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

smftools/plotting/qc_plotting.py

@@ -1,12 +1,13 @@
-import os
-import numpy as np
-import pandas as pd
-import matplotlib.pyplot as plt
+from __future__ import annotations
 
 import os
+
 import numpy as np
 import pandas as pd
-import matplotlib.pyplot as plt
+
+from smftools.optional_imports import require
+
+plt = require("matplotlib.pyplot", extra="plotting", purpose="QC plots")
 
 
 def plot_read_qc_histograms(
@@ -83,7 +84,11 @@ def plot_read_qc_histograms(
     for key in valid_keys:
         if not is_numeric[key]:
             continue
-        s = pd.to_numeric(adata.obs[key], errors="coerce").replace([np.inf, -np.inf], np.nan).dropna()
+        s = (
+            pd.to_numeric(adata.obs[key], errors="coerce")
+            .replace([np.inf, -np.inf], np.nan)
+            .dropna()
+        )
         if s.size < min_non_nan:
             # still set something to avoid errors; just use min/max or (0,1)
             lo, hi = (0.0, 1.0) if s.size == 0 else (float(s.min()), float(s.max()))
@@ -99,6 +104,7 @@ def plot_read_qc_histograms(
         global_ranges[key] = (lo, hi)
 
     def _sanitize(name: str) -> str:
+        """Sanitize a string for use in filenames."""
         return "".join(c if c.isalnum() or c in "-._" else "_" for c in str(name))
 
     ncols = len(valid_keys)
@@ -107,17 +113,18 @@ def plot_read_qc_histograms(
     fig_h_unit = figsize_cell[1]
 
     for start in range(0, len(sample_levels), rows_per_fig):
-        chunk = sample_levels[start:start + rows_per_fig]
+        chunk = sample_levels[start : start + rows_per_fig]
         nrows = len(chunk)
         fig, axes = plt.subplots(
-            nrows=nrows, ncols=ncols,
+            nrows=nrows,
+            ncols=ncols,
             figsize=(fig_w, fig_h_unit * nrows),
             dpi=dpi,
             squeeze=False,
         )
 
         for r, sample_val in enumerate(chunk):
-            row_mask = (adata.obs[sample_key].values == sample_val)
+            row_mask = adata.obs[sample_key].values == sample_val
             n_in_row = int(row_mask.sum())
 
             for c, key in enumerate(valid_keys):
@@ -125,7 +132,11 @@ def plot_read_qc_histograms(
                 series = adata.obs.loc[row_mask, key]
 
                 if is_numeric[key]:
-                    x = pd.to_numeric(series, errors="coerce").replace([np.inf, -np.inf], np.nan).dropna()
+                    x = (
+                        pd.to_numeric(series, errors="coerce")
+                        .replace([np.inf, -np.inf], np.nan)
+                        .dropna()
+                    )
                     if x.size < min_non_nan:
                         ax.text(0.5, 0.5, f"n={x.size} (<{min_non_nan})", ha="center", va="center")
                     else:
@@ -143,7 +154,9 @@ def plot_read_qc_histograms(
                 else:
                     vc = series.astype("category").value_counts(dropna=False)
                     if vc.sum() < min_non_nan:
-                        ax.text(0.5, 0.5, f"n={vc.sum()} (<{min_non_nan})", ha="center", va="center")
+                        ax.text(
+                            0.5, 0.5, f"n={vc.sum()} (<{min_non_nan})", ha="center", va="center"
+                        )
                     else:
                         vc_top = vc.iloc[:topn_categories][::-1]  # show top-N, reversed for barh
                         ax.barh(vc_top.index.astype(str), vc_top.values)
@@ -267,4 +280,4 @@ def plot_read_qc_histograms(
 #                 fname = f"{key}_{sample_key}_{safe_group}.png" if sample_key else f"{key}.png"
 #                 fname = fname.replace("/", "_")
 #                 fig.savefig(os.path.join(outdir, fname))
-#                 plt.close(fig)
+#                 plt.close(fig)

