@hongmaple0820/med-scale-research-os 0.43.0

package/target-research-platform/scripts/prepare_immune_data.py

@@ -0,0 +1,386 @@
+#!/usr/bin/env python3
+"""
+免疫浸润数据准备脚本
+
+用途：
+1. 生成示例免疫浸润数据（基于 TCGA 发表的典型分布）
+2. 用于开发/测试阶段，验证 pipeline 功能完整性
+
+生产环境请使用真实数据：
+- TIMER2.0: http://timer.comp-genomics.org/
+- TCIA: https://tcia.at/
+- CIBERSORT: https://cibersortx.stanford.edu/
+- Pan-Cancer Atlas: https://gdc.cancer.gov/about-data/publications/panimmuneatlas
+
+用法:
+  python scripts/prepare_immune_data.py          # 生成示例数据
+  python scripts/prepare_immune_data.py --check   # 检查数据状态
+
+生成的 CSV 格式:
+  sample_id,B_cell,CD4_T_cell,CD8_T_cell,Neutrophil,Macrophage,
+  Dendritic_cell,NK_cell,Monocyte,Mast_cell,Eosinophil
+"""
+import argparse
+import csv
+import os
+import sys
+from pathlib import Path
+
+import numpy as np
+
+# 添加 src 到路径
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+
+# TCGA 各癌型典型免疫浸润比例 (基于 published pan-cancer immune atlas)
+# 格式: {cancer: {cell_type: (mean, std)}}
+# 数值参考: Thorsson et al., Immunity 2018; Saltz et al., Cancer Cell 2018
+IMMUNE_PROFILES = {
+    "LUAD": {
+        "B_cell": (0.08, 0.04), "CD4_T_cell": (0.15, 0.06),
+        "CD8_T_cell": (0.12, 0.05), "Neutrophil": (0.06, 0.03),
+        "Macrophage": (0.18, 0.07), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.06, 0.03),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "BRCA": {
+        "B_cell": (0.10, 0.05), "CD4_T_cell": (0.18, 0.07),
+        "CD8_T_cell": (0.10, 0.04), "Neutrophil": (0.04, 0.02),
+        "Macrophage": (0.15, 0.06), "Dendritic_cell": (0.04, 0.02),
+        "NK_cell": (0.03, 0.02), "Monocyte": (0.05, 0.02),
+        "Mast_cell": (0.03, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "COAD": {
+        "B_cell": (0.06, 0.03), "CD4_T_cell": (0.12, 0.05),
+        "CD8_T_cell": (0.14, 0.06), "Neutrophil": (0.08, 0.04),
+        "Macrophage": (0.20, 0.08), "Dendritic_cell": (0.06, 0.03),
+        "NK_cell": (0.05, 0.02), "Monocyte": (0.07, 0.03),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.02, 0.01)
+    },
+    "LUSC": {
+        "B_cell": (0.07, 0.03), "CD4_T_cell": (0.14, 0.05),
+        "CD8_T_cell": (0.11, 0.05), "Neutrophil": (0.07, 0.03),
+        "Macrophage": (0.19, 0.07), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.06, 0.03),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "PRAD": {
+        "B_cell": (0.05, 0.02), "CD4_T_cell": (0.10, 0.04),
+        "CD8_T_cell": (0.08, 0.03), "Neutrophil": (0.04, 0.02),
+        "Macrophage": (0.12, 0.05), "Dendritic_cell": (0.04, 0.02),
+        "NK_cell": (0.03, 0.01), "Monocyte": (0.04, 0.02),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "STAD": {
+        "B_cell": (0.06, 0.03), "CD4_T_cell": (0.13, 0.05),
+        "CD8_T_cell": (0.15, 0.06), "Neutrophil": (0.07, 0.03),
+        "Macrophage": (0.17, 0.06), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.05, 0.02), "Monocyte": (0.06, 0.03),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "HNSC": {
+        "B_cell": (0.07, 0.03), "CD4_T_cell": (0.14, 0.06),
+        "CD8_T_cell": (0.13, 0.05), "Neutrophil": (0.06, 0.03),
+        "Macrophage": (0.16, 0.06), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.06, 0.03),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "KIRC": {
+        "B_cell": (0.09, 0.04), "CD4_T_cell": (0.16, 0.06),
+        "CD8_T_cell": (0.14, 0.06), "Neutrophil": (0.05, 0.02),
+        "Macrophage": (0.14, 0.05), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.06, 0.03), "Monocyte": (0.05, 0.02),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "LIHC": {
+        "B_cell": (0.06, 0.03), "CD4_T_cell": (0.12, 0.05),
+        "CD8_T_cell": (0.12, 0.05), "Neutrophil": (0.06, 0.03),
+        "Macrophage": (0.18, 0.07), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.06, 0.03), "Monocyte": (0.07, 0.03),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "THCA": {
