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.
- smftools/__init__.py +34 -0
- smftools/_settings.py +20 -0
- smftools/_version.py +1 -0
- smftools/cli.py +184 -0
- smftools/config/__init__.py +1 -0
- smftools/config/conversion.yaml +33 -0
- smftools/config/deaminase.yaml +56 -0
- smftools/config/default.yaml +253 -0
- smftools/config/direct.yaml +17 -0
- smftools/config/experiment_config.py +1191 -0
- smftools/datasets/F1_hybrid_NKG2A_enhander_promoter_GpC_conversion_SMF.h5ad.gz +0 -0
- smftools/datasets/F1_sample_sheet.csv +5 -0
- smftools/datasets/__init__.py +9 -0
- smftools/datasets/dCas9_m6A_invitro_kinetics.h5ad.gz +0 -0
- smftools/datasets/datasets.py +28 -0
- smftools/hmm/HMM.py +1576 -0
- smftools/hmm/__init__.py +20 -0
- smftools/hmm/apply_hmm_batched.py +242 -0
- smftools/hmm/calculate_distances.py +18 -0
- smftools/hmm/call_hmm_peaks.py +106 -0
- smftools/hmm/display_hmm.py +18 -0
- smftools/hmm/hmm_readwrite.py +16 -0
- smftools/hmm/nucleosome_hmm_refinement.py +104 -0
- smftools/hmm/train_hmm.py +78 -0
- smftools/informatics/__init__.py +14 -0
- smftools/informatics/archived/bam_conversion.py +59 -0
- smftools/informatics/archived/bam_direct.py +63 -0
- smftools/informatics/archived/basecalls_to_adata.py +71 -0
- smftools/informatics/archived/conversion_smf.py +132 -0
- smftools/informatics/archived/deaminase_smf.py +132 -0
- smftools/informatics/archived/direct_smf.py +137 -0
- smftools/informatics/archived/print_bam_query_seq.py +29 -0
- smftools/informatics/basecall_pod5s.py +80 -0
- smftools/informatics/fast5_to_pod5.py +24 -0
- smftools/informatics/helpers/__init__.py +73 -0
- smftools/informatics/helpers/align_and_sort_BAM.py +86 -0
- smftools/informatics/helpers/aligned_BAM_to_bed.py +85 -0
- smftools/informatics/helpers/archived/informatics.py +260 -0
- smftools/informatics/helpers/archived/load_adata.py +516 -0
- smftools/informatics/helpers/bam_qc.py +66 -0
- smftools/informatics/helpers/bed_to_bigwig.py +39 -0
- smftools/informatics/helpers/binarize_converted_base_identities.py +172 -0
- smftools/informatics/helpers/canoncall.py +34 -0
- smftools/informatics/helpers/complement_base_list.py +21 -0
- smftools/informatics/helpers/concatenate_fastqs_to_bam.py +378 -0
- smftools/informatics/helpers/converted_BAM_to_adata.py +245 -0
- smftools/informatics/helpers/converted_BAM_to_adata_II.py +505 -0
- smftools/informatics/helpers/count_aligned_reads.py +43 -0
- smftools/informatics/helpers/demux_and_index_BAM.py +52 -0
- smftools/informatics/helpers/discover_input_files.py +100 -0
- smftools/informatics/helpers/extract_base_identities.py +70 -0
- smftools/informatics/helpers/extract_mods.py +83 -0
- smftools/informatics/helpers/extract_read_features_from_bam.py +33 -0
- smftools/informatics/helpers/extract_read_lengths_from_bed.py +25 -0
- smftools/informatics/helpers/extract_readnames_from_BAM.py +22 -0
- smftools/informatics/helpers/find_conversion_sites.py +51 -0
- smftools/informatics/helpers/generate_converted_FASTA.py +99 -0
- smftools/informatics/helpers/get_chromosome_lengths.py +32 -0
- smftools/informatics/helpers/get_native_references.py +28 -0
- smftools/informatics/helpers/index_fasta.py +12 -0
- smftools/informatics/helpers/make_dirs.py +21 -0
- smftools/informatics/helpers/make_modbed.py +27 -0
- smftools/informatics/helpers/modQC.py +27 -0
- smftools/informatics/helpers/modcall.py +36 -0
- smftools/informatics/helpers/modkit_extract_to_adata.py +887 -0
- smftools/informatics/helpers/ohe_batching.py +76 -0
- smftools/informatics/helpers/ohe_layers_decode.py +32 -0
- smftools/informatics/helpers/one_hot_decode.py +27 -0
