smftools 0.2.5__py3-none-any.whl → 0.3.0__py3-none-any.whl

smftools/hmm/display_hmm.py

@@ -1,4 +1,7 @@
+from __future__ import annotations
+
 from smftools.logging_utils import get_logger
+from smftools.optional_imports import require
 
 logger = get_logger(__name__)
 
@@ -11,7 +14,7 @@ def display_hmm(hmm, state_labels=["Non-Methylated", "Methylated"], obs_labels=[
         state_labels: Optional labels for states.
         obs_labels: Optional labels for observations.
     """
-    import torch
+    torch = require("torch", extra="torch", purpose="HMM display")
 
     logger.info("**HMM Model Overview**")
     logger.info("%s", hmm)

smftools/hmm/hmm_readwrite.py

@@ -1,3 +1,8 @@
+from __future__ import annotations
+
+from smftools.optional_imports import require
+
+
 def load_hmm(model_path, device="cpu"):
     """
     Reads in a pretrained HMM.
@@ -5,7 +10,7 @@ def load_hmm(model_path, device="cpu"):
     Parameters:
         model_path (str): Path to a pretrained HMM
     """
-    import torch
+    torch = require("torch", extra="torch", purpose="HMM read/write")
 
     # Load model using PyTorch
     hmm = torch.load(model_path)
@@ -20,6 +25,6 @@ def save_hmm(model, model_path):
         model: HMM model instance.
         model_path: Output path for the model.
     """
-    import torch
+    torch = require("torch", extra="torch", purpose="HMM read/write")
 
     torch.save(model, model_path)

smftools/hmm/nucleosome_hmm_refinement.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from smftools.logging_utils import get_logger
 
 logger = get_logger(__name__)

smftools/informatics/__init__.py

@@ -1,37 +1,56 @@
-from .bam_functions import (
-    align_and_sort_BAM,
-    bam_qc,
-    concatenate_fastqs_to_bam,
-    count_aligned_reads,
-    demux_and_index_BAM,
-    extract_base_identities,
-    extract_read_features_from_bam,
-    extract_readnames_from_bam,
-    separate_bam_by_bc,
-    split_and_index_BAM,
-)
-from .basecalling import canoncall, modcall
-from .bed_functions import (
-    _bed_to_bigwig,
-    _plot_bed_histograms,
-    aligned_BAM_to_bed,
-    extract_read_lengths_from_bed,
-)
-from .converted_BAM_to_adata import converted_BAM_to_adata
-from .fasta_functions import (
-    find_conversion_sites,
-    generate_converted_FASTA,
-    get_chromosome_lengths,
-    get_native_references,
-    index_fasta,
-    subsample_fasta_from_bed,
-)
-from .h5ad_functions import add_demux_type_annotation, add_read_length_and_mapping_qc
-from .modkit_extract_to_adata import modkit_extract_to_adata
-from .modkit_functions import extract_mods, make_modbed, modQC
-from .ohe import ohe_batching, ohe_layers_decode, one_hot_decode, one_hot_encode
-from .pod5_functions import basecall_pod5s, fast5_to_pod5, subsample_pod5
-from .run_multiqc import run_multiqc
+from __future__ import annotations
+
+from importlib import import_module
+
+_LAZY_ATTRS = {
+    "_bed_to_bigwig": "smftools.informatics.bed_functions",
+    "_plot_bed_histograms": "smftools.informatics.bed_functions",
+    "add_demux_type_annotation": "smftools.informatics.h5ad_functions",
+    "add_read_length_and_mapping_qc": "smftools.informatics.h5ad_functions",
+    "align_and_sort_BAM": "smftools.informatics.bam_functions",
+    "bam_qc": "smftools.informatics.bam_functions",
+    "basecall_pod5s": "smftools.informatics.pod5_functions",
+    "canoncall": "smftools.informatics.basecalling",
+    "concatenate_fastqs_to_bam": "smftools.informatics.bam_functions",
+    "converted_BAM_to_adata": "smftools.informatics.converted_BAM_to_adata",
+    "count_aligned_reads": "smftools.informatics.bam_functions",
+    "demux_and_index_BAM": "smftools.informatics.bam_functions",
+    "extract_base_identities": "smftools.informatics.bam_functions",
+    "extract_mods": "smftools.informatics.modkit_functions",
+    "extract_read_features_from_bam": "smftools.informatics.bam_functions",
+    "extract_read_lengths_from_bed": "smftools.informatics.bed_functions",
+    "extract_readnames_from_bam": "smftools.informatics.bam_functions",
+    "fast5_to_pod5": "smftools.informatics.pod5_functions",
+    "find_conversion_sites": "smftools.informatics.fasta_functions",
+    "generate_converted_FASTA": "smftools.informatics.fasta_functions",
+    "get_chromosome_lengths": "smftools.informatics.fasta_functions",
+    "get_native_references": "smftools.informatics.fasta_functions",
+    "index_fasta": "smftools.informatics.fasta_functions",
+    "make_modbed": "smftools.informatics.modkit_functions",
+    "modQC": "smftools.informatics.modkit_functions",
+    "modcall": "smftools.informatics.basecalling",
+    "modkit_extract_to_adata": "smftools.informatics.modkit_extract_to_adata",
+    "ohe_batching": "smftools.informatics.ohe",
+    "ohe_layers_decode": "smftools.informatics.ohe",
+    "one_hot_decode": "smftools.informatics.ohe",
+    "one_hot_encode": "smftools.informatics.ohe",
+    "run_multiqc": "smftools.informatics.run_multiqc",
+    "separate_bam_by_bc": "smftools.informatics.bam_functions",
+    "split_and_index_BAM": "smftools.informatics.bam_functions",
+    "subsample_fasta_from_bed": "smftools.informatics.fasta_functions",
+    "subsample_pod5": "smftools.informatics.pod5_functions",
+    "aligned_BAM_to_bed": "smftools.informatics.bed_functions",
+}
+
+
+def __getattr__(name: str):
+    if name in _LAZY_ATTRS:
+        module = import_module(_LAZY_ATTRS[name])
+        attr = getattr(module, name)
+        globals()[name] = attr
+        return attr
+    raise AttributeError(f"module '{__name__}' has no attribute '{name}'")
+
 
