smftools 0.1.1__py3-none-any.whl → 0.1.6__py3-none-any.whl

smftools/readwrite.py

@@ -1,106 +0,0 @@
-## readwrite ##
-
-######################################################################################################
-## Datetime functionality
-def date_string():
-    """
-    Each time this is called, it returns the current date string
-    """
-    from datetime import datetime
-    current_date = datetime.now()
-    date_string = current_date.strftime("%Y%m%d")
-    date_string = date_string[2:]
-    return date_string
-
-def time_string():
-    """
-    Each time this is called, it returns the current time string
-    """
-    from datetime import datetime
-    current_time = datetime.now()
-    return current_time.strftime("%H:%M:%S")
-######################################################################################################
-
-######################################################################################################
-## Numpy, Pandas, Anndata functionality
-def adata_to_df(adata, layer=None):
-    """
-    Input: An adata object with a specified layer.
-    Output: A dataframe for the specific layer.
-    """
-    import pandas as pd
-    import anndata as ad
-
-    # Extract the data matrix from the given layer
-    if layer:
-        data_matrix = adata.layers[layer]
-    else:
-        data_matrix = adata.X
-    # Extract observation (read) annotations
-    obs_df = adata.obs
-    # Extract variable (position) annotations
-    var_df = adata.var
-    # Convert data matrix and annotations to pandas DataFrames
-    df = pd.DataFrame(data_matrix, index=obs_df.index, columns=var_df.index)
-    return df
-
-def save_matrix(matrix, save_name):
-    """
-    Input: A numpy matrix and a save_name
-    Output: A txt file representation of the data matrix
-    """
-    import numpy as np
-    np.savetxt(f'{save_name}.txt', matrix)
-
-def concatenate_h5ads(output_file, file_suffix='h5ad.gz', delete_inputs=True):
-    """
-    Concatenate all h5ad files in a directory and delete them after the final adata is written out.
-    Input: an output file path relative to the directory in which the function is called
-    """
-    import os
-    import anndata as ad
-    # Runtime warnings
-    import warnings
-    warnings.filterwarnings('ignore', category=UserWarning, module='anndata')
-    warnings.filterwarnings('ignore', category=FutureWarning, module='anndata')
-    
-    # List all files in the directory
-    files = os.listdir(os.getcwd())
-    # get current working directory
-    cwd = os.getcwd()
-    suffix = file_suffix
-    # Filter file names that contain the search string in their filename and keep them in a list
-    hdfs = [hdf for hdf in files if suffix in hdf]
-    # Sort file list by names and print the list of file names
-    hdfs.sort()
-    print('{0} sample files found: {1}'.format(len(hdfs), hdfs))
-    # Iterate over all of the hdf5 files and concatenate them.
-    final_adata = None
-    for hdf in hdfs:
-        print('{0}: Reading in {1} hdf5 file'.format(time_string(), hdf))
-        temp_adata = ad.read_h5ad(hdf)
-        if final_adata:
-            print('{0}: Concatenating final adata object with {1} hdf5 file'.format(time_string(), hdf))
-            final_adata = ad.concat([final_adata, temp_adata], join='outer', index_unique=None)
-        else:
-            print('{0}: Initializing final adata object with {1} hdf5 file'.format(time_string(), hdf))
-            final_adata = temp_adata
-    print('{0}: Writing final concatenated hdf5 file'.format(time_string()))
-    final_adata.write_h5ad(output_file, compression='gzip')
-
-    # Delete the individual h5ad files and only keep the final concatenated file
-    if delete_inputs:
-        files = os.listdir(os.getcwd())
-        hdfs = [hdf for hdf in files if suffix in hdf]
-        if output_file in hdfs:
-            hdfs.remove(output_file)
-            # Iterate over the files and delete them
-            for hdf in hdfs:
-                try:
-                    os.remove(hdf)
-                    print(f"Deleted file: {hdf}")
-                except OSError as e:
-                    print(f"Error deleting file {hdf}: {e}")
-    else:
-        print('Keeping input files')
-######################################################################################################

smftools-0.1.1.dist-info/METADATA

@@ -1,88 +0,0 @@
-Metadata-Version: 2.3
-Name: smftools
-Version: 0.1.1
-Summary: Single Molecule Footprinting Analysis in Python.
