smftools 0.1.0__py3-none-any.whl → 0.1.3__py3-none-any.whl

smftools-0.1.3.dist-info/RECORD

@@ -0,0 +1,84 @@
+smftools/__init__.py,sha256=zy4ckT7hKrLrlm6NiZQoupvc6oSN7wJsyOBCYdzukcQ,401
+smftools/_settings.py,sha256=Ed8lzKUA5ncq5ZRfSp0t6_rphEEjMxts6guttwTZP5Y,409
+smftools/_version.py,sha256=R5TtpJu7Qu6sOarfDpp-5Oyy8Pi2Ir3VewCvsCQiAgo,21
+smftools/readwrite.py,sha256=DgVisHYdkjzaO7suPbUvluImeTc3jqGDlioNveHUxPc,4158
+smftools/datasets/F1_hybrid_NKG2A_enhander_promoter_GpC_conversion_SMF.h5ad.gz,sha256=q6wJtgFRDln0o20XNCx1qad3lwcdCoylqPN7wskTfI8,2926497
+smftools/datasets/F1_sample_sheet.csv,sha256=9PodIIOXK2eamYPbC6DGnXdzgi9bRDovf296j1aM0ak,259
+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=0y597Ntp707bOgDwN6O-JEt9yxgplj66p0aj6Zs_IB4,779
+smftools/informatics/__init__.py,sha256=WQiMBr1yjDrlmHg8UNgW2MJsq4fPrVfh-UBr5tYI9x4,326
+smftools/informatics/conversion_smf.py,sha256=PS-TjgMttr3VRrT0zg5L_L01xMOewB_OXSsQyoM7DWI,4333
+smftools/informatics/direct_smf.py,sha256=ue7p7deuRwaZtEh9EFV1YTE8HKRAmOsx9oaRJdjCrbY,4697
+smftools/informatics/fast5_to_pod5.py,sha256=xfdZU3QluaAcR-q2uBRz8hcBwYt73nCnrFeahvi0OKQ,704
+smftools/informatics/load_adata.py,sha256=i-2YCSaeLzbPfNtKPrLwfkv-9u_TrTAZrbtNAj3FRWY,7271
+smftools/informatics/readwrite.py,sha256=DgVisHYdkjzaO7suPbUvluImeTc3jqGDlioNveHUxPc,4158
+smftools/informatics/subsample_fasta_from_bed.py,sha256=YqYV09rvEQdeiS5hTTrKa8xYmJfeM3Vk-UUqwpw0qBk,1983
+smftools/informatics/subsample_pod5.py,sha256=zDw9tRcrFRmPI62xkcy9dh8IfsJcuYm7R-FVeBC_g3s,4701
+smftools/informatics/archived/bam_conversion.py,sha256=I8EzXjQixMmqx2oWnoNSH5NURBhfT-krbWHkoi_M964,3330
+smftools/informatics/archived/bam_direct.py,sha256=jbEFtUIiUR8Wlp3po_sWkr19AUNS9WZjglojb9j28vo,3606
+smftools/informatics/archived/basecalls_to_adata.py,sha256=-Nag6lr_NAtU4t8jo0GSMdgIAIfmDge-5VEUPQbEatE,3692
+smftools/informatics/helpers/LoadExperimentConfig.py,sha256=gsWGoa9cydwY4Kd-hTXF2gtmxc8glRRD2V1JB88e9js,2822
+smftools/informatics/helpers/__init__.py,sha256=KrfyM08_RgDf3Ajvb4KNTvcOqZiWYSIVhEznCr01Gcc,2255
+smftools/informatics/helpers/align_and_sort_BAM.py,sha256=DouG6nGWXtz2ulZD5p0sEShE-4dbPudHaWcHFm4-oJA,2184
+smftools/informatics/helpers/aligned_BAM_to_bed.py,sha256=eYkGQFSM2gPEauASkY_-9Yvy6727vP8Q4wx_st85Dpc,2638
+smftools/informatics/helpers/bed_to_bigwig.py,sha256=AazYEZzKgKgukSFwCpeiApzxh1kbt11X4RFqRIiBIaY,1466
+smftools/informatics/helpers/binarize_converted_base_identities.py,sha256=iJlDah-YJ0zx0UrlHdtgvrALVNSA0TTTdDoKmNCVg0Q,1846
