343 lines
10 KiB
Python
343 lines
10 KiB
Python
|
"""
|
||
|
|
增强分析模块
|
||
|
|
|
||
|
|
本地优先 + API 增强的混合模式
|
||
|
|
|
||
|
|
设计原则:
|
||
|
|
1. 本地工具优先执行核心分析
|
||
|
|
2. API 用于补充最新信息和验证
|
||
|
|
3. API 失败不影响本地结果
|
||
|
|
4. 可配置是否启用 API 增强
|
||
|
|
"""
|
||
|
|
|
||
|
|
import json
|
||
|
|
from pathlib import Path
|
||
|
|
from typing import Dict, List, Optional, Any
|
||
|
|
from dataclasses import dataclass, asdict
|
||
|
|
|
||
|
|
from .api_clients import (
|
||
|
|
MultiAPIQuery,
|
||
|
|
PfamClient,
|
||
|
|
NCBIClient,
|
||
|
|
EnsemblPlantsClient,
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
@dataclass
|
||
|
|
class DomainResult:
|
||
|
|
"""Domain 分析结果（本地 + API 增强）"""
|
||
|
|
# 本地分析结果
|
||
|
|
pfam_acc: str
|
||
|
|
pfam_name: str
|
||
|
|
description: str
|
||
|
|
score: float
|
||
|
|
evalue: float
|
||
|
|
start: int
|
||
|
|
end: int
|
||
|
|
|
||
|
|
# API 增强信息（可选）
|
||
|
|
latest_description: Optional[str] = None
|
||
|
|
protein_count: Optional[int] = None
|
||
|
|
clan: Optional[str] = None
|
||
|
|
clan_name: Optional[str] = None
|
||
|
|
go_terms: Optional[List[str]] = None
|
||
|
|
interpro: Optional[Dict] = None
|
||
|
|
|
||
|
|
# 数据来源标记
|
||
|
|
data_source: str = "local" # "local" | "api" | "merged"
|
||
|
|
|
||
|
|
|
||
|
|
@dataclass
|
||
|
|
class GeneInfo:
|
||
|
|
"""基因信息（API 查询）"""
|
||
|
|
gene_id: str
|
||
|
|
symbol: str
|
||
|
|
description: str
|
||
|
|
organism: str
|
||
|
|
chromosome: Optional[str] = None
|
||
|
|
location: Optional[str] = None
|
||
|
|
synonyms: Optional[List[str]] = None
|
||
|
|
|
||
|
|
# 表达数据
|
||
|
|
expression_data: Optional[List[Dict]] = None
|
||
|
|
|
||
|
|
# 同源基因
|
||
|
|
orthologs: Optional[List[Dict]] = None
|
||
|
|
|
||
|
|
|
||
|
|
class EnhancedDomainAnalyzer:
|
||
|
|
"""
|
||
|
|
增强版 Domain 分析器
|
||
|
|
|
||
|
|
本地 Pfam HMMER 扫描 + API 补充最新注释
|
||
|
|
"""
|
||
|
|
|
||
|
|
def __init__(self, local_pfam_path: str, enable_api: bool = True):
|
||
|
|
"""
|
||
|
|
初始化分析器
|
||
|
|
|
||
|
|
Args:
|
||
|
|
local_pfam_path: 本地 Pfam HMM 文件路径
|
||
|
|
enable_api: 是否启用 API 增强
|
||
|
|
"""
|
||
|
|
self.local_pfam_path = Path(local_pfam_path)
|
||
|
|
self.enable_api = enable_api
|
||
|
|
|
||
|
|
if enable_api:
|
||
|
|
self.pfam_client = PfamClient()
|
||
|
|
self.query_manager = MultiAPIQuery()
|
||
|
|
|
||
|
|
def analyze(self, protein_fasta: str, enhance: bool = True) -> List[DomainResult]:
|
||
|
|
"""
|
||
|
|
分析蛋白质结构域
|
||
|
|
|
||
|
|
Args:
|
||
|
|
protein_fasta: 蛋白质 FASTA 文件路径
|
||
|
|
enhance: 是否用 API 增强结果
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
DomainResult 列表
|
||
|
|
"""
|
||
|
|
# 1. 本地 HMMER 扫描（核心功能，必须成功）
|
||
|
|
local_results = self._run_local_hmmscan(protein_fasta)
|
||
|
|
|
||
|
|
if not enhance or not self.enable_api:
|
||
|
|
return local_results
|
||
|
|
|
||
|
|
# 2. API 增强（可选，失败不影响结果）
|
||
|
|
enhanced_results = []
|
||
|
|
for domain in local_results:
|
||
|
|
try:
|
||
|
|
enhanced = self._enhance_with_api(domain)
|
||
|
|
enhanced_results.append(enhanced)
|
||
|
|
except Exception as e:
|
||
|
|
# API 失败，保留本地结果
|
||
|
|
print(f"[WARN] API enhancement failed for {domain.pfam_acc}: {e}")
|
||
|
|
domain.data_source = "local"
|
||
|
|
enhanced_results.append(domain)
|
||
|
|
|
||
|
|
return enhanced_results
|
||
|
|
|
||
|
|