 __all__ = [
     "basecall_pod5s",

smftools/informatics/archived/bam_conversion.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## bam_conversion
 
 def bam_conversion(fasta, output_directory, conversion_types, strands, basecalled_path, split_dir, mapping_threshold, experiment_name, bam_suffix):

smftools/informatics/archived/bam_direct.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## bam_direct
 
 def bam_direct(fasta, output_directory, mod_list, thresholds, bam_path, split_dir, mapping_threshold, experiment_name, bam_suffix, batch_size):

smftools/informatics/archived/basecall_pod5s.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # basecall_pod5s
 
 def basecall_pod5s(config_path):

smftools/informatics/archived/basecalls_to_adata.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## basecalls_to_adata
 
 def basecalls_to_adata(config_path):

smftools/informatics/archived/conversion_smf.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## conversion_smf
 
 def conversion_smf(fasta, output_directory, conversion_types, strands, model_dir, model, input_data_path, split_dir, barcode_kit, mapping_threshold, experiment_name, bam_suffix, basecall, barcode_both_ends, trim, device, make_bigwigs, threads, input_already_demuxed):

smftools/informatics/archived/deaminase_smf.py

@@ -1,3 +1,4 @@
+from __future__ import annotations
 
 def deaminase_smf(fasta, output_directory, conversion_types, strands, model_dir, model, input_data_path, split_dir, barcode_kit, mapping_threshold, experiment_name, bam_suffix, basecall, barcode_both_ends, trim, device, make_bigwigs, threads, input_already_demuxed):
     """

smftools/informatics/archived/direct_smf.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## direct_smf
 
 def direct_smf(fasta, output_directory, mod_list, model_dir, model, thresholds, input_data_path, split_dir, barcode_kit, mapping_threshold, experiment_name, bam_suffix, batch_size, basecall, barcode_both_ends, trim, device, make_bigwigs, skip_unclassified, delete_batch_hdfs, threads):

smftools/informatics/archived/fast5_to_pod5.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from pathlib import Path
 import subprocess
 from typing import Union, List

smftools/informatics/archived/helpers/archived/__init__.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # from .align_and_sort_BAM import align_and_sort_BAM
 # from .aligned_BAM_to_bed import aligned_BAM_to_bed
 # from .bam_qc import bam_qc

smftools/informatics/archived/helpers/archived/align_and_sort_BAM.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from pathlib import Path
 import os
 import subprocess

smftools/informatics/archived/helpers/archived/aligned_BAM_to_bed.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 def aligned_BAM_to_bed(aligned_BAM, out_dir, fasta, make_bigwigs, threads=None):
     """
     Takes an aligned BAM as input and writes a BED file of reads as output.

smftools/informatics/archived/helpers/archived/bed_to_bigwig.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from pathlib import Path
 import pybedtools
 import pyBigWig

smftools/informatics/archived/helpers/archived/canoncall.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## canoncall
 
