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

omnigenome/__init__.py

@@ -1,266 +1,26 @@
-# -*- coding: utf-8 -*-
-# file: __init__.py
-# time: 14:53 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 __init__.py file exposes the Key API Entries of the library for easy access.
-Use dir(omnigenome) to see all available APIs.
-
-Key API Entries:
-----------------
-- AutoBench: Automated benchmarking of genomic models
-- AutoTrain: Automated training of genomic models
-- BenchHub: Hub for accessing benchmarks
-- ModelHub: Hub for accessing pre-trained models
-- PipelineHub: Hub for accessing pipelines
-- Various model classes for different genomic tasks
-- Dataset classes for different data formats
-- Tokenizer classes for different sequence representations
-- Metric classes for evaluation
-- Trainer classes for model training
-"""
-
-__name__ = "omnigenbench"
-__version__ = "0.3.1alpha"
-
-__author__ = "YANG, HENG"
-__email__ = "yangheng2021@gmail.com"
-__license__ = "Apache-2.0"
-
-# Import core auto components
-from .auto.auto_bench.auto_bench import AutoBench
-from .auto.auto_bench.auto_bench_config import AutoBenchConfig
-from .auto.bench_hub.bench_hub import BenchHub
-from .auto.auto_train.auto_train import AutoTrain
-from .auto.auto_bench.auto_bench_cli import run_bench, bench_command
-from .auto.auto_train.auto_train_cli import run_train, train_command
-
-# Import source modules
-from .src import dataset as dataset
-from .src import metric as metric
-from .src import model as model
-from .src import tokenizer as tokenizer
-
-# Import abstract base classes
-from .src.abc.abstract_dataset import OmniDataset
-from .src.abc.abstract_metric import OmniMetric
-from .src.abc.abstract_model import OmniModel
-from .src.abc.abstract_tokenizer import OmniTokenizer
-from .src.abc.abstract_tokenizer import OmniTokenizer as AutoTokenizer
-
-# Import dataset classes
-from .src.dataset.omni_dataset import OmniDatasetForSequenceClassification
-from .src.dataset.omni_dataset import OmniDatasetForSequenceRegression
-from .src.dataset.omni_dataset import OmniDatasetForTokenClassification
-from .src.dataset.omni_dataset import OmniDatasetForTokenRegression
-
-# Import metric classes
-from .src.metric import ClassificationMetric, RegressionMetric, RankingMetric
-
-# Import utility functions
-from .src.misc import utils as utils
-from .src.misc.utils import clean_temp_dir_pt_files
-
-# Import model classes
-from .src.model import (
-    OmniModelForSequenceClassification,
-    OmniModelForMultiLabelSequenceClassification,
-    OmniModelForTokenClassification,
-    OmniModelForSequenceRegression,
-    OmniModelForTokenRegression,
-    OmniModelForStructuralImputation,
-    OmniModelForMatrixRegression,
-    OmniModelForMatrixClassification,
-    OmniModelForMLM,
-    OmniModelForSeq2Seq,
-    OmniModelForRNADesign,
-    OmniModelForEmbedding,
-    OmniModelForAugmentation,
-)
-
-# Import LoRA model
-from .src.lora.lora_model import OmniLoraModel
-
-# Import tokenizer classes
-from .src.tokenizer import OmniBPETokenizer
-from .src.tokenizer import OmniKmersTokenizer
-from .src.tokenizer import OmniSingleNucleotideTokenizer
-
-# Import trainer classes
-from .src.trainer.hf_trainer import HFTrainer
-from .src.trainer.trainer import Trainer
-from .src.trainer.accelerate_trainer import AccelerateTrainer
-
-# Import hub utilities
-from .utility.hub_utils import download_benchmark
-from .utility.hub_utils import download_model
-from .utility.hub_utils import download_pipeline
-from .utility import hub_utils as hub_utils