def _run_local_hmmscan(self, fasta_file: str) -> List[DomainResult]:
|
||
|
|
"""
|
||
|
|
运行本地 HMMER hmmscan
|
||
|
|
|
||
|
|
实际实现应调用 subprocess 运行 hmmscan
|
||
|
|
这里返回模拟结果
|
||
|
|
"""
|
||
|
|
import subprocess
|
||
|
|
|
||
|
|
output_file = Path(fasta_file).with_suffix('.domtblout')
|
||
|
|
|
||
|
|
cmd = [
|
||
|
|
'hmmscan',
|
||
|
|
'--domtblout', str(output_file),
|
||
|
|
'--noali',
|
||
|
|
'-E', '1e-5',
|
||
|
|
str(self.local_pfam_path),
|
||
|
|
fasta_file
|
||
|
|
]
|
||
|
|
|
||
|
|
try:
|
||
|
|
subprocess.run(cmd, check=True, capture_output=True)
|
||
|
|
return self._parse_domtblout(output_file)
|
||
|
|
except subprocess.CalledProcessError as e:
|
||
|
|
print(f"[ERROR] HMMER failed: {e}")
|
||
|
|
return []
|
||
|
|
except FileNotFoundError:
|
||
|
|
print("[WARN] hmmscan not found, returning empty results")
|
||
|
|
return []
|
||
|
|
|
||
|
|
def _parse_domtblout(self, domtblout_file: Path) -> List[DomainResult]:
|
||
|
|
"""解析 HMMER domtblout 文件"""
|
||
|
|
results = []
|
||
|
|
|
||
|
|
if not domtblout_file.exists():
|
||
|
|
return results
|
||
|
|
|
||
|
|
with open(domtblout_file) as f:
|
||
|
|
for line in f:
|
||
|
|
if line.startswith('#'):
|
||
|
|
continue
|
||
|
|
|
||
|
|
parts = line.split()
|
||
|
|
if len(parts) < 22:
|
||
|
|
continue
|
||
|
|
|
||
|
|
# domtblout 格式解析
|
||
|
|
try:
|
||
|
|
result = DomainResult(
|
||
|
|
pfam_acc=parts[1],
|
||
|
|
pfam_name=parts[0],
|
||
|
|
description=' '.join(parts[22:]) if len(parts) > 22 else '',
|
||
|
|
score=float(parts[13]),
|
||
|
|
evalue=float(parts[12]),
|
||
|
|
start=int(parts[19]),
|
||
|
|
end=int(parts[20]),
|
||
|
|
data_source="local"
|
||
|
|
)
|
||
|
|
results.append(result)
|
||
|
|
except (ValueError, IndexError):
|
||
|
|
continue
|
||
|
|
|
||
|
|
return results
|
||
|
|
|
||
|
|
def _enhance_with_api(self, domain: DomainResult) -> DomainResult:
|
||
|
|
"""
|
||
|
|
用 API 增强 Domain 结果
|
||
|
|
|
||
|
|
Args:
|
||
|
|
domain: 本地分析结果
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
增强后的结果
|
||
|
|
"""
|
||
|
|
# 查询 Pfam API
|
||
|
|
api_info = self.pfam_client.get_family_info(domain.pfam_acc)
|
||
|
|
|
||
|
|
if api_info:
|
||
|
|
domain.latest_description = api_info.get('description')
|
||
|
|
domain.protein_count = api_info.get('protein_count')
|
||
|
|
domain.clan = api_info.get('clan')
|
||
|
|
domain.clan_name = api_info.get('clan_name')
|
||
|
|
domain.go_terms = api_info.get('go_terms', [])
|
||
|
|
domain.interpro = api_info.get('interpro')
|
||
|
|
domain.data_source = "merged"
|
||
|
|
|
||
|
|
return domain
|
||
|
|
|
||
|
|
def generate_report(self, results: List[DomainResult], output_file: str):
|
||
|
|
"""
|
||
|
|
生成增强报告
|
||
|
|
|
||
|
|
Args:
|
||
|
|
results: DomainResult 列表
|
||
|
|
output_file: 输出文件路径
|
||
|
|
"""
|
||
|
|
report = {
|
||
|
|
'summary': {
|
||
|
|
'total_domains': len(results),
|
||
|
|
'local_only': sum(1 for r in results if r.data_source == 'local'),
|
||
|
|
'api_enhanced': sum(1 for r in results if r.data_source == 'merged'),
|
||
|
|
},
|
||
|
|
'domains': [asdict(r) for r in results],
|
||
|
|
}
|
||
|
|
|
||
|
|
with open(output_file, 'w') as f:
|
||
|
|
json.dump(report, f, indent=2)
|
||
|
|
|
||
|
|
print(f"[INFO] Report saved to {output_file}")
|
||
|
|
|
||
|
|
|
||
|
|
class EnhancedReportGenerator:
