FScanpy 1.0.0__tar.gz

fscanpy-1.0.0/CHANGELOG.md

@@ -0,0 +1,19 @@
+# Changelog
+
+## 1.0.0
+
+### Fixed
+- Include pretrained model weights and example data in package distributions.
+- Locate bundled models without the deprecated `pkg_resources` API.
+- Load PyTorch checkpoints with `weights_only=True` and pin scikit-learn to 1.7.2 for the bundled short model.
+- Accept region DataFrames containing `Long_Sequence` or `399bp`.
+- Accept pathlib paths when saving prediction plots.
+- Export `fscanr` and `extract_prf_regions` from the public package API.
+- Repair notebook examples and document Jupyter installation.
+
+### Added
+- Package regression tests and a notebook validation runner.
+- PyPI project metadata, maintainer contact, MIT license file, and project links.
+
+### Changed
+- Align the package's reported version with distribution version 1.0.0.

fscanpy-1.0.0/FScanpy/__init__.py

@@ -0,0 +1,206 @@
+from .predictor import PRFPredictor
+from . import data
+from .utils import fscanr, extract_prf_regions
+import pandas as pd
+import numpy as np
+from typing import Union, List, Dict
+
+__version__ = '1.0.0'
+__author__ = 'Yang Yuhao'
+__email__ = 'ykongxiang@qq.com'
+
+__all__ = ['PRFPredictor', 'predict_prf', 'plot_prf_prediction', 'fscanr', 'extract_prf_regions', 'data', '__version__', '__author__', '__email__']
+
+def predict_prf(
+    sequence: Union[str, List[str], None] = None,
+    data: Union[pd.DataFrame, None] = None,
+    window_size: int = 3,
+    short_threshold: float = 0.1,
+    ensemble_weight: float = 0.4,
+    model_dir: str = None
+) -> pd.DataFrame:
+    """
+    PRF site prediction function
+    
+    Args:
+        sequence: Single or multiple DNA sequences for sliding window prediction
+        data: DataFrame data, must contain 'Long_Sequence' or '399bp' column for region prediction
+        window_size: Sliding window size (default: 3)
+        short_threshold: Short model (HistGB) probability threshold (default: 0.1)
+        ensemble_weight: Weight of short model in ensemble (default: 0.4, long weight: 0.6)
+        model_dir: Model directory path (optional)
+    
+    Returns:
+        pandas.DataFrame: Prediction results containing the following main fields:
+            - Short_Probability: Short model prediction probability
+            - Long_Probability: Long model prediction probability  
+            - Ensemble_Probability: Ensemble prediction probability (main result)
+            - Ensemble_Weights: Weight configuration information
+        
+    Examples:
+        # 1. Single sequence sliding window prediction
+        >>> from FScanpy import predict_prf
+        >>> sequence = "ATGCGTACGT..."
+        >>> results = predict_prf(sequence=sequence)
+        
+        # 2. Multiple sequences sliding window prediction
+        >>> sequences = ["ATGCGTACGT...", "GCTATAGCAT..."]
+        >>> results = predict_prf(sequence=sequences)
+        
+        # 3. Custom ensemble weight ratio
+        >>> results = predict_prf(sequence=sequence, ensemble_weight=0.3)  # 3:7 ratio
+        
+        # 4. DataFrame region prediction
+        >>> import pandas as pd
+        >>> data = pd.DataFrame({
+        ...     'Long_Sequence': ['ATGCGT...', 'GCTATAG...']  # or use '399bp'
+        ... })
+        >>> results = predict_prf(data=data)
+    """
+    predictor = PRFPredictor(model_dir=model_dir)
+    
+    # Validate input parameters
+    if sequence is None and data is None:
+        raise ValueError("Must provide either sequence or data parameter")
+    if sequence is not None and data is not None:
+        raise ValueError("Cannot provide both sequence and data parameters")
+    if not (0.0 <= ensemble_weight <= 1.0):
+        raise ValueError("ensemble_weight must be between 0.0 and 1.0")
+    
+    # Sliding window prediction mode
+    if sequence is not None:
+        if isinstance(sequence, str):
+            # Single sequence prediction
+            return predictor.predict_sequence(
+                sequence, window_size, short_threshold, ensemble_weight)
+        elif isinstance(sequence, (list, tuple)):
+            # Multiple sequences prediction
+            results = []
+            for i, seq in enumerate(sequence, 1):
+                try:
+                    result = predictor.predict_sequence(
+                        seq, window_size, short_threshold, ensemble_weight)
+                    result['Sequence_ID'] = f'seq_{i}'
+                    results.append(result)
+                except Exception as e:
+                    print(f"Warning: Sequence {i} prediction failed - {str(e)}")
