smftools 0.1.6__py3-none-any.whl → 0.2.1__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (162) hide show
  1. smftools/__init__.py +34 -0
  2. smftools/_settings.py +20 -0
  3. smftools/_version.py +1 -0
  4. smftools/cli.py +184 -0
  5. smftools/config/__init__.py +1 -0
  6. smftools/config/conversion.yaml +33 -0
  7. smftools/config/deaminase.yaml +56 -0
  8. smftools/config/default.yaml +253 -0
  9. smftools/config/direct.yaml +17 -0
  10. smftools/config/experiment_config.py +1191 -0
  11. smftools/datasets/F1_hybrid_NKG2A_enhander_promoter_GpC_conversion_SMF.h5ad.gz +0 -0
  12. smftools/datasets/F1_sample_sheet.csv +5 -0
  13. smftools/datasets/__init__.py +9 -0
  14. smftools/datasets/dCas9_m6A_invitro_kinetics.h5ad.gz +0 -0
  15. smftools/datasets/datasets.py +28 -0
  16. smftools/hmm/HMM.py +1576 -0
  17. smftools/hmm/__init__.py +20 -0
  18. smftools/hmm/apply_hmm_batched.py +242 -0
  19. smftools/hmm/calculate_distances.py +18 -0
  20. smftools/hmm/call_hmm_peaks.py +106 -0
  21. smftools/hmm/display_hmm.py +18 -0
  22. smftools/hmm/hmm_readwrite.py +16 -0
  23. smftools/hmm/nucleosome_hmm_refinement.py +104 -0
  24. smftools/hmm/train_hmm.py +78 -0
  25. smftools/informatics/__init__.py +14 -0
  26. smftools/informatics/archived/bam_conversion.py +59 -0
  27. smftools/informatics/archived/bam_direct.py +63 -0
  28. smftools/informatics/archived/basecalls_to_adata.py +71 -0
  29. smftools/informatics/archived/conversion_smf.py +132 -0
  30. smftools/informatics/archived/deaminase_smf.py +132 -0
  31. smftools/informatics/archived/direct_smf.py +137 -0
  32. smftools/informatics/archived/print_bam_query_seq.py +29 -0
  33. smftools/informatics/basecall_pod5s.py +80 -0
  34. smftools/informatics/fast5_to_pod5.py +24 -0
  35. smftools/informatics/helpers/__init__.py +73 -0
  36. smftools/informatics/helpers/align_and_sort_BAM.py +86 -0
  37. smftools/informatics/helpers/aligned_BAM_to_bed.py +85 -0
  38. smftools/informatics/helpers/archived/informatics.py +260 -0
  39. smftools/informatics/helpers/archived/load_adata.py +516 -0
  40. smftools/informatics/helpers/bam_qc.py +66 -0
  41. smftools/informatics/helpers/bed_to_bigwig.py +39 -0
  42. smftools/informatics/helpers/binarize_converted_base_identities.py +172 -0
  43. smftools/informatics/helpers/canoncall.py +34 -0
  44. smftools/informatics/helpers/complement_base_list.py +21 -0
  45. smftools/informatics/helpers/concatenate_fastqs_to_bam.py +378 -0
  46. smftools/informatics/helpers/converted_BAM_to_adata.py +245 -0
  47. smftools/informatics/helpers/converted_BAM_to_adata_II.py +505 -0
  48. smftools/informatics/helpers/count_aligned_reads.py +43 -0
  49. smftools/informatics/helpers/demux_and_index_BAM.py +52 -0
  50. smftools/informatics/helpers/discover_input_files.py +100 -0
  51. smftools/informatics/helpers/extract_base_identities.py +70 -0
  52. smftools/informatics/helpers/extract_mods.py +83 -0
  53. smftools/informatics/helpers/extract_read_features_from_bam.py +33 -0
  54. smftools/informatics/helpers/extract_read_lengths_from_bed.py +25 -0
  55. smftools/informatics/helpers/extract_readnames_from_BAM.py +22 -0
  56. smftools/informatics/helpers/find_conversion_sites.py +51 -0
  57. smftools/informatics/helpers/generate_converted_FASTA.py +99 -0
  58. smftools/informatics/helpers/get_chromosome_lengths.py +32 -0
  59. smftools/informatics/helpers/get_native_references.py +28 -0
  60. smftools/informatics/helpers/index_fasta.py +12 -0
  61. smftools/informatics/helpers/make_dirs.py +21 -0
  62. smftools/informatics/helpers/make_modbed.py +27 -0
  63. smftools/informatics/helpers/modQC.py +27 -0
