omnigenome 0.3.1a0__py3-none-any.whl → 1.0.0b0__py3-none-any.whl

omnigenome/cli/__init__.py

@@ -1,12 +0,0 @@
-# -*- coding: utf-8 -*-
-# file: __init__.py
-# time: 13:04 05/02/2025
-# author: YANG, HENG <hy345@exeter.ac.uk> (杨恒)
-# Homepage: https://yangheng95.github.io
-# github: https://github.com/yangheng95
-# huggingface: https://huggingface.co/yangheng
-# google scholar: https://scholar.google.com/citations?user=NPq5a_0AAAAJ&hl=en
-# Copyright (C) 2019-2025. All Rights Reserved.
-"""
-This package contains modules for the command-line interface.
-"""

omnigenome/cli/commands/__init__.py

@@ -1,12 +0,0 @@
-# -*- coding: utf-8 -*-
-# file: __init__.py
-# time: 19:04 05/02/2025
-# author: YANG, HENG <hy345@exeter.ac.uk> (杨恒)
-# Homepage: https://yangheng95.github.io
-# github: https://github.com/yangheng95
-# huggingface: https://huggingface.co/yangheng
-# google scholar: https://scholar.google.com/citations?user=NPq5a_0AAAAJ&hl=en
-# Copyright (C) 2019-2025. All Rights Reserved.
-"""
-This package contains modules for the CLI commands.
-"""

omnigenome/cli/commands/base.py

@@ -1,83 +0,0 @@
-# -*- coding: utf-8 -*-
-# file: base.py
-# time: 19:04 05/02/2025
-# author: YANG, HENG <hy345@exeter.ac.uk> (杨恒)
-# Homepage: https://yangheng95.github.io
-# github: https://github.com/yangheng95
-# huggingface: https://huggingface.co/yangheng
-# google scholar: https://scholar.google.com/citations?user=NPq5a_0AAAAJ&hl=en
-# Copyright (C) 2019-2025. All Rights Reserved.
-from abc import ABC, abstractmethod
-
-
-class BaseCommand(ABC):
-    """
-    Abstract base class for all CLI commands in OmniGenome.
-
-    This class provides a common interface for all command-line interface
-    commands in the OmniGenome framework. It defines the structure that
-    all command classes must follow, including registration and common
-    argument handling.
-
-    Subclasses must implement the `register_command` method to define
-    their specific command-line interface and arguments.
-
-    Example:
-        >>> class MyCommand(BaseCommand):
-        ...     @classmethod
-        ...     def register_command(cls, subparsers):
-        ...         parser = subparsers.add_parser("mycommand", help="My command")
-        ...         parser.add_argument("--input", required=True)
-        ...         parser.set_defaults(func=cls.execute)
-        ...
-        ...     @staticmethod
-        ...     def execute(args):
-        ...         print(f"Executing with input: {args.input}")
-    """
-
-    @classmethod
-    @abstractmethod
-    def register_command(cls, subparsers):
-        """
-        Register the command and its arguments with the main parser.
-
-        This abstract method must be implemented by all subclasses to define
-        their specific command-line interface, including arguments, help text,
-        and default functions.
-
-        Args:
-            subparsers: The subparsers object from the main ArgumentParser
-
-        Example:
-            >>> parser = argparse.ArgumentParser()
-            >>> subparsers = parser.add_subparsers()
-            >>> MyCommand.register_command(subparsers)
-        """
-        pass
-
-    @classmethod
-    def add_common_arguments(cls, parser):
-        """
-        Add common arguments to a command's parser.
-
-        This method adds standard arguments that are common across all
-        OmniGenome CLI commands, such as logging level and output directory.
-
-        Args:
-            parser: The ArgumentParser for the specific command
-
-        Example:
-            >>> parser = argparse.ArgumentParser()
-            >>> BaseCommand.add_common_arguments(parser)
-        """
-        parser.add_argument(
-            "--log-level",
-            choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"],
-            default="INFO",
-            help="Set the logging level",
-        )
-        parser.add_argument(
-            "--output-dir",
-            default="results",
-            help="Output directory to save results",
-        )

