
-            except FileNotFoundError:
-                self.args.log.write("x  xTB is not installed (CREST cannot be used)! You can install the program with 'conda install -c conda-forge xtb'")
-                self.args.log.finalize()
-                sys.exit()
-
+            _ = check_xtb(self)
             model = None
 
         return model

aqme/csearch/base.py

@@ -206,7 +206,9 @@
 from aqme.utils import (
     substituted_mol,
     load_variables,
-    set_metal_atomic_number
+    set_metal_atomic_number,
+    check_xtb,
+    get_files
     )
 from aqme.csearch.crest import xtb_opt_main
 
@@ -239,14 +241,7 @@ def __init__(self, **kwargs):
             self.args.auto_metal_atoms = False
 
         if self.args.program.lower() == "crest":
-            try:
-                subprocess.run(
-                    ["xtb", "-h"], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL
-                )
-            except FileNotFoundError:
-                self.args.log.write("x  xTB is not installed (CREST cannot be used)! You can install the program with 'conda install -c conda-forge xtb'")
-                self.args.log.finalize()
-                sys.exit()
+            _ = check_xtb(self)
 
         if self.args.smi is None and self.args.input == "":
             self.args.log.write("\nx  Program requires either a SMILES or an input file to proceed! Please look up acceptable file formats. Specify: smi='CCC' (or input='filename.csv')")
@@ -271,7 +266,7 @@ def __init__(self, **kwargs):
         if self.args.smi is not None:
             csearch_files = [self.args.name]
         else:
-            csearch_files = glob.glob(self.args.input)
+            csearch_files = get_files(self.args.input)
             if len(csearch_files) == 0:
                 self.args.log.write(f"\nx  Input file ({self.args.input}) not found!")
                 self.args.log.finalize()
@@ -292,7 +287,7 @@ def __init__(self, **kwargs):
 
             # store all the information into a CSV file
             csearch_file_no_path = (
-                csearch_file.replace("/", "\\").split("\\")[-1].split(".")[0]
+                os.path.basename(csearch_file).split(".")[0]
             )
             self.csearch_csv_file = self.args.w_dir_main.joinpath(
                 f"CSEARCH-Data-{csearch_file_no_path}.csv"

aqme/csearch/utils.py

@@ -261,7 +261,7 @@ def prepare_cdx_files(args, csearch_file):
 
     job_inputs = []
     for i, (smiles, _) in enumerate(molecules):
-        name = f"{csearch_file.split('.')[0]}_{str(i)}"
+        name = f"{os.path.basename(csearch_file).split('.')[0]}_{str(i)}"
         name = add_prefix_suffix(name, args)
 
         obj = (
@@ -294,19 +294,22 @@ def generate_mol_from_cdx(csearch_file):
 def prepare_com_files(args, csearch_file):
     job_inputs = []
 
-    if csearch_file.split(".")[1] in ["gjf", "com"]:
+    filename = os.path.basename(csearch_file)
+    if filename.split('.')[1] in ["gjf", "com"]:
         xyz_file, _, _ = com_2_xyz(csearch_file)
         _, charge, mult = get_info_input(csearch_file)
     else:
         xyz_file = csearch_file
         charge, mult = read_xyz_charge_mult(xyz_file)
-    xyz_2_sdf(xyz_file)
-    name = os.path.splitext(csearch_file)[0]
-    name = add_prefix_suffix(name, args)
+    _ = xyz_2_sdf(xyz_file)
+
+    sdffile = f'{os.path.dirname(csearch_file)}/{filename.split(".")[0]}.sdf'
 
-    sdffile = f"{os.path.splitext(csearch_file)[0]}.sdf"
     suppl, _, _, _ = mol_from_sdf_or_mol_or_mol2(sdffile, "csearch")
 
+    name = filename.split('.')[0]
+    name = add_prefix_suffix(name, args)
+
     obj = (
         suppl[0],
         name,
@@ -318,28 +321,37 @@ def prepare_com_files(args, csearch_file):
         args.constraints_dihedral,
     )
     job_inputs.append(obj)
+    if os.path.basename(csearch_file).split('.')[1] in ["gjf", "com"]:
+        os.remove(xyz_file)
+    os.remove(sdffile)
 
     return job_inputs
 
 
 def prepare_pdb_files(args, csearch_file):
+    filename = os.path.basename(csearch_file)
+    sdffile = f'{os.path.dirname(csearch_file)}/{filename.split(".")[0]}.sdf'
     command_pdb = [
         "obabel",
         "-ipdb",
         csearch_file,
         "-osdf",
-        f'-O{csearch_file.split(".")[0]}.sdf',
+        f'-O{sdffile}',
     ]
     subprocess.run(command_pdb, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
     job_inputs = prepare_sdf_files(args, csearch_file)
-    os.remove(f'{csearch_file.split(".")[0]}.sdf')
+    os.remove(sdffile)
     return job_inputs
 
