Merge pull request #22 from theochem/pre_commit_config

Add `pre commit` checks

.gitignore

@@ -108,4 +108,3 @@ tags
 
 # version file generated by rob
 procrustes/_version.py
-

.pre-commit-config.yaml

@@ -0,0 +1,13 @@
+minimum_pre_commit_version: 3.4.0
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+      - id: check-merge-conflict  # Check for files that contain merge conflict strings.
+      - id: trailing-whitespace   # Trims trailing whitespace.
+        args: [--markdown-linebreak-ext=md]
+      - id: mixed-line-ending     # Replaces or checks mixed line ending.
+        args: [--fix=lf]
+      - id: end-of-file-fixer     # Makes sure files end in a newline and only a newline.
+      - id: check-merge-conflict  # Check for files that contain merge conflict strings.
+      - id: check-ast             # Simply check whether files parse as valid python.

MANIFEST.in

@@ -1,4 +1,3 @@
 include b3clf/pre_trained/*
 include b3clf/feature_list.txt
 include b3clf/data/B3clf_thresholds.xlsx
-

README.md

@@ -3,13 +3,13 @@
 ## About
 
 The blood-brain barrier (BBB) protects and regulations the microvasculature in the central nervous system (CNS)
-by inhibiting the transportation or passage of toxins and pathogens from the blood. Because of its resistance to 
+by inhibiting the transportation or passage of toxins and pathogens from the blood. Because of its resistance to
 exogenous compounds, the BBB also poses a challenge for the
-delivery of neuroactive molecules (i.e. drugs) into the CNS. 
-Understanding small molecules' BBB permeability is therefore vital for CNS drug discovery, and should 
+delivery of neuroactive molecules (i.e. drugs) into the CNS.
+Understanding small molecules' BBB permeability is therefore vital for CNS drug discovery, and should
 be considered at an early stage in the drug-development pipeline to avoid costly late-stage failures.
 
-`B3clf` uses data from 7407 molecules, taken from our curated dataset, 
+`B3clf` uses data from 7407 molecules, taken from our curated dataset,
 [B3DB](https://github.com/theochem/B3DB). It supports
 24 different models, with four different classification algorithms (_dtree_ for decision
 trees, _logreg_ for logistical regression, _knn_ for KNN, _xgb_ for XGBoost) and six resampling

b3clf/feature_list.txt

@@ -472,4 +472,4 @@ Dm
 E1v
 E2v
 E3v
-Dv
+Dv

b3clf/geometry_opt.py

@@ -96,7 +96,7 @@ def minimize_with_rdkit(input_molfname,
         mols = []
         for idx, smi in enumerate(smile_list):
             mol = Chem.MolFromSmiles(smi)
-            # This will overwrite 
+            # This will overwrite
             if mol is not None:
                 mol.SetProp("_Name", mol_name_list[idx])
                 mols.append(mol)

b3clf/test/test_SMILES.csv

@@ -4,4 +4,4 @@
 CCC
 CCCC
 CC(=O)OC1=CC=CC=C1C(=O)O
-CC(=O)OC1=C(C=C(C=C1)Cl)C(=O)OC(=O)C2=C(C=CC(=C2)Cl)OC(=O)C
+CC(=O)OC1=C(C=C(C=C1)Cl)C(=O)OC(=O)C2=C(C=CC(=C2)Cl)OC(=O)C

b3clf/test/test_input_sdf.sdf

@@ -109,22 +109,22 @@ H1_Bepotastine
  26 50  1  0
  27 51  1  0
 M  END
->  <compoud_name>  (1) 
+>  <compoud_name>  (1)
 H1_Bepotastine
 
->  <SMILES>  (1) 
+>  <SMILES>  (1)
 [H]OC(=O)C([H])([H])C([H])([H])C([H])([H])N1C([H])([H])C([H])([H])C([H])(OC([H])(c2nc([H])c([H])c([H])c2[H])c2c([H])c([H])c(Cl)c([H])c2[H])C([H])([H])C1([H])[H]
 
->  <cid>  (1) 
+>  <cid>  (1)
 2350
 
->  <category>  (1) 
+>  <category>  (1)
 N
 
->  <inchi>  (1) 
+>  <inchi>  (1)
 InChI=1S/C21H25ClN2O3/c22-17-8-6-16(7-9-17)21(19-4-1-2-12-23-19)27-18-10-14-24(15-11-18)13-3-5-20(25)26/h1-2,4,6-9,12,18,21H,3,5,10-11,13-15H2,(H,25,26)/t21-/m1/s1
 
->  <Energy>  (1) 
+>  <Energy>  (1)
 49.1758
 
 $$$$
@@ -226,22 +226,22 @@ H1_Quifenadine
  21 44  1  0
  22 45  1  0
 M  END
->  <compoud_name>  (2) 
+>  <compoud_name>  (2)
 H1_Quifenadine
 
->  <SMILES>  (2) 
+>  <SMILES>  (2)
 [H]OC(c1c([H])c([H])c([H])c([H])c1[H])(c1c([H])c([H])c([H])c([H])c1[H])C1([H])C([H])([H])N2C([H])([H])C([H])([H])C1([H])C([H])([H])C2([H])[H]
 
->  <cid>  (2) 
+>  <cid>  (2)
 65600
 
->  <category>  (2) 
+>  <category>  (2)
 N
 
->  <inchi>  (2) 
+>  <inchi>  (2)
 InChI=1S/C20H23NO/c22-20(17-7-3-1-4-8-17,18-9-5-2-6-10-18)19-15-21-13-11-16(19)12-14-21/h1-10,16,19,22H,11-15H2/t19-/m1/s1
 
->  <Energy>  (2) 
+>  <Energy>  (2)
 84.891
 
 $$$$
@@ -366,22 +366,22 @@ H1_Rupatadine
  30 55  1  0
  30 56  1  0
 M  END
->  <compoud_name>  (3) 
+>  <compoud_name>  (3)
 H1_Rupatadine
 
->  <SMILES>  (3) 
+>  <SMILES>  (3)
 [H]c1nc2c(c([H])c1[H])C([H])([H])C([H])([H])c1c([H])c(Cl)c([H])c([H])c1C2=C1C([H])([H])C([H])([H])N(C([H])([H])c2c([H])nc([H])c(C([H])([H])[H])c2[H])C([H])([H])C1([H])[H]
 
->  <cid>  (3) 
+>  <cid>  (3)
 133017
 
->  <category>  (3) 
+>  <category>  (3)
 N
 
->  <inchi>  (3) 
+>  <inchi>  (3)
 InChI=1S/C26H26ClN3/c1-18-13-19(16-28-15-18)17-30-11-8-20(9-12-30)25-24-7-6-23(27)14-22(24)5-4-21-3-2-10-29-26(21)25/h2-3,6-7,10,13-16H,4-5,8-9,11-12,17H2,1H3
 
->  <Energy>  (3) 
+>  <Energy>  (3)
 119.976
 
 $$$$