什么是 制药药理学代理？

制药药理学代理是专为在 Openclaw Skills 框架内从事药物研发的研究人员和开发人员设计的技术利器。它利用 RDKit 描述符和经过验证的基于规则的启发式算法，直接从 SMILES 字符串对分子候选物进行全面分析。通过将复杂的药理学数据合成为具有操作性的报告，该技能实现了对类药性和安全性概况的快速筛选。

该代理对于早期先导化合物优化特别有价值，允许团队在进入昂贵的实验阶段之前，识别潜在的药代动力学障碍，如吸收不良或高代谢风险。它无缝集成到更广泛的计算化学工作流中，使其成为数字化实验室环境中自动化药物分析和决策的基石。

下载入口:https://github.com/openclaw/skills/tree/main/skills/cheminem/pharma-pharmacology-agent

安装与下载

1. ClawHub CLI

从源直接安装技能的最快方式。

2. 手动安装

将技能文件夹复制到以下位置之一

优先级：工作区 > 本地 > 内置

3. 提示词安装

将此提示词复制到 OpenClaw 即可自动安装。

制药药理学代理 应用场景

• 对新设计的 SMILES 字符串进行自动化 ADME/PK 分析。
• 筛选分子库，确保符合 Lipinski 五倍律和 Veber 规则。
• 确定先导化合物的合成可及性 (SA) 和类药性 (QED) 评分。
• 标记潜在的安全问题，如 PAINS 警示或 CYP3A4 抑制风险。
• 与化学查询代理链式调用，构建全面的药物研发流水线。

1. 代理接收 SMILES 字符串输入（来自用户直接请求或作为链式工作流的一部分）。
2. 它使用 RDKit 计算基础分子描述符，包括分子量、logP 和 TPSA。
3. 将经过验证的启发式算法（如用于血脑屏障通透性的 Clark 规则和用于胃肠道吸收的 Egan egg 模型）应用于分子数据。
4. 该技能生成一份结构化的 JSON 报告，详细说明类药性、ADME 预测和安全警示。
5. 最终输出包括建议的后续步骤（如毒理学或 IP 扩展），以确保 Openclaw Skills 内流水线的连续性。

制药药理学代理 配置指南

要在您的 Openclaw Skills 设置中开始使用此药理学工具，请确保您的环境中安装了 RDKit 2024.03+。通过 CLI 使用以下命令结构执行分析脚本：

# 从 SMILES 字符串分析分子
exec python scripts/chain_entry.py --input-json '{"smiles": "CC(=O)Oc1ccccc1C(=O)O", "context": "user"}'

制药药理学代理 数据架构与分类体系

该代理生成标准化 JSON 架构，旨在实现 Openclaw Skills 内的高互操作性。数据组织为以下主要部分：

name: pharma-pharmacology-agent
description: Pharmacology agent for ADME/PK profiling of drug candidates from SMILES. Computes drug-likeness (Lipinski Ro5, Veber rules), QED, SA Score, ADME predictions (BBB permeability, aqueous solubility, GI absorption, CYP3A4 inhibition, P-gp substrate, plasma protein binding), and PAINS alerts. Chains from chemistry-query for SMILES input. Triggers on pharmacology, ADME, PK/PD, drug likeness, Lipinski, absorption, distribution, metabolism, excretion, BBB, solubility, bioavailability, lead optimization, drug profiling.

Pharma Pharmacology Agent v1.1.0

Overview

Predictive pharmacology profiling for drug candidates using RDKit descriptors and validated rule-based heuristics. Provides comprehensive ADME assessment, drug-likeness scoring, and risk flagging — all from a SMILES string.

Key capabilities:

• Drug-likeness: Lipinski Rule of Five, Veber oral bioavailability rules
• Scores: QED (Quantitative Estimate of Drug-likeness), SA Score (Synthetic Accessibility)
• ADME predictions: BBB permeability, aqueous solubility (ESOL), GI absorption (Egan), CYP3A4 inhibition risk, P-glycoprotein substrate, plasma protein binding
• Safety: PAINS (Pan-Assay Interference) filter alerts
• Risk assessment: Automated flagging of pharmacological concerns
• Standard chain output: JSON schema compatible with all downstream agents

Quick Start

# Profile a molecule from SMILES
exec python scripts/chain_entry.py --input-json '{"smiles": "CC(=O)Oc1ccccc1C(=O)O", "context": "user"}'

# Chain from chemistry-query output
exec python scripts/chain_entry.py --input-json '{"smiles": "", "context": "from_chemistry"}'

Scripts

scripts/chain_entry.py

Main entry point. Accepts JSON with smiles field, returns full pharmacology profile.

Input:

{"smiles": "CN1C=NC2=C1C(=O)N(C(=O)N2C)C", "context": "user"}

Output schema:

{
  "agent": "pharma-pharmacology",
  "version": "1.1.0",
  "smiles": "",
  "status": "success|error",
  "report": {
    "descriptors": {"mw": 194.08, "logp": -1.03, "tpsa": 61.82, "hbd": 0, "hba": 6, "rotb": 0, "arom_rings": 2, "heavy_atoms": 14, "mr": 51.2},
    "lipinski": {"pass": true, "violations": 0, "details": {...}},
    "veber": {"pass": true, "tpsa": {...}, "rotatable_bonds": {...}},
    "qed": 0.5385,
    "sa_score": 2.3,
    "adme": {
      "bbb": {"prediction": "moderate", "confidence": "medium", "rationale": "..."},
      "solubility": {"logS_estimate": -1.87, "class": "high", "rationale": "..."},
      "gi_absorption": {"prediction": "high", "rationale": "..."},
      "cyp3a4_inhibition": {"risk": "low", "rationale": "..."},
      "pgp_substrate": {"prediction": "unlikely", "rationale": "..."},
      "plasma_protein_binding": {"prediction": "moderate-low", "rationale": "..."}
    },
    "pains": {"alert": false}
  },
  "risks": [],
  "recommend_next": ["toxicology", "ip-expansion"],
  "confidence": 0.85,
  "warnings": [],
  "timestamp": "ISO8601"
}

ADME Prediction Rules

Chaining

This agent is designed to receive output from chemistry-query:

chemistry-query (name→SMILES+props) → pharma-pharmacology (ADME profile) → toxicology / ip-expansion

The recommend_next field always includes ["toxicology", "ip-expansion"] for pipeline continuation.

Tested With

All features verified end-to-end with RDKit 2024.03+:

Error Handling

• Invalid SMILES: Returns status: "error" with descriptive warning
• Missing input: Clear error message requesting smiles or name
• All errors produce valid JSON (never crashes)

Resources

• references/api_reference.md — API and methodology references

Changelog

v1.1.0 (2026-02-14)

• Initial production release with full ADME profiling
• Lipinski, Veber, QED, SA Score, PAINS
• BBB, solubility, GI absorption, CYP3A4, P-gp, PPB predictions
• Automated risk assessment
• Standard chain output schema
• Comprehensive error handling
• End-to-end tested with diverse molecules