增加受体准备说明与增加分批提交参数灵活性

README.md

@@ -32,6 +32,52 @@ project_root/
     └── analyze_results.py  
 ```
 
+## 受体准备 pdbqt 文件
+
+使用 alphafold 预测 pdb 文件 cif 文件。
+
+修复使用 moderller 同源建模，或者 pdbfixer，MOE，maestro 等
+
+这里使用 maestro 的 `Protein reparation Workflow` 模块
+
+然后导出 pdb 文件
+
+使用 meeko 准备受体文件 pdbqt 文件，详细可以[参考](https://meeko.readthedocs.io/en/release-doc/rec_overview.html)
+
+```shell
+micromamba run -n vina mk_prepare_receptor.py -i receptor/FgBar1_cut_proteinprep.pdb --write_pdbqt receptor/FgBar1_cut_proteinprep.pdbqt
+```
+
+选项组合用法
+
+### 举例1：用默认输出名生成 pdbqt 和 vina box 配置
+
+mk_prepare_receptor.py -i 1abc.pdb -o 1abc_clean --write_pdbqt --write_vina_box
+
+得到 1abc_clean_rigid.pdbqt, 1abc_clean.vina.txt
+
+### 举例2：为指定残基设置模板/柔性，并生成 box 配置
+
+```shell
+mk_prepare_receptor.py -i system.pdb \
+  --output_basename system_prep \
+  -f "A:42,B:23" \
+  -n "A:5,7=CYX,B:17=HID" \
+  --write_pdbqt --write_vina_box
+```
+
+
+### 举例3：自动包络某配体生成 box 配置
+
+```
+mk_prepare_receptor.py -i prot.pdb \
+  --box_enveloping ligand.pdb \
+  --padding 3.0 \
+  --output_basename dock_ready \
+  --write_pdbqt --write_vina_box
+```
+
+
 ## 小分子 3D 构象准备
 
 需要给小分子一个初始化的 3d 构象存放到`ligand/sdf`

vina_split_and_submit.py

@@ -3,8 +3,27 @@ import shutil
 from pathlib import Path
 import sys
 import subprocess
+import argparse
+import time
+
+parser = argparse.ArgumentParser(
+    description="Split pdbqt files and generate & submit vina shell scripts."
+)
+parser.add_argument(
+    '-n', '--n_splits', type=int, default=12, help="Number of splits/folders. Default: 12"
+)
+parser.add_argument(
+    '-r', '--receptor', type=str, required=True, help="Path to receptor pdbqt file"
+)
+parser.add_argument(
+    '-c', '--config', type=str, required=True, help="Path to box config txt file"
+)
+args = parser.parse_args()
+
+n_splits = args.n_splits
+receptor_path = args.receptor
+config_path = args.config
 
-n_splits = int(sys.argv[1]) if len(sys.argv) > 1 else 12   # 默认12份，可传参修改
 src_dir = Path('./ligand/pdbqt')
 dst_root = Path('./ligand')
 
@@ -34,8 +53,8 @@ sh_template = """#!/bin/bash
 date
 echo "autodock vina docking task{idx}, version: 1.2.7" 
 cd /share/home/lyzeng24/rdkit_script/vina
-./scripts/batch_docking.sh ./receptor/TrpE_entry_1.pdbqt \\
+./scripts/batch_docking.sh {receptor_path} \\
-                          ./config/TrpE_entry_1.box.txt \\
+                          {config_path} \\
                           ./ligand/pdbqt{idx} \\
                           ./result/poses{idx} \\
                           ./result/batch_docking{idx}.log ./vina 
@@ -47,7 +66,11 @@ date
 
 submit_sh_list = []
 for i in range(1, n_splits + 1):
-    sh_content = sh_template.format(idx=i)
+    sh_content = sh_template.format(
+        idx=i,
+        receptor_path=receptor_path,
+        config_path=config_path
+    )
     sh_path = Path(f'./submit_vina{i}.sh')
     with open(sh_path, 'w') as f:
         f.write(sh_content)
@@ -56,11 +79,16 @@ for i in range(1, n_splits + 1):
 
 print(f"Done! {total} pdbqt files split to {n_splits} folders, {n_splits} shell scripts generated.")
 
-import time
-
 # 自动提交
 for i, sh_path in enumerate(submit_sh_list, 1):
     print(f"提交: dsub -s {sh_path}")
     subprocess.run(['dsub', '-s', str(sh_path)])
     time.sleep(1)  # 每次提交后等待1秒
 
+"""
+使用示例：
+python vina_split_and_submit.py \
+    -n 128 \
+    -r ./receptor/FgBar1_cut_proteinprep.pdbqt \
+    -c ./config/FgBar1_entry_1.box.txt
+"""