-Project-URL: Source, https://github.com/jkmckenna/smftools
-Author: Joseph McKenna
-Maintainer-email: Joseph McKenna <jkmckenna@berkeley.edu>
-License-Expression: MIT
-License-File: LICENSE
-Keywords: anndata,chromatin-accessibility,machine-learning,nanopore,protein-dna-binding,single-locus,single-molecule-footprinting
-Classifier: Development Status :: 2 - Pre-Alpha
-Classifier: Environment :: Console
-Classifier: Intended Audience :: Developers
-Classifier: Intended Audience :: Science/Research
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Natural Language :: English
-Classifier: Operating System :: MacOS :: MacOS X
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
-Classifier: Topic :: Scientific/Engineering :: Visualization
-Requires-Python: >=3.9
-Requires-Dist: anndata>=0.10.0
-Requires-Dist: biopython>=1.79
-Requires-Dist: cython>=0.29.28
-Requires-Dist: networkx>=3.2
-Requires-Dist: numpy<2,>=1.22.0
-Requires-Dist: pandas>=1.4.2
-Requires-Dist: pod5>=0.1.21
-Requires-Dist: pomegranate>1.0.0
-Requires-Dist: pysam>=0.19.1
-Requires-Dist: scanpy>=1.9
-Requires-Dist: scikit-learn>=1.0.2
-Requires-Dist: scipy>=1.7.3
-Requires-Dist: seaborn>=0.11
-Requires-Dist: torch>=1.9.0
-Requires-Dist: tqdm
-Provides-Extra: base-tests
-Requires-Dist: pytest; extra == 'base-tests'
-Requires-Dist: pytest-cov; extra == 'base-tests'
-Provides-Extra: docs
-Requires-Dist: ipython>=7.20; extra == 'docs'
-Requires-Dist: matplotlib!=3.6.1; extra == 'docs'
-Requires-Dist: myst-nb>=1; extra == 'docs'
-Requires-Dist: myst-parser>=2; extra == 'docs'
-Requires-Dist: nbsphinx>=0.9; extra == 'docs'
-Requires-Dist: readthedocs-sphinx-search; extra == 'docs'
-Requires-Dist: setuptools; extra == 'docs'
-Requires-Dist: sphinx-autodoc-typehints>=1.25.2; extra == 'docs'
-Requires-Dist: sphinx-book-theme>=1.1.0; extra == 'docs'
-Requires-Dist: sphinx-copybutton; extra == 'docs'
-Requires-Dist: sphinx-design; extra == 'docs'
-Requires-Dist: sphinx>=7; extra == 'docs'
-Requires-Dist: sphinxcontrib-bibtex; extra == 'docs'
-Requires-Dist: sphinxext-opengraph; extra == 'docs'
-Description-Content-Type: text/markdown
-
-[![PyPI](https://img.shields.io/pypi/v/smftools.svg)](https://pypi.org/project/smftools)
-[![Docs](https://readthedocs.org/projects/smftools/badge/?version=latest)](https://smftools.readthedocs.io/en/latest/?badge=latest)
-
-# smftools
-A Python tool for processing raw sequencing data derived from single molecule footprinting experiments into [anndata](https://anndata.readthedocs.io/en/latest/) objects. Additional functionality for preprocessing, analysis, and visualization. Data structures are compatible with analyses developed within the [scverse](https://github.com/scverse) project, including [scanpy](https://github.com/scverse/scanpy) and [scvi-tools](https://github.com/scverse/scvi-tools).
-
-## Philosophy
-While most genomic data structures handle low-coverage data (<100X) along large references, smftools prioritizes high-coverage data (scalable to at least 1 million X coverage) of a few genomic loci at a time. This enables efficient data storage, rapid data operations, hierarchical metadata handling, seamless integration with various machine-learning packages, and ease of visualization. Furthermore, functionality is modularized, enabling analysis sessions to be saved, reloaded, and easily shared with collaborators. Analyses are centered around the [anndata](https://anndata.readthedocs.io/en/latest/) object, and are heavily inspired by the work conducted within the single-cell genomics community.
-
-## Dependencies
-The following CLI tools need to be installed and configured before using the informatics (smftools.inform) module of smftools:
-1) [Dorado](https://github.com/nanoporetech/dorado) -> For standard/modified basecalling and alignment. Can be attained by downloading and configuring nanopore MinKnow software.