+smftools/informatics/helpers/canoncall.py,sha256=M7HEqhYsWMUB0tLP3hzMM0L7PhcOTXgetl5lV3GgIaw,1062
+smftools/informatics/helpers/complement_base_list.py,sha256=k6EkLtxFoajaIufxw1p0pShJ2nPHyGLTbzZmIFFjB4o,532
+smftools/informatics/helpers/concatenate_fastqs_to_bam.py,sha256=RXPn7e6Dcwol9tnUsfXJu3EuZcMSOJJo5LNWouovvZs,2715
+smftools/informatics/helpers/converted_BAM_to_adata.py,sha256=Rsnydzpf9lMS3TQjXpbXJSSfCzhVTPn3rBDLiK-8utA,13991
+smftools/informatics/helpers/count_aligned_reads.py,sha256=uYyUYglF1asiaoxr-LKxPMUEbfyD7FS-dumTg2hJHzQ,2170
+smftools/informatics/helpers/extract_base_identities.py,sha256=E-_m9W82N52NjX5kz9Af5YH0S2k58hnq9KTrm4S5vgM,4370
+smftools/informatics/helpers/extract_mods.py,sha256=UBFjXDKz_A6ivjcocYT1_pKjvygY2Fdg0RjQmMS8UuA,2269
+smftools/informatics/helpers/extract_readnames_from_BAM.py,sha256=3FxSNqbZ1VsOK2RfHrvevQTzhWATf5E8bZ5yVOqayvk,759
+smftools/informatics/helpers/find_conversion_sites.py,sha256=5AghDQzEoSvE2Og98VsKoeWUFSLnIGY1LnRu1BtQavM,3700
+smftools/informatics/helpers/generate_converted_FASTA.py,sha256=ueaAsFnBuc7zKwkBivBR3DJg4DtkxkHHIQcVVSWzv-w,5161
+smftools/informatics/helpers/get_chromosome_lengths.py,sha256=sLumLrGsU_Xg_oJcdOpQyjUGpJoT2HbcmxWwbwzXUlE,1036
+smftools/informatics/helpers/get_native_references.py,sha256=fRuyEm9UJkfd5DwHmFb1bxEtNvtSI1_BxGRmrCymGkw,981
+smftools/informatics/helpers/index_fasta.py,sha256=N3IErfSiavYldeaat8xcQgA1MpykoQHcE0gHUeWuClE,267
+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=9PH7Peq4y-VBqQcMkbv0TwgePBlD5aM4_FmI7H4hbQQ,1142
+smftools/informatics/helpers/modkit_extract_to_adata.py,sha256=duPlRAIz4VWM-jm9iaLY7N6JHQcun_L0nhr2VyUjNTI,38184
+smftools/informatics/helpers/ohe_batching.py,sha256=_Mz2p1We5PVIb8S6Hbq_hREKJ9mGQiADwfFK_NgMGhA,1909
+smftools/informatics/helpers/one_hot_encode.py,sha256=hpZAuwa9ndkhyCm9sO65KVHE0lbFDKqRylfliEKyD4o,632
+smftools/informatics/helpers/plot_read_length_and_coverage_histograms.py,sha256=tAnXFleGzXJNjHRAgZ0NUJuZ0P3aKmUYIrK-V9VoJKY,1860
+smftools/informatics/helpers/separate_bam_by_bc.py,sha256=Fsi8OEmv5Ny13cWoHVV9JmEjVFEXT_ZxbBOlRdmyPbE,1742
+smftools/informatics/helpers/split_and_index_BAM.py,sha256=_TFJ8fcLbIf37JG83hSc1zgs1yxX70-NhA8y-PbhTpo,1966
+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=5FQNrj51KmaDLeAGGBA8iWMkYiSOe7O91ES8mT4aVtE,1399
+smftools/preprocessing/append_C_context.py,sha256=pP5u9o5U4JmHras0PK6yas65u4-U5KlX3sKLb-duo80,3728
+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=ut60et8bmIswtiLhctJWHNseIV4ZRQultYdtJPHcRPs,3224
