AutoDock-GPU_Output is a sample docking output log (.dlg) generated by running AutoDock-GPU. It contains information such as binding energy, conformation clustering, and final ligand attitude. It serves as a reference dataset for docking result parsing and can be used to learn result parsing and check whether the environment configuration is normal.

The relevant paper results areAccelerating AutoDock4 with GPUs and Gradient-Based Local Search", published by Diogo Santos-Martins et al. in 2021.

AutoDock-GPU is a GPU-accelerated version of AutoDock 4.2. It improves molecular docking speed by parallelizing genetic algorithms, achieving a 10–50x performance improvement compared to traditional CPU operation. It is commonly used for virtual drug screening and protein-ligand binding mode prediction.

Its features include:

• Supports CUDA, OpenCL, and SYCL; compatible with NVIDIA/AMD/Intel GPUs and multi-core CPUs.
• Supports local search methods such as ADADELTA and Solis-Wets.
• Supports batch virtual filtering and automatic search stop strategy
• Commonly used in drug design research and supercomputing performance benchmarking.

---

The dataset is stored in examples/output middle:

examples/output/
├── ocladock_cpu_1stp_nrun100.dlg
├── ocladock_cpu_3ce3_nrun100.dlg
├── ocladock_gpu_1stp_nrun100.dlg
└── ocladock_gpu_3ce3_nrun100.dlg

File naming explanation

| 文件名片段 | 含义说明 |
|---|---|
| `cpu` / `gpu` | 运行所使用的硬件设备类型 |
| `1stp` / `3ce3` | 对接所用的测试蛋白-配体体系名称 |
| `nrun100` | 运行的 LGA 对接轮数（如 100 次搜索）|

Example:
ocladock_gpu_1stp_nrun100.dlg
This indicates that 100 docking searches were performed on the 1stp architecture using the GPU.

---

Content Description

The file records the complete running results of AutoDock-GPU, including:

| 内容模块 | 说明 |
|---|---|
| 运行参数与搜索设置 | 遗传算法参数、局部优化算法、变异率等 |
| 结合能与评分 | 包含预测的结合自由能（Binding Energy）|
| 构象聚类分析 | 根据 RMSD 对所有构象进行聚类结果列表 |
| 最优构象坐标 | 最终配体坐标，可用于可视化展示 |

.dlg It's in plain text format and can be opened and viewed directly.

---

How to use

need	Methods and commands
Check docking energy	direct less file.dlg Or open with a text editor
Extracting the optimal conformation (PDBQT)	Add during runtime docking --gbest 1
Convert to PDB for visualization	obabel pose.pdbqt -O pose.pdb
Visualization of ligand posture	Using PyMOL / Chimera / AutoDockTools