mcpField
C
campaign-manager

campaign-manager

github.com/adaptyvbio其他17240 次安装20 周前更新
代码仓库

关于 campaign-manager

Campaign Manager 是面向蛋白质结合体设计研究的规划技能,可将目标和所需结合体数量转化为可执行流程。它列出工具选择、活动规模、预期筛选产出、时间和成本,并提供适用于不同优先级的流程方案。

主要功能

  1. 01生成从目标到流程的计划
  2. 02建议活动设计规模
  3. 03按设计场景比较工具
  4. 04估算活动时间和成本
  5. 05提供高通量与高质量方案

适用场景

  1. 01为目标规划结合体设计活动
  2. 02估算达到目标所需的设计数量
  3. 03为困难靶点选择流程
  4. 04比较快速探索与高质量运行

安装

复制下面的命令,在终端中运行。

$npx skills add https://github.com/adaptyvbio/protein-design-skills --skill campaign-manager

安装后在 Claude Code 中输入/campaign-manager确认已加载。

详细介绍

Campaign Manager

目标导向设计

从目标到流程

当用户说:“我需要 10 个适用于 EGFR 的优质结合剂”

活动规划:

Goal: 10 high-quality binders for EGFR
├── Achievable: Yes (standard target)
├── Recommended pipeline: rfdiffusion → proteinmpnn → chai → protein-qc
├── Estimated designs needed: 500 backbones (to get ~50 passing QC)
├── Estimated time: 8-12 hours total
├── Estimated cost: ~$60 (Modal GPU compute)
└── Expected yield:
    ├── After backbone (500): 500 structures
    ├── After sequence (×8): 4,000 sequences
    ├── After validation: 4,000 predictions
    ├── After QC (~10-15%): 400-600 candidates
    └── After clustering: 10-20 diverse final designs

完整流程生成器

标准微型蛋白结合剂活动
# Step 1: Fetch and prepare target (5 min)
curl -o target.pdb "https://files.rcsb.org/download/{PDB_ID}.pdb"
# Trim to binding region if needed

# Step 2: Generate backbones (2-3h, ~$15)
# RFdiffusion runs from the official repo, not biomodals
python run_inference.py \
  inference.input_pdb=target.pdb \
  contigmap.contigs=[A1-150/0 70-100] \
  ppi.hotspot_res=[A45,A67,A89] \
  inference.num_designs=500

# Checkpoint: ls output/*.pdb | wc -l  # Should be 500

# Step 3: Design sequences (1-2h, ~$10)
for f in output/*.pdb; do
  modal run modal_ligandmpnn.py \
    --input-pdb "$f" \
    --params-str "--number_of_batches 8 --temperature 0.1"
done

# Checkpoint: grep -c "^>" output/seqs/*.fa  # Should be ~4000

# Step 4: Quick ESM2 filter (30 min, ~$5, optional)
modal run modal_esm2_predict_masked.py --input-faa output/all_seqs.fa
# Filter sequences with PLL < 0.0

# Step 5: Structure validation (3-4h, ~$35)
modal run modal_alphafold.py \
  --input-faa output/filtered_seqs.fa \
  --out-dir predictions/

# Checkpoint: find predictions -name "*rank_001.pdb" | wc -l

# Step 6: Filter and rank (protein-qc skill)
# Apply thresholds: pLDDT > 0.85, ipTM > 0.5, scRMSD < 2.0
# Compute composite score
# Cluster at 70% identity, select top from each cluster

预计总耗时:8-12 小时 预计总成本:约 $60-70


活动规模建议

目标骨架数序列数/骨架序列总数预计通过数
5 个结合剂20081,600160-240
10 个结合剂50084,000400-600
20 个结合剂1,00088,000800-1,200
50 个结合剂2,500820,0002,000-3,000

