cloud-pkumdl/dsh-pdb

Name: cloud-pkumdl/dsh-pdb
Author: cloud-pkumdl

插件Plugin ⭐ 2 MIT cat_label.agentic-workflowcat_label.agentic-workflow cat_label.alphafoldcat_label.alphafold cat_label.bioinformaticscat_label.bioinformatics cat_label.dagcat_label.dag cat_label.drug-designcat_label.drug-design cat_label.protein-bindercat_label.protein-binder

dsh-pdb (Protein Design for Binder): agent-driven workflow orchestration for protein binder design. DAG-based plan visualization with human-in-the-loop review — unifying GUI-less protein design tools under one agentic pipeline.

项目介绍Project Overview

由知微Agent(zhiwei)编辑Edited by Zhiwei Agent (zhiwei)

dsh-pdb 是蛋白质结合体设计的智能体工作流编排层，将 RFdiffusion、ProteinMPNN、AlphaFold、ESMFold、Rosetta 等工具封装为可插拔节点。智能体根据自然语言目标生成 DAG 计划，人工审阅、剪枝或嫁接分支后执行，失败时自动回溯重规划，并实时追踪状态与指标。适用于多策略结合体设计探索。注意：项目处于早期开发阶段，且各后端工具需遵守其自身许可证。

dsh-pdb is an agent-driven workflow orchestration layer for protein binder design, wrapping tools like RFdiffusion, ProteinMPNN, AlphaFold, ESMFold, and Rosetta as pluggable nodes. An agent proposes a DAG plan from a natural-language goal; humans review, prune, or graft branches before execution, with live status tracking and automatic backtracking on failure. Use it for multi-strategy binder design campaigns. Caveat: it is in early development, and each wrapped backend tool retains its own license.

在 GitHub 查看View on GitHub

发给你的 DSH 安装Send to your DSH

请帮我了解并安装插件：【dsh-pdb】【https://github.com/cloud-pkumdl/dsh-pdb】

把上面这条消息直接发给当前会话里的 DSH，让它帮你了解并安装。安装命令不一定准确，发给 DSH 更稳。Send this message to DSH in your current session. CLI install commands may not be accurate across systems — DSH will figure it out for you.

或使用命令行安装（适合开发者）Or use CLI install (for developers)

命令行安装CLI Install

dsh plugin --profile web add github:cloud-pkumdl/dsh-pdb

把 cloud-pkumdl/dsh-pdb 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

3.0 KB · 缓存于 2026-08-27 05:42:23 · 3.0 KB

dsh-pdb

Protein Design for Binder — an agent-driven workflow orchestration layer for protein binder design.

Note: pdb here stands for Protein Design for Binder — not the Protein Data Bank.

Why

Most protein design tools (RFdiffusion, ProteinMPNN, AlphaFold2, ESMFold, Rosetta...) are powerful but command-line only, fragmented, and hard to chain. Running a full binder design campaign means manually stitching together a dozen scripts, tracking intermediate files by hand, and re-planning when a branch fails — with no unified view of what's been tried.

dsh-pdb unifies these tools under a single agentic pipeline. An AI agent proposes a design plan; you review and refine it; the pipeline executes and reports back — with every step visualized as a living DAG.

Core Idea

Machine plans, human reviews, the graph is the alignment interface.

Unlike cryoSPARC (human authors the workflow, machine executes, graph is a record), dsh-pdb inverts control:

Agent proposes — the agent generates an execution plan as a DAG (nodes = steps/strategies, edges = dependencies/derivations).
Human reviews — you see the plan as a flowchart, then approve, prune, or graft branches before anything runs.
Pipeline executes — approved nodes run; status flows back live (planned -> running -> success/failed).
Re-plan on failure — failed branches trigger the agent to backtrack and propose alternatives, all traceable to the root.

This lowers the planning barrier: you don't need to know the optimal workflow up front — the agent suggests one, you correct it.

Features (planned)

Agent-proposed design plans — DAG generated from a natural-language goal ("design a binder against target X")
Interactive plan review — visualize, approve/reject branches, edit nodes before execution
Multi-strategy DFS exploration — parallel design strategies with automatic backtracking
Unified tool wrapping — RFdiffusion / ProteinMPNN / AF2 / ESMFold / Rosetta as pluggable nodes
Full reproducibility — every node records inputs, params, and provenance back to the root
Live status tracking — real-time node states with metrics (ipTM, pLDDT, etc.)

Backend Tool Licenses

dsh-pdb wraps existing design tools; it does not redistribute their code or weights. When packaging or using them, respect each tool's own license:

Tool	License	Notes
RFdiffusion	BSD-3-Clause	Code + weights both covered
RFdiffusion2	BSD-3-Clause
ProteinMPNN	MIT
LigandMPNN	MIT
ESM / ESMFold	MIT
ColabFold	MIT
dl_binder_design	MIT
AlphaFold2	Apache-2.0 (code)	Weights: CC BY 4.0 (commercial OK)
AlphaFold3	Apache-2.0 (code)	Weights: non-commercial, request from DeepMind, no redistribution
Rosetta	Free for academic	Commercial use requires a paid RosettaCommons license

Status

Early development. Concept demo of the plan-review interface coming soon.

License

MIT — see LICENSE.

渲染基于仓库 cloud-pkumdl/dsh-pdb 的 README.md。在 GitHub 查看原文 →

命令行安装CLI Install 复制安装命令Copy Install