  64. smftools/informatics/helpers/modcall.py +36 -0
  65. smftools/informatics/helpers/modkit_extract_to_adata.py +887 -0
  66. smftools/informatics/helpers/ohe_batching.py +76 -0
  67. smftools/informatics/helpers/ohe_layers_decode.py +32 -0
  68. smftools/informatics/helpers/one_hot_decode.py +27 -0
  69. smftools/informatics/helpers/one_hot_encode.py +57 -0
  70. smftools/informatics/helpers/plot_bed_histograms.py +269 -0
  71. smftools/informatics/helpers/run_multiqc.py +28 -0
  72. smftools/informatics/helpers/separate_bam_by_bc.py +43 -0
  73. smftools/informatics/helpers/split_and_index_BAM.py +32 -0
  74. smftools/informatics/readwrite.py +106 -0
  75. smftools/informatics/subsample_fasta_from_bed.py +47 -0
  76. smftools/informatics/subsample_pod5.py +104 -0
  77. smftools/load_adata.py +1346 -0
  78. smftools/machine_learning/__init__.py +12 -0
  79. smftools/machine_learning/data/__init__.py +2 -0
  80. smftools/machine_learning/data/anndata_data_module.py +234 -0
  81. smftools/machine_learning/data/preprocessing.py +6 -0
  82. smftools/machine_learning/evaluation/__init__.py +2 -0
  83. smftools/machine_learning/evaluation/eval_utils.py +31 -0
  84. smftools/machine_learning/evaluation/evaluators.py +223 -0
  85. smftools/machine_learning/inference/__init__.py +3 -0
  86. smftools/machine_learning/inference/inference_utils.py +27 -0
  87. smftools/machine_learning/inference/lightning_inference.py +68 -0
  88. smftools/machine_learning/inference/sklearn_inference.py +55 -0
  89. smftools/machine_learning/inference/sliding_window_inference.py +114 -0
  90. smftools/machine_learning/models/__init__.py +9 -0
  91. smftools/machine_learning/models/base.py +295 -0
  92. smftools/machine_learning/models/cnn.py +138 -0
  93. smftools/machine_learning/models/lightning_base.py +345 -0
  94. smftools/machine_learning/models/mlp.py +26 -0
  95. smftools/machine_learning/models/positional.py +18 -0
  96. smftools/machine_learning/models/rnn.py +17 -0
  97. smftools/machine_learning/models/sklearn_models.py +273 -0
  98. smftools/machine_learning/models/transformer.py +303 -0
  99. smftools/machine_learning/models/wrappers.py +20 -0
  100. smftools/machine_learning/training/__init__.py +2 -0
  101. smftools/machine_learning/training/train_lightning_model.py +135 -0
  102. smftools/machine_learning/training/train_sklearn_model.py +114 -0
  103. smftools/machine_learning/utils/__init__.py +2 -0
  104. smftools/machine_learning/utils/device.py +10 -0
  105. smftools/machine_learning/utils/grl.py +14 -0
  106. smftools/plotting/__init__.py +18 -0
  107. smftools/plotting/autocorrelation_plotting.py +611 -0
  108. smftools/plotting/classifiers.py +355 -0
  109. smftools/plotting/general_plotting.py +682 -0
  110. smftools/plotting/hmm_plotting.py +260 -0
  111. smftools/plotting/position_stats.py +462 -0
  112. smftools/plotting/qc_plotting.py +270 -0
  113. smftools/preprocessing/__init__.py +38 -0
  114. smftools/preprocessing/add_read_length_and_mapping_qc.py +129 -0
  115. smftools/preprocessing/append_base_context.py +122 -0
  116. smftools/preprocessing/append_binary_layer_by_base_context.py +143 -0
  117. smftools/preprocessing/archives/mark_duplicates.py +146 -0
  118. smftools/preprocessing/archives/preprocessing.py +614 -0
  119. smftools/preprocessing/archives/remove_duplicates.py +21 -0
  120. smftools/preprocessing/binarize_on_Youden.py +45 -0
  121. smftools/preprocessing/binary_layers_to_ohe.py +40 -0
  122. smftools/preprocessing/calculate_complexity.py +72 -0
  123. smftools/preprocessing/calculate_complexity_II.py +248 -0