|
||
|
|
"""
|
||
|
|
增强报告生成器
|
||
|
|
|
||
|
|
本地分析结果 + API 补充基因信息
|
||
|
|
"""
|
||
|
|
|
||
|
|
def __init__(self, enable_api: bool = True):
|
||
|
|
self.enable_api = enable_api
|
||
|
|
|
||
|
|
if enable_api:
|
||
|
|
self.ncbi_client = NCBIClient()
|
||
|
|
self.ensembl_client = EnsemblPlantsClient()
|
||
|
|
self.query_manager = MultiAPIQuery()
|
||
|
|
|
||
|
|
def enhance_report(self, local_report: Dict, gene_symbols: List[str]) -> Dict:
|
||
|
|
"""
|
||
|
|
增强报告内容
|
||
|
|
|
||
|
|
Args:
|
||
|
|
local_report: 本地分析结果
|
||
|
|
gene_symbols: 基因符号列表
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
增强后的报告
|
||
|
|
"""
|
||
|
|
if not self.enable_api:
|
||
|
|
return local_report
|
||
|
|
|
||
|
|
enhanced = local_report.copy()
|
||
|
|
enhanced['gene_annotations'] = {}
|
||
|
|
|
||
|
|
for symbol in gene_symbols:
|
||
|
|
try:
|
||
|
|
# 查询基因信息
|
||
|
|
gene_info = self._query_gene_info(symbol)
|
||
|
|
if gene_info:
|
||
|
|
enhanced['gene_annotations'][symbol] = gene_info
|
||
|
|
except Exception as e:
|
||
|
|
print(f"[WARN] Failed to query gene {symbol}: {e}")
|
||
|
|
|
||
|
|
return enhanced
|
||
|
|
|
||
|
|
def _query_gene_info(self, symbol: str) -> Optional[Dict]:
|
||
|
|
"""查询基因详细信息"""
|
||
|
|
results = self.query_manager.query_all('gene', {
|
||
|
|
'gene_symbol': symbol,
|
||
|
|
'organism': 'Arabidopsis'
|
||
|
|
})
|
||
|
|
|
||
|
|
# 合并结果
|
||
|
|
gene_info = {
|
||
|
|
'symbol': symbol,
|
||
|
|
'ncbi': None,
|
||
|
|
'ensembl': None,
|
||
|
|
}
|
||
|
|
|
||
|
|
# 从 NCBI 获取信息
|
||
|
|
if 'ncbi' in results and results['ncbi'].status == 'success':
|
||
|
|
data = results['ncbi'].data
|
||
|
|
if isinstance(data, list) and len(data) > 0:
|
||
|
|
gene = data[0]
|
||
|
|
gene_info['ncbi'] = {
|
||
|
|
'gene_id': gene.gene_id,
|
||
|
|
'description': gene.description,
|
||
|
|
'chromosome': gene.chromosome,
|
||
|
|
'location': gene.location,
|
||
|
|
}
|
||
|
|
|
||
|
|
return gene_info if gene_info['ncbi'] or gene_info['ensembl'] else None
|
||
|
|
|
||
|
|
|
||
|
|
# 使用示例
|
||
|
|
if __name__ == "__main__":
|
||
|
|
# 示例 1: Domain 分析（本地 + API 增强）
|
||
|
|
print("=" * 60)
|
||
|
|
print("示例 1: Domain 分析（本地 + API 增强）")
|
||
|
|
print("=" * 60)
|
||
|
|
|
||
|
|
analyzer = EnhancedDomainAnalyzer(
|
||
|
|
local_pfam_path=str(Path(__file__).resolve().parents[1] / "data" / "hmm" / "Pfam-A.hmm"),
|
||
|
|
enable_api=True
|
||
|
|
)
|
||
|
|
|
||
|
|
# 分析蛋白质
|
||
|
|
# results = analyzer.analyze("/path/to/protein.fa", enhance=True)
|
||
|
|
# analyzer.generate_report(results, "domain_report.json")
|
||
|
|
|
||
|
|
print("\n配置:")
|
||
|
|
print(f" 本地 Pfam: {analyzer.local_pfam_path}")
|
||
|
|
print(f" API 增强: {'启用' if analyzer.enable_api else '禁用'}")
|
||
|
|
|
||
|
|
# 示例 2: 报告增强
|
||
|
|
print("\n" + "=" * 60)
|
||
|
|
print("示例 2: 报告增强")
|
||
|
|
print("=" * 60)
|
||
|
|
|
||
|
|
generator = EnhancedReportGenerator(enable_api=True)
|
||
|
|
|
||
|
|
# 假设的本地报告
|
||
|
|
local_report = {
|
||
|
|
'job_id': 'test_001',
|
||
|
|
'stages': ['identify', 'phylogeny', 'domain'],
|
||
|
|
'results': {}
|
||
|
|
}
|
||
|
|
|
||
|
|
# 增强报告
|
||
|
|
# enhanced = generator.enhance_report(local_report, ['SPL1', 'SPL2', 'SPL3'])
|
||
|
|
|
||
|
|
print("\n配置:")
|
||
|
|
print(f" API 增强: {'启用' if generator.enable_api else '禁用'}")
|