394 lines
12 KiB
Python
Executable File
394 lines
12 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""
|
|
Motif Analysis Skill - 保守基序分析技能
|
|
使用MEME Suite进行基因家族保守基序分析
|
|
|
|
Usage:
|
|
python run.py --input protein.fa --output ./motif
|
|
python run.py --config config.yaml --output ./motif
|
|
python run.py --demo --output ./motif
|
|
"""
|
|
|
|
import argparse
|
|
import hashlib
|
|
import json
|
|
import logging
|
|
import os
|
|
import shutil
|
|
import subprocess
|
|
import sys
|
|
from datetime import datetime
|
|
from pathlib import Path
|
|
from typing import Dict, List, Optional
|
|
|
|
import yaml
|
|
|
|
# 设置日志
|
|
logging.basicConfig(
|
|
level=logging.INFO,
|
|
format='%(asctime)s - %(levelname)s - %(message)s'
|
|
)
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class MotifSkill:
|
|
"""保守基序分析技能主类"""
|
|
|
|
def __init__(self, config_path: Optional[str] = None):
|
|
self.config = self._load_config(config_path)
|
|
self.commands = [] # 记录所有执行的命令
|
|
self.checksums = {} # 记录文件校验
|
|
|
|
def _load_config(self, config_path: Optional[str]) -> Dict:
|
|
"""加载配置文件"""
|
|
if config_path and os.path.exists(config_path):
|
|
with open(config_path) as f:
|
|
return yaml.safe_load(f)
|
|
default_config = Path(__file__).parent / "config.yaml"
|
|
with open(default_config) as f:
|
|
return yaml.safe_load(f)
|
|
|
|
def _which(self, cmd: str) -> Optional[str]:
|
|
"""检查命令是否存在"""
|
|
return shutil.which(cmd)
|
|
|
|
def _run_command(self, cmd: List[str], description: str):
|
|
"""运行命令并记录"""
|
|
logger.info(f"Running: {description}")
|
|
logger.info(f"Command: {' '.join(cmd)}")
|
|
|
|
self.commands.append({
|
|
"description": description,
|
|
"command": " ".join(cmd),
|
|
"timestamp": datetime.now().isoformat()
|
|
})
|
|
|
|
subprocess.run(cmd, check=True)
|
|
|
|
def _compute_checksum(self, filepath: Path) -> str:
|
|
"""计算文件SHA256校验"""
|
|
sha256 = hashlib.sha256()
|
|
with open(filepath, "rb") as f:
|
|
for chunk in iter(lambda: f.read(8192), b""):
|
|
sha256.update(chunk)
|
|
return sha256.hexdigest()
|
|
|
|
def _record_file(self, filepath: Path, file_type: str = "output"):
|
|
"""记录文件信息"""
|
|
if filepath.exists():
|
|
self.checksums[str(filepath)] = {
|
|
"sha256": self._compute_checksum(filepath),
|
|
"size": filepath.stat().st_size,
|
|
"type": file_type
|
|
}
|
|
|
|
def run_meme(self, protein_fasta: Path, output_dir: Path) -> Dict:
|
|
"""运行MEME motif分析"""
|
|
params = self.config["parameters"]["meme"]
|
|
cpu = self.config["parameters"]["cpu"]
|
|
|
|
meme = self._which("meme")
|
|
if not meme:
|
|
raise RuntimeError("meme not found. Please install MEME Suite.")
|
|
|
|
output_dir.mkdir(parents=True, exist_ok=True)
|
|
|
|
# 构建MEME命令
|
|
cmd = [
|
|
meme, str(protein_fasta),
|
|
"-protein",
|
|
"-oc", str(output_dir),
|
|
"-mod", params["model"],
|
|
"-nmotifs", str(params["nmotifs"]),
|
|
"-minw", str(params["minw"]),
|
|
"-maxw", str(params["maxw"]),
|
|
"-p", str(cpu),
|
|
]
|
|
|
|
self._run_command(cmd, "MEME保守基序分析")
|
|
|
|
meme_txt = output_dir / "meme.txt"
|
|
meme_html = output_dir / "meme.html"
|
|
|
|
self._record_file(meme_txt)
|
|
self._record_file(meme_html)
|
|
|
|
return {
|
|
"meme_txt": str(meme_txt),
|
|
"meme_html": str(meme_html)
|
|
}
|
|
|
|
def generate_report(self, output_dir: Path, nmotifs: int,
|
|
minw: int, maxw: int, model: str) -> Path:
|
|
"""生成分析报告"""
|
|
report_file = output_dir / "report.md"
|
|
|
|
report_content = f"""# 保守基序分析报告
|
|
|
|
## 基本信息
|
|
|
|
- **Motif数量**: {nmotifs}
|
|
- **最小宽度**: {minw}
|
|
- **最大宽度**: {maxw}
|
|