  124. smftools/preprocessing/calculate_consensus.py +47 -0
  125. smftools/preprocessing/calculate_coverage.py +51 -0
  126. smftools/preprocessing/calculate_pairwise_differences.py +49 -0
  127. smftools/preprocessing/calculate_pairwise_hamming_distances.py +27 -0
  128. smftools/preprocessing/calculate_position_Youden.py +115 -0
  129. smftools/preprocessing/calculate_read_length_stats.py +79 -0
  130. smftools/preprocessing/calculate_read_modification_stats.py +101 -0
  131. smftools/preprocessing/clean_NaN.py +62 -0
  132. smftools/preprocessing/filter_adata_by_nan_proportion.py +31 -0
  133. smftools/preprocessing/filter_reads_on_length_quality_mapping.py +158 -0
  134. smftools/preprocessing/filter_reads_on_modification_thresholds.py +352 -0
  135. smftools/preprocessing/flag_duplicate_reads.py +1351 -0
  136. smftools/preprocessing/invert_adata.py +37 -0
  137. smftools/preprocessing/load_sample_sheet.py +53 -0
  138. smftools/preprocessing/make_dirs.py +21 -0
  139. smftools/preprocessing/min_non_diagonal.py +25 -0
  140. smftools/preprocessing/recipes.py +127 -0
  141. smftools/preprocessing/subsample_adata.py +58 -0
  142. smftools/readwrite.py +1004 -0
  143. smftools/tools/__init__.py +20 -0
  144. smftools/tools/archived/apply_hmm.py +202 -0
  145. smftools/tools/archived/classifiers.py +787 -0
  146. smftools/tools/archived/classify_methylated_features.py +66 -0
  147. smftools/tools/archived/classify_non_methylated_features.py +75 -0
  148. smftools/tools/archived/subset_adata_v1.py +32 -0
  149. smftools/tools/archived/subset_adata_v2.py +46 -0
  150. smftools/tools/calculate_umap.py +62 -0
  151. smftools/tools/cluster_adata_on_methylation.py +105 -0
  152. smftools/tools/general_tools.py +69 -0
  153. smftools/tools/position_stats.py +601 -0
  154. smftools/tools/read_stats.py +184 -0
  155. smftools/tools/spatial_autocorrelation.py +562 -0
  156. smftools/tools/subset_adata.py +28 -0
  157. {smftools-0.1.6.dist-info → smftools-0.2.1.dist-info}/METADATA +9 -2
  158. smftools-0.2.1.dist-info/RECORD +161 -0
  159. smftools-0.2.1.dist-info/entry_points.txt +2 -0
  160. smftools-0.1.6.dist-info/RECORD +0 -4
  161. {smftools-0.1.6.dist-info → smftools-0.2.1.dist-info}/WHEEL +0 -0
  162. {smftools-0.1.6.dist-info → smftools-0.2.1.dist-info}/licenses/LICENSE +0 -0
@@ -0,0 +1,5 @@
1
+ Sample,Sample_names,MTase,Time (min),Notes
2
+ barcode0001_sorted,Neither,M.CviPI,7.5,Cultured in IL2
3
+ barcode0002_sorted,BALBC,M.CviPI,7.5,Cultured in IL2
4
+ barcode0003_sorted,B6,M.CviPI,7.5,Cultured in IL2
5
+ barcode0004_sorted,Both,M.CviPI,7.5,Cultured in IL2
@@ -0,0 +1,9 @@
1
+ from .datasets import (
2
+ dCas9_kinetics,
3
+ Kissiov_and_McKenna_2025
4
+ )
5
+
6
+ __all__ = [
7
+ "dCas9_kinetics",
8
+ "Kissiov_and_McKenna_2025"
9
+ ]
@@ -0,0 +1,28 @@
1
+ ## datasets
2
+
3
+ def import_HERE():
4
+ """
5
+ Imports HERE for loading datasets
6
+ """
7
+ from pathlib import Path
8
+ from .._settings import settings
9
+ HERE = Path(__file__).parent
10
+ return HERE
11
+
12
+ def dCas9_kinetics():
13
+ """
14
+ in vitro Hia5 dCas9 kinetics SMF dataset. Nanopore HAC m6A modcalls.
15
+ """
16
+ import anndata as ad
17
+ HERE = import_HERE()
18
+ filepath = HERE / "dCas9_m6A_invitro_kinetics.h5ad.gz"
19
+ return ad.read_h5ad(filepath)
20
+
21
+ def Kissiov_and_McKenna_2025():
22
+ """
23
+ F1 Hybrid M.CviPI natural killer cell SMF. Nanopore canonical calls of NEB EMseq converted SMF gDNA.
24
+ """
25
+ import anndata as ad
26
+ HERE = import_HERE()
27
+ filepath = HERE / "F1_hybrid_NKG2A_enhander_promoter_GpC_conversion_SMF.h5ad.gz"
28
+ return ad.read_h5ad(filepath)