+        "B_cell": (0.08, 0.04), "CD4_T_cell": (0.14, 0.05),
+        "CD8_T_cell": (0.08, 0.03), "Neutrophil": (0.04, 0.02),
+        "Macrophage": (0.12, 0.05), "Dendritic_cell": (0.04, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.05, 0.02),
+        "Mast_cell": (0.03, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "OV": {
+        "B_cell": (0.05, 0.02), "CD4_T_cell": (0.12, 0.05),
+        "CD8_T_cell": (0.10, 0.04), "Neutrophil": (0.05, 0.02),
+        "Macrophage": (0.20, 0.08), "Dendritic_cell": (0.04, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.06, 0.03),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "GBM": {
+        "B_cell": (0.03, 0.01), "CD4_T_cell": (0.08, 0.03),
+        "CD8_T_cell": (0.06, 0.02), "Neutrophil": (0.04, 0.02),
+        "Macrophage": (0.25, 0.10), "Dendritic_cell": (0.04, 0.02),
+        "NK_cell": (0.02, 0.01), "Monocyte": (0.08, 0.03),
+        "Mast_cell": (0.01, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "SKCM": {
+        "B_cell": (0.08, 0.04), "CD4_T_cell": (0.16, 0.06),
+        "CD8_T_cell": (0.18, 0.07), "Neutrophil": (0.05, 0.02),
+        "Macrophage": (0.14, 0.05), "Dendritic_cell": (0.06, 0.03),
+        "NK_cell": (0.05, 0.02), "Monocyte": (0.05, 0.02),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "BLCA": {
+        "B_cell": (0.07, 0.03), "CD4_T_cell": (0.14, 0.05),
+        "CD8_T_cell": (0.13, 0.05), "Neutrophil": (0.06, 0.03),
+        "Macrophage": (0.16, 0.06), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.06, 0.03),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "PAAD": {
+        "B_cell": (0.04, 0.02), "CD4_T_cell": (0.10, 0.04),
+        "CD8_T_cell": (0.08, 0.03), "Neutrophil": (0.08, 0.04),
+        "Macrophage": (0.22, 0.08), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.03, 0.01), "Monocyte": (0.07, 0.03),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "CESC": {
+        "B_cell": (0.07, 0.03), "CD4_T_cell": (0.15, 0.06),
+        "CD8_T_cell": (0.12, 0.05), "Neutrophil": (0.05, 0.02),
+        "Macrophage": (0.15, 0.06), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.05, 0.02),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "READ": {
+        "B_cell": (0.06, 0.03), "CD4_T_cell": (0.12, 0.05),
+        "CD8_T_cell": (0.14, 0.06), "Neutrophil": (0.07, 0.03),
+        "Macrophage": (0.18, 0.07), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.05, 0.02), "Monocyte": (0.06, 0.03),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "ESCA": {
+        "B_cell": (0.05, 0.02), "CD4_T_cell": (0.12, 0.05),
+        "CD8_T_cell": (0.14, 0.06), "Neutrophil": (0.06, 0.03),
+        "Macrophage": (0.17, 0.06), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.06, 0.03),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "UCEC": {
+        "B_cell": (0.07, 0.03), "CD4_T_cell": (0.14, 0.05),
+        "CD8_T_cell": (0.10, 0.04), "Neutrophil": (0.05, 0.02),
+        "Macrophage": (0.16, 0.06), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.05, 0.02),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "KIRP": {
+        "B_cell": (0.08, 0.04), "CD4_T_cell": (0.14, 0.05),
+        "CD8_T_cell": (0.12, 0.05), "Neutrophil": (0.05, 0.02),
+        "Macrophage": (0.14, 0.05), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.05, 0.02), "Monocyte": (0.05, 0.02),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "KICH": {
+        "B_cell": (0.07, 0.03), "CD4_T_cell": (0.13, 0.05),
+        "CD8_T_cell": (0.10, 0.04), "Neutrophil": (0.04, 0.02),
+        "Macrophage": (0.12, 0.05), "Dendritic_cell": (0.04, 0.02),
+        "NK_cell": (0.05, 0.02), "Monocyte": (0.05, 0.02),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "SARC": {
+        "B_cell": (0.05, 0.02), "CD4_T_cell": (0.10, 0.04),
+        "CD8_T_cell": (0.08, 0.03), "Neutrophil": (0.05, 0.02),
+        "Macrophage": (0.18, 0.07), "Dendritic_cell": (0.04, 0.02),