- smftools/informatics/helpers/one_hot_encode.py +57 -0
- smftools/informatics/helpers/plot_bed_histograms.py +269 -0
- smftools/informatics/helpers/run_multiqc.py +28 -0
- smftools/informatics/helpers/separate_bam_by_bc.py +43 -0
- smftools/informatics/helpers/split_and_index_BAM.py +32 -0
- smftools/informatics/readwrite.py +106 -0
- smftools/informatics/subsample_fasta_from_bed.py +47 -0
- smftools/informatics/subsample_pod5.py +104 -0
- smftools/load_adata.py +1346 -0
- smftools/machine_learning/__init__.py +12 -0
- smftools/machine_learning/data/__init__.py +2 -0
- smftools/machine_learning/data/anndata_data_module.py +234 -0
- smftools/machine_learning/data/preprocessing.py +6 -0
- smftools/machine_learning/evaluation/__init__.py +2 -0
- smftools/machine_learning/evaluation/eval_utils.py +31 -0
- smftools/machine_learning/evaluation/evaluators.py +223 -0
- smftools/machine_learning/inference/__init__.py +3 -0
- smftools/machine_learning/inference/inference_utils.py +27 -0
- smftools/machine_learning/inference/lightning_inference.py +68 -0
- smftools/machine_learning/inference/sklearn_inference.py +55 -0
- smftools/machine_learning/inference/sliding_window_inference.py +114 -0
- smftools/machine_learning/models/__init__.py +9 -0
- smftools/machine_learning/models/base.py +295 -0
- smftools/machine_learning/models/cnn.py +138 -0
- smftools/machine_learning/models/lightning_base.py +345 -0
- smftools/machine_learning/models/mlp.py +26 -0
- smftools/machine_learning/models/positional.py +18 -0
- smftools/machine_learning/models/rnn.py +17 -0
- smftools/machine_learning/models/sklearn_models.py +273 -0
- smftools/machine_learning/models/transformer.py +303 -0
- smftools/machine_learning/models/wrappers.py +20 -0
- smftools/machine_learning/training/__init__.py +2 -0
- smftools/machine_learning/training/train_lightning_model.py +135 -0
- smftools/machine_learning/training/train_sklearn_model.py +114 -0
- smftools/machine_learning/utils/__init__.py +2 -0
- smftools/machine_learning/utils/device.py +10 -0
- smftools/machine_learning/utils/grl.py +14 -0
- smftools/plotting/__init__.py +18 -0
- smftools/plotting/autocorrelation_plotting.py +611 -0
- smftools/plotting/classifiers.py +355 -0
- smftools/plotting/general_plotting.py +682 -0
- smftools/plotting/hmm_plotting.py +260 -0
- smftools/plotting/position_stats.py +462 -0
- smftools/plotting/qc_plotting.py +270 -0
- smftools/preprocessing/__init__.py +38 -0
- smftools/preprocessing/add_read_length_and_mapping_qc.py +129 -0
- smftools/preprocessing/append_base_context.py +122 -0
- smftools/preprocessing/append_binary_layer_by_base_context.py +143 -0
- smftools/preprocessing/archives/mark_duplicates.py +146 -0
- smftools/preprocessing/archives/preprocessing.py +614 -0
- smftools/preprocessing/archives/remove_duplicates.py +21 -0
- smftools/preprocessing/binarize_on_Youden.py +45 -0
- smftools/preprocessing/binary_layers_to_ohe.py +40 -0
- smftools/preprocessing/calculate_complexity.py +72 -0
- smftools/preprocessing/calculate_complexity_II.py +248 -0
- smftools/preprocessing/calculate_consensus.py +47 -0
- smftools/preprocessing/calculate_coverage.py +51 -0
- smftools/preprocessing/calculate_pairwise_differences.py +49 -0
- smftools/preprocessing/calculate_pairwise_hamming_distances.py +27 -0
- smftools/preprocessing/calculate_position_Youden.py +115 -0
- smftools/preprocessing/calculate_read_length_stats.py +79 -0
- smftools/preprocessing/calculate_read_modification_stats.py +101 -0
- smftools/preprocessing/clean_NaN.py +62 -0
- smftools/preprocessing/filter_adata_by_nan_proportion.py +31 -0