+            return pd.concat(results, ignore_index=True) if results else pd.DataFrame()
+    
+    # Region prediction mode
+    else:
+        if not isinstance(data, pd.DataFrame):
+            raise ValueError("data parameter must be pandas DataFrame type")
+        
+        # Check column names (support both new and old naming conventions)
+        seq_column = None
+        if 'Long_Sequence' in data.columns:
+            seq_column = 'Long_Sequence'
+        elif '399bp' in data.columns:
+            seq_column = '399bp'
+        else:
+            raise ValueError("DataFrame must contain 'Long_Sequence' or '399bp' column")
+        
+        # Call region prediction function
+        try:
+            results = predictor.predict_regions(
+                data[seq_column], short_threshold, ensemble_weight)
+                
+            # Add other columns from original data
+            for col in data.columns:
+                if col not in ['Long_Sequence', '399bp', 'Short_Sequence', '33bp']:
+                    results[col] = data[col].values
+                    
+            return results
+            
+        except Exception as e:
+            print(f"Warning: Region prediction failed - {str(e)}")
+            # Create empty results
+            long_weight = 1.0 - ensemble_weight
+            results = pd.DataFrame({
+                'Short_Probability': [0.0] * len(data),
+                'Long_Probability': [0.0] * len(data),
+                'Ensemble_Probability': [0.0] * len(data),
+                'Ensemble_Weights': [f'Short:{ensemble_weight:.1f}, Long:{long_weight:.1f}'] * len(data)
+            })
+            
+            # Add original data columns
+            for col in data.columns:
+                results[col] = data[col].values
+                
+            return results
+
+def plot_prf_prediction(
+    sequence: str,
+    window_size: int = 3,
+    short_threshold: float = 0.65,
+    long_threshold: float = 0.8,
+    ensemble_weight: float = 0.4,
+    title: str = None,
+    save_path: str = None,
+    figsize: tuple = (12, 8),
+    dpi: int = 300,
+    model_dir: str = None
+) -> tuple:
+    """
+    Plot PRF prediction results for sequence frameshifting probability
+    
+    Args:
+        sequence: Input DNA sequence
+        window_size: Sliding window size (default: 3)
+        short_threshold: Short model (HistGB) filtering threshold (default: 0.65)
+        long_threshold: Long model (BiLSTM-CNN) filtering threshold (default: 0.8)
+        ensemble_weight: Weight of short model in ensemble (default: 0.4, long weight: 0.6)
+        title: Plot title (optional)
+        save_path: Save path (optional, saves plot if provided)
+        figsize: Figure size (default: (12, 8))
+        dpi: Figure resolution (default: 300)
+        model_dir: Model directory path (optional)
+    
+    Returns:
+        tuple: (pd.DataFrame, matplotlib.figure.Figure) prediction results and figure object
+        
+    Examples:
+        # 1. Simple plotting
+        >>> from FScanpy import plot_prf_prediction
+        >>> sequence = "ATGCGTACGT..."
+        >>> results, fig = plot_prf_prediction(sequence)
+        >>> plt.show()
+        
+        # 2. Custom thresholds and ensemble weights
+        >>> results, fig = plot_prf_prediction(
+        ...     sequence, 
+        ...     short_threshold=0.7, 
+        ...     long_threshold=0.85,
+        ...     ensemble_weight=0.3,  # 3:7 weight ratio
+        ...     title="Custom Weight Prediction Results",
+        ...     save_path="prediction_result.png"
+        ... )
+        
+        # 3. Equal weight combination
+        >>> results, fig = plot_prf_prediction(
+        ...     sequence,
+        ...     ensemble_weight=0.5  # 5:5 equal weights
+        ... )
+        
+        # 4. Long model dominated
+        >>> results, fig = plot_prf_prediction(
+        ...     sequence,
+        ...     ensemble_weight=0.2  # 2:8 weights, long model dominated
+        ... )
+    """
+    if not (0.0 <= ensemble_weight <= 1.0):
+        raise ValueError("ensemble_weight must be between 0.0 and 1.0")
+    
+    predictor = PRFPredictor(model_dir=model_dir)
+    
+    return predictor.plot_sequence_prediction(
+        sequence=sequence,
+        window_size=window_size,
+        short_threshold=short_threshold,
+        long_threshold=long_threshold,
+        ensemble_weight=ensemble_weight,
+        title=title,
+        save_path=save_path,
+        figsize=figsize,
+        dpi=dpi
+    )

