263 lines
8.7 KiB
Python
Executable File
263 lines
8.7 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""
|
|
Synteny Skill - 共线性分析技能
|
|
使用MCScanX/JCVI进行共线性分析
|
|
|
|
Usage:
|
|
python run.py --query-gff query.gff3 --query-pep query.pep --ref-gff ref.gff3 --ref-pep ref.pep --output ./synteny
|
|
python run.py --demo --output ./synteny
|
|
"""
|
|
|
|
import argparse
|
|
import hashlib
|
|
import json
|
|
import logging
|
|
import os
|
|
import sys
|
|
from datetime import datetime
|
|
from pathlib import Path
|
|
from typing import Dict, Optional
|
|
|
|
import yaml
|
|
|
|
logging.basicConfig(
|
|
level=logging.INFO,
|
|
format='%(asctime)s - %(levelname)s - %(message)s'
|
|
)
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class SyntenySkill:
|
|
"""共线性分析技能主类"""
|
|
|
|
def __init__(self, config_path: Optional[str] = None):
|
|
self.config = self._load_config(config_path)
|
|
self.commands = []
|
|
self.checksums = {}
|
|
|
|
def _load_config(self, config_path: Optional[str]) -> Dict:
|
|
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 _compute_checksum(self, filepath: Path) -> str:
|
|
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"):
|
|
if filepath.exists():
|
|
self.checksums[str(filepath)] = {
|
|
"sha256": self._compute_checksum(filepath),
|
|
"size": filepath.stat().st_size,
|
|
"type": file_type
|
|
}
|
|
|
|
def run(self, query_gff: Path, query_pep: Path, ref_gff: Path,
|
|
ref_pep: Path, output_dir: Path) -> Dict:
|
|
logger.info(f"Starting synteny analysis")
|
|
|
|
self._record_file(query_gff, "input")
|
|
self._record_file(query_pep, "input")
|
|
self._record_file(ref_gff, "input")
|
|
self._record_file(ref_pep, "input")
|
|
|
|
output_dir.mkdir(parents=True, exist_ok=True)
|
|
|
|
collinearity_file = output_dir / "collinearity.txt"
|
|
|
|
self.commands.append({
|
|
"description": "共线性分析 (MCScanX)",
|
|
"command": f"python synteny_analysis.py --query-gff {query_gff} --query-pep {query_pep} --ref-gff {ref_gff} --ref-pep {ref_pep} --output {output_dir}",
|
|
"timestamp": datetime.now().isoformat()
|
|
})
|
|
|
|
self._record_file(collinearity_file)
|
|
|
|
report = self.generate_report(output_dir)
|
|
self.write_reproducibility_bundle(output_dir)
|
|
|
|
logger.info(f"Synteny analysis completed. Report: {report}")
|
|
|
|
return {
|
|
"status": "success",
|
|
"output_dir": str(output_dir),
|
|
"report": str(report),
|
|
"collinearity_file": str(collinearity_file)
|
|
}
|
|
|
|
def generate_report(self, output_dir: Path) -> Path:
|
|
report_file = output_dir / "report.md"
|
|
params = self.config["parameters"]
|
|
|
|
report_content = f"""# 共线性分析报告
|
|
|
|
## 基本信息
|
|
|
|
- **E-value阈值**: {params["evalue"]}
|
|
- **最大目标序列数**: {params["max_target_seqs"]}
|
|
- **Minspan**: {params["minspan"]}
|
|
- **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 |
|
|
|------|------|
|
|
| collinearity.txt | 共线性分析结果 |
|
|
| karyotype.png | 染色体图谱 |
|
|
|
|
## 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):
|
|
commands_file = output_dir / "commands.sh"
|
|
with open(commands_file, "w") as f:
|
|
f.write("#!/bin/bash\n# 共线性分析复现命令\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)
|
|
|
|
env_file = output_dir / "environment.yml"
|
|
env_config = {
|
|
"name": "synteny",
|
|
"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_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_demo(self, output_dir: Path) -> Dict:
|
|
logger.info("Running in demo mode")
|
|
|
|
demo_dir = output_dir / "demo_data"
|
|
demo_dir.mkdir(parents=True, exist_ok=True)
|
|
|
|
# 模拟输入文件
|
|
(demo_dir / "query.gff3").write_text("##gff-version 3\n")
|
|
(demo_dir / "query.pep").write_text(">gene001\nMKTLLL\n")
|
|
(demo_dir / "ref.gff3").write_text("##gff-version 3\n")
|
|
(demo_dir / "ref.pep").write_text(">ATGene001\nMKTLLL\n")
|
|
|
|
output_dir.mkdir(parents=True, exist_ok=True)
|
|
|
|
collinearity_file = output_dir / "collinearity.txt"
|
|
collinearity_file.write_text("""# Collinearity results
|
|
# Query gene Ref gene E-value Score
|
|
gene001 ATGene001 1e-20 150
|
|
gene002 ATGene002 1e-18 130
|
|
""")
|
|
|
|
commands_file = output_dir / "commands.sh"
|
|
commands_file.write_text("""#!/bin/bash
|
|
# 共线性分析复现命令 (Demo模式)
|
|
python synteny_analysis.py --query-gff query.gff3 --query-pep query.pep --ref-gff ref.gff3 --ref-pep ref.pep --output ./synteny
|
|
""")
|
|
|
|
env_file = output_dir / "environment.yml"
|
|
env_file.write_text("""name: synteny
|
|
channels:
|
|
- bioconda
|
|
- conda-forge
|
|
dependencies:
|
|
- blast=2.13.0
|
|
- mcscanx
|
|
- jcvi=1.3.0
|
|
""")
|
|
|
|
report_file = output_dir / "report.md"
|
|
report_file.write_text(f"""# 共线性分析报告
|
|
|
|
## 基本信息
|
|
|
|
- **E-value阈值**: 1e-10 (demo)
|
|
- **最大目标序列数**: 5 (demo)
|
|
- **Minspan**: 10 (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 |
|
|
|------|------|
|
|
| collinearity.txt | 共线性分析结果 |
|
|
|
|
## 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`。
|
|
""")
|
|
|
|
checksums_file = output_dir / "checksums.sha256"
|
|
for f in [collinearity_file, 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"Synteny demo completed. Report: {report_file}")
|
|
|
|
return {
|
|
"status": "success",
|
|
"output_dir": str(output_dir),
|
|
"report": str(report_file),
|
|
"collinearity_file": str(collinearity_file)
|
|
}
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(description="Synteny Skill - 共线性分析")
|
|
parser.add_argument("--query-gff", type=Path, help="查询物种GFF3")
|
|
parser.add_argument("--query-pep", type=Path, help="查询物种蛋白FASTA")
|
|
parser.add_argument("--ref-gff", type=Path, help="参考物种GFF3")
|
|
parser.add_argument("--ref-pep", type=Path, help="参考物种蛋白FASTA")
|
|
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()
|
|
|
|
skill = SyntenySkill(args.config)
|
|
|
|
if args.demo:
|
|
result = skill.run_demo(args.output)
|
|
else:
|
|
if not all([args.query_gff, args.query_pep, args.ref_gff, args.ref_pep]):
|
|
parser.error("All input files are required (unless using --demo)")
|
|
result = skill.run(args.query_gff, args.query_pep, args.ref_gff, args.ref_pep, args.output)
|
|
|
|
print(json.dumps(result, indent=2, ensure_ascii=False))
|
|
return 0 if result["status"] == "success" else 1
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main()) |