apply pre-commit changes

.vscode/settings.json

@@ -14,5 +14,5 @@
     "[yaml]": {
         "editor.suggest.showWords": false
     },
-    "notebook.output.textLineLimit": 100,
+    "notebook.output.textLineLimit": 100
 }

atomselect_demo.py

@@ -1,4 +1,8 @@
-def main(selection_string, input_pdb_path, output_pdb_path):
+from workflow_types import *
+# NOTE: No other top-level imports supported
+
+
+def main(selection_string, input_pdb_path, output_pdb_path):   # type: ignore[no-untyped-def]
     import mdtraj
     traj = mdtraj.load(input_pdb_path)
     print(traj)
@@ -8,9 +12,6 @@ def main(selection_string, input_pdb_path, output_pdb_path):
     traj.save(output_pdb_path)
 
 
-from workflow_types import *
-# NOTE: No other top-level imports supported
-
 inputs = {'selection_string': string,
           'input_pdb_path': pdbfile,
           'output_pdb_path': {**string, 'default': 'selection.pdb'}}

auth/settings.py

@@ -4,17 +4,12 @@
 
 from pydantic import BaseSettings
 
-"""
-Setup logger
-"""
+# Setup logger
 logging.basicConfig(format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")
 logger = logging.getLogger("plots.settings")
 
-"""
-Load environment variables
-"""
-
 
+# Load environment variables
 class Settings(BaseSettings):
     """Settings for the API.
     This defines the required inputs for the environment file.
@@ -29,7 +24,7 @@ class Settings(BaseSettings):
     JWKS_ENDPOINT: Optional[str] = None
     OFFLINE_USER: Optional[str] = None
 
-    class Config:  # NOQA:D106
+    class Config:  # NOQA: D106
 
         env_file = ".env"
 
@@ -46,7 +41,7 @@ class Config:  # NOQA:D106
         + "Make sure to create a .env file and specify a folder for serving data."
     )
 
-""" Define static types """
+# Define static types
 CLASS_TYPES = ["string"]
 
 SUPPORTED_FORMATS = [".feather", ".arrow", ".csv", ".parquet", ".hdf5"]
@@ -56,7 +51,5 @@ class Config:  # NOQA:D106
 CACHED_FILES: Dict[str, Dict[str, Any]] = {}
 
 
-"""
-Reusable Constants
-"""
+# Reusable Constants
 DEFAULT_USER: str = "default_user"

conftest.py

@@ -1,12 +1,13 @@
 # See https://docs.pytest.org/en/7.1.x/example/simple.html
+from typing import Any
 import pytest
 
 
-def pytest_addoption(parser) -> None:
+def pytest_addoption(parser: pytest.Parser) -> None:
     parser.addoption('--cwl_runner', type=str, required=False, default='cwltool', choices=['cwltool', 'toil-cwl-runner'],
                      help='The CWL runner to use for running workflows locally.')
 
 
 @pytest.fixture
-def cwl_runner(request):
+def cwl_runner(request: pytest.FixtureRequest) -> Any:
     return request.config.getoption("--cwl_runner")

cwl_adapters/file_format_conversions/biosimspace/conversion.py

@@ -10,6 +10,7 @@
 # we can use more precise edam formats and thus let CWL catch more errors.
 # In other words, the cwl scripts are type-safe wrappers around this script.
 
+
 def main() -> None:
     parser = argparse.ArgumentParser()
     required_args = parser.add_argument_group('required arguments')

cwl_adapters/yank/yank_wrapper.py

@@ -17,15 +17,15 @@ def check_options(options: Dict[str, Any], args: argparse.Namespace) -> None:
         args (argparse.Namespace): The command line arguments.
     """
     if 'verbose' not in options:
-        options['verbose'] = True #'yes'
+        options['verbose'] = True  # 'yes'
     if 'resume_setup' not in options:
-        options['resume_setup'] = True #'yes'
+        options['resume_setup'] = True  # 'yes'
     if 'resume_simulation' not in options:
-        options['resume_simulation'] = True #'yes'
+        options['resume_simulation'] = True  # 'yes'
 
     if options.get('start_from_trailblaze_samples', '') == 'yes':
         print('Warning: start_from_trailblaze_samples should always be set to no; setting to no')
-    options['start_from_trailblaze_samples'] = False #'no' # yes generates NaNs!
+    options['start_from_trailblaze_samples'] = False  # 'no' # yes generates NaNs!
 
