omnigenome 0.3.0a0__py3-none-any.whl → 0.3.1a0__py3-none-any.whl

omnigenome/src/abc/abstract_dataset.py

@@ -56,7 +56,7 @@ def covert_input_to_tensor(data):
 class OmniGenomeDict(dict):
     """
     A dictionary subclass that allows moving all tensor values to a specified device.
-    
+
     This class extends the standard Python dictionary to provide a convenient
     method for moving all tensor values to a specific device (CPU/GPU).
     """
@@ -87,14 +87,14 @@ class OmniGenomeDict(dict):
 class OmniDataset(torch.utils.data.Dataset):
     """
     Abstract base class for all datasets in OmniGenome.
-    
+
     This class provides a unified interface for genomic datasets in the OmniGenome
     framework. It handles data loading, preprocessing, tokenization, and provides
     a PyTorch-compatible dataset interface.
-    
+
     The class supports various data formats and can handle different types of
     genomic tasks including classification, regression, and token-level tasks.
-    
+
     Attributes:
         tokenizer: The tokenizer to use for processing sequences.
         max_length (int): The maximum sequence length for tokenization.
@@ -118,17 +118,17 @@ class OmniDataset(torch.utils.data.Dataset):
             **kwargs: Additional keyword arguments.
                 - label2id (dict): A mapping from labels to integer IDs.
                 - shuffle (bool): Whether to shuffle the data. Defaults to True.
-                - structure_in (bool): Whether to include secondary structure 
+                - structure_in (bool): Whether to include secondary structure
                   information. Defaults to False.
-                - drop_long_seq (bool): Whether to drop sequences longer than 
+                - drop_long_seq (bool): Whether to drop sequences longer than
                   max_length. Defaults to False.
 
         Example:
             >>> # Initialize with a single data file
             >>> dataset = OmniDataset("data.json", tokenizer, max_length=512)
-            
+
             >>> # Initialize with label mapping
-            >>> dataset = OmniDataset("data.json", tokenizer, 
+            >>> dataset = OmniDataset("data.json", tokenizer,
             ...                      label2id={"A": 0, "B": 1})
         """
         super(OmniDataset, self).__init__()
@@ -158,9 +158,7 @@ class OmniDataset(torch.utils.data.Dataset):
             )
             self.max_length = self.tokenizer.max_length
         else:
-            fprint(
-                f"No max_length detected, using default max_length=512."
-            )
+            fprint(f"No max_length detected, using default max_length=512.")
             self.max_length = 512
 
         self.tokenizer.max_length = self.max_length
@@ -417,23 +415,44 @@ class OmniDataset(torch.utils.data.Dataset):
                     lines = f.readlines()
                 for line in lines:
                     examples.append({"text": line.strip()})
-            elif data_source.endswith(('.fasta', '.fa', '.fna', '.ffn', '.faa', '.frn')):
+            elif data_source.endswith(
+                (".fasta", ".fa", ".fna", ".ffn", ".faa", ".frn")
+            ):
                 try:
                     from Bio import SeqIO
                 except ImportError:
-                    raise ImportError("Biopython is required for FASTA parsing. Please install with 'pip install biopython'.")
+                    raise ImportError(
+                        "Biopython is required for FASTA parsing. Please install with 'pip install biopython'."
+                    )
                 for record in SeqIO.parse(data_source, "fasta"):
-                    examples.append({"id": record.id, "sequence": str(record.seq), "description": record.description})
-            elif data_source.endswith(('.fastq', '.fq')):
+                    examples.append(
+                        {
+                            "id": record.id,
+                            "sequence": str(record.seq),
+                            "description": record.description,
+                        }
+                    )
+            elif data_source.endswith((".fastq", ".fq")):
                 try:
                     from Bio import SeqIO
                 except ImportError:
-                    raise ImportError("Biopython is required for FASTQ parsing. Please install with 'pip install biopython'.")
+                    raise ImportError(
+                        "Biopython is required for FASTQ parsing. Please install with 'pip install biopython'."
+                    )
                 for record in SeqIO.parse(data_source, "fastq"):
-                    examples.append({"id": record.id, "sequence": str(record.seq), "quality": record.letter_annotations.get("phred_quality", [])})
-            elif data_source.endswith('.bed'):
+                    examples.append(
+                        {
+                            "id": record.id,
+                            "sequence": str(record.seq),
+                            "quality": record.letter_annotations.get(
+                                "phred_quality", []
+                            ),
+                        }
+                    )
+            elif data_source.endswith(".bed"):
                 import pandas as pd
-                df = pd.read_csv(data_source, sep='\t', comment='#')
+
+                df = pd.read_csv(data_source, sep="\t", comment="#")
                 # Assign column names for standard BED fields
                 for _, row in df.iterrows():
                     examples.append(row.to_dict())