smftools/preprocessing/__init__.py

@@ -1,38 +1,36 @@
-from .append_base_context import append_base_context
-from .append_binary_layer_by_base_context import append_binary_layer_by_base_context
-from .binarize_on_Youden import binarize_on_Youden
-from .binarize import binarize_adata
-from .calculate_complexity_II import calculate_complexity_II
-from .calculate_read_modification_stats import calculate_read_modification_stats
-from .calculate_coverage import calculate_coverage
-from .calculate_position_Youden import calculate_position_Youden
-from .calculate_read_length_stats import calculate_read_length_stats
-from .clean_NaN import clean_NaN
-from .filter_adata_by_nan_proportion import filter_adata_by_nan_proportion
-from .filter_reads_on_modification_thresholds import filter_reads_on_modification_thresholds
-from .filter_reads_on_length_quality_mapping import filter_reads_on_length_quality_mapping
-from .invert_adata import invert_adata
-from .load_sample_sheet import load_sample_sheet
-from .flag_duplicate_reads import flag_duplicate_reads
-from .reindex_references_adata import reindex_references_adata
-from .subsample_adata import subsample_adata
+from __future__ import annotations
 
-__all__ = [
-    "append_base_context",
-    "append_binary_layer_by_base_context",
-    "binarize_on_Youden",
-    "binarize_adata",
-    "calculate_complexity_II",
-    "calculate_read_modification_stats",
-    "calculate_coverage",    
-    "calculate_position_Youden",
-    "calculate_read_length_stats",
-    "clean_NaN",   
-    "filter_adata_by_nan_proportion",
-    "filter_reads_on_modification_thresholds",
-    "filter_reads_on_length_quality_mapping",
-    "invert_adata",
-    "load_sample_sheet",
-    "flag_duplicate_reads",
-    "subsample_adata"
-]
+from importlib import import_module
+
+_LAZY_ATTRS = {
+    "append_base_context": "smftools.preprocessing.append_base_context",
+    "append_binary_layer_by_base_context": "smftools.preprocessing.append_binary_layer_by_base_context",
+    "binarize_adata": "smftools.preprocessing.binarize",
+    "binarize_on_Youden": "smftools.preprocessing.binarize_on_Youden",
+    "calculate_complexity_II": "smftools.preprocessing.calculate_complexity_II",
+    "calculate_coverage": "smftools.preprocessing.calculate_coverage",
+    "calculate_position_Youden": "smftools.preprocessing.calculate_position_Youden",
+    "calculate_read_length_stats": "smftools.preprocessing.calculate_read_length_stats",
+    "calculate_read_modification_stats": "smftools.preprocessing.calculate_read_modification_stats",
+    "clean_NaN": "smftools.preprocessing.clean_NaN",
+    "filter_adata_by_nan_proportion": "smftools.preprocessing.filter_adata_by_nan_proportion",
+    "filter_reads_on_length_quality_mapping": "smftools.preprocessing.filter_reads_on_length_quality_mapping",
+    "filter_reads_on_modification_thresholds": "smftools.preprocessing.filter_reads_on_modification_thresholds",
+    "flag_duplicate_reads": "smftools.preprocessing.flag_duplicate_reads",
+    "invert_adata": "smftools.preprocessing.invert_adata",
+    "load_sample_sheet": "smftools.preprocessing.load_sample_sheet",
+    "reindex_references_adata": "smftools.preprocessing.reindex_references_adata",
+    "subsample_adata": "smftools.preprocessing.subsample_adata",
+}
+
+
+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__ = list(_LAZY_ATTRS.keys())