     if 'checkpoint_interval' in options and 'switch_phase_interval' in options:
         if options['switch_phase_interval'] < 0 or options['checkpoint_interval'] < 0:
@@ -55,6 +55,7 @@ def check_options(options: Dict[str, Any], args: argparse.Namespace) -> None:
     if args.phase in ['setup_only', 'trailblaze', 'equilibration']:
         options['default_number_of_iterations'] = 0
 
+
 def make_molecules_tag(args: argparse.Namespace) -> Dict[str, Any]:
     """Returns the basic tags which describe the molecules in a system.
 
@@ -105,7 +106,7 @@ def make_systems_tag_group2(complex_top_filename: str, ligand_top_filename: str,
         'phase1_path': [complex_top_filename, args.input_complex_crd_path],
         'phase2_path': [ligand_top_filename, args.input_ligand_crd_path],
         'ligand_dsl': 'resname MOL',
-        #'solvent_dsl': 'resname WAT',  # optional
+        # ' solvent_dsl': 'resname WAT',  # optional
         'solvent': 'spce_50mM_acetate_55',
         'gromacs_include_dir': gromacs_include_dir,
     }}}
@@ -130,11 +131,11 @@ def make_experiment_tag(system_name: str = 'system_name') -> Dict[str, Any]:
             'temperature': '302.15*kelvin'},
         'protocol': 'binding-auto',
     }
-        # Cannot use restraints on 32 bit systems :(
-        #restraint:
-        #  #type: FlatBottom
-        #  restrained_ligand_atoms: (resname MOL) and (mass > 1.5)
-        #  restrained_receptor_atoms: f'({residue_indices_str}) and (mass > 1.5)'
+    # Cannot use restraints on 32 bit systems :(
+    # restraint:
+    #   #type: FlatBottom
+    #   restrained_ligand_atoms: (resname MOL) and (mass > 1.5)
+    #   restrained_receptor_atoms: f'({residue_indices_str}) and (mass > 1.5)'
     return exp
 
 
@@ -151,9 +152,9 @@ def unzip_topology_files(zip_path: str) -> str:
     with zipfile.ZipFile(zip_path, 'r') as zip_file:
         filenames = zip_file.namelist()
         # This extracts to a temporary directory which is not writable when using Docker.
-        #zip_file.extractall(Path(outdir).parent)
+        # zip_file.extractall(Path(outdir).parent)
     # Instead, use unzip which extracts in-place (in the same directory)
-    cmd = ['unzip', '-n', zip_path] # Use -n to avoid overwriting files.
+    cmd = ['unzip', '-n', zip_path]  # Use -n to avoid overwriting files.
     sub.run(cmd, check=True)
     top_filenames = [fn for fn in filenames if Path(fn).suffix == '.top']
     if len(top_filenames) != 1:
@@ -216,15 +217,15 @@ def main() -> None:
 
     if group1:
         systems_tag = make_systems_tag_group1()
-    else: # group2
+    else:  # group2
         systems_tag = make_systems_tag_group2(complex_top_filename, ligand_top_filename, args)
 
-    #yaml_dict['systems'] = {**yaml_dict['systems'], **systems_tag['systems']} # merge?
-    yaml_dict['systems'] = systems_tag['systems'] # overwrite
+    # yaml_dict['systems'] = {**yaml_dict['systems'], **systems_tag['systems']} # merge?
+    yaml_dict['systems'] = systems_tag['systems']  # overwrite
 
     yaml_dict['experiment_name'] = make_experiment_tag()
-    #yaml_dict['experiments'] = yaml_dict.get('experiments', []).append('experiment_name') # append?
-    yaml_dict['experiments'] = ['experiment_name'] # overwrite
+    # yaml_dict['experiments'] = yaml_dict.get('experiments', []).append('experiment_name')  # append?
+    yaml_dict['experiments'] = ['experiment_name']  # overwrite
 
     options: Dict[str, Any] = yaml_dict['options']
     check_options(options, args)
@@ -234,7 +235,7 @@ def main() -> None:
         f.write(yaml.dump(yaml_dict))
 