经验法则:生成所需设计数量的 50 倍(通过率为 10-15%,再进行聚类)。


工具选择指南

各工具的适用场景
场景推荐工具原因
标准微型蛋白RFdiffusion + ProteinMPNN多样性高,经过验证
需要更高的成功率BindCraft集成式设计循环
需要全原子精度BoltzGen考虑侧链
困难靶点Mosaic梯度、多模型目标
需要快速迭代ESMFold2 + ESM2快速筛选
靶点难度评估
指标容易的靶点困难的靶点
表面类型凹形口袋平坦或凸起
保守性高低
已知结合剂有无
柔性刚性柔性
预计通过率15-20%5-10%

活动健康状况评估

快速指标检查
import pandas as pd

def assess_campaign(csv_path):
    df = pd.read_csv(csv_path)

    # Calculate pass rates
    plddt_pass = (df['pLDDT'] > 0.85).mean()
    iptm_pass = (df['ipTM'] > 0.50).mean()
    scrmsd_pass = (df['scRMSD'] < 2.0).mean()
    all_pass = ((df['pLDDT'] > 0.85) & (df['ipTM'] > 0.5) & (df['scRMSD'] < 2.0)).mean()

    # Determine health
    if all_pass > 0.15:
        health = "EXCELLENT"
    elif all_pass > 0.10:
        health = "GOOD"
    elif all_pass > 0.05:
        health = "MARGINAL"
    else:
        health = "POOR"

    # Identify top issue
    issues = []
    if plddt_pass < 0.20:
        issues.append("Low pLDDT - backbone or sequence issue")
    if iptm_pass < 0.20:
        issues.append("Low ipTM - hotspot or interface issue")
    if scrmsd_pass < 0.50:
        issues.append("High scRMSD - sequence doesn't specify backbone")

    return {
        "health": health,
        "overall_pass_rate": all_pass,
        "plddt_pass_rate": plddt_pass,
        "iptm_pass_rate": iptm_pass,
        "scrmsd_pass_rate": scrmsd_pass,
        "top_issues": issues
    }
结果解读
健康状况通过率操作
极佳> 15%继续筛选
良好10-15%继续,产出正常
一般5-10%检查失败树
较差< 5%诊断并重新开始

成本估算

各工具成本(Modal)
工具GPU美元/小时典型任务成本
RFdiffusionA10G约 $1.20500 个设计/2 小时约 $2.50
ProteinMPNNT4约 $0.604000 条序列/1.5 小时约 $1.00
ESM2 (PLL)A10G约 $1.204000 条序列/30 分钟约 $0.60
AlphaFoldA100约 $4.504000 个预测/4 小时约 $18.00
ChaiA100约 $4.50500 个预测/1 小时约 $4.50
活动成本估算
活动规模总成本备注
小型(100 个骨架)约 $15快速探索
标准(500 个骨架)约 $60适用于大多数活动
大型(1000 个骨架)约 $120全面探索
超大型(5000 个骨架)约 $600非常全面

流程变体

高通量(最大化多样性)
# More backbones, fewer sequences each (RFdiffusion from the official repo)
python run_inference.py inference.num_designs=2000
modal run modal_ligandmpnn.py --input-pdb bb.pdb --params-str "--number_of_batches 4 --temperature 0.2"
高质量(最大化单个设计的质量)
# Fewer backbones, more sequences each, lower temperature
python run_inference.py inference.num_designs=200
modal run modal_ligandmpnn.py --input-pdb bb.pdb --params-str "--number_of_batches 32 --temperature 0.1"
快速探索(快速迭代)
# Small batch, ESMFold2 for fast single-sequence folding
# RFdiffusion runs from the official repo (not biomodals); see the rfdiffusion skill
modal run modal_ligandmpnn.py --input-pdb bb.pdb --params-str "--number_of_batches 8"
modal run modal_esmfold2.py --input-faa all_seqs.fa

另请参阅

  • 工具专属参数:rfdiffusion、proteinmpnn、mosaic、chai、boltz、alphafold
  • QC 阈值和筛选:protein-qc
  • 工具选择指南:binder-design

评论

支持 Markdown