- smftools/preprocessing/filter_reads_on_length_quality_mapping.py +158 -0
- smftools/preprocessing/filter_reads_on_modification_thresholds.py +352 -0
- smftools/preprocessing/flag_duplicate_reads.py +1351 -0
- smftools/preprocessing/invert_adata.py +37 -0
- smftools/preprocessing/load_sample_sheet.py +53 -0
- smftools/preprocessing/make_dirs.py +21 -0
- smftools/preprocessing/min_non_diagonal.py +25 -0
- smftools/preprocessing/recipes.py +127 -0
- smftools/preprocessing/subsample_adata.py +58 -0
- smftools/readwrite.py +1004 -0
- smftools/tools/__init__.py +20 -0
- smftools/tools/archived/apply_hmm.py +202 -0
- smftools/tools/archived/classifiers.py +787 -0
- smftools/tools/archived/classify_methylated_features.py +66 -0
- smftools/tools/archived/classify_non_methylated_features.py +75 -0
- smftools/tools/archived/subset_adata_v1.py +32 -0
- smftools/tools/archived/subset_adata_v2.py +46 -0
- smftools/tools/calculate_umap.py +62 -0
- smftools/tools/cluster_adata_on_methylation.py +105 -0
- smftools/tools/general_tools.py +69 -0
- smftools/tools/position_stats.py +601 -0
- smftools/tools/read_stats.py +184 -0
- smftools/tools/spatial_autocorrelation.py +562 -0
- smftools/tools/subset_adata.py +28 -0
- {smftools-0.1.6.dist-info → smftools-0.2.1.dist-info}/METADATA +9 -2
- smftools-0.2.1.dist-info/RECORD +161 -0
- smftools-0.2.1.dist-info/entry_points.txt +2 -0
- smftools-0.1.6.dist-info/RECORD +0 -4
- {smftools-0.1.6.dist-info → smftools-0.2.1.dist-info}/WHEEL +0 -0
- {smftools-0.1.6.dist-info → smftools-0.2.1.dist-info}/licenses/LICENSE +0 -0
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
## modcall
|
|
2
|
+
|
|
3
|
+
# Direct methylation specific
|
|
4
|
+
def modcall(model_dir, model, pod5_dir, barcode_kit, mod_list, bam, bam_suffix, barcode_both_ends=True, trim=False, device='auto'):
|
|
5
|
+
"""
|
|
6
|
+
Wrapper function for dorado modified base calling.
|
|
7
|
+
|
|
8
|
+
Parameters:
|
|
9
|
+
model_dir (str): a string representing the file path to the dorado basecalling model directory.
|
|
10
|
+
model (str): a string representing the the dorado basecalling model.
|
|
11
|
+
pod5_dir (str): a string representing the file path to the experiment directory containing the POD5 files.
|
|
12
|
+
barcode_kit (str): A string representing the barcoding kit used in the experiment.
|
|
13
|
+
mod_list (list): A list of modification types to use in the analysis.
|
|
14
|
+
bam (str): File path to the BAM file to output.
|
|
15
|
+
bam_suffix (str): The suffix to use for the BAM file.
|
|
16
|
+
barcode_both_ends (bool): Whether to require a barcode detection on both ends for demultiplexing.
|
|
17
|
+
trim (bool): Whether to trim barcodes, adapters, and primers from read ends
|
|
18
|
+
device (str): Device to use for basecalling. auto, metal, cpu, cuda.
|
|
19
|
+
|
|
20
|
+
Returns:
|
|
21
|
+
None
|
|
22
|
+
Outputs a BAM file holding the modified base calls output by the dorado basecaller.
|
|
23
|
+
"""
|
|
24
|
+
import subprocess
|
|
25
|
+
output = bam + bam_suffix
|
|
26
|
+
command = ["dorado", "basecaller", "--models-directory", model_dir, "--kit-name", barcode_kit, "--modified-bases"]
|
|
27
|
+
command += mod_list
|
|
28
|
+
command += ["--device", device, "--batchsize", "0"]
|
|
29
|
+
if barcode_both_ends:
|
|
30
|
+
command.append("--barcode-both-ends")
|
|
31
|
+
if not trim:
|
|
32
|
+
command.append("--no-trim")
|
|
33
|
+
command += [model, pod5_dir]
|
|
34
|
+
print(f'Running: {" ".join(command)}')
|
|
35
|
+
with open(output, "w") as outfile:
|
|
36
|
+
subprocess.run(command, stdout=outfile)
|