     # Run yank
-    subcommand = ['script', '-y', yaml_filename] # trailblaze, equilibration, production
+    subcommand = ['script', '-y', yaml_filename]  # trailblaze, equilibration, production
     if args.phase == 'setup_only':
         subcommand = ['script', '--setup-only', '-y', yaml_filename]
     if args.phase == 'analyze':

docs/conf.py

@@ -1,3 +1,4 @@
+from typing import Dict
 # Configuration file for the Sphinx documentation builder.
 #
 # This file only contains a selection of the most common options. For a full
@@ -29,8 +30,8 @@
 # ones.
 extensions = [
     'myst_parser',
-    'sphinx.ext.napoleon', # Support google (and numpy) docstring styles
-    "sphinx_autodoc_typehints", # Load AFTER napoleon
+    'sphinx.ext.napoleon',  # Support google (and numpy) docstring styles
+    "sphinx_autodoc_typehints",  # Load AFTER napoleon
     # See https://github.com/agronholm/sphinx-autodoc-typehints/issues/15
     # NOTE: sphinx_autodoc_typehints automatically strips type annotations
     # from the function signature and inserts them into the docstring.
@@ -70,11 +71,10 @@
 # can be added to autodoc_type_aliases instead of showing their expansions.
 # However, I can't seem to get it to work.
 # TODO: Consider removing all type aliases in favor of classes.
-from typing import Dict
 autodoc_type_aliases: Dict[str, str] = {
 }
 napoleon_use_param = True
-napoleon_type_aliases: Dict[str, str]  = {
+napoleon_type_aliases: Dict[str, str] = {
 }
 
 # Add any paths that contain templates here, relative to this directory.

docs/requirements.txt

@@ -1,6 +1,6 @@
+ipytree
+myst-parser
 # https://docs.readthedocs.io/en/stable/intro/getting-started-with-sphinx.html
 # "We strongly recommend to pin the Sphinx version used for your project to build the docs to avoid potential future incompatibilities."
 sphinx==6.1.*
-myst-parser
 sphinx-autodoc-typehints
-ipytree

examples/scripts/autodock_vina_filter.py

@@ -41,27 +41,25 @@
 
 # After the initial headers, an autodock vina log file consists of
 # 1 or more blocks of the following form:
-"""
-Performing docking (random seed: -193947260) ... 
-0%   10   20   30   40   50   60   70   80   90   100%
-|----|----|----|----|----|----|----|----|----|----|
-***************************************************
-
-mode |   affinity | dist from best mode
-     | (kcal/mol) | rmsd l.b.| rmsd u.b.
------+------------+----------+----------
-   1       -5.773          0          0
-   2       -5.577      4.821      7.207
-   3        -5.46      4.053      6.446
-   4        -5.44      1.344      3.349
-   5       -5.431      3.576       5.58
-   6       -5.412      3.012      5.868
-   7       -5.405      1.914      4.145
-   8       -5.403      3.209      6.271
-   9       -5.392      2.556      4.714
-"""
+# Performing docking (random seed: -193947260) ...
+# 0%   10   20   30   40   50   60   70   80   90   100%
+# |----|----|----|----|----|----|----|----|----|----|
+# ***************************************************
+
+# mode |   affinity | dist from best mode
+#      | (kcal/mol) | rmsd l.b.| rmsd u.b.
+# -----+------------+----------+----------
+#    1       -5.773          0          0
+#    2       -5.577      4.821      7.207
+#    3        -5.46      4.053      6.446
+#    4        -5.44      1.344      3.349
+#    5       -5.431      3.576       5.58
+#    6       -5.412      3.012      5.868
+#    7       -5.405      1.914      4.145
+#    8       -5.403      3.209      6.271
+#    9       -5.392      2.556      4.714
 # If rescoring, the relevant line from each log file is of the form:
-"""Estimated Free Energy of Binding   : -8.659 (kcal/mol) [=(1)+(2)+(3)-(4)]"""
+# Estimated Free Energy of Binding   : -8.659 (kcal/mol) [=(1)+(2)+(3)-(4)]
 
