smftools 0.2.1__py3-none-any.whl → 0.2.4__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 (114) hide show
  1. smftools/__init__.py +2 -6
  2. smftools/_version.py +1 -1
  3. smftools/cli/__init__.py +0 -0
  4. smftools/cli/archived/cli_flows.py +94 -0
  5. smftools/cli/helpers.py +48 -0
  6. smftools/cli/hmm_adata.py +361 -0
  7. smftools/cli/load_adata.py +637 -0
  8. smftools/cli/preprocess_adata.py +455 -0
  9. smftools/cli/spatial_adata.py +697 -0
  10. smftools/cli_entry.py +434 -0
  11. smftools/config/conversion.yaml +18 -6
  12. smftools/config/deaminase.yaml +18 -11
  13. smftools/config/default.yaml +151 -36
  14. smftools/config/direct.yaml +28 -1
  15. smftools/config/discover_input_files.py +115 -0
  16. smftools/config/experiment_config.py +225 -27
  17. smftools/hmm/HMM.py +12 -1
  18. smftools/hmm/__init__.py +0 -6
  19. smftools/hmm/archived/call_hmm_peaks.py +106 -0
  20. smftools/hmm/call_hmm_peaks.py +318 -90
  21. smftools/informatics/__init__.py +13 -7
  22. smftools/informatics/archived/fast5_to_pod5.py +43 -0
  23. smftools/informatics/archived/helpers/archived/__init__.py +71 -0
  24. smftools/informatics/archived/helpers/archived/align_and_sort_BAM.py +126 -0
  25. smftools/informatics/{helpers → archived/helpers/archived}/aligned_BAM_to_bed.py +6 -4
  26. smftools/informatics/archived/helpers/archived/bam_qc.py +213 -0
  27. smftools/informatics/archived/helpers/archived/bed_to_bigwig.py +90 -0
  28. smftools/informatics/archived/helpers/archived/concatenate_fastqs_to_bam.py +259 -0
  29. smftools/informatics/{helpers → archived/helpers/archived}/count_aligned_reads.py +2 -2
  30. smftools/informatics/{helpers → archived/helpers/archived}/demux_and_index_BAM.py +8 -10
  31. smftools/informatics/{helpers → archived/helpers/archived}/extract_base_identities.py +1 -1
  32. smftools/informatics/{helpers → archived/helpers/archived}/extract_mods.py +15 -13
  33. smftools/informatics/{helpers → archived/helpers/archived}/generate_converted_FASTA.py +2 -0
  34. smftools/informatics/{helpers → archived/helpers/archived}/get_chromosome_lengths.py +9 -8
  35. smftools/informatics/archived/helpers/archived/index_fasta.py +24 -0
  36. smftools/informatics/{helpers → archived/helpers/archived}/make_modbed.py +1 -2
  37. smftools/informatics/{helpers → archived/helpers/archived}/modQC.py +2 -2
  38. smftools/informatics/{helpers → archived/helpers/archived}/plot_bed_histograms.py +0 -19
  39. smftools/informatics/{helpers → archived/helpers/archived}/separate_bam_by_bc.py +6 -5
  40. smftools/informatics/{helpers → archived/helpers/archived}/split_and_index_BAM.py +7 -7
  41. smftools/informatics/archived/subsample_fasta_from_bed.py +49 -0
  42. smftools/informatics/bam_functions.py +811 -0
  43. smftools/informatics/basecalling.py +67 -0
  44. smftools/informatics/bed_functions.py +366 -0
  45. smftools/informatics/{helpers/converted_BAM_to_adata_II.py → converted_BAM_to_adata.py} +42 -30
  46. smftools/informatics/fasta_functions.py +255 -0
  47. smftools/informatics/h5ad_functions.py +197 -0
  48. smftools/informatics/{helpers/modkit_extract_to_adata.py → modkit_extract_to_adata.py} +142 -59
  49. smftools/informatics/modkit_functions.py +129 -0