+smftools/preprocessing/calculate_consensus.py,sha256=6zRpRmb2xdfDu5hctZrReALRb7Pjn8sy8xJZTm3o0nU,2442
+smftools/preprocessing/calculate_converted_read_methylation_stats.py,sha256=Si0DcES0lLMvg3XgdKpedxfPnXQ14tEFKrOAFRn3fHs,6059
+smftools/preprocessing/calculate_coverage.py,sha256=ZgRxQGpydxQg1exkvSiy8nHmzDIPGGqL5vL9XQ2PZQ4,2068
+smftools/preprocessing/calculate_pairwise_hamming_distances.py,sha256=e5Mzyex7pT29H2PY014uU4Fi_eewbut1JkzC1ffBbCg,961
+smftools/preprocessing/calculate_position_Youden.py,sha256=mfQ6nFfUaEaKg_icyHA1zZlhh0wHjpLE56BZDXOdP_4,6364
+smftools/preprocessing/calculate_read_length_stats.py,sha256=6m362JaCKlD0QoBUMnM2qsB6Jo_4shl7xFzqU1uZccU,4945
+smftools/preprocessing/clean_NaN.py,sha256=1vieT026p0gDJCbqB_CiLvAGGxlc-5xufoKJgZuBFFk,1150
+smftools/preprocessing/filter_converted_reads_on_methylation.py,sha256=SN5q0rqYtYW9j3i0sVSyTv9EmR_uLKI7GkjmJixeOU0,1307
+smftools/preprocessing/filter_reads_on_length.py,sha256=sAT66bjuI8ZtXyQc9SuPzq1dPIB1CNVx6VfWqVng4Dg,2191
+smftools/preprocessing/invert_adata.py,sha256=u6Y70EH0B5mXb9-HuukIlzpMgZ6rhzcJuy3YZZTx3SA,684
+smftools/preprocessing/load_sample_sheet.py,sha256=uGjzG9x-1t_1lCooH85P8Tfg80GdvVx8Jv1LPl9XNFM,915
+smftools/preprocessing/make_dirs.py,sha256=lWHXpwC76MFM5sSme9i_WeYUaxutzybendokhny03ds,537
+smftools/preprocessing/mark_duplicates.py,sha256=sQuPcTw8JsQoONOk-kMlAF965sIk2Pu-M7rIyfbyGGs,8145
+smftools/preprocessing/min_non_diagonal.py,sha256=hx1asW8CEmLaIroZISW8EcAf_RnBEC_nofGD8QG0b1E,711
+smftools/preprocessing/recipes.py,sha256=KzSw5JW0WJGzSis5Fm7moQY5PxOYl6-uYYf1NDj6nOE,7117
+smftools/preprocessing/remove_duplicates.py,sha256=Erooi5_1VOUNfWpzddzmMNYMCl1U1jJryt7ZtMhabAs,699
+smftools/preprocessing/archives/preprocessing.py,sha256=4mLT09A7vwRZ78FHmuwtv38mH9TQ9qrZc_WjHRhhkIw,34379
+smftools/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+smftools/tools/apply_HMM.py,sha256=AuVtOki69-Xs4mhjhTXJzd49KCVXwixFyWSUgDjtR6s,11
+smftools/tools/cluster.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+smftools/tools/read_HMM.py,sha256=N0MGG494VjlxYJcCVz1jN4OasGtRITZS98SJ2xB_j8k,10
+smftools/tools/subset_adata.py,sha256=qyU9iCal03edb5aUS3AZ2U4TlL3uQ42jGI9hX3QF7Fc,1047
+smftools/tools/train_HMM.py,sha256=x5ZcXj-heWQqDOX86nuuDoj1tPkYKl04fYA1fCKNQ0c,1380
+smftools-0.1.3.dist-info/METADATA,sha256=u26Og8tpAF2TgXZztotk3Q4EuP7Fvf73s1tlIjBDD-A,6410
+smftools-0.1.3.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+smftools-0.1.3.dist-info/licenses/LICENSE,sha256=F8LwmL6vMPddaCt1z1S83Kh_OZv50alTlY7BvVx1RXw,1066
+smftools-0.1.3.dist-info/RECORD,,

