smftools 0.2.4__py3-none-any.whl → 0.3.0__py3-none-any.whl

smftools/hmm/hmm_readwrite.py

@@ -1,16 +1,30 @@
-def load_hmm(model_path, device='cpu'):
+from __future__ import annotations
+
+from smftools.optional_imports import require
+
+
+def load_hmm(model_path, device="cpu"):
     """
     Reads in a pretrained HMM.
-    
+
     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)
-    hmm.to(device) 
+    hmm.to(device)
     return hmm
 
+
 def save_hmm(model, model_path):
-    import torch
-    torch.save(model, model_path)
+    """Save a pretrained HMM to disk.
+
+    Args:
+        model: HMM model instance.
+        model_path: Output path for the model.
+    """
+    torch = require("torch", extra="torch", purpose="HMM read/write")
+
+    torch.save(model, model_path)

smftools/hmm/nucleosome_hmm_refinement.py

@@ -1,4 +1,33 @@
-def refine_nucleosome_calls(adata, layer_name, nan_mask_layer, hexamer_size=120, octamer_size=147, max_wiggle=40, device="cpu"):
+from __future__ import annotations
+
+from smftools.logging_utils import get_logger
+
+logger = get_logger(__name__)
+
+
+def refine_nucleosome_calls(
+    adata,
+    layer_name,
+    nan_mask_layer,
+    hexamer_size=120,
+    octamer_size=147,
+    max_wiggle=40,
+    device="cpu",
+):
+    """Refine nucleosome calls into hexamer/octamer layers.
+
+    Args:
+        adata: AnnData with nucleosome calls.
+        layer_name: Layer containing initial nucleosome calls.
+        nan_mask_layer: Layer indicating NaN regions.
+        hexamer_size: Size for hexamer placement.
+        octamer_size: Size for octamer placement.
+        max_wiggle: Max boundary expansion into NaNs.
+        device: Device specifier (unused; kept for API parity).
+
+    Returns:
+        Updated AnnData with hexamer/octamer layers.
+    """
     import numpy as np
 
     nucleosome_layer = adata.layers[layer_name]
@@ -31,7 +60,10 @@ def refine_nucleosome_calls(adata, layer_name, nan_mask_layer, hexamer_size=120,
                         break
                 # Right
                 for i in range(1, max_wiggle + 1):
-                    if end_idx + i < nucleosome_layer.shape[1] and nan_mask[read_idx, end_idx + i] == 1:
+                    if (
+                        end_idx + i < nucleosome_layer.shape[1]
+                        and nan_mask[read_idx, end_idx + i] == 1
+                    ):
                         right_expand += 1
                     else:
                         break
@@ -40,26 +72,55 @@ def refine_nucleosome_calls(adata, layer_name, nan_mask_layer, hexamer_size=120,
                 expanded_end = end_idx + right_expand
 
                 available_size = expanded_end - expanded_start
-            
+
                 # Octamer placement
                 if available_size >= octamer_size:
                     center = (expanded_start + expanded_end) // 2
                     half_oct = octamer_size // 2
-                    octamer_layer[read_idx, center - half_oct: center - half_oct + octamer_size] = 1
+                    octamer_layer[
+                        read_idx, center - half_oct : center - half_oct + octamer_size
+                    ] = 1
 
                 # Hexamer placement
                 elif available_size >= hexamer_size:
                     center = (expanded_start + expanded_end) // 2
                     half_hex = hexamer_size // 2
-                    hexamer_layer[read_idx, center - half_hex: center - half_hex + hexamer_size] = 1
+                    hexamer_layer[
+                        read_idx, center - half_hex : center - half_hex + hexamer_size
+                    ] = 1
 
     adata.layers[f"{layer_name}_hexamers"] = hexamer_layer
     adata.layers[f"{layer_name}_octamers"] = octamer_layer
 
-    print(f"Added layers: {layer_name}_hexamers and {layer_name}_octamers")
+    logger.info("Added layers: %s_hexamers and %s_octamers", layer_name, layer_name)
     return adata
 