 # Conversion SMF specific

smftools/informatics/archived/helpers/archived/converted_BAM_to_adata.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## converted_BAM_to_adata
 
 def converted_BAM_to_adata(converted_FASTA, split_dir, mapping_threshold, experiment_name, conversion_types, bam_suffix):

smftools/informatics/archived/helpers/archived/count_aligned_reads.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## count_aligned_reads
 
 # General

smftools/informatics/archived/helpers/archived/demux_and_index_BAM.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## demux_and_index_BAM
 
 def demux_and_index_BAM(aligned_sorted_BAM, split_dir, bam_suffix, barcode_kit, barcode_both_ends, trim, fasta, make_bigwigs, threads):

smftools/informatics/archived/helpers/archived/extract_base_identities.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 def extract_base_identities(bam_file, chromosome, positions, max_reference_length, sequence):
     """
     Efficiently extracts base identities from mapped reads with reference coordinates.

smftools/informatics/archived/helpers/archived/extract_mods.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## extract_mods
 
 def extract_mods(thresholds, mod_tsv_dir, split_dir, bam_suffix, skip_unclassified=True, modkit_summary=False, threads=None):

smftools/informatics/archived/helpers/archived/extract_read_features_from_bam.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # extract_read_features_from_bam
 
 def extract_read_features_from_bam(bam_file_path):

smftools/informatics/archived/helpers/archived/extract_read_lengths_from_bed.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # extract_read_lengths_from_bed
 
 def extract_read_lengths_from_bed(file_path):

smftools/informatics/archived/helpers/archived/extract_readnames_from_BAM.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # extract_readnames_from_BAM
 
 def extract_readnames_from_BAM(aligned_BAM):

smftools/informatics/archived/helpers/archived/find_conversion_sites.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 def find_conversion_sites(fasta_file, modification_type, conversions, deaminase_footprinting=False):
     """
     Finds genomic coordinates of modified bases (5mC or 6mA) in a reference FASTA file.

smftools/informatics/archived/helpers/archived/generate_converted_FASTA.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import numpy as np
 import gzip
 import os

smftools/informatics/archived/helpers/archived/get_chromosome_lengths.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # get_chromosome_lengths
 
 def get_chromosome_lengths(fasta):

smftools/informatics/archived/helpers/archived/get_native_references.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## get_native_references
 
 # Direct methylation specific

smftools/informatics/archived/helpers/archived/index_fasta.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import pysam
 from pathlib import Path
 

smftools/informatics/archived/helpers/archived/informatics.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## fasta_module
 from .. import readwrite
 # bioinformatic operations

smftools/informatics/archived/helpers/archived/load_adata.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # load_adata
 ######################################################################################################
 # Archived helper; legacy imports removed for syntax compatibility.

smftools/informatics/archived/helpers/archived/make_modbed.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## make_modbed
 
 # Direct SMF

smftools/informatics/archived/helpers/archived/modQC.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## modQC
 
 # Direct SMF

smftools/informatics/archived/helpers/archived/modcall.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## modcall
 
 # Direct methylation specific

smftools/informatics/archived/helpers/archived/ohe_batching.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import os
 import anndata as ad
 import numpy as np

smftools/informatics/archived/helpers/archived/ohe_layers_decode.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # ohe_layers_decode
 
 def ohe_layers_decode(adata, obs_names):

smftools/informatics/archived/helpers/archived/one_hot_decode.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # one_hot_decode
 
 # String encodings

smftools/informatics/archived/helpers/archived/one_hot_encode.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # one_hot_encode
 
 def one_hot_encode(sequence, device='auto'):

smftools/informatics/archived/helpers/archived/plot_bed_histograms.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # plot_bed_histograms
 
 def plot_bed_histograms(

smftools/informatics/archived/helpers/archived/separate_bam_by_bc.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## separate_bam_by_bc
 
 def separate_bam_by_bc(input_bam, output_prefix, bam_suffix, split_dir):

smftools/informatics/archived/helpers/archived/split_and_index_BAM.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## split_and_index_BAM
 
 def split_and_index_BAM(aligned_sorted_BAM, split_dir, bam_suffix):

smftools/informatics/archived/print_bam_query_seq.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import pysam
 import sys
 

smftools/informatics/archived/subsample_fasta_from_bed.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from pathlib import Path
 from pyfaidx import Fasta
 

smftools/informatics/archived/subsample_pod5.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # subsample_pod5
 
 def subsample_pod5(pod5_path, read_name_path, output_directory):