smftools/informatics/helpers/align_BAM.py

@@ -1,49 +0,0 @@
-## align_BAM
-import subprocess
-
-def align_BAM(fasta, bam, bam_suffix):
-    """
-    A wrapper for running dorado aligner and samtools functions
-    """
-    aligned_BAM=f"{bam}_aligned"
-    aligned_sorted_BAM=f"{aligned_BAM}_sorted"
-    output = bam + bam_suffix
-    aligned_output = aligned_BAM + bam_suffix
-    aligned_sorted_output = aligned_sorted_BAM + bam_suffix
-    
-    # Run dorado aligner
-    subprocess.run([
-        "dorado", "aligner",
-        "--secondary=no",
-        fasta,
-        output
-    ], stdout=open(aligned_output, "w"))
-
-    # Sort the BAM on positional coordinates
-    subprocess.run([
-        "samtools", "sort",
-        "-o", aligned_sorted_output,
-        aligned_output
-    ])
-
-    # Create a BAM index file
-    subprocess.run([
-        "samtools", "index",
-        aligned_sorted_output
-    ])
-
-    # Make a bed file of coordinates for the BAM
-    subprocess.run([
-        "samtools", "view",
-        aligned_sorted_output
-    ], stdout=subprocess.PIPE) | subprocess.run([
-        "awk", '{print $3, $4, $4+length($10)-1}'
-    ], stdin=subprocess.PIPE, stdout=open(f"{aligned_sorted_BAM}_bed.bed", "w"))
-
-    # Make a text file of reads for the BAM
-    subprocess.run([
-        "samtools", "view",
-        aligned_sorted_output
-    ], stdout=subprocess.PIPE) | subprocess.run([
-        "cut", "-f1"
-    ], stdin=subprocess.PIPE, stdout=open(f"aligned_sorted_BAM_read_names.txt", "w"))

smftools/informatics/helpers/load_experiment_config.py

@@ -1,17 +0,0 @@
-## load_experiment_config
-import csv
-
-def load_experiment_config(experiment_config):
-    """
-    Loads in the experiment configuration csv and saves global variables with experiment configuration parameters
-    """
-    with open(experiment_config, mode='r', encoding='utf-8-sig') as csvfile:
-        reader = csv.DictReader(csvfile)
-        for row in reader:
-            # Extract variable name and value from each row
-            var_name = row['variable']
-            value = row['value']
-
-            # Alternatively, set it directly in the globals() dictionary
-            globals()[var_name] = value
-

smftools/informatics/pod5_conversion.py

@@ -1,26 +0,0 @@
-## pod5_conversion
-from .helpers import align_BAM, canoncall, converted_BAM_to_adata, generate_converted_FASTA, split_and_index_BAM
-import subprocess
-
-def pod5_conversion(fasta, output_directory, conversion_types, strands, model, pod5_dir, split_dir, barcode_kit, mapping_threshold, experiment_name, bam_suffix):
-    """
-    Converts a POD5 file from a nanopore conversion SMF experiment to an adata object
-    """
-    bam=f"{output_directory}/HAC_basecalls"
-    aligned_BAM=f"{bam}_aligned"
-    aligned_sorted_BAM=f"{aligned_BAM}_sorted"
-    # 1) Convert FASTA file
-    converted_FASTA=fasta.split('.fa')[0]+'_converted.fasta'
-    generate_converted_FASTA(fasta, conversion_types, strands, converted_FASTA)
-
-    # 2) Basecall from the input POD5 to generate a singular output BAM
-    canoncall(model, pod5_dir, barcode_kit, bam, bam_suffix)
-
-    # 3) Align the BAM to the converted reference FASTA and sort the bam on positional coordinates. Also make an index and a bed file of mapped reads
-    align_BAM(converted_FASTA, bam, bam_suffix)
-
-    ### 4) Split the aligned and sorted BAM files by barcode (BC Tag) into the split_BAM directory###
-    split_and_index_BAM(aligned_sorted_BAM, split_dir, bam_suffix)
-
-    # 5) Take the converted BAM and load it into an adata object. 
-    converted_BAM_to_adata(converted_FASTA, split_dir, mapping_threshold, experiment_name, conversion_types, bam_suffix)

smftools/informatics/pod5_direct.py

@@ -1,29 +0,0 @@
-## pod5_direct
-from .helpers import align_BAM, extract_mods, make_modbed, modcall, modkit_extract_to_adata, modQC, split_and_index_BAM
-
-def pod5_direct(fasta, output_directory, mod_list, model, thresholds, pod5_dir, split_dir, barcode_kit, mapping_threshold, experiment_name, bam_suffix, batch_size):
-    """
-    
-    """
-    bam=f"{output_directory}/HAC_mod_calls"
-    aligned_BAM=f"{bam}_aligned"
-    aligned_sorted_BAM=f"{aligned_BAM}_sorted"
-    mod_bed_dir=f"{output_directory}/split_mod_beds"
-    mod_tsv_dir=f"{output_directory}/split_mod_tsvs"
-
-    aligned_sorted_output = aligned_sorted_BAM + bam_suffix
-    mod_map = {'6mA': '6mA', '5mC_5hmC': '5mC'}
-    mods = [mod_map[mod] for mod in mod_list]
-
-    # 1) Basecall using dorado
-    modcall(model, pod5_dir, barcode_kit, mod_list, bam, bam_suffix)
-    # 2) Align the BAM to the converted reference FASTA. Also make an index and a bed file of mapped reads
-    align_BAM(fasta, bam, bam_suffix)
-    # 3) Split the aligned and sorted BAM files by barcode (BC Tag) into the split_BAM directory
-    split_and_index_BAM(aligned_sorted_BAM, split_dir, bam_suffix)
-    # 4) Using nanopore modkit to work with modified BAM files ###
-    modQC(aligned_sorted_output, thresholds) # get QC metrics for mod calls
-    make_modbed(aligned_sorted_output, thresholds, mod_bed_dir) # Generate bed files of position methylation summaries for every sample
-    extract_mods(thresholds, mod_tsv_dir, split_dir, bam_suffix) # Extract methylations calls for split BAM files into split TSV files
-    #5 Load the modification data from TSVs into an adata object
-    modkit_extract_to_adata(fasta, aligned_sorted_output, mapping_threshold, experiment_name, mods, batch_size)

smftools/informatics/pod5_to_adata.py

@@ -1,17 +0,0 @@
-## pod5_to_adata
-from .helpers import load_experiment_config
-from.pod5_direct import pod5_direct
-from.pod5_conversion import pod5_conversion
-
-def pod5_to_adata(config_path, ):
-    """
-    
-    """
-    # Load experiment config parameters into global variables
-    load_experiment_config(config_path)
-    if smf_modality == 'conversion':
-        (fasta, output_directory, conversion_types, strands, model, pod5_dir, split_dir, barcode_kit, mapping_threshold, experiment_name, bam_suffix)
-    elif smf_modality == 'direct':
-        pod5_direct(fasta, output_directory, mod_list, model, thresholds, pod5_dir, split_dir, barcode_kit, mapping_threshold, experiment_name, bam_suffix, batch_size)
-    else:
-        print("Error")