  50. smftools/informatics/ohe.py +160 -0
  51. smftools/informatics/pod5_functions.py +224 -0
  52. smftools/informatics/{helpers/run_multiqc.py → run_multiqc.py} +5 -2
  53. smftools/plotting/autocorrelation_plotting.py +1 -3
  54. smftools/plotting/general_plotting.py +1084 -363
  55. smftools/plotting/position_stats.py +3 -3
  56. smftools/preprocessing/__init__.py +4 -4
  57. smftools/preprocessing/append_base_context.py +35 -26
  58. smftools/preprocessing/append_binary_layer_by_base_context.py +6 -6
  59. smftools/preprocessing/binarize.py +17 -0
  60. smftools/preprocessing/binarize_on_Youden.py +11 -9
  61. smftools/preprocessing/calculate_complexity_II.py +1 -1
  62. smftools/preprocessing/calculate_coverage.py +16 -13
  63. smftools/preprocessing/calculate_position_Youden.py +42 -26
  64. smftools/preprocessing/calculate_read_modification_stats.py +2 -2
  65. smftools/preprocessing/filter_reads_on_length_quality_mapping.py +1 -1
  66. smftools/preprocessing/filter_reads_on_modification_thresholds.py +20 -20
  67. smftools/preprocessing/flag_duplicate_reads.py +2 -2
  68. smftools/preprocessing/invert_adata.py +1 -1
  69. smftools/preprocessing/load_sample_sheet.py +1 -1
  70. smftools/preprocessing/reindex_references_adata.py +37 -0
  71. smftools/readwrite.py +360 -140
  72. {smftools-0.2.1.dist-info → smftools-0.2.4.dist-info}/METADATA +26 -19
  73. smftools-0.2.4.dist-info/RECORD +176 -0
  74. smftools-0.2.4.dist-info/entry_points.txt +2 -0
  75. smftools/cli.py +0 -184
  76. smftools/informatics/fast5_to_pod5.py +0 -24
  77. smftools/informatics/helpers/__init__.py +0 -73
  78. smftools/informatics/helpers/align_and_sort_BAM.py +0 -86
  79. smftools/informatics/helpers/bam_qc.py +0 -66
  80. smftools/informatics/helpers/bed_to_bigwig.py +0 -39
  81. smftools/informatics/helpers/concatenate_fastqs_to_bam.py +0 -378
  82. smftools/informatics/helpers/discover_input_files.py +0 -100
  83. smftools/informatics/helpers/index_fasta.py +0 -12
  84. smftools/informatics/helpers/make_dirs.py +0 -21
  85. smftools/informatics/readwrite.py +0 -106
  86. smftools/informatics/subsample_fasta_from_bed.py +0 -47
  87. smftools/load_adata.py +0 -1346
  88. smftools-0.2.1.dist-info/RECORD +0 -161
  89. smftools-0.2.1.dist-info/entry_points.txt +0 -2
  90. /smftools/hmm/{apply_hmm_batched.py → archived/apply_hmm_batched.py} +0 -0
  91. /smftools/hmm/{calculate_distances.py → archived/calculate_distances.py} +0 -0
  92. /smftools/hmm/{train_hmm.py → archived/train_hmm.py} +0 -0
  93. /smftools/informatics/{basecall_pod5s.py → archived/basecall_pod5s.py} +0 -0
  94. /smftools/informatics/{helpers → archived/helpers/archived}/canoncall.py +0 -0
  95. /smftools/informatics/{helpers → archived/helpers/archived}/converted_BAM_to_adata.py +0 -0
  96. /smftools/informatics/{helpers → archived/helpers/archived}/extract_read_features_from_bam.py +0 -0
  97. /smftools/informatics/{helpers → archived/helpers/archived}/extract_read_lengths_from_bed.py +0 -0
  98. /smftools/informatics/{helpers → archived/helpers/archived}/extract_readnames_from_BAM.py +0 -0
  99. /smftools/informatics/{helpers → archived/helpers/archived}/find_conversion_sites.py +0 -0