omnigenome/src/abc/abstract_metric.py

@@ -15,17 +15,17 @@ from ..misc.utils import env_meta_info
 class OmniMetric:
     """
     Abstract base class for all metrics in OmniGenome, based on scikit-learn.
-    
+
     This class provides a unified interface for evaluation metrics in the OmniGenome
     framework. It integrates with scikit-learn's metric functions and provides
     additional functionality for handling genomic data evaluation.
-    
+
     The class automatically exposes all scikit-learn metrics as attributes,
     making them easily accessible for evaluation tasks.
-    
+
     Attributes:
         metric_func (callable): A callable metric function from `sklearn.metrics`.
-        ignore_y (any): A value in the ground truth labels to be ignored during 
+        ignore_y (any): A value in the ground truth labels to be ignored during
                        metric computation.
         metadata (dict): Metadata about the metric including version info.
     """
@@ -35,10 +35,10 @@ class OmniMetric:
         Initializes the metric.
 
         Args:
-            metric_func (callable, optional): A callable metric function from 
+            metric_func (callable, optional): A callable metric function from
                                             `sklearn.metrics`. If None, subclasses
                                             should implement their own compute method.
-            ignore_y (any, optional): A value in the ground truth labels to be 
+            ignore_y (any, optional): A value in the ground truth labels to be
                                     ignored during metric computation.
             *args: Additional positional arguments.
             **kwargs: Additional keyword arguments.
@@ -46,7 +46,7 @@ class OmniMetric:
         Example:
             >>> # Initialize with a specific metric function
             >>> metric = OmniMetric(metrics.accuracy_score)
-            
+
             >>> # Initialize with ignore value
             >>> metric = OmniMetric(ignore_y=-100)
         """

omnigenome/src/abc/abstract_model.py

@@ -47,14 +47,14 @@ def count_parameters(model):
 class OmniModel(torch.nn.Module):
     """
     Abstract base class for all models in OmniGenome.
-    
+
     This class provides a unified interface for all genomic models in the OmniGenome
     framework. It handles model initialization, forward passes, loss computation,
     prediction, inference, and model persistence.
-    
+
     The class is designed to work with various types of genomic data and tasks,
     including sequence classification, token classification, regression, and more.
-    
+
     Attributes:
         model (torch.nn.Module): The underlying PyTorch model.
         config: The model configuration.
@@ -76,16 +76,16 @@ class OmniModel(torch.nn.Module):
         - From a configuration object
 
         Args:
-            config_or_model: A model configuration, a pre-trained model path (str), 
+            config_or_model: A model configuration, a pre-trained model path (str),
                            or a `torch.nn.Module` instance.
             tokenizer: The tokenizer associated with the model.
             *args: Additional positional arguments.
             **kwargs: Additional keyword arguments.
                 - label2id (dict): Mapping from class labels to IDs.
                 - num_labels (int): The number of labels.
-                - trust_remote_code (bool): Whether to trust remote code when loading 
+                - trust_remote_code (bool): Whether to trust remote code when loading
                   from Hugging Face Hub. Defaults to True.
-                - ignore_mismatched_sizes (bool): Whether to ignore size mismatches 
+                - ignore_mismatched_sizes (bool): Whether to ignore size mismatches
                   when loading pre-trained weights. Defaults to False.
                 - dropout (float): Dropout rate. Defaults to 0.0.
 
@@ -97,7 +97,7 @@ class OmniModel(torch.nn.Module):
         Example:
             >>> # Initialize from a pre-trained model
             >>> model = OmniModelForSequenceClassification("model_path", tokenizer)
-            
+
             >>> # Initialize from a configuration
             >>> config = AutoConfig.from_pretrained("model_path")
             >>> model = OmniModelForSequenceClassification(config, tokenizer)
@@ -202,7 +202,9 @@ class OmniModel(torch.nn.Module):
             )
             self.config.num_labels = len(self.config.id2label)
 
-        assert len(self.config.label2id) == num_labels, f"Expected {num_labels} labels, but got {len(self.config.label2id)} in label2id dictionary."
+        assert (
+            len(self.config.label2id) == num_labels
+        ), f"Expected {num_labels} labels, but got {len(self.config.label2id)} in label2id dictionary."
 