smftools/preprocessing/append_base_context.py

@@ -1,28 +1,38 @@
-def append_base_context(adata, 
-                        ref_column='Reference_strand', 
-                        use_consensus=False,
-                        native=False, 
-                        mod_target_bases=['GpC', 'CpG'],
-                        bypass=False,
-                        force_redo=False,
-                        uns_flag='append_base_context_performed'
-):
-    """
-    Adds nucleobase context to the position within the given category. When use_consensus is True, it uses the consensus sequence, otherwise it defaults to the FASTA sequence.
-    This needs to be performed prior to AnnData inversion step.
-
-    Parameters:
-        adata (AnnData): The input adata object.
-        ref_column (str): The observation column in which to stratify on. Default is 'Reference_strand', which should not be changed for most purposes.
-        use_consensus (bool): A truth statement indicating whether to use the consensus sequence from the reads mapped to the reference. If False, the reference FASTA is used instead.
-        native (bool): If False, perform conversion SMF assumptions. If True, perform native SMF assumptions
-        mod_target_bases (list): Base contexts that may be modified.
-    
-    Returns:
-        None
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+from smftools.logging_utils import get_logger
+
+if TYPE_CHECKING:
+    import anndata as ad
+
+logger = get_logger(__name__)
+
+
+def append_base_context(
+    adata: "ad.AnnData",
+    ref_column: str = "Reference_strand",
+    use_consensus: bool = False,
+    native: bool = False,
+    mod_target_bases: list[str] = ["GpC", "CpG"],
+    bypass: bool = False,
+    force_redo: bool = False,
+    uns_flag: str = "append_base_context_performed",
+) -> None:
+    """Append base context annotations to ``adata``.
+
+    Args:
+        adata: AnnData object.
+        ref_column: Obs column used to stratify references.
+        use_consensus: Whether to use consensus sequences rather than FASTA references.
+        native: If ``True``, use native SMF assumptions; otherwise use conversion assumptions.
+        mod_target_bases: Base contexts that may be modified.
+        bypass: Whether to skip processing.
+        force_redo: Whether to rerun even if ``uns_flag`` is set.
+        uns_flag: Flag in ``adata.uns`` indicating prior completion.
     """
     import numpy as np
-    import anndata as ad
 
     # Only run if not already performed
     already = bool(adata.uns.get(uns_flag, False))
@@ -30,102 +40,118 @@ def append_base_context(adata,
         # QC already performed; nothing to do
         return
 
-    print('Adding base context based on reference FASTA sequence for sample')
+    logger.info("Adding base context based on reference FASTA sequence for sample")
     references = adata.obs[ref_column].cat.categories
     site_types = []
-    
-    if any(base in mod_target_bases for base in ['GpC', 'CpG', 'C']):
-        site_types += ['GpC_site', 'CpG_site', 'ambiguous_GpC_CpG_site', 'other_C_site', 'C_site']
-    
-    if 'A' in mod_target_bases:
-        site_types += ['A_site']
+
+    if any(base in mod_target_bases for base in ["GpC", "CpG", "C"]):
+        site_types += ["GpC_site", "CpG_site", "ambiguous_GpC_CpG_site", "other_C_site", "C_site"]
+
+    if "A" in mod_target_bases:
+        site_types += ["A_site"]
 
     for ref in references:
         # Assess if the strand is the top or bottom strand converted
-        if 'top' in ref:
-            strand = 'top'
-        elif 'bottom' in ref:
-            strand = 'bottom'
+        if "top" in ref:
+            strand = "top"
+        elif "bottom" in ref:
+            strand = "bottom"
 
         if native:
             basename = ref.split(f"_{strand}")[0]
             if use_consensus:
-                sequence = adata.uns[f'{basename}_consensus_sequence']
+                sequence = adata.uns[f"{basename}_consensus_sequence"]
             else:
                 # This sequence is the unconverted FASTA sequence of the original input FASTA for the locus
-                sequence = adata.uns[f'{basename}_FASTA_sequence']
+                sequence = adata.uns[f"{basename}_FASTA_sequence"]
         else:
             basename = ref.split(f"_{strand}")[0]
             if use_consensus:
-                sequence = adata.uns[f'{basename}_consensus_sequence']
+                sequence = adata.uns[f"{basename}_consensus_sequence"]
             else:
                 # This sequence is the unconverted FASTA sequence of the original input FASTA for the locus
-                sequence = adata.uns[f'{basename}_FASTA_sequence']
+                sequence = adata.uns[f"{basename}_FASTA_sequence"]
 
-        # Init a dict keyed by reference site type that points to a bool of whether the position is that site type.    
+        # Init a dict keyed by reference site type that points to a bool of whether the position is that site type.
         boolean_dict = {}
         for site_type in site_types:
-            boolean_dict[f'{ref}_{site_type}'] = np.full(len(sequence), False, dtype=bool)
+            boolean_dict[f"{ref}_{site_type}"] = np.full(len(sequence), False, dtype=bool)
 