-
-# Import hub classes
-from .utility.model_hub.model_hub import ModelHub
-from .utility.dataset_hub.dataset_hub import load_benchmark_datasets
-from .utility.pipeline_hub.pipeline import Pipeline
-from .utility.pipeline_hub.pipeline_hub import PipelineHub
-
-# Import module utilities
-from .src.model.module_utils import OmniPooling
-
-# --------------------------------------------------------------------------------
-# For backward compatibility version 0.2.7alpha and earlier
-from .src.abc.abstract_tokenizer import OmniTokenizer as OmniGenomeTokenizer
-from .src.abc.abstract_dataset import OmniDataset as OmniGenomeDataset
-from .src.abc.abstract_metric import OmniMetric as OmniGenomeMetric
-from .src.abc.abstract_model import OmniModel as OmniGenomeModel
-from .src.dataset.omni_dataset import (
-    OmniDatasetForSequenceClassification as OmniGenomeDatasetForSequenceClassification,
-)
-from .src.dataset.omni_dataset import (
-    OmniDatasetForSequenceRegression as OmniGenomeDatasetForSequenceRegression,
-)
-from .src.dataset.omni_dataset import (
-    OmniDatasetForTokenClassification as OmniGenomeDatasetForTokenClassification,
-)
-from .src.dataset.omni_dataset import (
-    OmniDatasetForTokenRegression as OmniGenomeDatasetForTokenRegression,
-)
-from .src.lora.lora_model import OmniLoraModel as OmniGenomeLoraModel
-from .src.model import (
-    OmniModelForSequenceClassification as OmniGenomeModelForSequenceClassification,
-    OmniModelForMultiLabelSequenceClassification as OmniGenomeModelForMultiLabelSequenceClassification,
-    OmniModelForTokenClassification as OmniGenomeModelForTokenClassification,
-    OmniModelForSequenceRegression as OmniGenomeModelForSequenceRegression,
-    OmniModelForTokenRegression as OmniGenomeModelForTokenRegression,
-    OmniModelForStructuralImputation as OmniGenomeModelForStructuralImputation,
-    OmniModelForMatrixRegression as OmniGenomeModelForMatrixRegression,
-    OmniModelForMatrixClassification as OmniGenomeModelForMatrixClassification,
-    OmniModelForMLM as OmniGenomeModelForMLM,
-    OmniModelForSeq2Seq as OmniGenomeModelForSeq2Seq,
-    OmniModelForRNADesign as OmniGenomeModelForRNADesign,
-    OmniModelForEmbedding as OmniGenomeModelForEmbedding,
-    OmniModelForAugmentation as OmniGenomeModelForAugmentation,
-)
-
-from .utility.ensemble import VoteEnsemblePredictor
-
-# ------------------------------------------------------------------------------
-
-
-__all__ = [
-    "load_benchmark_datasets",
-    "OmniDataset",
-    "OmniModel",
-    "OmniMetric",
-    "AutoTokenizer",
-    "OmniTokenizer",
-    "OmniKmersTokenizer",
-    "OmniSingleNucleotideTokenizer",
-    "OmniBPETokenizer",
-    "ModelHub",
-    "Pipeline",
-    "PipelineHub",
-    "BenchHub",
-    "AutoBench",
-    "AutoBenchConfig",
-    "utils",
-    "model",
-    "tokenizer",
-    "dataset",
-    "OmniModelForSequenceClassification",
-    "OmniModelForMultiLabelSequenceClassification",
-    "OmniModelForTokenClassification",
-    "OmniModelForSequenceRegression",
-    "OmniModelForTokenRegression",
-    "OmniModelForRNADesign",
-    "OmniModelForEmbedding",
-    "OmniModelForAugmentation",
-    "OmniModelForStructuralImputation",
-    "OmniModelForMatrixRegression",
-    "OmniModelForMatrixClassification",
-    "OmniModelForMLM",
-    "OmniModelForSeq2Seq",
-    "OmniDatasetForTokenClassification",
-    "OmniDatasetForTokenRegression",
-    "OmniDatasetForSequenceClassification",
-    "OmniDatasetForSequenceRegression",
-    "OmniLoraModel",
-    "ClassificationMetric",