 
 def prepare_sdf_files(args, csearch_file):
-    suppl, charges, mults, IDs = mol_from_sdf_or_mol_or_mol2(csearch_file, "csearch")
-    job_inputs = []
+    filename = os.path.basename(csearch_file)
+    sdffile = f'{os.path.dirname(csearch_file)}/{filename}'
+    suppl, charges, mults, IDs = mol_from_sdf_or_mol_or_mol2(sdffile, "csearch")
+    if sdffile.split('.')[0] in ['mol','mol2']:
+        os.remove(f'{sdffile.split(".")[0]}.sdf')
 
+    job_inputs = []
     for mol, charge, mult, name in zip(suppl, charges, mults, IDs):
         name = add_prefix_suffix(name, args)
         obj = (
@@ -391,15 +403,16 @@ def com_2_xyz(input_file):
     COM to XYZ to SDF for obabel
     """
 
-    filename = input_file.split(".")[0]
+    filename = os.path.basename(input_file).split('.')[0]
+    path_xyz = f'{os.path.dirname(input_file)}/{filename}.xyz'
 
     # Create the 'xyz' file and/or get the total charge
     xyz, charge, mult = get_info_input(input_file)
     xyz_txt = "\n".join(xyz)
-    with open(f"{filename}.xyz", "w") as F:
+    with open(path_xyz, "w") as F:
         F.write(f"{len(xyz)}\n{filename}\n{xyz_txt}\n")
 
-    return f"{filename}.xyz", charge, mult
+    return path_xyz, charge, mult
 
 
 def minimize_rdkit_energy(mol, conf, log, FF, maxsteps):

aqme/qcorr.py

@@ -82,6 +82,7 @@
     load_variables,
     read_file,
     cclib_atoms_coords,
+    check_files
 )
 from aqme.qcorr_utils import (
     detect_linear,
@@ -108,13 +109,11 @@ def __init__(self, **kwargs):
         # load default and user-specified variables
         self.args = load_variables(kwargs, "qcorr")
 
-        if len(self.args.files) == 0:
-            self.args.log.write('\nx  No files were found! Make sure you use quotation marks if you are using * (i.e. --files "*.log")')
-            self.args.log.finalize()
-            sys.exit()
+        # retrieves the different files to run in QCORR
+        _ = check_files(self,'qcorr')
 
         # QCORR analysis
-        if self.args.files[0].split('.')[1].lower() not in ['log','out','json']:
+        if os.path.basename(self.args.files[0]).split('.')[1].lower() not in ['log','out','json']:
             self.args.log.write(f"\nx  The format used ({self.args.files[0].split('.')[1].lower()}) is not compatible with QCORR! Formats accepted: log, out, json")
             self.args.log.finalize()
             sys.exit()

aqme/qdescp.py

@@ -85,7 +85,8 @@
     load_variables,
     read_xyz_charge_mult,
     mol_from_sdf_or_mol_or_mol2,
-    run_command
+    run_command,
+    check_files
 )
 from aqme.qdescp_utils import (
     get_boltz_avg_properties_xtb,
@@ -116,10 +117,8 @@ def __init__(self, **kwargs):
         else:
             destination = Path(self.args.destination)
 
-        if len(self.args.files) == 0:
-            self.args.log.write('\nx  No files were found! Make sure you use quotation marks if you are using * (i.e. --files "*.sdf")')
-            self.args.log.finalize()
-            sys.exit()
+        # retrieves the different files to run in QDESCP
+        _ = check_files(self,'qdescp')
 
         qdescp_program = True
         if self.args.program is None:

aqme/qprep.py

@@ -61,6 +61,7 @@
     read_xyz_charge_mult,
     mol_from_sdf_or_mol_or_mol2,
     add_prefix_suffix,
+    check_files
 )
 from aqme.csearch.crest import xyzall_2_xyz
 from pathlib import Path
@@ -77,10 +78,8 @@ def __init__(self, create_dat=True, **kwargs):
         # load default and user-specified variables
         self.args = load_variables(kwargs, "qprep", create_dat=create_dat)
 
-        if len(self.args.files) == 0:
-            self.args.log.write('\nx  No files were found! Make sure you use quotation marks if you are using * (i.e. --files "*.sdf")')
-            self.args.log.finalize()
-            sys.exit()
+        # retrieves the different files to run in QPREP
+        _ = check_files(self,'qprep')
 
         file_format = os.path.splitext(self.args.files[0])[1].split('.')[1]
         if file_format.lower() not in ['sdf', 'xyz', 'pdb', 'log', 'out', 'json']: