DockingAtHOME / README.md

Mentors4EDU

Remove Docker Pull (Not Available Yet) and API Documentation (Localhost)

bbcb5c7 verified about 1 month ago

preview code

raw

history blame

8.61 kB

metadata

license: gpl-3.0
language:
  - en
metrics:
  - bleu
  - accuracy
base_model:
  - OpenPeerAI/Cloud-Agents
library_name: dockingathome
tags:
  - chemistry
  - biology
  - agent

Docking@HOME

Distributed and Parallel Molecular Docking Platform

Overview

Docking@HOME is a cutting-edge distributed computing platform that leverages the power of volunteer computing, GPU acceleration, decentralized networking, and AI-driven orchestration to perform large-scale molecular docking simulations. This project combines multiple state-of-the-art technologies to democratize drug discovery and computational chemistry.

Key Features

🧬 AutoDock Integration: Uses AutoDock Suite 4.2.6 for molecular docking simulations
🚀 GPU Acceleration: CUDPP-powered parallel processing for enhanced performance
🌐 Distributed Computing: BOINC framework for volunteer computing at scale
🔗 Decentralized Networking: Distributed Network Settings-based coordination using the Decentralized Internet SDK
🤖 AI Orchestration: Cloud Agents for intelligent task distribution and optimization
📊 HuggingFace Integration: Model cards and datasets for reproducible research

Architecture

┌─────────────────────────────────────────────────────────────┐
│                    Docking@HOME Platform                     │
├─────────────────────────────────────────────────────────────┤
│  ┌──────────────┐  ┌──────────────┐  ┌─────────────────┐  │
│  │ Cloud Agents │  │ Decentralized│  │  BOINC Server   │  │
│  │ (AI Routing) │◄─┤  Internet    │◄─┤  (Task Mgmt)    │  │
│  └──────────────┘  └──────────────┘  └─────────────────┘  │
│         ▼                                      ▼            │
│  ┌──────────────────────────────────────────────────────┐  │
│  │         Distributed Worker Nodes (BOINC Clients)     │  │
│  │  ┌──────────────┐        ┌──────────────┐           │  │
│  │  │   AutoDock   │◄──────►│    CUDPP     │           │  │
│  │  │  (Docking)   │        │ (GPU Accel)  │           │  │
│  │  └──────────────┘        └──────────────┘           │  │
│  └──────────────────────────────────────────────────────┘  │
└─────────────────────────────────────────────────────────────┘

Components

1. AutoDock Suite (v4.2.6)

Core molecular docking engine that predicts binding modes and affinities of small molecules to protein targets.

2. CUDPP (CUDA Data Parallel Primitives Library)

Provides GPU-accelerated parallel primitives for enhancing AutoDock's computational performance.

3. BOINC (Berkeley Open Infrastructure for Network Computing)

Distributed computing middleware that manages volunteer computing resources globally.

4. The Decentralized Internet SDK

Enables Distributed Network Settings-based coordination, ensuring transparency and decentralization of task distribution.

5. Cloud Agents

AI-powered orchestration layer that optimizes task scheduling and resource allocation based on workload characteristics.

Authors & Contributors

OpenPeer AI - AI/ML Integration & Cloud Agents
Riemann Computing Inc. - Distributed Computing Architecture
Bleunomics - Bioinformatics & Drug Discovery Expertise
Andrew Magdy Kamal - Project Lead & System Integration

Installation

Prerequisites

C++ compiler (GCC 7+ or MSVC 2019+)
CUDA Toolkit 11.0+ (for GPU acceleration)
Python 3.8+
Node.js 16+ (for the Decentralized Internet SDK)
BOINC client/server software

Build Instructions

# Clone the repository
git clone https://huggingface.co/OpenPeerAI/DockingAtHOME
cd DockingAtHOME

# Initialize submodules
git submodule update --init --recursive

# Build the project
mkdir build && cd build
cmake ..
make -j$(nproc)

# Install
sudo make install

Quick Start

Web GUI (Recommended!)

# Install dependencies
pip install -r requirements.txt

# Start the GUI server
python start.py

# Open browser to: http://localhost:8080

The GUI provides:

🖱️ Drag-and-drop file upload
📊 Real-time progress monitoring
📈 Live statistics dashboard
🎯 Interactive job management
📱 Responsive design

Command Line

# Run docking from terminal
docking-at-home dock -l molecule.pdbqt -r protein.pdbqt

# Start server
docking-at-home server --port 8080

# Start worker
docking-at-home worker --local

Python API

from docking_at_home.server import job_manager, initialize_server
import asyncio

async def main():
    await initialize_server()
    
    job_id = await job_manager.submit_job(
        ligand_file="molecule.pdbqt",
        receptor_file="protein.pdbqt",
        num_runs=100,
        use_gpu=True
    )
    
    # Monitor progress
    while True:
        job = job_manager.get_job(job_id)
        if job["status"] == "completed":
            print(f"Best energy: {job['results']['best_energy']}")
            break
        await asyncio.sleep(1)

asyncio.run(main())

Running on Localhost

# Start the local server
docking-at-home server --port 8080

# In another terminal, run the worker
docking-at-home worker --local

Configuration

Configuration files are located in config/:

autodock.conf - AutoDock parameters
boinc_server.conf - BOINC server settings
gpu_config.conf - CUDPP and GPU settings
decentralized.conf - Distributed Network Settings
cloud_agents.conf - AI orchestration parameters

Performance

On a typical configuration:

CPU-only: ~100 docking runs/hour
Single GPU (RTX 3090): ~2,000 docking runs/hour
Distributed (1000 nodes): ~100,000+ docking runs/hour

Use Cases

🔬 Drug Discovery and Virtual Screening
🧪 Protein-Ligand Binding Studies
📚 Large-Scale Chemical Library Screening
🎓 Educational Computational Chemistry
🌍 Pandemic Response (e.g., COVID-19 drug discovery)

Contributing

We welcome contributions! Please see CONTRIBUTING.md for guidelines.

License

This project is licensed under the GNU General Public License v3.0 - see LICENSE for details.

Individual components retain their original licenses:

AutoDock: GNU GPL v2
BOINC: GNU LGPL v3
CUDPP: BSD License

Citation

If you use Docking@HOME in your research, please cite:

@software{docking_at_home_2025,
  title={Docking@HOME: A Distributed Platform for Molecular Docking},
  author={OpenPeer AI and Riemann Computing Inc. and Bleunomics and Andrew Magdy Kamal},
  year={2025},
  url={https://huggingface.co/OpenPeerAI/DockingAtHOME}
}

HuggingFace Integration

Model cards and datasets are available at:

🤗 https://huggingface.co/OpenPeerAI/DockingAtHOME

Support

📧 Email: andrew@bleunomics.com
� Issues: HuggingFace Issues
🤗 Community: HuggingFace Discussions

Acknowledgments

The AutoDock development team at The Scripps Research Institute
BOINC project at UC Berkeley
CUDPP developers
Lonero Team for the Decentralized Internet SDK
OpenPeer AI for Cloud Agents framework

Made with ❤️ by the open-source computational chemistry community