omnigenome/cli/commands/bench/__init__.py

@@ -1,12 +0,0 @@
-# -*- coding: utf-8 -*-
-# file: __init__.py
-# time: 19:10 05/02/2025
-# author: YANG, HENG <hy345@exeter.ac.uk> (杨恒)
-# Homepage: https://yangheng95.github.io
-# github: https://github.com/yangheng95
-# huggingface: https://huggingface.co/yangheng
-# google scholar: https://scholar.google.com/citations?user=NPq5a_0AAAAJ&hl=en
-# Copyright (C) 2019-2025. All Rights Reserved.
-"""
-This package contains modules for the benchmark command.
-"""

omnigenome/cli/commands/bench/bench_cli.py

@@ -1,202 +0,0 @@
-# -*- coding: utf-8 -*-
-# file: auto_bench_cli.py
-# time: 21:06 31/01/2025
-# author: YANG, HENG <hy345@exeter.ac.uk> (Yang Heng)
-# Homepage: https://yangheng95.github.io
-# github: https://github.com/yangheng95
-# huggingface: https://huggingface.co/yangheng
-# google scholar: https://scholar.google.com/citations?user=NPq5a_0AAAAJ&hl=en
-# Copyright (C) 2019-2025. All Rights Reserved.
-import argparse
-import os
-import platform
-import sys
-import time
-from pathlib import Path
-
-from ....auto.auto_bench.auto_bench import AutoBench
-from ....src.misc.utils import fprint
-from ..base import BaseCommand
-
-
-class BenchCommand(BaseCommand):
-    """
-    Command-line interface for running automated benchmarking of genomic foundation models.
-    
-    This class provides a CLI interface for the AutoBench functionality, allowing users
-    to easily run comprehensive evaluations of genomic models across multiple benchmarks.
-    It supports various benchmarks, models, and training configurations.
-    
-    Attributes:
-        benchmarks (list): List of available benchmarks (RGB, PGB, GUE, GB, BEACON)
-        trainers (list): List of available trainers (native, accelerate, hf_trainer)
-        
-    Example:
-        >>> # Run basic benchmark
-        >>> python -m omnigenome.cli autobench --model "model_name" --benchmark "RGB"
-        
-        >>> # Run with custom settings
-        >>> python -m omnigenome.cli autobench \
-        ...     --model "model_name" \
-        ...     --benchmark "RGB" \
-        ...     --trainer "accelerate" \
-        ...     --bs_scale 2 \
-        ...     --overwrite True
-    """
-
-    @classmethod
-    def register_command(cls, subparsers):
-        """
-        Register the autobench command with the argument parser.
-
-        This method sets up the command-line interface for the autobench functionality,
-        including all necessary arguments and their descriptions.
-
-        Args:
-            subparsers: The subparsers object from argparse to add the command to
-
-        Example:
-            >>> parser = argparse.ArgumentParser()
-            >>> subparsers = parser.add_subparsers()
-            >>> BenchCommand.register_command(subparsers)
-        """
-        parser = subparsers.add_parser(
-            "autobench",
-            help="Run Auto-benchmarking for Genomic Foundation Models.",
-            formatter_class=argparse.ArgumentDefaultsHelpFormatter,
-        )
-        # Required argument
-        parser.add_argument(
-            "-b",
-            "--benchmark",
-            type=str,
-            default="RGB",
-            choices=["RGB", "PGB", "GUE", "GB", "BEACON"],
-            help="Path to the BEACON benchmark root directory.",
-        )
-        parser.add_argument(
-            "-t",
-            "--tokenizer",
-            type=str,
-            default=None,
-            help="Path to the tokenizer to use (HF tokenizer ID or local path).",
-        )
-
-        parser.add_argument(
-            "-m",
-            "--model",
-            type=str,
-            required=True,
-            help="Path to the model to evaluate (HF model ID or local path).",
-        )
-
-        # Optional arguments
-        parser.add_argument(
-            "--overwrite",
-            type=bool,
-            default=False,
-            help="Overwrite existing bench results, otherwise resume from benchmark checkpoint.",
-        )
-        parser.add_argument(