smftools-0.1.0.dist-info/METADATA

@@ -1,75 +0,0 @@
-Metadata-Version: 2.3
-Name: smftools
-Version: 0.1.0
-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: 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: tqdm
-Provides-Extra: base-tests
-Requires-Dist: pytest; extra == 'base-tests'
-Requires-Dist: pytest-cov; extra == 'base-tests'
-Provides-Extra: doc
-Requires-Dist: ipython>=7.20; extra == 'doc'
-Requires-Dist: matplotlib!=3.6.1; extra == 'doc'
-Requires-Dist: myst-nb>=1; extra == 'doc'
-Requires-Dist: myst-parser>=2; extra == 'doc'
-Requires-Dist: nbsphinx>=0.9; extra == 'doc'
-Requires-Dist: readthedocs-sphinx-search; extra == 'doc'
-Requires-Dist: setuptools; extra == 'doc'
-Requires-Dist: sphinx-autodoc-typehints>=1.25.2; extra == 'doc'
-Requires-Dist: sphinx-book-theme>=1.1.0; extra == 'doc'
-Requires-Dist: sphinx-copybutton; extra == 'doc'
-Requires-Dist: sphinx-design; extra == 'doc'
-Requires-Dist: sphinx>=7; extra == 'doc'
-Requires-Dist: sphinxcontrib-bibtex; extra == 'doc'
-Requires-Dist: sphinxext-opengraph; extra == 'doc'
-Provides-Extra: torch
-Requires-Dist: pomeganate>=1.0.0; extra == 'torch'
-Requires-Dist: torch>=1.9.0; extra == 'torch'
-Provides-Extra: torch-tests
-Requires-Dist: pomeganate>=1.0.0; extra == 'torch-tests'
-Requires-Dist: pytest; extra == 'torch-tests'
-Requires-Dist: pytest-cov; extra == 'torch-tests'
-Requires-Dist: torch>=1.9.0; extra == 'torch-tests'
-Description-Content-Type: text/markdown
-
-# smftools
-A tool for processing raw sequencing data for single molecule footprinting experiments at single genomic loci.
-
-## Dependencies
-The following tools need to be installed and configured:
-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