-def infer_nucleosomes_in_large_bound(adata, large_bound_layer, combined_nuc_layer, nan_mask_layer, nuc_size=147, linker_size=50, exclusion_buffer=30, device="cpu"):
+
+def infer_nucleosomes_in_large_bound(
+    adata,
+    large_bound_layer,
+    combined_nuc_layer,
+    nan_mask_layer,
+    nuc_size=147,
+    linker_size=50,
+    exclusion_buffer=30,
+    device="cpu",
+):
+    """Infer nucleosomes in large-bound regions while respecting exclusions.
+
+    Args:
+        adata: AnnData with bound regions and existing nucleosomes.
+        large_bound_layer: Layer marking large-bound segments.
+        combined_nuc_layer: Layer with existing nucleosome calls.
+        nan_mask_layer: Layer indicating NaN regions.
+        nuc_size: Nucleosome size in bp.
+        linker_size: Minimum linker spacing.
+        exclusion_buffer: Buffer to avoid nearby existing nucleosomes.
+        device: Device specifier (unused; kept for API parity).
+
+    Returns:
+        Updated AnnData with inferred nucleosome layer.
+    """
     import numpy as np
 
     large_bound = adata.layers[large_bound_layer]
@@ -82,23 +143,52 @@ def infer_nucleosomes_in_large_bound(adata, large_bound_layer, combined_nuc_laye
 
                 # Adjust boundaries into flanking NaN regions without getting too close to existing nucleosomes
                 left_expand = start_idx
-                while left_expand > 0 and nan_mask[read_idx, left_expand - 1] == 1 and np.sum(existing_nucs[read_idx, max(0, left_expand - exclusion_buffer):left_expand]) == 0:
+                while (
+                    left_expand > 0
+                    and nan_mask[read_idx, left_expand - 1] == 1
+                    and np.sum(
+                        existing_nucs[
+                            read_idx, max(0, left_expand - exclusion_buffer) : left_expand
+                        ]
+                    )
+                    == 0
+                ):
                     left_expand -= 1
 
                 right_expand = end_idx
-                while right_expand < row.shape[0] and nan_mask[read_idx, right_expand] == 1 and np.sum(existing_nucs[read_idx, right_expand:min(row.shape[0], right_expand + exclusion_buffer)]) == 0:
+                while (
+                    right_expand < row.shape[0]
+                    and nan_mask[read_idx, right_expand] == 1
+                    and np.sum(
+                        existing_nucs[
+                            read_idx,
+                            right_expand : min(row.shape[0], right_expand + exclusion_buffer),
+                        ]
+                    )
+                    == 0
+                ):
                     right_expand += 1
 
                 # Phase nucleosomes with linker spacing only
                 region = (left_expand, right_expand)
                 pos_cursor = region[0]
                 while pos_cursor + nuc_size <= region[1]:
-                    if np.all((existing_nucs[read_idx, pos_cursor - exclusion_buffer:pos_cursor + nuc_size + exclusion_buffer] == 0)):
-                        inferred_layer[read_idx, pos_cursor:pos_cursor + nuc_size] = 1
-                        pos_cursor += nuc_size + linker_size 
+                    if np.all(
+                        (
+                            existing_nucs[
+                                read_idx,
+                                pos_cursor - exclusion_buffer : pos_cursor
+                                + nuc_size
+                                + exclusion_buffer,
+                            ]
+                            == 0
+                        )
+                    ):
+                        inferred_layer[read_idx, pos_cursor : pos_cursor + nuc_size] = 1
+                        pos_cursor += nuc_size + linker_size
                     else:
                         pos_cursor += 1
 
     adata.layers[f"{large_bound_layer}_phased_nucleosomes"] = inferred_layer
-    print(f"Added layer: {large_bound_layer}_phased_nucleosomes")
-    return adata
+    logger.info("Added layer: %s_phased_nucleosomes", large_bound_layer)
+    return adata

smftools/informatics/__init__.py

@@ -1,14 +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 aligned_BAM_to_bed, _bed_to_bigwig, extract_read_lengths_from_bed, _plot_bed_histograms
-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_functions import extract_mods, make_modbed, modQC
-from .modkit_extract_to_adata import modkit_extract_to_adata
-from .ohe import one_hot_encode, one_hot_decode, ohe_layers_decode, ohe_batching
-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",
@@ -16,5 +58,5 @@ __all__ = [
     "subsample_fasta_from_bed",
     "subsample_pod5",
     "fast5_to_pod5",
-    "run_multiqc"
-]
+    "run_multiqc",
+]