-2) [Samtools](https://github.com/samtools/samtools) -> For working with SAM/BAM files
-3) [Minimap2](https://github.com/lh3/minimap2) -> The aligner used by Dorado
-4) [Modkit](https://github.com/nanoporetech/modkit) -> Extracting summary statistics and read level methylation calls from modified BAM files
-
-## Modules
-- Informatics: Processes raw SMF data coming from Nanopore POD5 files, BAM files, or FASTQ files and organizes it into an AnnData object.
-- Preprocessing: Filters the AnnData object on read length, total methylation, and a variety of QC metrics.
-- Tools: Appends various analyses to the AnnData object.
-- Plotting: Visualization of analyses stored within the AnnData object.
-
-## Announcements
-### 09/09/24 - The pre-alpha phase package ([smftools-0.1.1](https://pypi.org/project/smftools/))
-The informatics module has been bumped to alpha-phase status. This module can deal with POD5s and unaligned BAMS from nanopore conversion and direct SMF experiments, as well as FASTQs from Illumina conversion SMF experiments. Primary output from this module is an AnnData object containing all relevant SMF data, which is compatible with all downstream smftools modules. The other modules are still in pre-alpha phase. Preprocessing, Tools, and Plotting modules should be promoted to alpha-phase within the next month or so.
-
-### 08/30/24 - The pre-alpha phase package ([smftools-0.1.0](https://pypi.org/project/smftools/)) is installable through pypi!
-Currently, this package (smftools-0.1.0) is going through rapid improvement (dependency handling accross Linux and Mac OS, testing, documentation, debugging) and is still too early in development for standard use. The underlying functionality was originally developed as a collection of scripts for single molecule footprinting (SMF) experiments in our lab, but is being packaged/developed to facilitate the expansion of SMF to any lab that is interested in performing these styles of experiments/analyses. The alpha-phase package is expected to be available within a couple months, so stay tuned!

smftools-0.1.1.dist-info/RECORD

@@ -1,64 +0,0 @@
-smftools/__init__.py,sha256=zy4ckT7hKrLrlm6NiZQoupvc6oSN7wJsyOBCYdzukcQ,401
-smftools/_settings.py,sha256=RkGSrezDzZnh6AODA3o2LiSAINBxxxal5weq-2RZuM0,379
-smftools/_version.py,sha256=8oAxKUG747GUokmxjkrWejyJa5yPNEsoJDlXxoedxTw,21
-smftools/readwrite.py,sha256=DgVisHYdkjzaO7suPbUvluImeTc3jqGDlioNveHUxPc,4158
-smftools/datasets/F1_hybrid_NKG2A_enhander_promoter_GpC_conversion_SMF.h5ad.gz,sha256=q6wJtgFRDln0o20XNCx1qad3lwcdCoylqPN7wskTfI8,2926497
-smftools/datasets/__init__.py,sha256=xkSTlPuakVYVCuRurif9BceNBDt6bsngJvvjI8757QI,142
-smftools/datasets/dCas9_m6A_invitro_kinetics.h5ad.gz,sha256=niOcVHaYY7h3XyvwSkN-V_NMBaRt2vTP5TrJO0CwMCs,8385050
-smftools/datasets/datasets.py,sha256=FZ6e7SU6Zt1-gf3az71AgQLpyNvAEiOb5ctbwyP3XSU,553
