kdock 0.0.2__py3-none-any.whl → 0.0.4__py3-none-any.whl

kdock/__init__.py

@@ -1 +1 @@
-__version__ = "0.0.2"
+__version__ = "0.0.4"

kdock/_modidx.py

@@ -42,6 +42,10 @@ d = { 'settings': { 'branch': 'main',
                                                                                              'kdock/af3/protein_pairs.py'),
                                          'kdock.af3.protein_pairs.get_protein_subjson': ( 'af3/protein_pairs.html#get_protein_subjson',
                                                                                           'kdock/af3/protein_pairs.py')},
+            'kdock.boltz.dock': { 'kdock.boltz.dock.plot_scatter_spearman': ( 'core/boltz/dock.html#plot_scatter_spearman',
+                                                                              'kdock/boltz/dock.py'),
+                                  'kdock.boltz.dock.prepare_boltz': ('core/boltz/dock.html#prepare_boltz', 'kdock/boltz/dock.py'),
+                                  'kdock.boltz.dock.run_boltz': ('core/boltz/dock.html#run_boltz', 'kdock/boltz/dock.py')},
             'kdock.core.data': { 'kdock.core.data.Collins': ('core/data.html#collins', 'kdock/core/data.py'),
                                  'kdock.core.data.Collins.get_antibiotics_2k': ( 'core/data.html#collins.get_antibiotics_2k',
                                                                                  'kdock/core/data.py'),
@@ -54,8 +58,10 @@ d = { 'settings': { 'branch': 'main',
                                  'kdock.core.data.Kras.get_mirati_g12d_raw': ( 'core/data.html#kras.get_mirati_g12d_raw',
                                                                                'kdock/core/data.py'),
                                  'kdock.core.data.Kras.get_seq': ('core/data.html#kras.get_seq', 'kdock/core/data.py'),
-                                 'kdock.core.data.fetch_csv': ('core/data.html#fetch_csv', 'kdock/core/data.py')},
+                                 'kdock.core.data.fetch_csv': ('core/data.html#fetch_csv', 'kdock/core/data.py'),
+                                 'kdock.core.data.name2smi': ('core/data.html#name2smi', 'kdock/core/data.py')},
             'kdock.core.ligand': { 'kdock.core.ligand.compress_fp': ('core/ligand.html#compress_fp', 'kdock/core/ligand.py'),
+                                   'kdock.core.ligand.contain_acrylamide': ('core/ligand.html#contain_acrylamide', 'kdock/core/ligand.py'),
                                    'kdock.core.ligand.get_fp': ('core/ligand.html#get_fp', 'kdock/core/ligand.py'),
                                    'kdock.core.ligand.get_rdkit': ('core/ligand.html#get_rdkit', 'kdock/core/ligand.py'),
                                    'kdock.core.ligand.get_rdkit_3d': ('core/ligand.html#get_rdkit_3d', 'kdock/core/ligand.py'),

kdock/af3/analyze.py

@@ -1,15 +1,15 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/af3/03_analyze.ipynb.
 
-# %% auto 0
+# %% auto #0
 __all__ = ['read_summary_json', 'get_summary_df', 'process_summary_df', 'get_top_cases', 'get_3d_report', 'get_report',
            'copy_file']
 
-# %% ../../nbs/af3/03_analyze.ipynb 3
+# %% ../../nbs/af3/03_analyze.ipynb #bfdd4fae-37c7-4835-afb1-524e5a731add
 import json, shutil, pandas as pd
 from pathlib import Path
 import plotly.graph_objects as go
 
-# %% ../../nbs/af3/03_analyze.ipynb 5
+# %% ../../nbs/af3/03_analyze.ipynb #7b982142-f161-414b-b893-56234282cfb7
 def read_summary_json(json_path):
     "Read json file to dictionary"
     json_path = Path(json_path)
@@ -29,7 +29,7 @@ def read_summary_json(json_path):
             row[key] = value
     return row
 
-# %% ../../nbs/af3/03_analyze.ipynb 7
+# %% ../../nbs/af3/03_analyze.ipynb #6efc38e3-f8d8-4c3c-b068-f5a37a4af057
 def get_summary_df(output_dir):
     "Pack the summary json from the output folder to the df"
     
@@ -37,7 +37,7 @@ def get_summary_df(output_dir):
     print(len(path_list),'summary_confidences.json files detected')
     return pd.DataFrame(list(map(read_summary_json,path_list)))
 
-# %% ../../nbs/af3/03_analyze.ipynb 10
+# %% ../../nbs/af3/03_analyze.ipynb #2ae7e00d-f285-4fc1-a40c-af0f64d74376
 def process_summary_df(df,generate_report=False):
     "Post process the json-converted pandas df; remove redundant columns; available for pairs"
     
@@ -90,7 +90,7 @@ def process_summary_df(df,generate_report=False):
     
     return df
 
-# %% ../../nbs/af3/03_analyze.ipynb 12
+# %% ../../nbs/af3/03_analyze.ipynb #e1af07e2-b86a-492d-b8d7-0fd2f8d90779
 def get_top_cases(df,n=30):
     "Get top cases from the metric"
     idxs = set()
@@ -109,7 +109,7 @@ def get_top_cases(df,n=30):
 
     return list(idxs)
 
-# %% ../../nbs/af3/03_analyze.ipynb 14
+# %% ../../nbs/af3/03_analyze.ipynb #89900087-ff2c-48e3-bbe7-3077de2d1f32
 def get_3d_report(df,index_list, x='iptm',y='ptm',z='chain_pair_pae_min_add',save_dir='af_report'):
     "Generate 3d plot html file given case index and x, y, z colname"
     annotation = df.index.where(df.index.isin(index_list),'').str.split('_').str[1]
@@ -140,7 +140,7 @@ def get_3d_report(df,index_list, x='iptm',y='ptm',z='chain_pair_pae_min_add',sav
     fig.write_html(Path(save_dir)/'3d_scatter_plot.html',full_html=True)
     print('Exported the html to 3d_scatter_plot.html')
 
-# %% ../../nbs/af3/03_analyze.ipynb 16
+# %% ../../nbs/af3/03_analyze.ipynb #02cab7f4-a581-43fb-a0b9-6df5ce6d1d08
 def get_report(out_dir,save_dir='af_report'):
     "Generate summary report based on summary_confidences file; return summary df and top cases"
     out = get_summary_df(out_dir)
@@ -153,7 +153,7 @@ def get_report(out_dir,save_dir='af_report'):
     
     return out, top_cases
 
-# %% ../../nbs/af3/03_analyze.ipynb 18
+# %% ../../nbs/af3/03_analyze.ipynb #11319fd1-0bee-4e8c-b224-9eed52b8cbb2
 def copy_file(idx_name, source_dir, dest_dir):
     "Copy all model cif generated by AF3 to the new dest folder"
     source_path = Path(source_dir)/f"{idx_name}/{idx_name}_model.cif"

kdock/af3/docker.py

@@ -1,12 +1,12 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/af3/01_docker.ipynb.
 
-# %% auto 0
+# %% auto #0
 __all__ = ['get_docker_command', 'docker_single_full', 'docker_multi_full', 'docker_multi_msa', 'docker_multi_infer']
 
-# %% ../../nbs/af3/01_docker.ipynb 3
+# %% ../../nbs/af3/01_docker.ipynb #57b6887a-a451-462e-9452-d850d3028317
 from fastcore.meta import delegates
 
-# %% ../../nbs/af3/01_docker.ipynb 6
+# %% ../../nbs/af3/01_docker.ipynb #10f9c68f-0374-4cb2-b10e-65bb0107844f
 def get_docker_command(
     input_dir="af_input", # Directory for input data
     output_dir="af_output", # Directory for output results
@@ -80,7 +80,7 @@ def get_docker_command(
     docker_command = "\n".join(cmd_parts)
     print(docker_command)
 
-# %% ../../nbs/af3/01_docker.ipynb 12
+# %% ../../nbs/af3/01_docker.ipynb #5e5c9de1-0b4b-433f-90a8-02fa755aafc3
 @delegates(get_docker_command)
 def docker_single_full(json_path,output_dir,cache_dir=False,**kwargs):
     "Single json task with full pipeline."
@@ -90,7 +90,7 @@ def docker_single_full(json_path,output_dir,cache_dir=False,**kwargs):
         cache_dir=cache_dir,
         **kwargs)
 
-# %% ../../nbs/af3/01_docker.ipynb 16
+# %% ../../nbs/af3/01_docker.ipynb #996f65a3-64ee-4288-aed7-3a0acba73175
 @delegates(get_docker_command)
 def docker_multi_full(input_dir,output_dir,**kwargs):
     "Folder of json as input with full pipeline."
@@ -99,7 +99,7 @@ def docker_multi_full(input_dir,output_dir,**kwargs):
         output_dir=output_dir,
         **kwargs)
 
-# %% ../../nbs/af3/01_docker.ipynb 19
+# %% ../../nbs/af3/01_docker.ipynb #7512a43c-28c2-41f8-b4c5-4ddf1e56f716
 @delegates(get_docker_command)
 def docker_multi_msa(input_dir,output_dir,search_only=True,**kwargs):
     "MSA search only, without structure inference; CPU only."
@@ -109,7 +109,7 @@ def docker_multi_msa(input_dir,output_dir,search_only=True,**kwargs):
         search_only=search_only,
         **kwargs)
 
-# %% ../../nbs/af3/01_docker.ipynb 22
+# %% ../../nbs/af3/01_docker.ipynb #403f1d8f-6055-486a-a0f9-bc4b2ca8feaa
 @delegates(get_docker_command)
 def docker_multi_infer(input_dir,output_dir,skip_search=True,**kwargs):
     "Infer only with pre-calculated MSA; GPU is needed."

kdock/af3/json.py

@@ -1,10 +1,10 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/af3/00_json.ipynb.
 
-# %% auto 0
+# %% auto #0
 __all__ = ['dump_json', 'get_protein_json', 'read_json', 'get_protein_smiles_json', 'get_protein_ccdcode_json',
            'assign_atom_names_from_graph', 'mol_to_ccd_text', 'sdf2ccd', 'get_protein_ccd_json', 'split_nfolder']
 
-# %% ../../nbs/af3/00_json.ipynb 2
+# %% ../../nbs/af3/00_json.ipynb #1d0467e3-9fcb-4e07-a59f-58405b640950
 import re, shutil, json, pandas as pd, numpy as np
 from pathlib import Path
 
@@ -14,13 +14,13 @@ from rdkit import Chem
 
 from Bio.PDB import PDBParser
 
-# %% ../../nbs/af3/00_json.ipynb 4
+# %% ../../nbs/af3/00_json.ipynb #62063f37-32aa-4a12-8e57-29ef4fff1413
 def dump_json(data, save_path):
     "Save json data into a file"
     with open(save_path,'w') as f: 
         json.dump(data,f,indent=4)
 
-# %% ../../nbs/af3/00_json.ipynb 5
+# %% ../../nbs/af3/00_json.ipynb #14d9fdb5-7e05-47f6-b596-9d751f9f5618
 def get_protein_json(name, # job name
                      seq, # aa sequence
                      save_path=None, # .json
@@ -48,13 +48,13 @@ def get_protein_json(name, # job name
         dump_json(json_data,save_path)
     return json_data
 
-# %% ../../nbs/af3/00_json.ipynb 9
+# %% ../../nbs/af3/00_json.ipynb #9bb34b3b-e90f-4112-a947-aee8a8610335
 def read_json(file_path):
     with open(file_path,'r') as f: 
         data = json.load(f)
     return data
 
-# %% ../../nbs/af3/00_json.ipynb 11
+# %% ../../nbs/af3/00_json.ipynb #b9490613-30cd-4cf9-93a7-0e53a6645932
 def get_protein_smiles_json(smi_id:str, 
                             SMILES:str, 
                             protein_json, # json type
@@ -88,7 +88,7 @@ def get_protein_smiles_json(smi_id:str,
         dump_json(json_data,save_path)
     return json_data
 
-# %% ../../nbs/af3/00_json.ipynb 18
+# %% ../../nbs/af3/00_json.ipynb #300bb051-4246-400e-bdc3-dd43e4da47d1
 def get_protein_ccdcode_json(protein_json,  # dict with protein sequence
                               ccd_code,      # str or list of str
                               job_id: str,   # job/task ID
@@ -128,7 +128,7 @@ def get_protein_ccdcode_json(protein_json,  # dict with protein sequence
 
     return json_data
 
-# %% ../../nbs/af3/00_json.ipynb 22
+# %% ../../nbs/af3/00_json.ipynb #e850527d-826d-4c7f-9a66-bf307c44b809
 # Mapping bond types to mmCIF-compatible values
 _RDKIT_BOND_TYPE_TO_MMCIF = {
     rd_chem.BondType.SINGLE: 'SING',
@@ -208,7 +208,7 @@ def mol_to_ccd_text(mol, component_id, pdbx_smiles=None, include_hydrogens=False
 
     return "\n".join(lines)
 
-# %% ../../nbs/af3/00_json.ipynb 23
+# %% ../../nbs/af3/00_json.ipynb #c099dc24-d29e-49a1-9cbb-d14e7bc2a3de
 def sdf2ccd(sdf_path,
             CCD_name='lig-1', # do not use '_'; use as less letter as possible, 'lig-any' leads to extra ligands
             ):
@@ -218,7 +218,7 @@ def sdf2ccd(sdf_path,
     mol = supplier[0]  # Get the first molecule
     return mol_to_ccd_text(mol,CCD_name)
 
-# %% ../../nbs/af3/00_json.ipynb 26
+# %% ../../nbs/af3/00_json.ipynb #3953bc6b-3bc0-40e5-a87b-08eb640b8fcf
 def get_protein_ccd_json(protein_json, # dict with protein sequence
                          rec_residue_num:int, # 1-indexed, for bondedAtomPairs, e.g., ["A", 145, "SG"] 
                          rec_atom_id:str, # for bondedAtomPairs, e.g., ["A", 145, "SG"] 
@@ -262,7 +262,7 @@ def get_protein_ccd_json(protein_json, # dict with protein sequence
 
     return json_data
 
-# %% ../../nbs/af3/00_json.ipynb 30
+# %% ../../nbs/af3/00_json.ipynb #c7f16eec-082a-4233-b3ed-b96d58ecedb4
 def split_nfolder(folder_dir, 
                   n=4):
     "Move json files from a folder into subfolders (folder_0, folder_1, ..., folder_N)."

kdock/af3/protein_pairs.py

@@ -1,10 +1,10 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/af3/02_protein_pairs.ipynb.
 
-# %% auto 0
+# %% auto #0
 __all__ = ['get_colabfold_cmd', 'copy_a3m', 'a3m_to_seq', 'get_protein_subjson', 'dump_json_folder', 'get_multi_protein_json',
            'generate_pair_df']
 
-# %% ../../nbs/af3/02_protein_pairs.ipynb 4
+# %% ../../nbs/af3/02_protein_pairs.ipynb #92000c0e-6470-423c-9c55-9972a341282b
 import os, json, shutil, pandas as pd
 from tqdm import tqdm
 from itertools import combinations
@@ -12,12 +12,12 @@ from pathlib import Path
 from .json import *
 from .docker import *
 
-# %% ../../nbs/af3/02_protein_pairs.ipynb 9
+# %% ../../nbs/af3/02_protein_pairs.ipynb #3f3ae31b-287e-4810-9e10-db969c3fcc6b
 def get_colabfold_cmd(csv_path,project_name):
     print('Run below in terminal:')
     print(f'\n colabfold_batch {csv_path} msa_{project_name} --msa-only')
 
-# %% ../../nbs/af3/02_protein_pairs.ipynb 13
+# %% ../../nbs/af3/02_protein_pairs.ipynb #9fb90cd0-3260-4dd1-a169-340a75633ab0
 def copy_a3m(a3m_dir: str, # Path to the source directory containing .a3m files.
              dest_dir: str, # Path to the destination directory where files will be copied
              ):
@@ -33,12 +33,12 @@ def copy_a3m(a3m_dir: str, # Path to the source directory containing .a3m files.
 
     print(f"Copied {len(files)} a3m files from {a3m_dir} to {dest_dir}")
 
-# %% ../../nbs/af3/02_protein_pairs.ipynb 17
+# %% ../../nbs/af3/02_protein_pairs.ipynb #def3928f-c895-479f-9e88-093fdf3892da
 def a3m_to_seq(file_path:Path):
     "Get protein sequence from a3m file"
     return file_path.read_text().splitlines()[2] # protein sequence is located on line 2
 
-# %% ../../nbs/af3/02_protein_pairs.ipynb 19
+# %% ../../nbs/af3/02_protein_pairs.ipynb #03da4db8-60b5-409e-889a-f44b2fb27705
 def get_protein_subjson(gene_name, a3m_dir=".",idx = 'A',run_template=True):
     "Get subjson (protein part) with colabfold unpairedMSA .a3m path"
     file_path = Path(a3m_dir)/f"{gene_name}.a3m"
@@ -55,13 +55,13 @@ def get_protein_subjson(gene_name, a3m_dir=".",idx = 'A',run_template=True):
 
     return json_data
 
-# %% ../../nbs/af3/02_protein_pairs.ipynb 22
+# %% ../../nbs/af3/02_protein_pairs.ipynb #76c918a2-630a-48ac-a682-501cfe4a522f
 def dump_json_folder(json_data, folder):
     "Save json under a folder"
     file_path = Path(folder)/f"{json_data['name']}.json"
     with open(file_path,'w') as f: json.dump(json_data,f,indent=4)
 
-# %% ../../nbs/af3/02_protein_pairs.ipynb 23
+# %% ../../nbs/af3/02_protein_pairs.ipynb #8e97b4ea-17ec-48dd-bca0-c2f11763205a
 def get_multi_protein_json(gene_list,a3m_dir,run_template=True,save_folder=None):
     'Get json of multiple proteins, with unpaired MSA path indicated (from colabfold MSA)'
     sequences = []
@@ -82,7 +82,7 @@ def get_multi_protein_json(gene_list,a3m_dir,run_template=True,save_folder=None)
         dump_json_folder(json_data,save_folder)
     return json_data
 
-# %% ../../nbs/af3/02_protein_pairs.ipynb 27
+# %% ../../nbs/af3/02_protein_pairs.ipynb #8cc62d64-4643-49a3-a7ed-be7231abb0b9
 def generate_pair_df(gene_list,self_pair=True):
     "Unique pair genes in a gene list"
     pairs = list(combinations(gene_list, 2))

kdock/boltz/dock.py

@@ -0,0 +1,107 @@
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/core/boltz/00_dock.ipynb.
+
+# %% auto #0
+__all__ = ['prepare_boltz', 'run_boltz', 'plot_scatter_spearman']
+
+# %% ../../nbs/core/boltz/00_dock.ipynb #3b60daa9
+# basics
+import subprocess
+from pathlib import Path
+
+# %% ../../nbs/core/boltz/00_dock.ipynb #71a6ad95
+def prepare_boltz(seq: str, # Amino acid sequence of the protein the protein
+                    smiles: str, # SMILES string of the ligand
+                    fname: str, # Output filename (should end with .yaml)
+                    ):
+    "Create a YAML file for protein-ligand affinity prediction."
+    yaml_content = f"""version: 1
+sequences:
+  - protein:
+      id: "A"
+      sequence: "{seq}"
+  - ligand:
+      id: "B"
+      smiles: "{smiles}"
+properties:
+  - affinity:
+      binder: "B"
+"""
+    with open(fname, "w") as f:
+        f.write(yaml_content)
+
+# %% ../../nbs/core/boltz/00_dock.ipynb #486e2576
+def run_boltz(file_list:list[Path], # list of .yaml path in Pathlib object
+                     api_key):
+    
+    "Run Boltz-Lab predictions for a list of YAML files."
+
+    # config key
+    subprocess.run(
+        ["boltz-lab", "config", "--api-key", api_key.strip()],
+        check=True
+    )
+    failed = []
+
+    for file in file_list:
+        print(f"\nSubmitting: {str(file)}")
+
+        result = subprocess.run(
+            ["boltz-lab", "predict", str(file),
+             "--no-wait", # for batch run, so no need to wait the results til the next
+             "--name",file.stem, # job name appeared in boltz
+             ],
+            capture_output=True,
+            text=True,
+        )
+
+        if result.returncode != 0: failed.append(file.name)
+
+        print(result.stdout)
+
+
+    print("\n======== SUMMARY ========")
+    print(f"Total: {len(file_list)}")
+    print(f"Failed: {len(failed)}")
+
+    return failed
+
+
+# %% ../../nbs/core/boltz/00_dock.ipynb #45b0e6aa
+import matplotlib.pyplot as plt
+import seaborn as sns, numpy as np
+from scipy.stats import spearmanr
+
+# %% ../../nbs/core/boltz/00_dock.ipynb #eec74db7
+def plot_scatter_spearman(data, x, y, ax=None):
+    """
+    Plot scatter + Spearman correlation and p-value annotation.
+    """
+    if ax is None:
+        ax = plt.gca()
+
+    # Drop NA
+    sub = data[[x, y]].dropna()
+    x_vals = sub[x]
+    y_vals = sub[y]
+
+    # Compute Spearman
+    rho, p = spearmanr(x_vals, y_vals)
+
+    # Plot
+    sns.scatterplot(data=sub, x=x, y=y, ax=ax)
+
+    # Annotate
+    text = f"Spearman ρ = {rho:.3f}\np = {p:.2e}"
+    ax.text(
+        0.98, 0.98,   # x, y in axes fraction
+        text,
+        transform=ax.transAxes,
+        ha='right',          # horizontal align
+        va='top',            # vertical align
+        fontsize=11,
+        bbox=dict(boxstyle="round", facecolor="white", alpha=0.7)
+    )
+
+    ax.set_title(f'{x} vs {y}')
+
+    return rho, p

kdock/core/data.py

@@ -1,22 +1,32 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/core/00_data.ipynb.
 
-# %% auto 0
-__all__ = ['BASE_URL', 'fetch_csv', 'Collins', 'Kras']
+# %% auto #0
+__all__ = ['BASE_URL', 'name2smi', 'fetch_csv', 'Collins', 'Kras']
 
-# %% ../../nbs/core/00_data.ipynb 3
+# %% ../../nbs/core/00_data.ipynb #e61ba13c
 import pandas as pd
 import requests
 from functools import lru_cache
+import pubchempy as pcp
 
-# %% ../../nbs/core/00_data.ipynb 7
+# %% ../../nbs/core/00_data.ipynb #b97285b8
+def name2smi(name):
+    "Given a compound name, get SMILES in PubChem database. "
+    compounds = pcp.get_compounds(name, 'name')
+    if not compounds: return None
+    # get the first rank
+    c = compounds[0]
+    return c.smiles # can also return c.cid compound ID
+
+# %% ../../nbs/core/00_data.ipynb #209ffb82
 BASE_URL = "https://github.com/sky1ove/kdock/raw/main/"
 
-# %% ../../nbs/core/00_data.ipynb 8
+# %% ../../nbs/core/00_data.ipynb #d7e2b62a
 @lru_cache()
 def fetch_csv(url):
     return pd.read_csv(url)
 
-# %% ../../nbs/core/00_data.ipynb 9
+# %% ../../nbs/core/00_data.ipynb #1f1a2239
 class Collins:
     "A class of loading compound datasets from Collins lab."
 
@@ -45,7 +55,7 @@ class Collins:
         """
         return fetch_csv(BASE_URL + "dataset/antibiotics_enzyme.csv")
 
-# %% ../../nbs/core/00_data.ipynb 19
+# %% ../../nbs/core/00_data.ipynb #16424d50
 class Kras:
     "A class of fetching various KRAS datasets."
     @staticmethod

kdock/core/ligand.py

@@ -1,10 +1,11 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/core/03_ligand.ipynb.
 
-# %% auto 0
-__all__ = ['plot_drug', 'rdkit_conformer', 'tanimoto', 'get_rdkit', 'get_rdkit_3d', 'get_rdkit_all', 'remove_hi_corr',
-           'preprocess', 'get_rdkit_df', 'get_fp', 'compress_fp', 'tanimoto_numba', 'hash_fp', 'get_same_mol_group']
+# %% auto #0
+__all__ = ['contain_acrylamide', 'plot_drug', 'rdkit_conformer', 'tanimoto', 'get_rdkit', 'get_rdkit_3d', 'get_rdkit_all',
+           'remove_hi_corr', 'preprocess', 'get_rdkit_df', 'get_fp', 'compress_fp', 'tanimoto_numba', 'hash_fp',
+           'get_same_mol_group']
 
-# %% ../../nbs/core/03_ligand.ipynb 3
+# %% ../../nbs/core/03_ligand.ipynb #b02d7ca8-fcbe-4c95-a0bc-4c1a1471578c
 import pandas as pd, numpy as np
 from rdkit import Chem,RDLogger,DataStructs
 from rdkit.Chem import Draw, rdDepictor, Descriptors,Descriptors3D, AllChem
@@ -16,7 +17,17 @@ from tqdm.contrib.concurrent import process_map
 from tqdm import tqdm
 RDLogger.DisableLog('rdApp.warning')
 
-# %% ../../nbs/core/03_ligand.ipynb 5
+# %% ../../nbs/core/03_ligand.ipynb #e9c0f1db
+def contain_acrylamide(smiles,
+                        ACRYLAMIDE_SMARTS="C=CC(=O)N", # SMARTS pattern for acrylamide
+                        ):
+    "Check if the SMILES contain acrylamide (can form covalent bond with cysteine in protein)"
+    acrylamide_pattern = Chem.MolFromSmarts(ACRYLAMIDE_SMARTS)
+    mol = Chem.MolFromSmiles(smiles)
+    if mol is None: raise ValueError("Invalid SMILES")
+    return mol.HasSubstructMatch(acrylamide_pattern)
+
+# %% ../../nbs/core/03_ligand.ipynb #18c2b546
 def plot_drug(drug_dict, flip_list=None, save_path=None):
     flip_list = flip_list or []
     mols = []
@@ -55,7 +66,7 @@ def plot_drug(drug_dict, flip_list=None, save_path=None):
         # display(SVG(svg_str))
         return svg_obj
 
-# %% ../../nbs/core/03_ligand.ipynb 8
+# %% ../../nbs/core/03_ligand.ipynb #3136f2ba-17fc-49a8-ab9e-15107d39cb62
 def rdkit_conformer(SMILES, # SMILES string
                     output=None, # file ".sdf" to be saved
                     method='ETKDG', # Optimization method, can be 'UFF', 'MMFF' or 'ETKDGv3'
@@ -98,7 +109,7 @@ def rdkit_conformer(SMILES, # SMILES string
         w.close()
     return mol
 
-# %% ../../nbs/core/03_ligand.ipynb 10
+# %% ../../nbs/core/03_ligand.ipynb #6b5f7fdd-89e2-481e-9f37-f999fccf3c86
 def tanimoto(df, # df with SMILES and ID columns
              smiles_col='SMILES', # colname of SMILES
              id_col='ID', # colname of compound ID
@@ -136,7 +147,7 @@ def tanimoto(df, # df with SMILES and ID columns
 
     return result_df
 
-# %% ../../nbs/core/03_ligand.ipynb 14
+# %% ../../nbs/core/03_ligand.ipynb #9268af86-13e9-4051-8300-635c12e00186
 def get_rdkit(SMILES:str):
     """
     Extract chemical features from SMILES
@@ -145,7 +156,7 @@ def get_rdkit(SMILES:str):
     mol = Chem.MolFromSmiles(SMILES)
     return Descriptors.CalcMolDescriptors(mol)
 
-# %% ../../nbs/core/03_ligand.ipynb 15
+# %% ../../nbs/core/03_ligand.ipynb #e003dc50-9fac-44f1-b2dd-15e9ecd812ce
 def get_rdkit_3d(SMILES:str):
     "Extract 3d features from SMILES"
     mol = Chem.MolFromSmiles(SMILES)
@@ -154,14 +165,14 @@ def get_rdkit_3d(SMILES:str):
     AllChem.UFFOptimizeMolecule(mol)
     return Descriptors3D.CalcMolDescriptors3D(mol)
 
-# %% ../../nbs/core/03_ligand.ipynb 16
+# %% ../../nbs/core/03_ligand.ipynb #7512ba88-69bf-4aaa-97b5-3624ad63184c
 def get_rdkit_all(SMILES:str):
     "Extract chemical features and 3d features from SMILES"
     feat = get_rdkit(SMILES)
     feat_3d = get_rdkit_3d(SMILES)
     return feat|feat_3d
 
-# %% ../../nbs/core/03_ligand.ipynb 17
+# %% ../../nbs/core/03_ligand.ipynb #081e1e1c-5b9e-4297-886c-3f17e3594dfa
 def remove_hi_corr(df: pd.DataFrame, 
                    thr=0.99 # threshold
                    ):
@@ -171,7 +182,7 @@ def remove_hi_corr(df: pd.DataFrame,
     to_drop = [column for column in upper.columns if any(upper[column] > thr)]
     return df.drop(to_drop, axis=1), to_drop
 
-# %% ../../nbs/core/03_ligand.ipynb 18
+# %% ../../nbs/core/03_ligand.ipynb #bdaca119-3060-4df6-b86f-1a2e9adf0950
 def preprocess(df: pd.DataFrame, thr=0.99):
     "Remove features with no variance, and highly correlated features based on threshold."
     col_ori = df.columns
@@ -196,7 +207,7 @@ def preprocess(df: pd.DataFrame, thr=0.99):
     
     return df
 
-# %% ../../nbs/core/03_ligand.ipynb 19
+# %% ../../nbs/core/03_ligand.ipynb #8d66039a-89ad-4da4-bee1-c37e78c59e36
 def get_rdkit_df(df: pd.DataFrame,
                  include_3d=False,
                  col='SMILES',
@@ -217,7 +228,7 @@ def get_rdkit_df(df: pd.DataFrame,
 
     return out
 
-# %% ../../nbs/core/03_ligand.ipynb 25
+# %% ../../nbs/core/03_ligand.ipynb #40788d6f-b180-4b07-9b01-b8d607939523
 def get_fp(SMILES, 
            name='ecfp',
            ELEMENTS_PER_WORKER = 1_000_000):
@@ -242,12 +253,12 @@ def get_fp(SMILES,
     
     return np.concatenate(middle_parts)
 
-# %% ../../nbs/core/03_ligand.ipynb 29
+# %% ../../nbs/core/03_ligand.ipynb #a1a77f98-f3c6-462c-9e5e-c4caf18a40a2
 def compress_fp(array):
     "Compress binary finterprints using np.packbits"
     return np.packbits(array,axis=1)
 
-# %% ../../nbs/core/03_ligand.ipynb 47
+# %% ../../nbs/core/03_ligand.ipynb #d27a7e74-83cd-414b-8c96-c8439535fe6f
 @numba.njit(parallel=True)
 def tanimoto_numba(fps):
     "Get a NxN matrix of tanimoto similarity among N compounds."
@@ -263,12 +274,12 @@ def tanimoto_numba(fps):
             result[j, i] = sim  # fill symmetric position
     return result
 
-# %% ../../nbs/core/03_ligand.ipynb 50
+# %% ../../nbs/core/03_ligand.ipynb #9e6d6bf4-061c-4f13-b916-9d7366fbde63
 def hash_fp(fp_row):
     "Hash a binary fingerprint row using SHA256"
     return hashlib.sha256(fp_row.tobytes()).hexdigest()
 
-# %% ../../nbs/core/03_ligand.ipynb 52
+# %% ../../nbs/core/03_ligand.ipynb #07ad9560-7afd-4c16-8614-c9ab39afbbec
 def get_same_mol_group(df, smi_col='SMILES'):
     "Assign a group number to the same compounds by utilizing hash sha256 to encode morgan fp and find same molecule."
     df = df.copy()

kdock/core/plot.py

@@ -2,10 +2,10 @@
 
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/core/04_plot.ipynb.
 
-# %% auto 0
+# %% auto #0
 __all__ = ['reduce_feature', 'set_sns', 'plot_2d', 'plot_corr']
 
-# %% ../../nbs/core/04_plot.ipynb 3
+# %% ../../nbs/core/04_plot.ipynb #1fdc92f2
 import pandas as pd, seaborn as sns
 from fastcore.meta import delegates
 from matplotlib import pyplot as plt
@@ -18,7 +18,7 @@ from sklearn.decomposition import PCA
 from sklearn.manifold import TSNE
 from umap import UMAP
 
-# %% ../../nbs/core/04_plot.ipynb 6
+# %% ../../nbs/core/04_plot.ipynb #2e65eb15
 def reduce_feature(data, # df or numpy array
                    method='pca', # dimensionality reduction method, accept both capital and lower case
                    complexity=20, # None for PCA; perfplexity for TSNE, recommend: 30; n_neigbors for UMAP, recommend: 15
@@ -53,13 +53,13 @@ def reduce_feature(data, # df or numpy array
 
     return embedding_df
 
-# %% ../../nbs/core/04_plot.ipynb 10
+# %% ../../nbs/core/04_plot.ipynb #3012ced7
 def set_sns():
     sns.set(rc={"figure.dpi":300, 'savefig.dpi':300})
     sns.set_context('notebook')
     sns.set_style("ticks")
 
-# %% ../../nbs/core/04_plot.ipynb 12
+# %% ../../nbs/core/04_plot.ipynb #e284443d
 @delegates(sns.scatterplot)
 def plot_2d(X: pd.DataFrame, # a dataframe that has first column to be x, and second column to be y
             **kwargs, # arguments for sns.scatterplot
@@ -68,7 +68,7 @@ def plot_2d(X: pd.DataFrame, # a dataframe that has first column to be x, and se
     plt.figure(figsize=(7,7))
     sns.scatterplot(data = X,x=X.columns[0],y=X.columns[1],alpha=0.7,**kwargs)
 
-# %% ../../nbs/core/04_plot.ipynb 14
+# %% ../../nbs/core/04_plot.ipynb #afb87d13
 def plot_corr(x,#a column of df
               y,#a column of df
               xlabel=None,# x axis label

kdock/core/protein.py

@@ -1,10 +1,10 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/core/02_protein.ipynb.
 
-# %% auto 0
+# %% auto #0
 __all__ = ['get_uniprot_seq', 'get_uniprot_features', 'get_uniprot_kd', 'get_uniprot_type', 'apply_mut_single',
            'apply_mut_complex', 'compare_seq']
 
-# %% ../../nbs/core/02_protein.ipynb 3
+# %% ../../nbs/core/02_protein.ipynb #d1ba401f-ec26-4182-986a-e40837f9a915
 import pandas as pd
 import requests,re
 from functools import lru_cache
@@ -12,7 +12,7 @@ from functools import lru_cache
 # for compare seq
 from Bio.Align import PairwiseAligner
 
-# %% ../../nbs/core/02_protein.ipynb 5
+# %% ../../nbs/core/02_protein.ipynb #81c804f5-a4d8-4b99-a47e-3355779a1bbd
 @lru_cache()
 def get_uniprot_seq(uniprot_id):
     "Queries the UniProt database to retrieve the protein sequence for a given UniProt ID."
@@ -29,7 +29,7 @@ def get_uniprot_seq(uniprot_id):
     else:
         return f"Error: Unable to retrieve sequence for UniProt ID {uniprot_id}. Status code: {response.status_code}"
 
-# %% ../../nbs/core/02_protein.ipynb 7
+# %% ../../nbs/core/02_protein.ipynb #68c733a5-bbc9-4373-b9d2-23c545e74316
 @lru_cache()
 def get_uniprot_features(uniprot_id):
     "Given uniprot_id, get specific region for uniprot features."
@@ -63,7 +63,7 @@ def get_uniprot_features(uniprot_id):
     else:
         raise ValueError(f"Failed to retrieve UniProt features for {uniprot_id}")
 
-# %% ../../nbs/core/02_protein.ipynb 9
+# %% ../../nbs/core/02_protein.ipynb #26d793bb-3f87-4e84-bcf6-6ca62a794b32
 def get_uniprot_kd(uniprot_id):
     "Query 'Domain: Protein kinase' based on UniProt ID and get its sequence info."
     data = get_uniprot_features(uniprot_id)
@@ -86,7 +86,7 @@ def get_uniprot_kd(uniprot_id):
 
     return out
 
-# %% ../../nbs/core/02_protein.ipynb 11
+# %% ../../nbs/core/02_protein.ipynb #4005a8aa-f8a1-4b99-819e-d7c08d487bf2
 def get_uniprot_type(uniprot_id,type_='Signal'):
     "Get region sequences based on UniProt ID features."
     data = get_uniprot_features(uniprot_id)
@@ -118,7 +118,7 @@ def get_uniprot_type(uniprot_id,type_='Signal'):
 
     return out
 
-# %% ../../nbs/core/02_protein.ipynb 16
+# %% ../../nbs/core/02_protein.ipynb #f06c0c1d-829d-4f9e-bcc2-9457050faaf4
 def apply_mut_single(seq, # protein sequence
            *mutations, # e.g., E709A
            start_pos=1, # if the protein sequence does not start from index 1, indicate the start index to match the mutations
@@ -142,7 +142,7 @@ def apply_mut_single(seq, # protein sequence
         
     return ''.join(seq_list)
 
-# %% ../../nbs/core/02_protein.ipynb 18
+# %% ../../nbs/core/02_protein.ipynb #5c66ef12-8348-4dc6-affc-04858c1411f5
 def apply_mut_complex(seq, # protein sequence
                       mut, # mutation (e.g., G776delinsVC/S783C, G778dupGSP)
                       start_pos=1, # if truncated protein sequence, indicate where it starts to match the position of mutation
@@ -196,7 +196,7 @@ def apply_mut_complex(seq, # protein sequence
 
     return ''.join(seq)
 
-# %% ../../nbs/core/02_protein.ipynb 22
+# %% ../../nbs/core/02_protein.ipynb #5ac69a8c-fe83-48fc-926f-b99a15624ce3
 def compare_seq(
     seq1: str,
     seq2: str,

kdock/core/utils.py

@@ -1,9 +1,9 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/core/01_utils.ipynb.
 
-# %% auto 0
+# %% auto #0
 __all__ = ['rglob', 'copy_files', 'get_rec_lig', 'get_box', 'view_mol', 'view_complex']
 
-# %% ../../nbs/core/01_utils.ipynb 3
+# %% ../../nbs/core/01_utils.ipynb #61fddcbc
 from pathlib import Path
 import subprocess,shutil,zipfile
 import numpy as np
@@ -11,7 +11,7 @@ import numpy as np
 import py3Dmol
 from rdkit import Chem
 
-# %% ../../nbs/core/01_utils.ipynb 6
+# %% ../../nbs/core/01_utils.ipynb #2cb26b85
 def rglob(path, pattern, max_depth):
     "Get a file list given folder depths"
     base_path = Path(path).resolve()
@@ -19,7 +19,7 @@ def rglob(path, pattern, max_depth):
         if len(path.relative_to(base_path).parts) <= max_depth:
             yield path
 
-# %% ../../nbs/core/01_utils.ipynb 8
+# %% ../../nbs/core/01_utils.ipynb #8d003773
 def copy_files(file_list, dest_dir):
     "Copy a list of files to the destination directory, or zip them if dest_dir ends with .zip."
     dest_path = Path(dest_dir)
@@ -37,7 +37,7 @@ def copy_files(file_list, dest_dir):
             shutil.copy2(file_path, dest_path / file_path.name)
         print(f'Copied {len(file_list)} files to {dest_path}')
 
-# %% ../../nbs/core/01_utils.ipynb 11
+# %% ../../nbs/core/01_utils.ipynb #3ffd3d10
 def get_rec_lig(pdb_id: str, # pdb id for download
                             lig_id: str, # ligand id shown on the protein page
                             out_dir = '.', # directory path to save pdb files
@@ -81,7 +81,7 @@ def get_rec_lig(pdb_id: str, # pdb id for download
 
     return str(rec_file), str(lig_sdf_file)
 
-# %% ../../nbs/core/01_utils.ipynb 14
+# %% ../../nbs/core/01_utils.ipynb #491e748e
 def get_box(sdf_file, autobox_add=4.0,tolist=False):
     "Get the box coordinates of ligand.sdf; mimic GNINA's --autobox_ligand behavior."
     mol = Chem.SDMolSupplier(str(sdf_file), removeHs=False)[0]
@@ -107,7 +107,7 @@ def get_box(sdf_file, autobox_add=4.0,tolist=False):
     }
     return list(box_dict.values()) if tolist else box_dict
 
-# %% ../../nbs/core/01_utils.ipynb 18
+# %% ../../nbs/core/01_utils.ipynb #cdf59cb8
 def view_mol(file, #sdf or pdb file
             ):
     "Visualize pdb or sdf file"
@@ -118,7 +118,7 @@ def view_mol(file, #sdf or pdb file
     v.zoomTo()
     v.show()
 
-# %% ../../nbs/core/01_utils.ipynb 20
+# %% ../../nbs/core/01_utils.ipynb #83cd0e6a
 def view_complex(receptor,           # protein file
                  ligand,             # ligand (green), or docked ligand
                  ori_ligand=None,    # original ligand (yellow)

kdock/gnina/dock.py

@@ -1,9 +1,9 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/gnina/04_gnina_docking.ipynb.
 
-# %% auto 0
+# %% auto #0
 __all__ = ['setup_gnina_local', 'setup_gnina_docker', 'extract_gnina_dock', 'gnina_dock']
 
-# %% ../../nbs/gnina/04_gnina_docking.ipynb 3
+# %% ../../nbs/gnina/04_gnina_docking.ipynb #e20fcc7c
 # basics
 import re,subprocess, py3Dmol
 from tqdm import tqdm
@@ -14,7 +14,7 @@ import pandas as pd,numpy as np
 from rdkit import Chem
 from rdkit.Chem import AllChem
 
-# %% ../../nbs/gnina/04_gnina_docking.ipynb 8
+# %% ../../nbs/gnina/04_gnina_docking.ipynb #1ce62365
 def setup_gnina_local(version='v1.3'):
     "Download and install gnina in the current directory"
     # Check CUDA availability
@@ -35,14 +35,14 @@ def setup_gnina_local(version='v1.3'):
     
     print('Finish setup!')
 
-# %% ../../nbs/gnina/04_gnina_docking.ipynb 13
+# %% ../../nbs/gnina/04_gnina_docking.ipynb #c259e599
 def setup_gnina_docker():
     "Pull gnina docker image"
     print("Pulling GNINA Docker image: gnina/gnina")
     subprocess.run(["docker", "pull", "gnina/gnina"], check=True,stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
     print("GNINA Docker image is ready.")
 
-# %% ../../nbs/gnina/04_gnina_docking.ipynb 18
+# %% ../../nbs/gnina/04_gnina_docking.ipynb #a68899f4
 def extract_gnina_dock(gnina_output):
     "Extract values from gnina output"
     mode1_line = re.search(r'\b1\s+(-?\d+\.\d+)\s+(-?\d+\.\d+)\s+(-?\d+\.\d+)\b', gnina_output)
@@ -56,7 +56,7 @@ def extract_gnina_dock(gnina_output):
     
     return None
 
-# %% ../../nbs/gnina/04_gnina_docking.ipynb 19
+# %% ../../nbs/gnina/04_gnina_docking.ipynb #78d04091
 def gnina_dock(receptor, # receptor file
               ligand, # ligand file
               autobox_ligand, # ligand file isolated from the complex
@@ -85,7 +85,7 @@ def gnina_dock(receptor, # receptor file
 
     return values
 
-# %% ../../nbs/gnina/04_gnina_docking.ipynb 21
+# %% ../../nbs/gnina/04_gnina_docking.ipynb #8e868b74
 def gnina_dock(df, 
                  ID_col = 'ID',
                  smi_col = 'SMILES',

kdock/gnina/rescore.py

@@ -1,10 +1,10 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/gnina/05_gnina_AF3_rescore.ipynb.
 
-# %% auto 0
+# %% auto #0
 __all__ = ['ChainSelect', 'rename_residues', 'split_cif', 'pdb2sdf', 'prepare_rec_lig', 'gnina_rescore_local',
            'gnina_rescore_docker', 'extract_gnina_rescore', 'get_gnina_rescore', 'get_gnina_rescore_folder']
 
-# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb 3
+# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb #37eb344f-6e5c-4350-b0fd-962340a4bf0d
 import pandas as pd
 import re, os, subprocess, py3Dmol
 from Bio.PDB import MMCIFParser, PDBIO, Select
@@ -15,7 +15,7 @@ from fastcore.all import L
 from tqdm.contrib.concurrent import process_map
 from functools import partial
 
-# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb 5
+# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb #2e53d110-a6a6-4d46-8b04-9e7a76069995
 class ChainSelect(Select):
     "Select chain to save"
     def __init__(self, chain_ids):
@@ -23,7 +23,7 @@ class ChainSelect(Select):
     def accept_chain(self, chain):
         return chain.get_id() in self.chain_ids
 
-# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb 6
+# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb #44e31366-70c4-4b9a-9e27-603442683fed
 def rename_residues(structure, chain_id, new_resname='LIG'):
     "Rename residue name from LIG_L to LIG as LIG_L exceeds lengths and leads to error in RDKit"
     for model in structure:
@@ -32,7 +32,7 @@ def rename_residues(structure, chain_id, new_resname='LIG'):
                 for residue in chain:
                     residue.resname = new_resname
 
-# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb 7
+# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb #a760f9d5-7aba-47fc-b47f-593a862587f9
 def split_cif(cif_path, rec_chain_id,lig_chain_id, rec_pdb_path, lig_pdb_path):
     "Split AF3 output CIF to protein and ligand PDBs"
     parser = MMCIFParser(QUIET=True)
@@ -43,7 +43,7 @@ def split_cif(cif_path, rec_chain_id,lig_chain_id, rec_pdb_path, lig_pdb_path):
     io.save(str(rec_pdb_path), ChainSelect(rec_chain_id))  # receptor
     io.save(str(lig_pdb_path), ChainSelect(lig_chain_id))  # ligand
 
-# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb 8
+# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb #ecf8c5a3-84e5-4c96-a97a-1f22e1d52b4e
 def pdb2sdf(pdb_path, sdf_path):
     "Convert ligand pdb to sdf file"
     mol = Chem.MolFromPDBFile(pdb_path, sanitize=True, removeHs=False)
@@ -56,7 +56,7 @@ def pdb2sdf(pdb_path, sdf_path):
         print('Conversion failed for:', pdb_path)
         return pdb_path
 
-# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb 9
+# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb #223e66d6-f08e-4af8-96f9-cf2a78e9dfc1
 def prepare_rec_lig(cif_path, rec_chain_id, lig_chain_id, rec_pdb_path, lig_pdb_path):
     "Split AF3 cif to protein.pdb (chainA) and ligand.sdf (chainL) "
     
@@ -70,7 +70,7 @@ def prepare_rec_lig(cif_path, rec_chain_id, lig_chain_id, rec_pdb_path, lig_pdb_
         pass
     return failed
 
-# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb 15
+# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb #e2d3a635-ce64-4e0a-a235-e659f191121f
 def gnina_rescore_local(protein_pdb,  # receptor file
                         ligand_sdf,   # ligand file
                         CNN_affinity=True,
@@ -91,7 +91,7 @@ def gnina_rescore_local(protein_pdb,  # receptor file
     result = subprocess.run(command, capture_output=True, text=True)
     return result.stdout
 
-# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb 17
+# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb #e1d09a6e-8323-4503-b80c-5d5f95889b8f
 def gnina_rescore_docker(protein_pdb, 
                          ligand_sdf, 
                          CNN_affinity=True, 
@@ -124,7 +124,7 @@ def gnina_rescore_docker(protein_pdb,
     result = subprocess.run(command, capture_output=True, text=True)
     return result.stdout
 
-# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb 19
+# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb #c9bd835a-b955-469e-a732-edbad6e2ddee
 def extract_gnina_rescore(txt):
     """Extract GNINA output metrics into a dictionary (partial match allowed)."""
     result = {}
@@ -145,7 +145,7 @@ def extract_gnina_rescore(txt):
 
     return result
 
-# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb 24
+# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb #b21d71d8-a420-4e7b-8882-1caa55e84dc2
 def get_gnina_rescore(cif_path,
                       rec_chain_id='A', 
                       lig_chain_id='L', 
@@ -170,7 +170,7 @@ def get_gnina_rescore(cif_path,
         gnina_output = gnina_rescore_docker(rec_path,lig_path,CNN_affinity,vinardo)
     return extract_gnina_rescore(gnina_output)
 
-# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb 29
+# %% ../../nbs/gnina/05_gnina_AF3_rescore.ipynb #1e80f250-2c22-45e9-8a97-6f68c2e8514d
 def get_gnina_rescore_folder(cif_folder,
                              rec_chain_id='A', 
                              lig_chain_id='L',

kdock/px/core.py

@@ -1,13 +1,13 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/protenix/07_protenix.ipynb.
 
-# %% auto 0
+# %% auto #0
 __all__ = ['get_single_job', 'get_single_protein_ligand_json', 'get_protein_ligand_df_json', 'get_virtual_screening_json']
 
-# %% ../../nbs/protenix/07_protenix.ipynb 6
+# %% ../../nbs/protenix/07_protenix.ipynb #b64cf79f-8926-4928-81c0-45d90ffcf425
 import json
 from pathlib import Path
 
-# %% ../../nbs/protenix/07_protenix.ipynb 9
+# %% ../../nbs/protenix/07_protenix.ipynb #d883059f-1b5c-4abc-af97-f8be1f24e2c9
 def get_single_job(job_name, protein_seq, msa_dir, SMILES=None,CCD=None):
     "Get protenix json format of protein and ligand."
     
@@ -40,7 +40,7 @@ def get_single_job(job_name, protein_seq, msa_dir, SMILES=None,CCD=None):
         ]
     }
 
-# %% ../../nbs/protenix/07_protenix.ipynb 11
+# %% ../../nbs/protenix/07_protenix.ipynb #42c3b0ef-c991-401f-9c8c-a1e0dbf5ed2d
 def get_single_protein_ligand_json(job_name, 
                                    protein_seq, 
                                    msa_dir, 
@@ -59,7 +59,7 @@ def get_single_protein_ligand_json(job_name,
 
     return data
 
-# %% ../../nbs/protenix/07_protenix.ipynb 16
+# %% ../../nbs/protenix/07_protenix.ipynb #129512dd-a788-4593-9986-1b1f2c27d4b8
 def get_protein_ligand_df_json(df,
                                id_col,
                                seq_col, 
@@ -96,7 +96,7 @@ def get_protein_ligand_df_json(df,
     return all_jobs
 
 
-# %% ../../nbs/protenix/07_protenix.ipynb 19
+# %% ../../nbs/protenix/07_protenix.ipynb #b6ed9bf7-4a0b-4230-bb89-89fb30f4025e
 def get_virtual_screening_json(df, 
                                protein_seq, 
                                msa_dir, 

kdock/px/dock.py

@@ -1,9 +1,9 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/protenix/06_proteinix_dock.ipynb.
 
-# %% auto 0
+# %% auto #0
 __all__ = ['capture_output', 'get_protenix_dock', 'get_protenix_vina_dock', 'json2sdf']
 
-# %% ../../nbs/protenix/06_proteinix_dock.ipynb 11
+# %% ../../nbs/protenix/06_proteinix_dock.ipynb #97f1b541-c8d4-4d9f-bf5b-a081269a0a70
 # kdock
 from ..core.utils import *
 
@@ -28,7 +28,7 @@ except ImportError as e:
     write_ligand_to_sdf = None
 
 
-# %% ../../nbs/protenix/06_proteinix_dock.ipynb 15
+# %% ../../nbs/protenix/06_proteinix_dock.ipynb #b885d4cd-7783-4595-8803-a74fbeb24a38
 @contextlib.contextmanager
 def capture_output(log_path):
     with open(log_path, 'a') as log_file:  # Append mode prevents overwriting
@@ -56,7 +56,7 @@ def capture_output(log_path):
             os.close(old_stdout_fd)
             os.close(old_stderr_fd)
 
-# %% ../../nbs/protenix/06_proteinix_dock.ipynb 16
+# %% ../../nbs/protenix/06_proteinix_dock.ipynb #77c25ec1-7edd-4e18-8a64-61bff5071f3a
 def get_protenix_dock(receptor_pdb, # pdb path
                       ligand_sdf, # sdf path
                       box:list, # center xyz + size xyz
@@ -81,7 +81,7 @@ def get_protenix_dock(receptor_pdb, # pdb path
     print(f'Docking complete. Results in: {result_dir}')
     print('Cache dir:', cache_dir)
 
-# %% ../../nbs/protenix/06_proteinix_dock.ipynb 20
+# %% ../../nbs/protenix/06_proteinix_dock.ipynb #59033dc5-d02c-4a1c-a4ef-f56ef9364ff8
 def get_protenix_vina_dock(receptor_pdb, # pdb path
                       ligand_sdf, # sdf path
                       box:list, # center xyz + size xyz
@@ -100,7 +100,7 @@ def get_protenix_vina_dock(receptor_pdb, # pdb path
 
     print(f'Docking complete. Results in: {result_dir}')
 
-# %% ../../nbs/protenix/06_proteinix_dock.ipynb 23
+# %% ../../nbs/protenix/06_proteinix_dock.ipynb #ce3d018b-6762-450f-b2aa-bcdb942445c8
 def json2sdf(json_path,
              sdf_path=None, # .sdf to be saved
              ):

{kdock-0.0.2.dist-info → kdock-0.0.4.dist-info}/METADATA

@@ -1,20 +1,17 @@
 Metadata-Version: 2.4
 Name: kdock
-Version: 0.0.2
+Version: 0.0.4
 Summary: A collection of docking tools
-Home-page: https://github.com/sky1ove/kdock
-Author: Lily Cai
-Author-email: lcai888666@gmail.com
-License: Apache Software License 2.0
-Keywords: nbdev jupyter notebook python
-Classifier: Development Status :: 4 - Beta
-Classifier: Intended Audience :: Developers
+Author-email: Lily Cai <lcai888666@gmail.com>
+License: Apache-2.0
+Project-URL: Repository, https://github.com/sky1ove/kdock
+Project-URL: Documentation, https://sky1ove.github.io/kdock
+Keywords: nbdev,jupyter,notebook,python
 Classifier: Natural Language :: English
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Intended Audience :: Developers
+Classifier: Development Status :: 3 - Alpha
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
@@ -35,22 +32,12 @@ Requires-Dist: openpyxl
 Requires-Dist: biopython
 Requires-Dist: requests
 Requires-Dist: scikit-fingerprints
+Requires-Dist: pubchempy
 Provides-Extra: dev
 Requires-Dist: nbdev; extra == "dev"
 Requires-Dist: ipykernel; extra == "dev"
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: keywords
-Dynamic: license
+Requires-Dist: twine; extra == "dev"
 Dynamic: license-file
-Dynamic: provides-extra
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
 
 # kdock
 
@@ -59,8 +46,13 @@ Dynamic: summary
 
 ## Installation
 
-Install latest from the GitHub
-[repository](https://github.com/sky1ove/kdock):
+Install stable version from Pypi:
+
+``` sh
+$ pip install kdock
+```
+
+Install latest from the GitHub:
 
 ``` sh
 $ pip install -U git+https://github.com/sky1ove/kdock.git

kdock-0.0.4.dist-info/RECORD

@@ -0,0 +1,27 @@
+kdock/__init__.py,sha256=1mptEzQihbdyqqzMgdns_j5ZGK9gz7hR2bsgA_TnjO4,22
+kdock/_modidx.py,sha256=wDTqXS4lSFzownRvr2ldeTcZH8t6kXKkxaN3FuLKs9g,16155
+kdock/af3/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kdock/af3/analyze.py,sha256=Fl_Edh1tKLC4Bkqi14LFQv0fNLZyD9GCKvc3oSDAnMo,6111
+kdock/af3/docker.py,sha256=_CKbagpQaWB43DfhiLOuDI7xA-XX5mp_m1WBclWtJ44,4822
+kdock/af3/json.py,sha256=nB7j9T61crClEUA8sDwwiIHkrMGLf3KlxTiK54vM1BI,9877
+kdock/af3/protein_pairs.py,sha256=p7D2u_g7N_xQ0r8xEjlDWvmwbwnIVKYk3AxqyN-XSls,3878
+kdock/boltz/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kdock/boltz/dock.py,sha256=Tp7PoTYKBmOutTxCg8ATRQWbgZKG8lWv2DnxXSWAAuY,2841
+kdock/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kdock/core/data.py,sha256=_T2TjYrfifjGj6mZelacCVHbSywqWhKf9awOtp7nIqQ,2779
+kdock/core/ligand.py,sha256=8ndoNrjfWFDxdSk8iw-JBn918Z6eu55bv_t6AAREgz0,11660
+kdock/core/plot.py,sha256=_CRiVLpBH3rp0pv9YrT7t8Y9hGYPpTtwJMvXPS7Smkg,3332
+kdock/core/protein.py,sha256=DPhd6sHrAybQK9VBP0gC1_ZfwZ4sD_l_HiytpsKnowQ,10709
+kdock/core/utils.py,sha256=2M7FyQfUsRsGQLG892p8B1vFiPZpl1tV0RNl9Pv3EKI,5723
+kdock/gnina/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kdock/gnina/dock.py,sha256=LconAw4yFXJmR4JWhf6AlVouapC84Dy07nWi7aHOGXs,4401
+kdock/gnina/rescore.py,sha256=LhWikIrWM1lRf4otVMFfLRcvx0M0sUfSCj7cIqSQ8Jg,7870
+kdock/px/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kdock/px/core.py,sha256=T_SkMqT56pfJQoI8A1U6gzf8OsqFXlheOIuj-jEvhiI,4715
+kdock/px/dock.py,sha256=_RA3mDP_KOmhEI0s24Vz9z4cyuk8u-CXy3TO_fKWGME,4682
+kdock-0.0.4.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+kdock-0.0.4.dist-info/METADATA,sha256=5fbtbMYp22xHndW0kREt7H7gqjyUQvgQbpUspK33JBY,1838
+kdock-0.0.4.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+kdock-0.0.4.dist-info/entry_points.txt,sha256=YwnlRC6hsrK3yz6gon_F9IGMri124qmi8VfsymI1Fz0,32
+kdock-0.0.4.dist-info/top_level.txt,sha256=HfWUyFy5aRDePTmNrMCw2m5HNtpfBhbpm6zbXjfsVnA,6
+kdock-0.0.4.dist-info/RECORD,,

{kdock-0.0.2.dist-info → kdock-0.0.4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: setuptools (80.10.2)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

kdock-0.0.2.dist-info/RECORD

@@ -1,25 +0,0 @@
-kdock/__init__.py,sha256=QvlVh4JTl3JL7jQAja76yKtT-IvF4631ASjWY1wS6AQ,22
-kdock/_modidx.py,sha256=TaXYpAMNa4XCw-wAUH1LZaMQ2uzJvDcIPFfWGhtUD08,15422
-kdock/af3/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kdock/af3/analyze.py,sha256=cdVkWx3bW293XF-SgXBW54zDjXd3nWY3j_hUPfPD7AE,5827
-kdock/af3/docker.py,sha256=0jTP7lFQ6kGRostX_aemWAXpnGf-c2w3ICGIJYxz_b8,4609
-kdock/af3/json.py,sha256=2h6ixv1PTy7KvPzepMvVHb9QuvhSebjTS1Kn5q9YrUs,9522
-kdock/af3/protein_pairs.py,sha256=-Ade5JjSpz2j8hOG3L1T9IO67QiONhPP6ukv4wyDTy8,3595
-kdock/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kdock/core/data.py,sha256=XmV_65YTgdsWygG9GifjWOkP-5D9mzbzQI19AlS0yxc,2392
-kdock/core/ligand.py,sha256=PSDPnceov6nLkmtMagkEexJ3eTn6v1N7uGOj3swiYSs,10631
-kdock/core/plot.py,sha256=kbkIDqksiOXTvisG5TcjEHkZSImisV1Yxl7r_CGOmNo,3294
-kdock/core/protein.py,sha256=y0BzCPRphbYY4aW6DBCiRbbMv8GQXMZy4n7lzr4_E90,10424
-kdock/core/utils.py,sha256=Lpnu6mWNFOIkxJExp39Gei9EHlWCMn-ZOFiDUesrvoU,5670
-kdock/gnina/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kdock/gnina/dock.py,sha256=BY2lvmLplDq-x6VTOhckBvVWmtlMfbAoB14W2dxXtAw,4356
-kdock/gnina/rescore.py,sha256=n2Nwa8c9fyrNfwTC7UuZn-8kb9CqHZPr25sjCumYFXk,7478
-kdock/px/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kdock/px/core.py,sha256=P_dmbv0pyT1TY5wlq0r-b32x6BEzNWyeTkoy1C_gK6A,4537
-kdock/px/dock.py,sha256=WZEUG-m0IUDmVZ0CJ_oKZm1mcgCvI_pnVUzj3QLv1io,4506
-kdock-0.0.2.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-kdock-0.0.2.dist-info/METADATA,sha256=xcQCel5oQm2FL8VwmxnCYz6nfwq4cuklPlqRssULfd8,2122
-kdock-0.0.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-kdock-0.0.2.dist-info/entry_points.txt,sha256=YwnlRC6hsrK3yz6gon_F9IGMri124qmi8VfsymI1Fz0,32
-kdock-0.0.2.dist-info/top_level.txt,sha256=HfWUyFy5aRDePTmNrMCw2m5HNtpfBhbpm6zbXjfsVnA,6
-kdock-0.0.2.dist-info/RECORD,,