         # The metadata of the model
         self.metadata = env_meta_info()
@@ -240,7 +242,7 @@ class OmniModel(torch.nn.Module):
         model architectures by mapping input parameters appropriately.
 
         Args:
-            **inputs: The inputs to the model, compatible with the base model's 
+            **inputs: The inputs to the model, compatible with the base model's
                      forward method. Typically includes 'input_ids', 'attention_mask',
                      and other model-specific parameters.
 
@@ -386,7 +388,7 @@ class OmniModel(torch.nn.Module):
         predictions for further processing.
 
         Args:
-            sequence_or_inputs: A sequence (str), list of sequences, or 
+            sequence_or_inputs: A sequence (str), list of sequences, or
                                tokenized inputs (dict/tuple).
             **kwargs: Additional arguments for tokenization and inference.
 
@@ -398,7 +400,7 @@ class OmniModel(torch.nn.Module):
         Example:
             >>> # Predict on a single sequence
             >>> outputs = model.predict("ATCGATCG")
-            
+
             >>> # Predict on multiple sequences
             >>> outputs = model.predict(["ATCGATCG", "GCTAGCTA"])
         """
@@ -416,7 +418,7 @@ class OmniModel(torch.nn.Module):
         to class labels or probabilities.
 
         Args:
-            sequence_or_inputs: A sequence (str), list of sequences, or 
+            sequence_or_inputs: A sequence (str), list of sequences, or
                                tokenized inputs (dict/tuple).
             **kwargs: Additional arguments for tokenization and inference.
 
@@ -429,7 +431,7 @@ class OmniModel(torch.nn.Module):
             >>> # Inference on a single sequence
             >>> results = model.inference("ATCGATCG")
             >>> print(results['predictions'])  # Class labels
-            
+
             >>> # Inference on multiple sequences
             >>> results = model.inference(["ATCGATCG", "GCTAGCTA"])
         """
@@ -686,4 +688,3 @@ class OmniModel(torch.nn.Module):
         info += f"Model Config: {self.config}\n"
         fprint(info)
         return info
-

omnigenome/src/abc/abstract_tokenizer.py

@@ -16,15 +16,15 @@ from ..misc.utils import env_meta_info, load_module_from_path
 class OmniTokenizer:
     """
     A wrapper class for tokenizers to provide a consistent interface within OmniGenome.
-    
+
     This class provides a unified interface for tokenizers in the OmniGenome framework.
     It wraps underlying tokenizers (typically from Hugging Face) and provides
     additional functionality for genomic sequence processing.
-    
+
     The class handles various tokenization strategies and provides compatibility
     with different model architectures. It also supports custom tokenizer wrappers
     for specialized genomic tasks.
-    
+
     Attributes:
         base_tokenizer: The underlying tokenizer instance (e.g., from Hugging Face).
         max_length (int): The default maximum sequence length.
@@ -52,7 +52,7 @@ class OmniTokenizer:
             >>> from transformers import AutoTokenizer
             >>> base_tokenizer = AutoTokenizer.from_pretrained("model_name")
             >>> tokenizer = OmniTokenizer(base_tokenizer, max_length=512)
-            
+
             >>> # Initialize with sequence conversion
             >>> tokenizer = OmniTokenizer(base_tokenizer, u2t=True)
         """
@@ -87,9 +87,9 @@ class OmniTokenizer:
         Example:
             >>> # Load from a pre-trained model
             >>> tokenizer = OmniTokenizer.from_pretrained("model_name")
-            
+
             >>> # Load with custom parameters
-            >>> tokenizer = OmniTokenizer.from_pretrained("model_name", 
+            >>> tokenizer = OmniTokenizer.from_pretrained("model_name",
             ...                                          trust_remote_code=True)
         """
         wrapper_path = f"{model_name_or_path.rstrip('/')}/omnigenome_wrapper.py"
@@ -104,7 +104,9 @@ class OmniTokenizer:
             warnings.warn(
                 f"No tokenizer wrapper found in {wrapper_path} -> Exception: {e}"
             )
-            kwargs.pop("num_labels", None) # Remove num_labels if it exists, as it may not be applicable
+            kwargs.pop(
+                "num_labels", None
+            )  # Remove num_labels if it exists, as it may not be applicable
 
             tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, **kwargs)
 