smftools-0.1.0.dist-info/RECORD

@@ -1,58 +0,0 @@
-smftools/__init__.py,sha256=pWcysCXCokCdW4YySaA8BMumZkE56m15otMPG88nQGc,444
-smftools/_settings.py,sha256=a1uYWNBNtQb30cGSdpjeiIMnQV1Fip7IZAQrNzjXR5w,324
-smftools/readwrite.py,sha256=p-K_RYOrM0vDawBTcuCUyuwVzmYwJqNMvhv9fCTLDKE,4159
-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=rAcp7_Raa8Uv95DISj-oACY1fE_5fIfb5Poj-9WVOWo,473
-smftools/informatics/__init__.py,sha256=Bjufdncl978d-tNriuRHX92mjeAO5axjTlZP7iePjms,235
-smftools/informatics/pod5_conversion.py,sha256=m_qNRSNeUndl5KO8PJPMLCOWqcVq-TJSvoyUnJW-UHE,1399
-smftools/informatics/pod5_direct.py,sha256=MGQkpHI2qQuEO0IDFOiXjL0Pq59oC1DwUaIWH7jTHiU,1707
-smftools/informatics/pod5_to_adata.py,sha256=R31bkGbparRGpYpTZ69znQThK1xCGChlf4oP836IC9Y,722
-smftools/informatics/readwrite.py,sha256=p-K_RYOrM0vDawBTcuCUyuwVzmYwJqNMvhv9fCTLDKE,4159
-smftools/informatics/helpers/__init__.py,sha256=ws8Zyxin68L7G5R9Rna_qoBnkSNOaD1ndlcrooV2d-k,1466
-smftools/informatics/helpers/align_BAM.py,sha256=vZpkbI-mUqd6qJaovRhuNM03s816fjd5hNEcfA0oHxo,1414
-smftools/informatics/helpers/binarize_converted_base_identities.py,sha256=rTdk06BmU_bvuE1NOU1LGSQs9ytkl7vQjZcwMbA5Yx0,1409
-smftools/informatics/helpers/canoncall.py,sha256=Ujz0Pkp_wW-XJyb3uB2fzVpB12c2MCOWVTg_uIOQL8c,397
-smftools/informatics/helpers/converted_BAM_to_adata.py,sha256=7tntnkTZpNqS0WTMbO42ksxXqzk9NFpXK0q6uWSqtkM,8593
-smftools/informatics/helpers/count_aligned_reads.py,sha256=Q9iU0zwwNZRn0oOxRl_x5OAF7YgaRkSpQBojaBccQsI,1814
-smftools/informatics/helpers/extract_base_identities.py,sha256=nrQy8cUyOA2C8cKKL6SpZ97U0ZGhChw8Qdk0BwuxIT4,2406
-smftools/informatics/helpers/extract_mods.py,sha256=IQdpQxh_2NStKK4kIVKa8UAcV-fVJSs_bzB3JLe0Jx4,1602
-smftools/informatics/helpers/find_conversion_sites.py,sha256=aer63p2JHqaoB3wSK9xqpSjow7w7UyrMSJ06aKTQSiQ,3208
-smftools/informatics/helpers/generate_converted_FASTA.py,sha256=xHjspkeCiSKjqb6zUrjCG13OKW597LJ4_w33tg-wFok,3006
-smftools/informatics/helpers/get_native_references.py,sha256=wx_RXnPwj0NGp7Tx1_hXyO8ZzQJHZwa0b3a6r3266FY,976
-smftools/informatics/helpers/informatics.py,sha256=gKb2ZJ_LcAeEXuQqn9e-QDF_sS4tMpMTr2vZlqa7n54,14572
-smftools/informatics/helpers/load_adata.py,sha256=DhvYYqO9VLsZqhL1WjN9sd-e3fgvdXGlgTP18z1h0L0,33654
-smftools/informatics/helpers/load_experiment_config.py,sha256=boF524jZZKzBjc2yvAiMYvhM4OW_efXSbwU-nINKDdg,607
-smftools/informatics/helpers/make_dirs.py,sha256=UxghbuquyXgDD-H24Ghf1B7Kfpdt04NgMs8GE6zSJ3U,475
-smftools/informatics/helpers/make_modbed.py,sha256=m1lQUbw0W63YjiM_Tmy6QOL3GkHgvSuCrkX2Bo8sCco,741
-smftools/informatics/helpers/modQC.py,sha256=C-WVaoLN7Dxh--JcWa4UXzhwFpf0AXrFA99IsxfVXwo,770
-smftools/informatics/helpers/modcall.py,sha256=f41SkaXi2fYgv7B0oAFwj-9CZ0XVhvzWHfe977rT0wQ,493
