secse v1.3 update

README.md

@@ -20,7 +20,7 @@ further validation.
 ----------------------------
 
 1. Setting up dependencies 
-  python ~=3.9, perl ~=5.32
+ python ~=3.9, perl ~=5.32
  ```bash
  conda create --name secse -c conda-forge parallel tqdm biopandas openbabel chemprop xlrd=2 pandarallel rdkit=2022.09
  conda activate secse
@@ -114,6 +114,10 @@ further validation.
  - _spiro_site_count_, maximum of spiro ring site count, default=1, type=int
  - _fused_site_count_, maximum of fused ring site count, default=3, type=int
  - _rdkit_sa_score_, synthetic accessibility score (calculated by RDKit) cutoff, default=5, type=float
+ - _substructure_filter_, files containing the customized unwanted substructure SMARTS in "*.xls" format, set the
+ value to 0 if you do not have any additional unwanted substructure. PANIS already includes as default. The file
+ should include columns for **`Pattern`**, **`ID`**, and **`Max`**, where the **`ID`** should be unique for each SMARTS. You can
+ refer to the example file [subtructure_filter_demo.xls](demo/subtructure_filter_demo.xls), default=0, type=string
 
  Config file of a demo case [phgdh_demo_vina.ini](demo/phgdh_demo_vina.ini) 
  Customized rule json template [rules.json](demo/rules.json). Rule ID should be in the form G-001-XXXX, like
@@ -139,7 +143,8 @@ GNU Parallel installation
 
 python ~=3.9, perl ~=5.32
 
-numpy~=1.24.3, pandas~=1.3.3, xlrd～=2.0.1, pandarallel~=1.5.2, tqdm~=4.65.0, biopandas~=0.4.1, openbabel~=3.1.1, rdkit~=2022.09, chemprop~=1.5.2, pytorch~=2.0.0+cu117
+numpy~=1.24.3, pandas~=1.3.3, xlrd～=2.0.1, pandarallel~=1.5.2, tqdm~=4.65.0, biopandas~=0.4.1, openbabel~=3.1.1, rdkit~
+=2022.09, chemprop~=1.5.2, pytorch~=2.0.0+cu117
 
 Linux server with CPUs only also works.
 

demo/phgdh_demo_vina.ini

@@ -48,4 +48,5 @@ ring_system_count = 4
 bridged_site_count = 2
 spiro_site_count = 1
 fused_site_count = 3
-rdkit_sa_score = 5
+rdkit_sa_score = 5
+substructure_filter = 0

secse/growing/filter.py

@@ -33,10 +33,17 @@ def __init__(self, gen, config_path):
  self.input_smiles = None
  self.mol = None
  self.pains_smarts = None
- self.strutFilter = StructureFilter()
 
  config = configparser.ConfigParser()
  config.read(config_path)
+
+ substructure_filter_file = config.get("properties", "substructure_filter")
+ if substructure_filter_file == "0":
+ self.strutFilter = StructureFilter()
+ else:
+ # print("Use additional substructure filter patters.")
+ self.strutFilter = StructureFilter(substructure_filter_file)
+
  self.MW = config.getfloat("properties", "MW")
  self.logP_lower = config.getfloat("properties", "logP_lower")
  self.logP_upper = config.getfloat("properties", "logP_upper")
@@ -143,19 +150,7 @@ def alert_filter(self):
  yield "PAINS"
  yield "PASS"
 
- def element_filter(self):
- f_count = self.input_smiles.count("F")
- br_count = self.input_smiles.count("Br")
- cl_count = self.input_smiles.count("Cl")
- i_count = self.input_smiles.count("I")
- s_count = self.input_smiles.count("S") + self.input_smiles.count("s")
- p_count = self.input_smiles.count("P")
- if not all([f_count <= 5, br_count <= 2, cl_count <= 3, i_count <= 1, s_count <= 2, p_count <= 1]):
- yield "element"
- yield "PASS"
-
  def substructure_filter(self):
- # self.element_filter()
  yield self.strutFilter.sfilter(self.mol)
 
  def ring_system_filter(self):

secse/utilities/substructure_filter.py

@@ -9,13 +9,13 @@
 import pandas as pd
 from rdkit import Chem
 
-FILTER_FILE = "Structure Filter_20211015_v1.12.xls"
+FILTER_FILE = os.path.join(os.getenv("SECSE"), "utilities", "Structure Filter_20211015_v1.12.xls")
 
 
 class StructureFilter:
- def __init__(self):
- df = pd.read_excel(os.path.join(os.getenv("SECSE"), "utilities", FILTER_FILE),
-  usecols=["Pattern", "ID", "Max"]).dropna()
+ def __init__(self, filter_lst=FILTER_FILE):
+ df = pd.read_excel(filter_lst, usecols=["Pattern", "ID", "Max"]).dropna()
+ df["ID"] = df["ID"].astype(str)
  df = df.set_index("ID")
  df["Pattern_sma"] = df["Pattern"].apply(lambda x: Chem.MolFromSmarts(x))
  self.fdic = df[["Pattern_sma", "Max"]].T.to_dict()