-            "--bs_scale",
-            type=int,
-            default=1,
-            help="Batch size scale factor. To increase GPU memory utilization, set to 2 or 4, etc.",
-        )
-        parser.add_argument(
-            "--trainer",
-            type=str,
-            default="accelerate",
-            choices=["native", "accelerate", "hf_trainer"],
-            help="Trainer to use for training. \n"
-            "Use 'accelerate' for distributed training. Set to false to disable. "
-            "You can use 'accelerate config' to customize behavior.\n"
-            "Use 'hf_trainer' for Hugging Face Trainer. \n"
-            "Set to 'native' to use native PyTorch training loop.\n",
-        )
-
-        cls.add_common_arguments(parser)
-        parser.set_defaults(func=cls.execute)
-
-    @staticmethod
-    def execute(args: argparse.Namespace):
-        """
-        Execute the autobench command with the provided arguments.
-
-        This method runs the automated benchmarking process using the AutoBench
-        class. It handles model and tokenizer loading, benchmark execution,
-        and result logging.
-
-        Args:
-            args (argparse.Namespace): Parsed command-line arguments containing
-                                      benchmark configuration and model settings
-
-        Example:
-            >>> args = parser.parse_args(['autobench', '--model', 'model_name'])
-            >>> BenchCommand.execute(args)
-        """
-        fprint("Running benchmark, this may take a while, please be patient...")
-        fprint("You can find the logs in the 'autobench_logs' directory.")
-        fprint("You can find the metrics in the 'autobench_evaluations' directory.")
-        fprint(
-            "If you don't intend to use accelerate, please add '--trainer native' to the command."
-        )
-        fprint(
-            "If you want to alter accelerate's behavior, please refer to 'accelerate config' command."
-        )
-        fprint(
-            "If you encounter any issues, please report them on the GitHub repository."
-        )
-        # 特殊模型处理
-        if "multimolecule" in args.model:
-            from multimolecule import RnaTokenizer, AutoModelForTokenPrediction
-
-            tokenizer = RnaTokenizer.from_pretrained(args.model)
-            model = AutoModelForTokenPrediction.from_pretrained(
-                args.model, trust_remote_code=True
-            ).base_model
-        else:
-            tokenizer = args.tokenizer
-            model = args.model
-
-        autobench = AutoBench(
-            benchmark=args.benchmark,
-            model_name_or_path=model,
-            tokenizer=tokenizer,
-            overwrite=args.overwrite,
-            trainer=args.trainer,
-        )
-        autobench.run(**vars(args))
-        log_dir = Path(args.output_dir) / "autobench_evaluations"
-        log_dir.mkdir(parents=True, exist_ok=True)
-
-        timestamp = time.strftime("%Y%m%d-%H%M%S")
-        log_file = log_dir / f"bench_{args.benchmark}_{timestamp}.log"
-
-        cmd_base = f"{sys.executable} -m omnigenome_cli.bench_internal " + " ".join(
-            f"--{k}={v}" if v is not None else f"--{k}"
-            for k, v in vars(args).items()
-            if k not in {"func", "output_dir", "log_level"}
-        )
-
-        if platform.system() == "Windows":
-            return f"{cmd_base} 2>&1 | powershell -Command \"tee-object -FilePath '{log_file}'\""
-        os.system(f"{cmd_base} 2>&1 | tee {log_file}")
-
-
-def register_command(subparsers):
-    """
-    Register the autobench command with the CLI.
-
-    This function is a convenience wrapper for registering the BenchCommand
-    with the argument parser.
-
-    Args:
-        subparsers: The subparsers object from argparse to add the command to
-
-    Example:
-        >>> parser = argparse.ArgumentParser()
-        >>> subparsers = parser.add_subparsers()
-        >>> register_command(subparsers)
-    """
-    BenchCommand.register_command(subparsers)