-smftools/informatics/helpers/modkit_extract_to_adata.py,sha256=TvIHDXWTO2QxArGyIU3w-dQBVyq0rQ1A4iMvV9Rb_7A,24407
-smftools/informatics/helpers/one_hot_encode.py,sha256=jxfTNREED0YhdvwhVmRrt2BZUfiOrOUURVSOVtGypns,439
-smftools/informatics/helpers/separate_bam_by_bc.py,sha256=AFT-v0XXuW2rRYG6FC-8gulhAA6a4YGAa0UEuMDlimc,1235
-smftools/informatics/helpers/split_and_index_BAM.py,sha256=HqPAy5YxK0jokCWCUlUIWSLf2n-Gubkge-xxYfX4XLE,755
-smftools/plotting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-smftools/preprocessing/__init__.py,sha256=ngs4XYcd9gSXwSa-gi1pWMblCRJ_uZo5MMkg5vuhDOU,1438
-smftools/preprocessing/append_C_context.py,sha256=sfHiV3gBOum3KyZ6wFOCUcDUieW9rra3hKFkWEb8wmk,2063
-smftools/preprocessing/binarize_on_Youden.py,sha256=CO0KnxxHmCwq7tlrBh7BuY0_6SEacR7NwRhkwaWoVUg,2056
-smftools/preprocessing/binary_layers_to_ohe.py,sha256=zahq1YcgAeva-b1CcEVaBK4XaNmMgE6IpfiedYepI5k,876
-smftools/preprocessing/calculate_complexity.py,sha256=H4j0mCWL-jFWZ8UoTGa5lNEcqByfwIDtlsJrpNRNkg4,2751
-smftools/preprocessing/calculate_converted_read_methylation_stats.py,sha256=ZIOKGkbWI15RzpnfgWU4MUXFz3LlUjL_yjodGrye8-A,2626
-smftools/preprocessing/calculate_coverage.py,sha256=Q-RjTqbYt9jc-Axk807_h0m7_oDFdewrO805FQARLUA,1852
-smftools/preprocessing/calculate_pairwise_hamming_distances.py,sha256=l0IYlWu9RCDq4R2pJm_qGXN_RyFkIuah9fFLvg1Hti0,843
-smftools/preprocessing/calculate_position_Youden.py,sha256=FUSsrhp8L8TLoJaX2cSl8u1phNbYpTRJfVqsrwMOWgY,6008
-smftools/preprocessing/calculate_read_length_stats.py,sha256=kKcEw4zS-GnJ2nyC5c24YVMY2oBmxmcxjPWLGnrkwws,1711
-smftools/preprocessing/clean_NaN.py,sha256=HCRX_nA6H3o7CysCa6yxN07xQEoh6LvdkX7aAYqSKR8,1024
-smftools/preprocessing/filter_converted_reads_on_methylation.py,sha256=krqDb6TNjQx4IICXbEQ8SDcaSjrWZ-9ChtaEiIxU5KY,962
-smftools/preprocessing/filter_reads_on_length.py,sha256=-tXMIpg8Mx8GskCfjBy0ZBczuJRTZdyuSZtDyb6KDJs,1737
-smftools/preprocessing/invert_adata.py,sha256=vpR0jynLODhE8mpiHZQIv1XUY9pd7cEG0ujC-GArXIE,616
-smftools/preprocessing/mark_duplicates.py,sha256=Qd1fluCHkL7ZAY37wGmBe40HwkRipOkbDAp6lnoLU9I,6818
-smftools/preprocessing/min_non_diagonal.py,sha256=o79E5xy-aO-cSwN5dUVi5oj8_EfQBDPcj1D0_7fvk1Q,644
-smftools/preprocessing/preprocessing.py,sha256=4mLT09A7vwRZ78FHmuwtv38mH9TQ9qrZc_WjHRhhkIw,34379
-smftools/preprocessing/remove_duplicates.py,sha256=sgdRjZSLakocTRwAukdp1RpFhODbeOjNN_EWZkTshAc,395
-smftools/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-smftools-0.1.0.dist-info/METADATA,sha256=Loh3iFQgPLn6Xe_WdbeATlGiMqggFaYJOqgwf5e8WRI,3422
-smftools-0.1.0.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-smftools-0.1.0.dist-info/licenses/LICENSE,sha256=F8LwmL6vMPddaCt1z1S83Kh_OZv50alTlY7BvVx1RXw,1066
-smftools-0.1.0.dist-info/RECORD,,