Runchuan-BU / BioClaw

BioClaw AI-Powered Bioinformatics Research Assistant on WhatsApp English | 简体中文 **BioClaw** brings the power of computational biology directly into WhatsApp group chats. Researchers can run BLAST searches, render protein structures, generate publication-quality plots, perform sequencing QC, and search the literature — all through natural language messages. Built on the NanoClaw architecture with bioinformatics tools and skills from the STELLA project, powered by the Claude Agent SDK. Join WeChat Group Welcome to join our WeChat group to discuss and exchange ideas! Scan the QR code below to join: Scan to join the BioClaw community Contents • Overview • Quick Start • Messaging channels • Demo Examples • System Architecture • Included Tools • Project Structure • Citation • License Overview The rapid growth of biomedical data, tools, and literature has created a fragmented research landscape that outpaces human expertise. Researchers frequently need to switch between command-line bioinformatics tools, visualization software, databases, and literature search engines — often across different machines and environments. **BioClaw** addresses this by providing a conversational interface to a comprehensive bioinformatics toolkit. By messaging in a WhatsApp group, researchers can: • **Sequence Analysis** — Run BLAST searches against NCBI databases, align reads with BWA/minimap2, and call variants • **Quality Control** — Generate FastQC reports on sequencing data with automated interpretation • **Structural Biology** — Fetch and render 3D protein structures from PDB with PyMOL • **Data Visualization** — Create volcano plots, heatmaps, and expression figures from CSV data • **Literature Search** — Query PubMed for recent papers with structured summaries • **Workspace Management** — Triage files, recommend analysis steps, and manage shared group workspaces Results — including images, plots, and structured reports — are delivered directly back to the chat. Quick Start Prerequisites • **macOS / Linux / Windows** (Windows requires PowerShell 5.1+) • Node.js 20+ • Docker Desktop • Anthropic API key or OpenRouter API key Installation **One-command setup** (recommended for first-time users): macOS / Linux Windows (PowerShell) The setup script will check prerequisites, install dependencies, build the Docker image, and walk you through API key configuration interactively. **Manual setup:** Model Provider Configuration BioClaw now supports two provider paths: • **Anthropic** — default, keeps the original Claude Agent SDK flow • **OpenRouter / OpenAI-compatible** — optional path for OpenRouter and similar providers Create a file in the project root and choose **one** of the following setups. **Option A — Anthropic (default)** **Option B — OpenRouter** (Gemini, DeepSeek, Claude, GPT, and more) Popular model IDs: , , . Full list: openrouter.ai/models **Note:** Use models that support tool calling (e.g. DeepSeek, Gemini, Claude). Session history is preserved within a container session; after idle timeout, a new container starts with a fresh context. **Generic OpenAI-compatible setup** After updating , restart BioClaw: When a container starts, will show which provider path is active. Usage In any connected chat, simply message: Messaging channels Supported platforms include **WhatsApp** (default), **Feishu (Lark)**, **WeCom**, **Discord**, **Slack** (Socket Mode), **WeChat Personal** (experimental), and optional **local web** (browser) chat. Full setup steps, env vars, and disabling channels are in **docs/CHANNELS.md** (简体中文：docs/CHANNELS.zh-CN.md). **Lab trace** (SSE timeline, workspace tree) is built into the local web UI — no extra config needed. See **docs/DASHBOARD.md**. Second Quick Start Just send the message to OpenClaw: See the ExampleTask document for 6 ready-to-use demo prompts with expected outputs. Demo Examples Below are live demonstrations of BioClaw handling real bioinformatics tasks via WhatsApp. • Workspace Triage & Next Steps > Analyze files in a shared workspace and recommend the best next analysis steps. --- • FastQC Quality Control > Run FastQC on paired-end FASTQ files and deliver the QC report with key findings. --- • BLAST Sequence Search > BLAST a protein sequence against the NCBI nr database and return structured top hits. --- • Volcano Plot Generation > Create a differential expression volcano plot from a CSV file and interpret the results. --- • Protein Structure Rendering > Fetch a PDB structure, render it in rainbow coloring with PyMOL, and send the image. --- • PubMed Literature Search > Search PubMed for recent high-impact papers and provide structured summaries. --- • Hydrogen Bond Analysis > Visualize hydrogen bonds between a ligand and protein in PDB 1M17. --- • Binding Site Visualization > Show residues within 5Å of ligand AQ4 in PDB 1M17. --- System Architecture BioClaw is built on the NanoClaw container-based agent architecture, extended with biomedical tools and domain knowledge from the STELLA framework. **Key design principles (inherited from NanoClaw):** | Component | Description | |-----------|-------------| | **Container Isolation** | Each conversation group runs in its own Docker container with pre-installed bioinformatics tools | | **Filesystem IPC** | Text and image results are communicated between the agent and orchestrator via the filesystem | | **Per-Group State** | SQLite database tracks messages, sessions, and group-specific workspaces | | **Channel Agnostic** | Channels self-register at startup; the orchestrator connects whichever ones have credentials | **Biomedical capabilities (attributed to STELLA):** The bioinformatics tool suite and domain-specific skills — including sequence analysis, structural biology, literature mining, and data visualization — draw from the tool ecosystem developed in the STELLA project, a self-evolving multi-agent framework for biomedical research. Included Tools Command-Line…