omnigenome/cli/commands/rna/__init__.py

@@ -1,12 +0,0 @@
-# -*- coding: utf-8 -*-
-# file: __init__.py
-# time: 19:07 05/02/2025
-# author: YANG, HENG <hy345@exeter.ac.uk> (杨恒)
-# Homepage: https://yangheng95.github.io
-# github: https://github.com/yangheng95
-# huggingface: https://huggingface.co/yangheng
-# google scholar: https://scholar.google.com/citations?user=NPq5a_0AAAAJ&hl=en
-# Copyright (C) 2019-2025. All Rights Reserved.
-"""
-This package contains modules for the rna command.
-"""

omnigenome/cli/commands/rna/rna_design.py

@@ -1,177 +0,0 @@
-# -*- coding: utf-8 -*-
-# file: rna_design.py
-# time: 19:06 05/02/2025
-# author: YANG, HENG <hy345@exeter.ac.uk> (杨恒)
-# Homepage: https://yangheng95.github.io
-# github: https://github.com/yangheng95
-# huggingface: https://huggingface.co/yangheng
-# google scholar: https://scholar.google.com/citations?user=NPq5a_0AAAAJ&hl=en
-# Copyright (C) 2019-2025. All Rights Reserved.
-import json
-import argparse
-from pathlib import Path
-from typing import Optional
-from omnigenome import OmniModelForRNADesign
-from ..base import BaseCommand
-
-
-class RNADesignCommand(BaseCommand):
-    """
-    Command-line interface for RNA sequence design using genetic algorithms.
-    
-    This class provides a CLI interface for designing RNA sequences that fold into
-    specific secondary structures. It uses genetic algorithms with customizable
-    parameters to optimize sequence design for target structures.
-    
-    The design process involves:
-    1. Loading a pre-trained RNA design model
-    2. Running genetic algorithm optimization
-    3. Generating sequences that match the target structure
-    4. Saving results to file (optional)
-    
-    Attributes:
-        model_path (str): Path to the pre-trained RNA design model
-        structure (str): Target RNA secondary structure in dot-bracket notation
-        mutation_ratio (float): Genetic algorithm mutation rate
-        num_population (int): Population size for genetic algorithm
-        num_generation (int): Number of generations for evolution
-        
-    Example:
-        >>> # Basic RNA design
-        >>> python -m omnigenome.cli design --structure "(((...)))"
-        
-        >>> # Design with custom parameters
-        >>> python -m omnigenome.cli design \
-        ...     --structure "(((...)))" \
-        ...     --model-path "yangheng/OmniGenome-186M" \
-        ...     --mutation-ratio 0.3 \
-        ...     --num-population 200 \
-        ...     --num-generation 150 \
-        ...     --output "results.json"
-    """
-
-    @classmethod
-    def register_command(cls, subparsers):
-        """
-        Register the RNA design command with the argument parser.
-
-        This method sets up the command-line interface for RNA sequence design,
-        including all necessary arguments and their descriptions.
-
-        Args:
-            subparsers: The subparsers object from argparse to add the command to
-
-        Example:
-            >>> parser = argparse.ArgumentParser()
-            >>> subparsers = parser.add_subparsers()
-            >>> RNADesignCommand.register_command(subparsers)
-        """
-        parser: argparse.ArgumentParser = subparsers.add_parser(
-            "design",
-            help="RNA Sequence Design based on Secondary Structure, Using Genetic Algorithm by OmniGenome",
-            formatter_class=argparse.ArgumentDefaultsHelpFormatter,
-        )
-        parser.add_argument(
-            "--structure",
-            required=True,