-    "RegressionMetric",
-    "RankingMetric",
-    "Trainer",
-    "HFTrainer",
-    "AccelerateTrainer",
-    "AutoBenchConfig",
-    "AutoBench",
-    "download_benchmark",
-    "download_model",
-    "download_pipeline",
-    "VoteEnsemblePredictor",
-]
-
-
-LOGO1 = r"""                       
-    **@@ #========= @@**            ___                     _ 
-      **@@ +----- @@**             / _ \  _ __ ___   _ __  (_)
-        **@@ = @@**               | | | || '_ ` _ \ | '_ \ | |
-           **@@                   | |_| || | | | | || | | || |
-        @@** = **@@                \___/ |_| |_| |_||_| |_||_|
-     @@** ------+ **@@                
-   @@** =========# **@@            ____  
-  @@ ---------------+ @@          / ___|  ___  _ __   
- @@ ================== @@        | |  _  / _ \| '_ \
-  @@ +--------------- @@         | |_| ||  __/| | | |
-   @@** #========= **@@           \____| \___||_| |_| 
-    @@** +------ **@@          
-       @@** = **@@           
-          @@**                    ____                      _   
-       **@@ = @@**               | __ )   ___  _ __    ___ | |__  
-    **@@ -----+  @@**            |  _ \  / _ \| '_ \  / __|| '_ \ 
-  **@@ ==========# @@**          | |_) ||  __/| | | || (__ | | | |
-  @@ --------------+ @@**        |____/  \___||_| |_| \___||_| |_|
-"""
-
-LOGO2 = r"""
-
-   **  +----------- **           ___                     _ 
-  @@                 @@         / _ \  _ __ ___   _ __  (_)
- @@* #============== *@@       | | | || '_ ` _ \ | '_ \ | |
- @@*                 *@@       | |_| || | | | | || | | || |
- *@@  +------------ *@@         \___/ |_| |_| |_||_| |_||_|
-  *@*               @@*       
-   *@@  #========= @@*        
-    *@@*         *@@*          
-      *@@  +---@@@*              ____  
-        *@@*   **               / ___|  ___  _ __  
-          **@**                | |  _  / _ \| '_ \ 
-        *@@* *@@*              | |_| ||  __/| | | |
-      *@@ ---+  @@*             \____| \___||_| |_|
-    *@@*         *@@*          
-   *@@ =========#  @@*         
-  *@@               @@*        
- *@@ -------------+  @@*        ____                      _   
- @@                   @@       | __ )   ___  _ __    ___ | |__ 
- @@ ===============#  @@       |  _ \  / _ \| '_ \  / __|| '_ \ 
-  @@                 @@        | |_) ||  __/| | | || (__ | | | |
-   ** -----------+  **         |____/  \___||_| |_| \___||_| |_|
-"""
-
-art_dna_color_map = {
-    "*": "blue",  # Bases represented by '*'
-    "@": "white",  # Bases represented by '@'
-    "-": "yellow",  # Hydrogen bonds, assuming '-' represents a bond
-    "=": "light_cyan",  # Hydrogen bonds, assuming '=' represents a bond
-    "+": "yellow",  # '+' symbols in cyan
-    " ": "black",  # Use red for undefined characters
-}
-import random
-
-LOGO = random.choice([LOGO1, LOGO2])
-print(LOGO)
-
-clean_temp_dir_pt_files()
+# -*- coding: utf-8 -*-
+# file: __init__.py
+# time: 14:53 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.
+
+"""
+OmniGenBench - Alias package for omnigenome
+============================================
+
+This package provides the same functionality as omnigenome but with the omnigenbench name.
+All imports are redirected to the omnigenome package.
+"""
+
+# Import everything from omnigenome to maintain compatibility
+from omnigenbench import *
+
+# Override package metadata to reflect omnigenbench
+__name__ = "omnigenome"
+__version__ = "1.0.0beta"
+__author__ = "Yang, Heng"
+__email__ = "yangheng2021@gmail.com"
+__license__ = "Apache-2.0"