-smftools/informatics/__init__.py,sha256=Aa-QNdfrpZrTPq8xqP4NBA7bb1VLLYaduH-US6pKNA4,280
-smftools/informatics/bam_conversion.py,sha256=mLjIVx-07sa3TDQ_qhPKoAfTjqThvyh-MAq8BDtatHg,2719
-smftools/informatics/bam_direct.py,sha256=2Y7C8N9QrgJyXqP3WEVZ7fi5qU-iNj_KN0ve-xvXD-U,2964
-smftools/informatics/basecalls_to_adata.py,sha256=krnf5fdOuXZmnwW-y_eDC5hEjODUUyMEoY5z6R-65UI,1905
-smftools/informatics/fast5_to_pod5.py,sha256=i2sPWME6p6jttG6WbcQFCzI22WVpwcXgZBG9RXqIlzU,717
-smftools/informatics/pod5_conversion.py,sha256=x_d55jk2vX5hiSWH6-W4oWdmI-uTce8iRhhBqSzYS_I,3073
-smftools/informatics/pod5_direct.py,sha256=aozZQdeYA5AFAEnku6un5gtGtZEdekk-6W7e7K_pBLw,3383
-smftools/informatics/pod5_to_adata.py,sha256=1lSr32fAKXkxU5nV3C0UBDW6i2FnSbD_aqlKG4Yn9RU,1763
-smftools/informatics/readwrite.py,sha256=DgVisHYdkjzaO7suPbUvluImeTc3jqGDlioNveHUxPc,4158
-smftools/informatics/subsample_pod5.py,sha256=6g8fV2K1YJFEDVHs_bTJDuOSsIkMWpw5Lvk9uittW9k,2188
-smftools/informatics/helpers/LoadExperimentConfig.py,sha256=gsWGoa9cydwY4Kd-hTXF2gtmxc8glRRD2V1JB88e9js,2822
-smftools/informatics/helpers/__init__.py,sha256=luoFmS4B3XnG68XVziqtmPEZy-X3228LEZzQaHX84Cc,1487
-smftools/informatics/helpers/align_and_sort_BAM.py,sha256=835lNQafsdY-PMQZAv3HgLcXNkeduZA4HUewXgGV87M,2447
-smftools/informatics/helpers/binarize_converted_base_identities.py,sha256=kAYtPwMY5-gUL2muXOcbSiowQ2Mkls90GXXFaCKG5Pk,1773
-smftools/informatics/helpers/canoncall.py,sha256=XaAM_Vd_Q3SQIIlb10-7z5Zo-YADnIcC4eMQjZt1H-E,961
-smftools/informatics/helpers/converted_BAM_to_adata.py,sha256=cD-4gnJqCULGexedtETo-NGz-uqq16HwK_9zgCM7w_8,9769
-smftools/informatics/helpers/count_aligned_reads.py,sha256=Jttzh94T2uALC-dCvjlq58tupj5VxuKj3j301ICj7eI,2058
-smftools/informatics/helpers/extract_base_identities.py,sha256=-iBSEgnsp3EESSOupGcDGObGWykxucD5YC7aW_pEJ2k,2733
-smftools/informatics/helpers/extract_mods.py,sha256=UBFjXDKz_A6ivjcocYT1_pKjvygY2Fdg0RjQmMS8UuA,2269
-smftools/informatics/helpers/find_conversion_sites.py,sha256=52RvFQkIBly-CqToFe2zaKkpsUSixe8rHxZfL32EygA,3570
-smftools/informatics/helpers/generate_converted_FASTA.py,sha256=fKmjpvBQF8fHljzcGtqUgMwdWIfnmwnhI-Y3A59_qDk,3939
-smftools/informatics/helpers/get_native_references.py,sha256=fRuyEm9UJkfd5DwHmFb1bxEtNvtSI1_BxGRmrCymGkw,981
-smftools/informatics/helpers/make_dirs.py,sha256=lWHXpwC76MFM5sSme9i_WeYUaxutzybendokhny03ds,537
-smftools/informatics/helpers/make_modbed.py,sha256=cOQ97gPfRiCcw_fqboxousXIiOYjp78IFYLbu749U1Y,939
-smftools/informatics/helpers/modQC.py,sha256=LeOBObG8gAVVdgESIMceYhd5AW1gfN7ABo91OQtOzTM,1041
-smftools/informatics/helpers/modcall.py,sha256=ZcBl3QK622gG1IFy6agOWVADvsjr7WZIcglhSmYl02E,1133
-smftools/informatics/helpers/modkit_extract_to_adata.py,sha256=KDnFSHH0PdaANH6uzcVpoii7s5u5gIfkSMgsQCiWORs,25279