-            help="The target RNA structure in dot-bracket notation (e.g., '(((...)))')",
-        )
-        parser.add_argument(
-            "--model-path",
-            default="yangheng/OmniGenome-186M",
-            help="Model path to the pre-trained model (default: yangheng/OmniGenome-186M)",
-        )
-        parser.add_argument(
-            "--mutation-ratio",
-            type=float,
-            default=0.5,
-            help="Mutation ratio for genetic algorithm (0.0-1.0, default: 0.5)",
-        )
-        parser.add_argument(
-            "--num-population",
-            type=int,
-            default=100,
-            help="Number of individuals in population (default: 100)",
-        )
-        parser.add_argument(
-            "--num-generation",
-            type=int,
-            default=100,
-            help="Number of generations to evolve (default: 100)",
-        )
-        parser.add_argument(
-            "--output", type=Path, help="Output JSON file to save results"
-        )
-        cls.add_common_arguments(parser)
-        parser.set_defaults(func=cls.execute)
-
-    @staticmethod
-    def execute(args: argparse.Namespace):
-        """
-        Execute the RNA design command with the provided arguments.
-
-        This method runs the RNA sequence design process using genetic algorithms.
-        It validates parameters, loads the model, runs the design optimization,
-        and outputs or saves the results.
-
-        Args:
-            args (argparse.Namespace): Parsed command-line arguments containing
-                                      design parameters and model settings
-
-        Raises:
-            ValueError: If mutation_ratio is not between 0.0 and 1.0
-
-        Example:
-            >>> args = parser.parse_args(['design', '--structure', '(((...)))'])
-            >>> RNADesignCommand.execute(args)
-        """
-        # 参数验证逻辑
-        if not 0 <= args.mutation_ratio <= 1:
-            raise ValueError("--mutation-ratio should be between 0.0 and 1.0")
-
-        # 核心业务逻辑
-        model = OmniModelForRNADesign(model_path=args.model_path)
-        best_sequences = model.design(
-            structure=args.structure,
-            mutation_ratio=args.mutation_ratio,
-            num_population=args.num_population,
-            num_generation=args.num_generation,
-        )
-
-        # 结果输出
-        print(f"The best RNA sequences for {args.structure}:")
-        for seq in best_sequences:
-            print(f"- {seq}")
-
-        # 结果保存
-        if args.output:
-            args.output.parent.mkdir(parents=True, exist_ok=True)
-            with open(args.output, "w") as f:
-                json.dump(
-                    {
-                        "structure": args.structure,
-                        "parameters": vars(args),
-                        "best_sequences": best_sequences,
-                    },
-                    f,
-                    indent=2,
-                )
-            print(f"\nResults saved to {args.output}")
-
-
-def register_command(subparsers):
-    """
-    Register the RNA design command with the CLI.
-
-    This function is a convenience wrapper for registering the RNADesignCommand
-    with the argument parser.
-
-    Args:
-        subparsers: The subparsers object from argparse to add the command to
-
-    Example:
-        >>> parser = argparse.ArgumentParser()
-        >>> subparsers = parser.add_subparsers()
-        >>> register_command(subparsers)
-    """
-    RNADesignCommand.register_command(subparsers)