omnigenome/src/dataset/omni_dataset.py

@@ -27,11 +27,11 @@ from ... import __name__, __version__
 class OmniDatasetForTokenClassification(OmniDataset):
     """
     Dataset class specifically designed for token classification tasks in genomics.
-    
+
     This class extends `OmniDataset` to provide functionalities for preparing input sequences
     and their corresponding token-level labels. It's designed for tasks where each token
     in a sequence needs to be classified independently.
-    
+
     Attributes:
         metadata: Dictionary containing dataset metadata including library information
         label2id: Mapping from label strings to integer IDs
@@ -68,7 +68,7 @@ class OmniDatasetForTokenClassification(OmniDataset):
     def prepare_input(self, instance, **kwargs):
         """
         Prepare a single data instance for token classification.
-        
+
         This method handles both string sequences and dictionary instances
         containing sequence and label information. It tokenizes the input
         sequence and prepares token-level labels for classification.
@@ -138,11 +138,11 @@ class OmniDatasetForTokenClassification(OmniDataset):
 class OmniDatasetForSequenceClassification(OmniDataset):
     """
     Dataset class for sequence classification tasks in genomics.
-    
+
     This class extends `OmniDataset` to prepare input sequences and their corresponding
     sequence-level labels. It's designed for tasks where the entire sequence needs
     to be classified into one of several categories.
-    
+
     Attributes:
         metadata: Dictionary containing dataset metadata including library information
         label2id: Mapping from label strings to integer IDs
@@ -179,7 +179,7 @@ class OmniDatasetForSequenceClassification(OmniDataset):
     def prepare_input(self, instance, **kwargs):
         """
         Prepare a single data instance for sequence classification.
-        
+
         This method handles both string sequences and dictionary instances
         containing sequence and label information. It tokenizes the input
         sequence and prepares sequence-level labels for classification.
@@ -238,11 +238,11 @@ class OmniDatasetForSequenceClassification(OmniDataset):
 class OmniDatasetForTokenRegression(OmniDataset):
     """
     Dataset class for token regression tasks in genomics.
-    
+
     This class extends `OmniDataset` to prepare input sequences and their corresponding
     token-level regression targets. It's designed for tasks where each token in a
     sequence needs to be assigned a continuous value.
-    
+
     Attributes:
         metadata: Dictionary containing dataset metadata including library information
     """
@@ -278,7 +278,7 @@ class OmniDatasetForTokenRegression(OmniDataset):
     def prepare_input(self, instance, **kwargs):
         """
         Prepare a single data instance for token regression.
-        
+
         This method handles both string sequences and dictionary instances
         containing sequence and regression target information. It tokenizes
         the input sequence and prepares token-level regression targets.
@@ -330,7 +330,9 @@ class OmniDatasetForTokenRegression(OmniDataset):
             # Handle token-level regression labels
             if isinstance(labels, (list, tuple)):
                 # Ensure labels match sequence length
-                labels = list(labels)[:self.max_length - 2]  # Account for special tokens
+                labels = list(labels)[
+                    : self.max_length - 2
+                ]  # Account for special tokens
                 labels = [-100] + labels + [-100]  # Add padding for special tokens
             else:
                 # Single value for the entire sequence
@@ -343,11 +345,11 @@ class OmniDatasetForTokenRegression(OmniDataset):
 class OmniDatasetForSequenceRegression(OmniDataset):
     """
     Dataset class for sequence regression tasks in genomics.
-    
+
     This class extends `OmniDataset` to prepare input sequences and their corresponding
     sequence-level regression targets. It's designed for tasks where the entire
     sequence needs to be assigned a continuous value.
-    
+
     Attributes:
         metadata: Dictionary containing dataset metadata including library information
     """
@@ -383,7 +385,7 @@ class OmniDatasetForSequenceRegression(OmniDataset):
     def prepare_input(self, instance, **kwargs):
         """
         Prepare a single data instance for sequence regression.
-        
+
         This method handles both string sequences and dictionary instances
         containing sequence and regression target information. It tokenizes
         the input sequence and prepares sequence-level regression targets.
@@ -432,4 +434,4 @@ class OmniDatasetForSequenceRegression(OmniDataset):
             labels = float(labels)
 
         tokenized_inputs["labels"] = torch.tensor(labels, dtype=torch.float32)
-        return tokenized_inputs
+        return tokenized_inputs

omnigenome/src/lora/__init__.py

@@ -10,4 +10,3 @@
 """
 This package contains modules for LoRA (Low-Rank Adaptation) fine-tuning.
 """
-