  100. /smftools/informatics/{helpers → archived/helpers/archived}/get_native_references.py +0 -0
  101. /smftools/informatics/{helpers → archived/helpers}/archived/informatics.py +0 -0
  102. /smftools/informatics/{helpers → archived/helpers}/archived/load_adata.py +0 -0
  103. /smftools/informatics/{helpers → archived/helpers/archived}/modcall.py +0 -0
  104. /smftools/informatics/{helpers → archived/helpers/archived}/ohe_batching.py +0 -0
  105. /smftools/informatics/{helpers → archived/helpers/archived}/ohe_layers_decode.py +0 -0
  106. /smftools/informatics/{helpers → archived/helpers/archived}/one_hot_decode.py +0 -0
  107. /smftools/informatics/{helpers → archived/helpers/archived}/one_hot_encode.py +0 -0
  108. /smftools/informatics/{subsample_pod5.py → archived/subsample_pod5.py} +0 -0
  109. /smftools/informatics/{helpers/binarize_converted_base_identities.py → binarize_converted_base_identities.py} +0 -0
  110. /smftools/informatics/{helpers/complement_base_list.py → complement_base_list.py} +0 -0
  111. /smftools/preprocessing/{add_read_length_and_mapping_qc.py → archives/add_read_length_and_mapping_qc.py} +0 -0
  112. /smftools/preprocessing/{calculate_complexity.py → archives/calculate_complexity.py} +0 -0
  113. {smftools-0.2.1.dist-info → smftools-0.2.4.dist-info}/WHEEL +0 -0
  114. {smftools-0.2.1.dist-info → smftools-0.2.4.dist-info}/licenses/LICENSE +0 -0
@@ -1,47 +0,0 @@
1
- # subsample_fasta_from_bed
2
-
3
- def subsample_fasta_from_bed(input_FASTA, input_bed, output_directory, output_FASTA):
4
- """
5
- Take a genome-wide FASTA file and a bed file containing coordinate windows of interest. Outputs a subsampled FASTA.
6
-
7
- Parameters:
8
- input_FASTA (str): String representing the path to the input FASTA file.
9
- input_bed (str): String representing the path to the input BED file.
10
- output_directory (str): String representing the path to the output directory for the new FASTA file.
11
- output_FASTA (str): Name of the output FASTA.
12
-
13
- Returns:
14
- None
15
- """
16
- from pyfaidx import Fasta
17
- import os
18
-
19
- # Load the FASTA file using pyfaidx
20
- fasta = Fasta(input_FASTA)
21
-
22
- output_FASTA_path = os.path.join(output_directory, output_FASTA)
23
-
24
- # Open the BED file
25
- with open(input_bed, 'r') as bed, open(output_FASTA_path, 'w') as out_fasta:
26
- for line in bed:
27
- # Each line in BED file contains: chrom, start, end (and possibly more columns)
28
- fields = line.strip().split()
29
- n_fields = len(fields)
30
- chrom = fields[0]
31
- start = int(fields[1]) # BED is 0-based
32
- end = int(fields[2]) # BED is 0-based and end is exclusive
33
- if n_fields > 3:
34
- description = " ".join(fields[3:])
35
-
36
- # Check if the chromosome exists in the FASTA file
37
- if chrom in fasta:
38
- # pyfaidx is 1-based, so convert coordinates accordingly
39
- sequence = fasta[chrom][start:end].seq
40
- # Write the sequence to the output FASTA file
41
- if n_fields > 3:
42
- out_fasta.write(f">{chrom}:{start}-{end} {description}\n")
43
- else:
44
- out_fasta.write(f">{chrom}:{start}-{end}\n")
45
- out_fasta.write(f"{sequence}\n")
46
- else:
47
- print(f"Warning: {chrom} not found in the FASTA file")