omnigenome/cli/omnigenome_cli.py

@@ -1,128 +0,0 @@
-# -*- coding: utf-8 -*-
-# file: omnigenome_cli.py
-# time: 12:51 05/02/2025
-# author: YANG, HENG <hy345@exeter.ac.uk> (杨恒)
-# Homepage: https://yangheng95.github.io
-# github: https://github.com/yangheng95
-# huggingface: https://huggingface.co/yangheng
-# google scholar: https://scholar.google.com/citations?user=NPq5a_0AAAAJ&hl=en
-# Copyright (C) 2019-2025. All Rights Reserved.
-import argparse
-import json
-
-
-def main():
-    """
-    The main entry point for the OmniGenome command-line interface.
-    
-    This function sets up the command-line argument parser and handles
-    the execution of different subcommands. Currently supports RNA design
-    functionality with genetic algorithm optimization.
-    
-    The CLI provides a user-friendly interface for common OmniGenome tasks
-    without requiring Python programming knowledge.
-    
-    Example:
-        >>> # Design RNA sequences from command line
-        >>> python -m omnigenome.cli.omnigenome_cli rna_design --structure "(((...)))"
-        
-        >>> # Design with custom parameters
-        >>> python -m omnigenome.cli.omnigenome_cli rna_design \
-        ...     --structure "(((...)))" \
-        ...     --model "yangheng/OmniGenome-186M" \
-        ...     --mutation-ratio 0.3 \
-        ...     --num-population 200 \
-        ...     --num-generation 150 \
-        ...     --output-file "results.json"
-    """
-    parser = argparse.ArgumentParser(description="OmniGenome CLI")
-    subparsers = parser.add_subparsers(
-        dest="command", required=True, help="Sub-command help"
-    )
-
-    # Design command
-    design_parser = subparsers.add_parser(
-        "rna_design", help="Design RNA sequences for a given secondary structure"
-    )
-    design_parser.add_argument(
-        "--structure",
-        type=str,
-        required=True,
-        help='Target RNA structure in dot-bracket notation (e.g., "(((...)))")',
-    )
-    design_parser.add_argument(
-        "--model",
-        type=str,
-        default="yangheng/OmniGenome-186M",
-        help="Path to the pre-trained model (default: yangheng/OmniGenome-186M)",
-    )
-    design_parser.add_argument(
-        "--mutation-ratio",
-        type=float,
-        default=0.5,
-        help="Mutation ratio for genetic algorithm (0.0-1.0, default: 0.5)",
-    )
-    design_parser.add_argument(
-        "--num-population",
-        type=int,
-        default=100,
-        help="Number of individuals in population (default: 100)",
-    )
-    design_parser.add_argument(
-        "--num-generation",
-        type=int,
-        default=100,
-        help="Number of generations to evolve (default: 100)",
-    )
-    design_parser.add_argument(
-        "--output-file", type=str, help="Output JSON file to save results"
-    )
-
-    args = parser.parse_args()
-
-    if args.command == "rna_design":
-        from omnigenome import OmniModelForRNADesign
-
-        # Validate parameters
-        if not 0 <= args.mutation_ratio <= 1:
-            raise ValueError("--mutation-ratio must be between 0.0 and 1.0")
-        if args.num_population <= 0 or args.num_generation <= 0:
-            raise ValueError(
-                "Population and generation numbers must be positive integers"
-            )
-
-        # Run RNA design
-        model = OmniModelForRNADesign(model=args.model)
-        best_sequences = model.design(
-            structure=args.structure,
-            mutation_ratio=args.mutation_ratio,
-            num_population=args.num_population,
-            num_generation=args.num_generation,
-        )
-
-        # Output results
-        print(f"Best RNA sequences for {args.structure}:")
-        for seq in best_sequences:
-            print(f"- {seq}")
-
-        # Save to file if specified
-        if args.output_file:
-            with open(args.output_file, "w") as f:
-                json.dump(
-                    {
-                        "structure": args.structure,
-                        "parameters": {
-                            "mutation_ratio": args.mutation_ratio,
-                            "population": args.num_population,
-                            "generations": args.num_generation,
-                        },
-                        "best_sequences": best_sequences,
-                    },
-                    f,
-                    indent=2,
-                )
-            print(f"\nResults saved to {args.output_file}")
-
-
-if __name__ == "__main__":
-    main()

omnigenome/src/__init__.py

@@ -1,11 +0,0 @@
-# -*- coding: utf-8 -*-
-# file: __init__.py
-# time: 21:11 08/04/2024
-# author: YANG, HENG <hy345@exeter.ac.uk> (杨恒)
-# github: https://github.com/yangheng95
-# huggingface: https://huggingface.co/yangheng
-# google scholar: https://scholar.google.com/citations?user=NPq5a_0AAAAJ&hl=en
-# Copyright (C) 2019-2024. All Rights Reserved.
-"""
-This package contains the core source code of the OmniGenome library.
-"""

omnigenome/src/abc/__init__.py

@@ -1,11 +0,0 @@
-# -*- coding: utf-8 -*-
-# file: __init__.py
-# time: 14:11 06/04/2024
-# author: YANG, HENG <hy345@exeter.ac.uk> (杨恒)
-# github: https://github.com/yangheng95
-# huggingface: https://huggingface.co/yangheng
-# google scholar: https://scholar.google.com/citations?user=NPq5a_0AAAAJ&hl=en
-# Copyright (C) 2019-2024. All Rights Reserved.
-"""
-This package contains abstract base classes for datasets, models, and tokenizers.
-"""