 scores: List[float] = []
 scores_all: List[List[float]] = []

examples/scripts/generate_conformers.py

@@ -1,13 +1,20 @@
 # pylint: disable=import-outside-toplevel,no-member
-# type: ignore
 import distutils.util
 import math
 from typing import List
 
 from workflow_types import *
 
 
-def calculate_dG(Kd):
+def calculate_dG(Kd: float) -> float:
+    """ Calculates binding free energy from Kd
+
+    Args:
+        Kd (float): The binding affinity of the protein-ligand complex
+
+    Returns:
+        float: The binding free energy
+    """
     # Calculate the binding free energy from Kd so we can make the correlation plots.
     # See https://en.wikipedia.org/wiki/Binding_constant
     ideal_gas_constant = 8.31446261815324  # J/(Mol*K)
@@ -26,7 +33,7 @@ def calculate_dG(Kd):
     return dG
 
 
-def main(input_excel_path, query, min_row, max_row, smiles_column,
+def main(input_excel_path, query, min_row, max_row, smiles_column,  # type: ignore[no-untyped-def]
          binding_data_column, convert_Kd_dG, output_txt_path):
     import pandas
     import rdkit
@@ -119,8 +126,8 @@ def main(input_excel_path, query, min_row, max_row, smiles_column,
 
 inputs = {'input_excel_path': xlsxfile,
           'query': string,
-          'min_row': {**integer, 'default': 1},
-          'max_row': {**integer, 'default': -1},
+          'min_row': {'type': 'int', 'format': 'edam:format_2330', 'default': 1},
+          'max_row': {'type': 'int', 'format': 'edam:format_2330', 'default': -1},
           'smiles_column': string,
           'binding_data_column': string,
           'convert_Kd_dG': string,

examples/scripts/generate_pdbbind_complex.py

@@ -1,5 +1,4 @@
 # pylint: disable=import-outside-toplevel,no-member
-# type: ignore
 from collections import defaultdict
 import distutils.util
 import math
@@ -88,7 +87,7 @@ def read_index_file(index_file_path: str) -> pd.DataFrame:
             standard_type = re.split(r"=[-+]?(?:\d*\.\d+|\d+)", words[4])[0]
             kd = float(re.findall(r"[-+]?(?:\d*\.\d+|\d+)", words[4])[0])
             data['Kd_Ki'].append(standard_type)
-            data['value'].append(kd * unit_conv[unit])
+            data['value'].append(str(kd * unit_conv[unit]))
             data['ligand_name'].append(re.findall(r'\((.*?)\)', words[7])[0])
 
     return pd.DataFrame.from_dict(data)
@@ -124,7 +123,6 @@ def load_data(index_file_name: str, base_dir: str, query: str, output_txt_path:
     # Calculate dG
     df = df[['PDB_code', 'value', 'Kd_Ki']]
     binding_data: List[str] = []
-    convert_Kd_dG = distutils.util.strtobool(convert_Kd_dG)
     microMolar = 0.000001  # uM
     for _, row in enumerate(df.values):
 

examples/scripts/nmr4md.py

@@ -1,7 +1,7 @@
 from workflow_types import *
 
 
-def main(input_tpr_path, input_trr_path, output_png_path):
+def main(input_tpr_path, input_trr_path, output_png_path):  # type: ignore[no-untyped-def]
     import MDAnalysis as mda
     import nmrformd
     from matplotlib import pyplot as plt

examples/scripts/python_cwl_driver.py

@@ -68,7 +68,11 @@ def import_python_file(python_module_name: str, python_file_path: Path) -> Modul
     if spec:
         module_ = importlib.util.module_from_spec(spec)
         sys.modules[python_module_name] = module_
-        spec.loader.exec_module(module_)  # type: ignore
+        if spec.loader:
+            spec.loader.exec_module(module_)  # guard behind if to satisfy mypy
+        else:
+            print(f'Error! Cannot load {spec}')
+            sys.exit(1)
         # Note that now (after calling exec_module) we can call import_module without error
         # module_ = importlib.import_module(python_module_name)
     else: