kdock 0.0.2__tar.gz → 0.0.4__tar.gz

{kdock-0.0.2/kdock.egg-info → kdock-0.0.4}/PKG-INFO

@@ -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-0.0.2 → kdock-0.0.4}/README.md

@@ -5,8 +5,13 @@
 
 ## 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/kdock/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.4"

{kdock-0.0.2 → kdock-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-0.0.2 → kdock-0.0.4}/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-0.0.2 → kdock-0.0.4}/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-0.0.2 → kdock-0.0.4}/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-0.0.2 → kdock-0.0.4}/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-0.0.4/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-0.0.2 → kdock-0.0.4}/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