fscanpy-1.0.0/FScanpy/data/__init__.py

@@ -0,0 +1,122 @@
+"""
+FScanpy数据模块
+提供测试数据访问和处理功能
+"""
+
+import os
+from pathlib import Path
+from typing import List
+
+def get_test_data_path(filename: str) -> str:
+    """
+    获取测试数据文件的完整路径
+    
+    Args:
+        filename: 测试数据文件名
+        
+    Returns:
+        str: 文件的完整路径
+        
+    Examples:
+        >>> from FScanpy.data import get_test_data_path
+        >>> blastx_file = get_test_data_path('blastx_example.xlsx')
+        >>> mrna_file = get_test_data_path('mrna_example.fasta')
+        >>> region_file = get_test_data_path('region_example.csv')
+        >>> full_seq_file = get_test_data_path('full_seq.xlsx')
+    """
+    current_dir = Path(__file__).parent
+    test_data_dir = current_dir / "test_data"
+    file_path = test_data_dir / filename
+    
+    if not file_path.exists():
+        available_files = list_test_data()
+        raise FileNotFoundError(
+            f"测试数据文件不存在: {filename}\n"
+            f"可用的测试数据文件: {available_files}"
+        )
+    
+    return str(file_path)
+
+def list_test_data() -> List[str]:
+    """
+    列出所有可用的测试数据文件
+    
+    Returns:
+        List[str]: 测试数据文件名列表
+        
+    Examples:
+        >>> from FScanpy.data import list_test_data
+        >>> files = list_test_data()
+        >>> print(files)
+        ['blastx_example.xlsx', 'mrna_example.fasta', 'region_example.csv']
+    """
+    try:
+        current_dir = Path(__file__).parent
+        test_data_dir = current_dir / "test_data"
+        
+        if not test_data_dir.exists():
+            return []
+        
+        files = []
+        for file_path in test_data_dir.iterdir():
+            if file_path.is_file() and not file_path.name.startswith('.'):
+                files.append(file_path.name)
+        
+        return sorted(files)
+        
+    except Exception:
+        return []
+
+def print_test_data_info():
+    """
+    打印测试数据的详细信息
+    """
+    print("📋 FScanpy 测试数据信息:")
+    print("=" * 50)
+    
+    try:
+        current_dir = Path(__file__).parent
+        test_data_dir = current_dir / "test_data"
+        
+        if not test_data_dir.exists():
+            print("❌ 测试数据目录不存在")
+            return
+        
+        files = list_test_data()
+        if not files:
+            print("❌ 没有找到测试数据文件")
+            return
+        
+        print(f"📁 数据目录: {test_data_dir}")
+        print(f"📊 文件数量: {len(files)}")
+        print()
+        
+        file_descriptions = {
+            'blastx_example.xlsx': '🧬 BLASTX比对结果示例 (1000条记录)',
+            'mrna_example.fasta': '🧬 mRNA序列示例数据',
+            'region_example.csv': '🎯 PRF区域验证数据 (含标签)',
+            'full_seq.xlsx': '🧬 完整序列示例数据'
+        }
+        
+        for filename in files:
+            file_path = test_data_dir / filename
+            size_mb = file_path.stat().st_size / (1024 * 1024)
+            
+            description = file_descriptions.get(filename, '📄 数据文件')
+            print(f"  {description}")
+            print(f"    文件名: {filename}")
+            print(f"    大小: {size_mb:.2f} MB")
+            print(f"    路径: {file_path}")
+            print()
+        
+        print("🚀 使用示例:")
+        print("  from FScanpy.data import get_test_data_path")
+        print("  blastx_file = get_test_data_path('blastx_example.xlsx')")
+        print("  mrna_file = get_test_data_path('mrna_example.fasta')")
+        print("  region_file = get_test_data_path('region_example.csv')")
+        print("  full_seq_file = get_test_data_path('full_seq.xlsx')")
+    except Exception as e:
+        print(f"❌ 获取数据信息时出错: {e}")
+
+# 导出主要函数
+__all__ = ['get_test_data_path', 'list_test_data', 'print_test_data_info']