103 lines
3.0 KiB
Python
Executable File
103 lines
3.0 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""
|
|
Annotation Skill 使用示例
|
|
展示如何在 pipeline 中集成 eggNOG-mapper 功能注释
|
|
"""
|
|
|
|
import subprocess
|
|
from pathlib import Path
|
|
|
|
|
|
def run_annotation_skill(protein_fasta: Path, output_dir: Path, **kwargs):
|
|
"""
|
|
调用 annotation skill 进行功能注释
|
|
|
|
Args:
|
|
protein_fasta: 蛋白序列FASTA文件路径
|
|
output_dir: 输出目录
|
|
**kwargs: 可选参数 (cpu, mode, evalue, etc.)
|
|
|
|
Returns:
|
|
dict: 包含 annotations 文件路径和统计信息
|
|
"""
|
|
skill_path = Path(__file__).parent / "run.py"
|
|
|
|
cmd = [
|
|
"python3", str(skill_path),
|
|
"--input", str(protein_fasta),
|
|
"--output", str(output_dir),
|
|
]
|
|
|
|
# 添加可选参数
|
|
if "cpu" in kwargs:
|
|
cmd.extend(["--cpu", str(kwargs["cpu"])])
|
|
if "mode" in kwargs:
|
|
cmd.extend(["--mode", kwargs["mode"]])
|
|
if "evalue" in kwargs:
|
|
cmd.extend(["--evalue", str(kwargs["evalue"])])
|
|
if "prefix" in kwargs:
|
|
cmd.extend(["--prefix", kwargs["prefix"]])
|
|
|
|
result = subprocess.run(cmd, capture_output=True, text=True)
|
|
|
|
if result.returncode != 0:
|
|
raise RuntimeError(f"Annotation failed: {result.stderr}")
|
|
|
|
import json
|
|
return json.loads(result.stdout)
|
|
|
|
|
|
def integrate_with_pipeline(gene_family_pep: Path, work_dir: Path):
|
|
"""
|
|
集成到基因家族分析 pipeline 的示例
|
|
|
|
在基因鉴定后，对鉴定出的基因家族成员进行功能注释
|
|
"""
|
|
annotation_dir = work_dir / "05_annotation"
|
|
annotation_dir.mkdir(parents=True, exist_ok=True)
|
|
|
|
print(f"[Pipeline] Running functional annotation for {gene_family_pep.name}")
|
|
|
|
# 调用 annotation skill
|
|
result = run_annotation_skill(
|
|
protein_fasta=gene_family_pep,
|
|
output_dir=annotation_dir,
|
|
prefix="gene_family",
|
|
cpu=8,
|
|
mode="diamond",
|
|
evalue=0.001,
|
|
)
|
|
|
|
if result["status"] == "success":
|
|
print(f"[Pipeline] Annotation completed!")
|
|
print(f" - Annotations file: {result['annotations']}")
|
|
print(f" - Report: {result['report']}")
|
|
print(f" - Stats: {result['stats']['total_genes']} genes, "
|
|
f"{result['stats']['with_go']} with GO, "
|
|
f"{result['stats']['with_kegg']} with KEGG")
|
|
|
|
return result
|
|
else:
|
|
raise RuntimeError("Annotation failed")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
# 示例用法
|
|
print("=" * 60)
|
|
print("Annotation Skill Integration Example")
|
|
print("=" * 60)
|
|
|
|
# 创建示例蛋白文件
|
|
demo_pep = Path("/tmp/demo_genes.pep")
|
|
demo_pep.write_text(">Gene001\nMKTLLLPLLLLVLLLLLVQGSISAQAAAAAA\n"
|
|
">Gene002\nMKTLLLPLLLLVLLLLLVQGSISAQBBBBBB\n")
|
|
|
|
# 运行注释
|
|
result = integrate_with_pipeline(demo_pep, Path("/tmp/demo_annotation"))
|
|
|
|
print("\n" + "=" * 60)
|
|
print("Result:")
|
|
print(f" Status: {result['status']}")
|
|
print(f" Output dir: {result['output_dir']}")
|
|
print(f" Annotations: {result['annotations']}")
|