- **搜索模式**: {model}
|
|
- **分析时间**: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}
|
|
- **技能版本**: {self.config["skill"]["version"]}
|
|
|
|
## 分析结果
|
|
|
|
| 文件 | 描述 |
|
|
|------|------|
|
|
| meme.txt | Motif文本报告 |
|
|
| meme.html | Motif HTML报告 |
|
|
|
|
## 可复现性
|
|
|
|
所有分析命令已记录在 `commands.sh` 中，
|
|
环境配置见 `environment.yml`。
|
|
|
|
## 校验信息
|
|
|
|
文件SHA256校验值见 `checksums.sha256`。
|
|
"""
|
|
|
|
with open(report_file, "w") as f:
|
|
f.write(report_content)
|
|
|
|
self._record_file(report_file)
|
|
return report_file
|
|
|
|
def write_reproducibility_bundle(self, output_dir: Path):
|
|
"""写入可复现性文件包"""
|
|
# commands.sh
|
|
commands_file = output_dir / "commands.sh"
|
|
with open(commands_file, "w") as f:
|
|
f.write("#!/bin/bash\n# 保守基序分析复现命令\n\n")
|
|
for cmd in self.commands:
|
|
f.write(f"# {cmd['description']}\n")
|
|
f.write(f"{cmd['command']}\n\n")
|
|
os.chmod(commands_file, 0o755)
|
|
|
|
# environment.yml
|
|
env_file = output_dir / "environment.yml"
|
|
env_config = {
|
|
"name": "motif-analysis",
|
|
"channels": self.config["dependencies"]["conda"]["channels"],
|
|
"dependencies": self.config["dependencies"]["conda"]["packages"]
|
|
}
|
|
with open(env_file, "w") as f:
|
|
yaml.dump(env_config, f, default_flow_style=False)
|
|
|
|
# checksums.sha256
|
|
checksums_file = output_dir / "checksums.sha256"
|
|
with open(checksums_file, "w") as f:
|
|
for filepath, info in self.checksums.items():
|
|
f.write(f"{info['sha256']} {filepath}\n")
|
|
|
|
def run(self, protein_fasta: Path, output_dir: Path) -> Dict:
|
|
"""运行完整的保守基序分析流程"""
|
|
|
|
logger.info(f"Starting motif analysis")
|
|
|
|
# 记录输入文件
|
|
self._record_file(protein_fasta, "input")
|
|
|
|
# 运行MEME
|
|
params = self.config["parameters"]["meme"]
|
|
meme_results = self.run_meme(protein_fasta, output_dir)
|
|
|
|
# 生成报告
|
|
report = self.generate_report(
|
|
output_dir,
|
|
params["nmotifs"],
|
|
params["minw"],
|
|
params["maxw"],
|
|
params["model"]
|
|
)
|
|
|
|
# 写入可复现性文件
|
|
self.write_reproducibility_bundle(output_dir)
|
|
|
|
logger.info(f"Motif analysis completed. Report: {report}")
|
|
|
|
return {
|
|
"status": "success",
|
|
"output_dir": str(output_dir),
|
|
"report": str(report),
|
|
"meme_txt": meme_results["meme_txt"],
|
|
"meme_html": meme_results["meme_html"]
|
|
}
|
|
|
|
def run_demo(self, output_dir: Path) -> Dict:
|
|
"""运行Demo模式"""
|
|
logger.info("Running in demo mode")
|
|
|
|
# 创建模拟数据
|
|
demo_dir = output_dir / "demo_data"
|
|
demo_dir.mkdir(parents=True, exist_ok=True)
|
|
|
|
# 模拟蛋白质FASTA
|
|
protein_fasta = demo_dir / "demo_proteins.fa"
|
|
with open(protein_fasta, "w") as f:
|
|
f.write(">FtGene001\nMKTLLLPLLLLVLLLLLVQGSISAQ\n"
|
|
">FtGene002\nMKTLLLPLLLLVLLLLLVQGSISAQ\n"
|
|
">AtGene001\nMKTLLLPLLLLVLLLLLVQGSISAQ\n")
|
|
|
|
# 创建模拟输出文件
|
|
output_dir.mkdir(parents=True, exist_ok=True)
|
|
|
|
# meme.txt (模拟)
|
|
meme_txt = output_dir / "meme.txt"
|
|
meme_txt.write_text("""MEME VERSION 5.5.0
|
|
|
|
ALPHABET= ACGT
|
|
|
|
Strands: + -
|
|
|
|
Cache size: 10000
|
|
|
|
Sequence name Weight Sequence length
|
|
------------- ------ -----
|
|
FtGene001 1.000 25
|
|
FtGene002 1.000 25
|
|
AtGene001 1.000 25
|
|
|
|
MOTIF 1
|
|
Letter-probability matrix: alength= 4 w= 8 nsites= 3 E= 0.21
|
|
0.125 0.125 0.625 0.125
|
|
0.125 0.125 0.625 0.125
|
|
0.125 0.125 0.625 0.125
|
|
0.125 0.125 0.625 0.125
|
|
0.125 0.125 0.625 0.125
|
|
0.125 0.125 0.625 0.125
|
|
0.125 0.125 0.625 0.125
|
|
0.125 0.125 0.625 0.125
|
|
""")
|
|
|
|
# meme.html (模拟)
|
|
meme_html = output_dir / "meme.html"
|
|