-smftools/informatics/helpers/one_hot_encode.py,sha256=rNHAfLG8smkpSEDBYj73cVwCNNbFhVfMW4SB2ijydMk,577
-smftools/informatics/helpers/separate_bam_by_bc.py,sha256=mGiB6y4xs_WATf-VDyVz4tg6BG3I6ZzYcpuEjeA1oVo,1580
-smftools/informatics/helpers/split_and_index_BAM.py,sha256=p2qRV-bOXj1P0JcvBqmK3ihRyM7_bVnKCi3bog_2kR8,1143
-smftools/informatics/helpers/archived/informatics.py,sha256=gKb2ZJ_LcAeEXuQqn9e-QDF_sS4tMpMTr2vZlqa7n54,14572
-smftools/informatics/helpers/archived/load_adata.py,sha256=DhvYYqO9VLsZqhL1WjN9sd-e3fgvdXGlgTP18z1h0L0,33654
-smftools/plotting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-smftools/preprocessing/__init__.py,sha256=PoemcyddUsfRPtJ7Ggr5G69nTXIQCFmz6lctpoEXYUA,1153
-smftools/preprocessing/append_C_context.py,sha256=-4P3Dkq60QW57AB9NR6iRjmz-Dl27s2V-HqWWOTB21M,2485
-smftools/preprocessing/binarize_on_Youden.py,sha256=slkkt56DZ1FZWy8Un5mNJEZ49JlPnPKow2zU4GoHEr8,2303
-smftools/preprocessing/binary_layers_to_ohe.py,sha256=931eHuVda6pMZTvC7jVTKkY2a_KQWpSfgi-nkA5NmaI,1238
-smftools/preprocessing/calculate_complexity.py,sha256=nDdEzHaN7KBN7QfqaFgQoTBT_6cpOa44l8IDHwa76fs,3224
-smftools/preprocessing/calculate_converted_read_methylation_stats.py,sha256=FCDVLOxT8iHTBeG6EbEFt_S_mIQvYosEAb9-hbc8fhA,2720
-smftools/preprocessing/calculate_coverage.py,sha256=46-U7YW98uL3pEVnfhBueGZOnNr3a3rWr3mT7YToglM,2019
-smftools/preprocessing/calculate_pairwise_hamming_distances.py,sha256=EIcIOOw0tpECR9hfZeMNlq0J_L2-J-Jp5-RzVkoGO7o,951
-smftools/preprocessing/calculate_position_Youden.py,sha256=mfQ6nFfUaEaKg_icyHA1zZlhh0wHjpLE56BZDXOdP_4,6364
-smftools/preprocessing/calculate_read_length_stats.py,sha256=wIz-EtOz7S_RDSqAAv7SoiTIQq9Ovkfs4dE4BdHXyNo,1793
-smftools/preprocessing/clean_NaN.py,sha256=nnm_zCEGilgDGvxxPBP81sYHJ9LrZ2MVvI1ydf0iPxk,1160
-smftools/preprocessing/filter_converted_reads_on_methylation.py,sha256=3BwBWyPnVuOH46J2mgafRXcNzWYRxc4sr7nKTInLyfU,1242
-smftools/preprocessing/filter_reads_on_length.py,sha256=LfGz0h3Xf8XUxv3ifXLbfeAOzSYYZVUJcHy73ykUu3A,2135
-smftools/preprocessing/invert_adata.py,sha256=6ab7WjUjGUYd2uqXV93k1B4U6laxSwlWSgaR0Lg7apc,655
-smftools/preprocessing/mark_duplicates.py,sha256=nKbdUEikJFekWuJ259J4XBPE5elcp44VkyY14jLLZEk,7167
-smftools/preprocessing/min_non_diagonal.py,sha256=hx1asW8CEmLaIroZISW8EcAf_RnBEC_nofGD8QG0b1E,711
-smftools/preprocessing/remove_duplicates.py,sha256=W0QQ5LLmIGj8OTfXuiTLJjFhOjv5r-TTipTupq-nf50,432
-smftools/preprocessing/archives/preprocessing.py,sha256=4mLT09A7vwRZ78FHmuwtv38mH9TQ9qrZc_WjHRhhkIw,34379
-smftools/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-smftools-0.1.1.dist-info/METADATA,sha256=8iWTWzl1ZIZvpYRbp6ov1NizrUJMwBbWNCs31QV3LjY,6262
-smftools-0.1.1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-smftools-0.1.1.dist-info/licenses/LICENSE,sha256=F8LwmL6vMPddaCt1z1S83Kh_OZv50alTlY7BvVx1RXw,1066
-smftools-0.1.1.dist-info/RECORD,,