A comprehensive technical skill for implementing and managing the DeepPurpose molecular modeling library for advanced drug-target interaction and compound prediction.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install deeppurpose
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install deeppurpose using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is DeepPurpose AI Skill?
The DeepPurpose skill is a specialized toolkit designed for developers and researchers working on molecular modeling and drug discovery within the Openclaw Skills ecosystem. It provides deep integration with the DeepPurpose library, enabling high-fidelity predictions for drug-target interactions (DTI), compound property predictions, and protein-protein interactions (PPI).
By leveraging this skill, users can seamlessly navigate complex biochemical datasets, automate the generation of model configurations, and execute virtual screening pipelines. It prioritizes local repository intelligence over generic web summaries, ensuring that implementations are technically accurate and aligned with the latest upstream API standards.
DeepPurpose AI Skill Use Cases
- Automating drug-target interaction (DTI) predictions and virtual screening for drug discovery.
- Implementing compound property prediction and drug-drug interaction (DDI) workflows.
- Streamlining protein-protein interaction (PPI) and protein function prediction tasks.
- Accelerating drug repurposing projects using optimized one-liner API helpers.
- Troubleshooting complex RDKit, PyTorch, and Descriptastorus environment dependencies.
How DeepPurpose AI Skill Works
- Request Classification: The skill identifies if the user needs help with installation, dataset formatting, model training, or demo adaptation.
- Context Retrieval: It references specific internal documentation such as
tasks-and-entrypoints.mdordata-and-pretrained.mdbased on the task. - Local Verification: The skill validates advice against local source files like
DeepPurpose/utils.pyandsetup.pyto ensure environment compatibility. - API Mapping: It maps user intent to the correct functional module, such as
DTI.pyfor interactions orCompoundPred.pyfor property analysis. - Execution & Feedback: The skill guides the user through data processing, config generation, and model initialization while monitoring for network download triggers.
DeepPurpose AI Skill Setup
To get started with this DeepPurpose integration within Openclaw Skills, ensure your local environment is prepared:
# Clone the DeepPurpose repository
git clone https://github.com/kexinhuang12345/DeepPurpose.git
cd DeepPurpose
# Install core dependencies (requires RDKit and PyTorch)
pip install -r requirements.txt
python setup.py install
Verify the installation by running a smoke test using the provided toy_data/ directory.
DeepPurpose AI Skill Data Schema & Taxonomy
The skill organizes molecular data and model outputs according to the following taxonomy:
| Component | Description | Primary File/Path |
|---|---|---|
| Drug Data | SMILES strings or 2D/3D descriptors | X_drug, toy_data/ |
| Target Data | Amino acid sequences or protein descriptors | X_target |
| Configs | Model hyperparameters and encoding types | generate_config() |
| Demos | Implementation examples and starting points | DEMO/ |
| Utils | Helper functions for data loading and splitting | DeepPurpose/dataset.py |
DeepPurpose AI Skill Advanced Features
- Support for multi-agent workflows in drug repurposing using
oneliner.repurpose. - Automated management of heavy dependency chains including RDKit and Descriptastorus.
- Intelligent selection of pretrained models for rapid inference without full retraining.
- Seamless transition from toy datasets to large-scale benchmarking datasets.
- Integrated validation rules to distinguish between static environment checks and runtime model execution.
SKILL.md
Loading
Related Openclaw Skills
PPTX Notes Editor
A specialized technical utility for AI agents to unpack, modify, and manage PowerPoint speaker notes through direct XML manipulation.
Agent Browser
A high-performance Rust-based headless browser CLI that empowers AI agents to interact with web pages through structured commands and element references.
Chrome CDP Controller
A lightweight Puppeteer-based tool for controlling existing Chrome instances via the Chrome DevTools Protocol.
Gemini Deep Research CLI
Automate comprehensive multi-source inquiries and structured report generation using the Gemini CLI.
WakaTime Coding Stats Tracker
A powerful analytics integration for tracking coding time, project breakdowns, and language usage via the WakaTime API.
Auto Fortune Chat Skill
An automated AI agent skill designed to intercept user messages and provide instant, API-driven fortune-telling and lifestyle consultations.
Featured*