+        "NK_cell": (0.03, 0.01), "Monocyte": (0.06, 0.03),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "LGG": {
+        "B_cell": (0.03, 0.01), "CD4_T_cell": (0.08, 0.03),
+        "CD8_T_cell": (0.05, 0.02), "Neutrophil": (0.03, 0.01),
+        "Macrophage": (0.22, 0.08), "Dendritic_cell": (0.03, 0.01),
+        "NK_cell": (0.02, 0.01), "Monocyte": (0.07, 0.03),
+        "Mast_cell": (0.01, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    # 以下为罕见癌种，基于相近组织类型推断
+    "ACC": {
+        "B_cell": (0.05, 0.02), "CD4_T_cell": (0.10, 0.04),
+        "CD8_T_cell": (0.08, 0.03), "Neutrophil": (0.04, 0.02),
+        "Macrophage": (0.14, 0.05), "Dendritic_cell": (0.04, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.05, 0.02),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "CHOL": {
+        "B_cell": (0.05, 0.02), "CD4_T_cell": (0.11, 0.04),
+        "CD8_T_cell": (0.10, 0.04), "Neutrophil": (0.06, 0.03),
+        "Macrophage": (0.18, 0.07), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.06, 0.03),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "DLBC": {
+        "B_cell": (0.30, 0.10), "CD4_T_cell": (0.15, 0.06),
+        "CD8_T_cell": (0.08, 0.03), "Neutrophil": (0.04, 0.02),
+        "Macrophage": (0.10, 0.04), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.04, 0.02),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "LAML": {
+        "B_cell": (0.03, 0.01), "CD4_T_cell": (0.10, 0.04),
+        "CD8_T_cell": (0.06, 0.02), "Neutrophil": (0.15, 0.06),
+        "Macrophage": (0.08, 0.03), "Dendritic_cell": (0.04, 0.02),
+        "NK_cell": (0.05, 0.02), "Monocyte": (0.10, 0.04),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.02, 0.01)
+    },
+    "MESO": {
+        "B_cell": (0.04, 0.02), "CD4_T_cell": (0.12, 0.05),
+        "CD8_T_cell": (0.10, 0.04), "Neutrophil": (0.05, 0.02),
+        "Macrophage": (0.20, 0.08), "Dendritic_cell": (0.04, 0.02),
+        "NK_cell": (0.03, 0.01), "Monocyte": (0.06, 0.03),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "PCPG": {
+        "B_cell": (0.05, 0.02), "CD4_T_cell": (0.10, 0.04),
+        "CD8_T_cell": (0.07, 0.03), "Neutrophil": (0.04, 0.02),
+        "Macrophage": (0.12, 0.05), "Dendritic_cell": (0.04, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.05, 0.02),
+        "Mast_cell": (0.03, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "TGCT": {
+        "B_cell": (0.06, 0.03), "CD4_T_cell": (0.14, 0.05),
+        "CD8_T_cell": (0.12, 0.05), "Neutrophil": (0.04, 0.02),
+        "Macrophage": (0.12, 0.05), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.05, 0.02), "Monocyte": (0.05, 0.02),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "THYM": {
+        "B_cell": (0.04, 0.02), "CD4_T_cell": (0.25, 0.08),
+        "CD8_T_cell": (0.18, 0.06), "Neutrophil": (0.03, 0.01),
+        "Macrophage": (0.08, 0.03), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.04, 0.02),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "UCS": {
+        "B_cell": (0.06, 0.03), "CD4_T_cell": (0.12, 0.05),
+        "CD8_T_cell": (0.09, 0.04), "Neutrophil": (0.05, 0.02),
+        "Macrophage": (0.16, 0.06), "Dendritic_cell": (0.04, 0.02),
+        "NK_cell": (0.04, 0.02), "Monocyte": (0.05, 0.02),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+    "UVM": {
+        "B_cell": (0.05, 0.02), "CD4_T_cell": (0.12, 0.05),
+        "CD8_T_cell": (0.14, 0.06), "Neutrophil": (0.04, 0.02),
+        "Macrophage": (0.14, 0.05), "Dendritic_cell": (0.05, 0.02),
+        "NK_cell": (0.05, 0.02), "Monocyte": (0.05, 0.02),
+        "Mast_cell": (0.02, 0.01), "Eosinophil": (0.01, 0.01)
+    },
+}
+
+
+def generate_sample_data(cancer_type: str, n_samples: int = 200) -> list[dict]:
+    """生成指定癌型的示例免疫浸润数据"""
+    profile = IMMUNE_PROFILES.get(cancer_type)
+    if not profile:
+        # 使用 LUAD 作为默认模板
+        profile = IMMUNE_PROFILES["LUAD"]
+
+    samples = []
+    for i in range(n_samples):