meme_html.write_text("""<!DOCTYPE html>
|
|
<html>
|
|
<head><title>MEME - Motif Analysis Results</title></head>
|
|
<body>
|
|
<h1>MEME Motif Analysis Results (Demo)</h1>
|
|
<p>Found 1 motif</p>
|
|
</body>
|
|
</html>
|
|
""")
|
|
|
|
# report.md
|
|
report_file = output_dir / "report.md"
|
|
report_file.write_text(f"""# 保守基序分析报告
|
|
|
|
## 基本信息
|
|
|
|
- **Motif数量**: 10 (demo)
|
|
- **最小宽度**: 6 (demo)
|
|
- **最大宽度**: 200 (demo)
|
|
- **搜索模式**: anr (demo)
|
|
- **分析时间**: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}
|
|
- **技能版本**: {self.config["skill"]["version"]}
|
|
|
|
## 分析结果
|
|
|
|
| 文件 | 描述 |
|
|
|------|------|
|
|
| meme.txt | Motif文本报告 |
|
|
| meme.html | Motif HTML报告 |
|
|
|
|
## 可复现性
|
|
|
|
所有分析命令已记录在 `commands.sh` 中，环境配置见 `environment.yml`。
|
|
|
|
## 校验信息
|
|
|
|
文件SHA256校验值见 `checksums.sha256`。
|
|
""")
|
|
|
|
# commands.sh
|
|
commands_file = output_dir / "commands.sh"
|
|
commands_file.write_text("""#!/bin/bash
|
|
# 保守基序分析复现命令 (Demo模式)
|
|
|
|
meme input_proteins.fa -protein -oc ./motif -mod anr -nmotifs 10 -minw 6 -maxw 200 -p 8
|
|
""")
|
|
|
|
# environment.yml
|
|
env_file = output_dir / "environment.yml"
|
|
env_file.write_text("""name: motif-analysis
|
|
channels:
|
|
- bioconda
|
|
- conda-forge
|
|
dependencies:
|
|
- meme=5.5.0
|
|
- biopython=1.81
|
|
""")
|
|
|
|
# checksums.sha256
|
|
checksums_file = output_dir / "checksums.sha256"
|
|
for f in [meme_txt, meme_html, report_file, commands_file, env_file]:
|
|
if f.exists():
|
|
sha256 = hashlib.sha256()
|
|
with open(f, "rb") as fp:
|
|
for chunk in iter(lambda: fp.read(8192), b""):
|
|
sha256.update(chunk)
|
|
checksums_file.write_text(f"{sha256.hexdigest()} {f.name}\n")
|
|
|
|
logger.info(f"Motif demo completed. Report: {report_file}")
|
|
|
|
return {
|
|
"status": "success",
|
|
"output_dir": str(output_dir),
|
|
"report": str(report_file),
|
|
"meme_txt": str(meme_txt),
|
|
"meme_html": str(meme_html)
|
|
}
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(
|
|
description="Motif Analysis Skill - 保守基序分析"
|
|
)
|
|
parser.add_argument("--input", "-i", type=Path, help="蛋白序列FASTA文件")
|
|
parser.add_argument("--nmotifs", type=int, help="发现的motif数量")
|
|
parser.add_argument("--minw", type=int, help="最小motif宽度")
|
|
parser.add_argument("--maxw", type=int, help="最大motif宽度")
|
|
parser.add_argument("--model", choices=["anr", "zoops", "oops"], help="搜索模式")
|
|
parser.add_argument("--cpu", type=int, help="CPU线程数")
|
|
parser.add_argument("--output", "-o", type=Path, required=True, help="输出目录")
|
|
parser.add_argument("--config", "-c", type=Path, help="配置文件路径")
|
|
parser.add_argument("--demo", action="store_true", help="运行Demo模式")
|
|
|
|
args = parser.parse_args()
|
|
|
|
# 初始化技能
|
|
skill = MotifSkill(args.config)
|
|
|
|
# 更新配置参数
|
|
if args.nmotifs:
|
|
skill.config["parameters"]["meme"]["nmotifs"] = args.nmotifs
|
|
if args.minw:
|
|
skill.config["parameters"]["meme"]["minw"] = args.minw
|
|
if args.maxw:
|
|
skill.config["parameters"]["meme"]["maxw"] = args.maxw
|
|
if args.model:
|
|
skill.config["parameters"]["meme"]["model"] = args.model
|
|
if args.cpu:
|
|
skill.config["parameters"]["cpu"] = args.cpu
|
|
|
|
# 运行
|
|
if args.demo:
|
|
result = skill.run_demo(args.output)
|
|
else:
|
|
if not args.input:
|
|
parser.error("--input is required (unless using --demo)")
|
|
result = skill.run(args.input, args.output)
|
|
|
|
# 输出结果
|
|
print(json.dumps(result, indent=2, ensure_ascii=False))
|
|
|
|
return 0 if result["status"] == "success" else 1
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main()) |