Catalyst Design Agent v1.0.0
Overview
Recommends organometallic catalysts for drug synthesis steps and designs novel ligand modifications. Two core workflows: recommend (find the right catalyst) and design (create novel ligand variants).
Quick Start
CODEBLOCK0
Scripts
scripts/catalyst_recommend.py
Scores and ranks catalysts from curated database (12 catalysts, 28 reaction types).
CODEBLOCK1
Scoring (0-100): reaction match (50), cost (15), metal preference (10), enantioselectivity (10), loading efficiency (5), advantages (5), earth-abundance (5).
scripts/ligand_designer.py
Generates novel ligand variants via three strategies:
| Strategy | Method | Output |
|---|
| steric | Add methyl/iPr/tBu to aromatic rings | Modified SMILES + properties |
| electronic |
Add OMe/F/CF3 substituents | Modified SMILES + properties |
| bioisosteric | P→NHC, phenyl→pyridyl, phosphine→phosphite | Conceptual suggestions + rationale |
CODEBLOCK2
scripts/chain_entry.py
Standard PharmaClaw chain interface. Accepts JSON, routes to recommend/design/both.
Input keys: reaction, scaffold/ligand, substrate/smiles, constraints, enantioselective, strategy, draw, INLINECODE12
If only reaction is given, also auto-runs ligand optimization on the top recommended catalyst's ligand.
Chaining
| From | Input | To | Output |
|---|
| Chemistry Query / Retrosynthesis | Reaction type needed for a synthesis step | Catalyst Design | Ranked catalysts + conditions |
| Catalyst Design |
Top catalyst ligand SMILES | Ligand Designer | Novel ligand variants |
|
Catalyst Design | Novel ligand SMILES | IP Expansion | Patent landscape check |
|
Catalyst Design | Recommended conditions | Chemistry Query | Forward reaction simulation |
Database
INLINECODE14 — 12 catalysts, 8 metals, 28 reaction types. Includes SMILES, conditions, loading ranges, cost ratings, advantages/limitations, and literature DOIs.
Expandable: add entries following the existing schema.
Ligand Aliases
PPh3, PCy3, dppe, dppp, NHCIMes, NHCIPr — resolved automatically to SMILES.
催化剂设计代理 v1.0.0
概述
为药物合成步骤推荐有机金属催化剂,并设计新型配体修饰。包含两个核心工作流:推荐(寻找合适的催化剂)和设计(创建新型配体变体)。
快速开始
bash
为Suzuki偶联反应推荐催化剂
python scripts/catalyst_recommend.py --reaction suzuki
带约束条件的推荐(偏好廉价、地壳丰度高的金属)
python scripts/catalyst
recommend.py --reaction C-N coupling --constraints {preferearth
abundant: true, maxcost: medium}
基于PPh3设计新型配体变体
python scripts/ligand_designer.py --scaffold PPh3 --strategy all --draw
完整链路:反应 → 催化剂 → 配体优化
python scripts/chain_entry.py --input-json {reaction: suzuki, context: retrosynthesis}
脚本
scripts/catalyst_recommend.py
从精选数据库(12种催化剂,28种反应类型)中对催化剂进行评分和排序。
--reaction <类型> 必需。例如:suzuki, metathesis, C-N coupling, hydrogenation
--substrate 可选。底物上下文
--constraints 可选。{prefermetal, maxcost, preferearthabundant}
--enantioselective 标志。优先考虑手性催化剂
评分标准(0-100分):反应匹配度(50)、成本(15)、金属偏好(10)、对映选择性(10)、负载效率(5)、优势(5)、地壳丰度(5)。
scripts/ligand_designer.py
通过三种策略生成新型配体变体:
| 策略 | 方法 | 输出 |
|---|
| 位阻 | 向芳香环添加甲基/iPr/tBu | 修饰后的SMILES + 性质 |
| 电子效应 |
添加OMe/F/CF3取代基 | 修饰后的SMILES + 性质 |
| 生物电子等排 | P→NHC, 苯基→吡啶基, 膦→亚磷酸酯 | 概念性建议 + 原理说明 |
--scaffold 必需。PPh3, NHCIMes, NHCIPr, PCy3, dppe, dppp或原始SMILES
--strategy <类型> steric|electronic|bioisosteric|all(默认:all)
--draw 生成变体的2D网格PNG图
--output <路径> 将JSON结果保存到文件
scripts/chain_entry.py
标准PharmaClaw链路接口。接收JSON,路由至推荐/设计/两者。
输入键:reaction, scaffold/ligand, substrate/smiles, constraints, enantioselective, strategy, draw, context
如果仅提供reaction,则自动对排名最高的推荐催化剂的配体进行配体优化。
链路
| 来源 | 输入 | 目标 | 输出 |
|---|
| 化学查询/逆合成 | 合成步骤所需的反应类型 | 催化剂设计 | 排名催化剂 + 条件 |
| 催化剂设计 |
最佳催化剂配体SMILES | 配体设计器 | 新型配体变体 |
|
催化剂设计 | 新型配体SMILES | 知识产权扩展 | 专利布局检查 |
|
催化剂设计 | 推荐条件 | 化学查询 | 正向反应模拟 |
数据库
references/catalyst_database.json — 12种催化剂,8种金属,28种反应类型。包含SMILES、条件、负载范围、成本评级、优势/局限性以及文献DOI。
可扩展:按照现有模式添加条目。
配体别名
PPh3, PCy3, dppe, dppp, NHCIMes, NHCIPr — 自动解析为SMILES。