{omnigenome-0.3.1a0.dist-info → omnigenome-1.0.0b0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: omnigenome
-Version: 0.3.1a0
+Version: 1.0.0b0
 Summary: OmniGenome: A comprehensive toolkit for genome analysis.
 Home-page: https://github.com/yangheng95/OmniGenBench
 Author: Yang, Heng
@@ -34,7 +34,6 @@ Requires-Dist: transformers>=4.46.0
 Requires-Dist: packaging
 Requires-Dist: peft
 Requires-Dist: dill
-Requires-Dist: accelerate
 Provides-Extra: dev
 Requires-Dist: dill; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
@@ -54,7 +53,7 @@ Dynamic: summary
 
 ![favicon.png](asset/favicon.png)
 
-<h3 align="center">OmniGenBench is a modular benchmarking platform for evaluating genomic foundation models (GFMs) across diverse tasks like RNA structure prediction, gene function classification, and multi-species generalization.</h3>
+<h3 align="center">OmniGenBench offers an all-in-one solution for genomic foundation model finetuning, inference, deployment and automated benchmarking, designed for research and applications in genomics.</h3>
 
 <div align="center">
 
@@ -104,15 +103,15 @@ Dynamic: summary
 ## Installation
 
 ### Requirements
-Before installing OmniGenome, you need to install the following dependencies:
+Before installing OmniGenoBench, you need to install the following dependencies:
 - Python 3.10+
 - PyTorch 2.5+
 - Transformers 4.46.0+
 
 ### PyPI Installation
-To install OmniGenome, you can use pip:
+To install OmniGenoBench, you can use pip:
 ```bash
-pip install omnigenome -U
+pip install omnigenbench -U
 ```
 
 ### Source Installation
@@ -136,7 +135,7 @@ You can find a visualization of AutoBench [here](asset/AutoBench.gif).
 ### Auto-benchmark via Python API
 Or you can use the following python code to run the auto-benchmark:
 ```python
-from omnigenome import AutoBench
+from omnigenbench import AutoBench
 gfm = 'LongSafari/hyenadna-medium-160k-seqlen-hf'
 # benchmark could be "RGB", "GB", "PGB", "GUE", which will be downloaded from the Hugging Face model hub
 benchmark = "RGB"
@@ -185,7 +184,7 @@ OmniGenBench supports five curated benchmark suites covering both **sequence-lev
 ### RNA Design
 RNA design is a fundamental problem in synthetic biology,
 where the goal is to design RNA sequences that fold into a target structure.
-In this demo, we show how to use OmniGenome to design RNA sequences 
+In this demo, we show how to use OmniGenoBench to design RNA sequences 
 that fold into a target structure using a pre-trained model.
 The tutorials of RNA Design Demo can be found in [RNA_Design_Tutorial.ipynb](examples/rna_design/RNA_Design_Tutorial.ipynb).
 
@@ -195,7 +194,7 @@ You can find a visual example of RNA Design [here](asset/RNA_Design.gif).
 
 RNA secondary structure prediction is a fundamental problem in computational biology,
 where the goal is to predict the secondary structure of an RNA sequence.
-In this demo, we show how to use OmniGenome to predict the secondary structure of RNA sequences using a pre-trained model.
+In this demo, we show how to use OmniGenoBench to predict the secondary structure of RNA sequences using a pre-trained model.
 The tutorials of RNA Secondary Structure Prediction can be found in
 [Secondary_Structure_Prediction_Tutorial.ipynb](examples/rna_secondary_structure_prediction/Secondary_Structure_Prediction_Tutorial.ipynb).
 

omnigenome-1.0.0b0.dist-info/RECORD

@@ -0,0 +1,6 @@
+omnigenome/__init__.py,sha256=JL0bSHQvgNHRLRvbywvuaf-tFJ-sGmnPgpF_4lpSDCI,887
+omnigenome-1.0.0b0.dist-info/licenses/LICENSE,sha256=oQoefBV6siHctF0ET-OO3EaSZgtqGtf-wdIAmokS8iY,11560
+omnigenome-1.0.0b0.dist-info/METADATA,sha256=72rfG-qBr9ex44k4r6gAQqQXVvb4lGBo-Utbjw461Ak,10278
+omnigenome-1.0.0b0.dist-info/WHEEL,sha256=lTU6B6eIfYoiQJTZNc-fyaR6BpL6ehTzU3xGYxn2n8k,91
+omnigenome-1.0.0b0.dist-info/top_level.txt,sha256=LVFxm_WPaxjj9KnAqdW94W4D4lbOk30gdsaKlJiSzTo,11
+omnigenome-1.0.0b0.dist-info/RECORD,,

omnigenome/auto/__init__.py

@@ -1,3 +0,0 @@
-"""
-This package contains modules for automated processes such as benchmarking and training.
-"""

omnigenome/auto/auto_bench/__init__.py

@@ -1,11 +0,0 @@
-# -*- coding: utf-8 -*-
-# file: __init__.py
-# time: 18:28 11/04/2024
-# 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 modules for automated benchmarking of models.
-"""