+        sample_id = f"TCGA-{cancer_type[:2].upper()}-{i + 1:04d}-01A"
+        row = {"sample_id": sample_id}
+
+        for cell_type, (mean, std) in profile.items():
+            # 使用对数正态分布，确保值为正
+            value = np.random.lognormal(np.log(mean + 0.001), 0.5)
+            # 裁剪到合理范围 [0, 1]
+            value = max(0.0, min(1.0, value))
+            row[cell_type] = round(value, 4)
+
+        samples.append(row)
+
+    return samples
+
+
+def write_csv(file_path: Path, samples: list[dict]):
+    """写入 CSV 文件"""
+    cell_types = [
+        "B_cell", "CD4_T_cell", "CD8_T_cell", "Neutrophil",
+        "Macrophage", "Dendritic_cell", "NK_cell", "Monocyte",
+        "Mast_cell", "Eosinophil"
+    ]
+    fieldnames = ["sample_id"] + cell_types
+
+    with open(file_path, 'w', newline='', encoding='utf-8') as f:
+        writer = csv.DictWriter(f, fieldnames=fieldnames)
+        writer.writeheader()
+        writer.writerows(samples)
+
+
+def check_data_status(data_dir: Path):
+    """检查数据状态"""
+    print(f"数据目录: {data_dir}")
+    print(f"目录存在: {data_dir.exists()}")
+
+    if not data_dir.exists():
+        print("目录不存在，无数据文件")
+        return
+
+    files = list(data_dir.glob("*.csv")) + list(data_dir.glob("*.tsv")) + list(data_dir.glob("*.csv.gz"))
+    print(f"数据文件数: {len(files)}")
+
+    if files:
+        print("\n已有的癌型数据:")
+        for f in sorted(files):
+            size = f.stat().st_size
+            print(f"  {f.name} ({size:,} bytes)")
+    else:
+        print("无数据文件")
+
+    # 检查哪些癌型缺少数据
+    from src.api_clients.immune_data_manager import ImmuneDataManager
+    manager = ImmuneDataManager(data_dir=str(data_dir))
+    status = manager.get_data_status()
+
+    available = [c for c, s in status.items() if s["local_data"]]
+    missing = [c for c, s in status.items() if not s["local_data"]]
+
+    print(f"\n可用癌型 ({len(available)}): {', '.join(available) if available else '无'}")
+    print(f"缺少癌型 ({len(missing)}): {', '.join(missing) if missing else '无'}")
+
+
+def main():
+    parser = argparse.ArgumentParser(description="免疫浸润数据准备工具")
+    parser.add_argument("--check", action="store_true", help="检查数据状态")
+    parser.add_argument("--cancers", nargs="+", help="指定要生成的癌型（默认全部）")
+    parser.add_argument("--n-samples", type=int, default=200, help="每个癌型的样本数")
+    parser.add_argument("--output", default="./data/immune_infiltration", help="输出目录")
+    args = parser.parse_args()
+
+    data_dir = Path(args.output)
+
+    if args.check:
+        check_data_status(data_dir)
+        return
+
+    # 确保目录存在
+    data_dir.mkdir(parents=True, exist_ok=True)
+
+    cancers = args.cancers or list(IMMUNE_PROFILES.keys())
+
+    print(f"生成免疫浸润示例数据")
+    print(f"癌型数: {len(cancers)}")
+    print(f"每癌型样本数: {args.n_samples}")
+    print(f"输出目录: {data_dir}")
+    print()
+
+    for cancer in cancers:
+        if cancer not in IMMUNE_PROFILES:
+            print(f"  [跳过] {cancer} — 无免疫浸润配置")
+            continue
+
+        samples = generate_sample_data(cancer, args.n_samples)
+        file_path = data_dir / f"{cancer}.csv"
+        write_csv(file_path, samples)
+        print(f"  [完成] {cancer} → {file_path.name} ({len(samples)} 样本)")
+
+    print(f"\n数据生成完成！文件保存至: {data_dir}")
+    print("\n注意：这是基于 published 分布的示例数据，用于开发/测试。")
+    print("生产环境请替换为真实 TIMER2.0/CIBERSORT 数据。")
+
+
+if __name__ == "__main__":
+    main()

package/target-research-platform/src/__init__.py

@@ -0,0 +1,4 @@
+"""
+药物靶点智能研究平台
+"""
+__version__ = "0.1.0"

package/target-research-platform/src/analysis/__init__.py

@@ -0,0 +1,3 @@
+"""
+分析模块
+"""

package/target-research-platform/src/analysis/stage1_expression/__init__.py

@@ -0,0 +1,12 @@
+"""
+阶段1：靶点表达全景与预后挖掘
+"""
+from .survival_analysis import SurvivalAnalyzer
+from .immune_correlation import ImmuneCorrelationAnalyzer
+from .pipeline import Stage1Pipeline
+
+__all__ = [
+    "SurvivalAnalyzer",
+    "ImmuneCorrelationAnalyzer",
+    "Stage1Pipeline"
+]