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
@@ -20,6 +22,13 @@ def _bam_to_fastq_with_pysam(bam_path: Union[str, Path], fastq_path: Union[str,
             fq.write(f"@{name}\n{seq}\n+\n{qual}\n")
 
 def _sort_bam_with_pysam(in_bam: Union[str, Path], out_bam: Union[str, Path], threads: Optional[int] = None) -> None:
+    """Sort a BAM file using pysam.
+
+    Args:
+        in_bam: Input BAM path.
+        out_bam: Output BAM path.
+        threads: Optional thread count.
+    """
     in_bam, out_bam = str(in_bam), str(out_bam)
     args = []
     if threads:
@@ -28,6 +37,12 @@ def _sort_bam_with_pysam(in_bam: Union[str, Path], out_bam: Union[str, Path], th
     pysam.sort(*args)
 
 def _index_bam_with_pysam(bam_path: Union[str, Path], threads: Optional[int] = None) -> None:
+    """Index a BAM file using pysam.
+
+    Args:
+        bam_path: BAM path to index.
+        threads: Optional thread count.
+    """
     bam_path = str(bam_path)
     # pysam.index supports samtools-style args
     if threads:
@@ -123,4 +138,4 @@ def align_and_sort_BAM(fasta,
     #     index_command = ["samtools", "index", "-@", threads, aligned_sorted_output]
     # else:
     #     index_command = ["samtools", "index", aligned_sorted_output]
-    # subprocess.run(index_command)
+    # subprocess.run(index_command)

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/bam_qc.py

@@ -35,6 +35,7 @@ def bam_qc(
     bam_files = [Path(b) for b in bam_files]
 
     def _has_index(p: Path) -> bool:
+        """Return True if a BAM/CRAM index exists for the path."""
         if p.suffix.lower() == ".bam":
             bai = p.with_suffix(p.suffix + ".bai")
             bai_alt = Path(str(p) + ".bai")
@@ -45,6 +46,7 @@ def bam_qc(
         return False
 
     def _ensure_index(p: Path) -> None:
+        """Ensure a BAM/CRAM index exists, creating one if needed."""
         if _has_index(p):
             return
         if HAVE_PYSAM:
@@ -55,6 +57,14 @@ def bam_qc(
             subprocess.run(cmd, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
 
     def _run_one(bam: Path) -> Tuple[Path, List[Tuple[str, int]]]:
+        """Run QC tasks for a single BAM file.
+
+        Args:
+            bam: Path to the BAM file.
+
+        Returns:
+            Tuple of (bam_path, list of (task_name, return_code)).
+        """
         # outputs + return (file, [(task_name, returncode)])
         results: List[Tuple[str, int]] = []
         base = bam.stem  # filename without .bam
@@ -71,6 +81,7 @@ def bam_qc(
 
         # Choose runner per task
         def run_stats():
+            """Run stats collection for a BAM file."""
             if not stats:
                 return
             if HAVE_PYSAM and hasattr(pysam, "stats"):
@@ -86,6 +97,7 @@ def bam_qc(
                     raise RuntimeError(cp.stderr.decode(errors="replace"))
 
         def run_flagstat():
+            """Run flagstat collection for a BAM file."""
             if not flagstats:
                 return
             if HAVE_PYSAM and hasattr(pysam, "flagstat"):
@@ -101,6 +113,7 @@ def bam_qc(
                     raise RuntimeError(cp.stderr.decode(errors="replace"))
 
         def run_idxstats():
+            """Run idxstats collection for a BAM file."""
             if not idxstats:
                 return
             if HAVE_PYSAM and hasattr(pysam, "idxstats"):
@@ -210,4 +223,4 @@ def bam_qc(
 #         elif modality == 'direct':
 #             pass
 
-#     print("QC processing completed.")   
+#     print("QC processing completed.")   

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/concatenate_fastqs_to_bam.py

@@ -60,6 +60,7 @@ def concatenate_fastqs_to_bam(
         return p.stem  # fallback: remove last suffix only
 
     def _extract_barcode_from_filename(p: Path) -> str:
+        """Extract a barcode token from a FASTQ filename."""
         stem = _strip_fastq_ext(p)
         if "_" in stem:
             token = stem.split("_")[-1]
@@ -68,6 +69,7 @@ def concatenate_fastqs_to_bam(
         return stem
 
     def _classify_read_token(stem: str) -> Tuple[Optional[str], Optional[int]]:
+        """Classify a FASTQ filename stem into (prefix, read_number)."""
         # return (prefix, readnum) if matches; else (None, None)
         patterns = [
             r"(?i)(.*?)[._-]r?([12])$",        # prefix_R1 / prefix.r2 / prefix-1
@@ -80,6 +82,7 @@ def concatenate_fastqs_to_bam(
         return None, None
 
     def _pair_by_filename(paths: List[Path]) -> Tuple[List[Tuple[Path, Path]], List[Path]]:
+        """Pair FASTQ files based on filename conventions."""
         pref_map: Dict[str, Dict[int, Path]] = {}
         unpaired: List[Path] = []
         for pth in paths:
@@ -101,6 +104,7 @@ def concatenate_fastqs_to_bam(
         return pairs, leftovers
 
     def _fastq_iter(p: Path):
+        """Yield FASTQ records using pysam.FastxFile."""
         # pysam.FastxFile handles compressed extensions transparently
         with pysam.FastxFile(str(p)) as fx:
             for rec in fx:
@@ -114,6 +118,7 @@ def concatenate_fastqs_to_bam(
         read1: bool,
         read2: bool,
     ) -> pysam.AlignedSegment:
+        """Construct an unaligned pysam.AlignedSegment."""
         a = pysam.AlignedSegment()
         a.query_name = name
         a.query_sequence = seq
@@ -136,6 +141,7 @@ def concatenate_fastqs_to_bam(
 
     # ---------- normalize inputs to Path ----------
     def _to_path_pair(x) -> Tuple[Path, Path]:
+        """Convert a tuple of path-like objects to Path instances."""
         a, b = x
         return Path(a), Path(b)
 
@@ -205,6 +211,7 @@ def concatenate_fastqs_to_bam(
 
             for rec1, rec2 in zip_longest(it1, it2, fillvalue=None):
                 def _clean(n: Optional[str]) -> Optional[str]:
+                    """Normalize FASTQ read names by trimming read suffixes."""
                     if n is None:
                         return None
                     return re.sub(r"(?:/1$|/2$|\s[12]$)", "", n)
@@ -256,4 +263,4 @@ def concatenate_fastqs_to_bam(
         "paired_pairs_written": paired_pairs_written,
         "singletons_written": singletons_written,
         "barcodes": barcodes_in_order,
-    }
+    }

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

@@ -1,12 +1,14 @@
+from __future__ import annotations
+
 # load_adata
 ######################################################################################################
-import .utils
+# Archived helper; legacy imports removed for syntax compatibility.
 # File I/O
 import subprocess
 import gc
 
 # bioinformatic operations
-import .informatics_module
+# import .informatics_module
 
 # User interface
 from tqdm import tqdm
@@ -513,4 +515,4 @@ def modkit_extract_to_adata(fasta, bam, mapping_threshold, experiment_name, mods
             print(f"Deleted file: {hdf}")
         except OSError as e:
             print(f"Error deleting file {hdf}: {e}")
-######################################################################################################
+######################################################################################################

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

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