-        if any(base in mod_target_bases for base in ['GpC', 'CpG', 'C']):
-            if strand == 'top':
+        if any(base in mod_target_bases for base in ["GpC", "CpG", "C"]):
+            if strand == "top":
                 # Iterate through the sequence and apply the criteria
                 for i in range(1, len(sequence) - 1):
-                    if sequence[i] == 'C':
-                        boolean_dict[f'{ref}_C_site'][i] = True
-                        if sequence[i - 1] == 'G' and sequence[i + 1] != 'G':
-                            boolean_dict[f'{ref}_GpC_site'][i] = True
-                        elif sequence[i - 1] == 'G' and sequence[i + 1] == 'G':
-                            boolean_dict[f'{ref}_ambiguous_GpC_CpG_site'][i] = True
-                        elif sequence[i - 1] != 'G' and sequence[i + 1] == 'G':
-                            boolean_dict[f'{ref}_CpG_site'][i] = True
-                        elif sequence[i - 1] != 'G' and sequence[i + 1] != 'G':
-                            boolean_dict[f'{ref}_other_C_site'][i] = True
-            elif strand == 'bottom':
+                    if sequence[i] == "C":
+                        boolean_dict[f"{ref}_C_site"][i] = True
+                        if sequence[i - 1] == "G" and sequence[i + 1] != "G":
+                            boolean_dict[f"{ref}_GpC_site"][i] = True
+                        elif sequence[i - 1] == "G" and sequence[i + 1] == "G":
+                            boolean_dict[f"{ref}_ambiguous_GpC_CpG_site"][i] = True
+                        elif sequence[i - 1] != "G" and sequence[i + 1] == "G":
+                            boolean_dict[f"{ref}_CpG_site"][i] = True
+                        elif sequence[i - 1] != "G" and sequence[i + 1] != "G":
+                            boolean_dict[f"{ref}_other_C_site"][i] = True
+            elif strand == "bottom":
                 # Iterate through the sequence and apply the criteria
                 for i in range(1, len(sequence) - 1):
-                    if sequence[i] == 'G':
-                        boolean_dict[f'{ref}_C_site'][i] = True
-                        if sequence[i + 1] == 'C' and sequence[i - 1] != 'C':
-                            boolean_dict[f'{ref}_GpC_site'][i] = True
-                        elif sequence[i - 1] == 'C' and sequence[i + 1] == 'C':
-                            boolean_dict[f'{ref}_ambiguous_GpC_CpG_site'][i] = True
-                        elif sequence[i - 1] == 'C' and sequence[i + 1] != 'C':
-                            boolean_dict[f'{ref}_CpG_site'][i] = True
-                        elif sequence[i - 1] != 'C' and sequence[i + 1] != 'C':
-                            boolean_dict[f'{ref}_other_C_site'][i] = True
+                    if sequence[i] == "G":
+                        boolean_dict[f"{ref}_C_site"][i] = True
+                        if sequence[i + 1] == "C" and sequence[i - 1] != "C":
+                            boolean_dict[f"{ref}_GpC_site"][i] = True
+                        elif sequence[i - 1] == "C" and sequence[i + 1] == "C":
+                            boolean_dict[f"{ref}_ambiguous_GpC_CpG_site"][i] = True
+                        elif sequence[i - 1] == "C" and sequence[i + 1] != "C":
+                            boolean_dict[f"{ref}_CpG_site"][i] = True
+                        elif sequence[i - 1] != "C" and sequence[i + 1] != "C":
+                            boolean_dict[f"{ref}_other_C_site"][i] = True
             else:
-                print('Error: top or bottom strand of conversion could not be determined. Ensure this value is in the Reference name.')
+                logger.error(
+                    "Top or bottom strand of conversion could not be determined. Ensure this value is in the Reference name."
+                )
 
-        if 'A' in mod_target_bases:
-            if strand == 'top':
+        if "A" in mod_target_bases:
+            if strand == "top":
                 # Iterate through the sequence and apply the criteria
                 for i in range(1, len(sequence) - 1):
-                    if sequence[i] == 'A':
-                        boolean_dict[f'{ref}_A_site'][i] = True
-            elif strand == 'bottom':
+                    if sequence[i] == "A":
+                        boolean_dict[f"{ref}_A_site"][i] = True
+            elif strand == "bottom":
                 # Iterate through the sequence and apply the criteria
                 for i in range(1, len(sequence) - 1):
-                    if sequence[i] == 'T':
-                        boolean_dict[f'{ref}_A_site'][i] = True
+                    if sequence[i] == "T":
+                        boolean_dict[f"{ref}_A_site"][i] = True
             else:
-                print('Error: top or bottom strand of conversion could not be determined. Ensure this value is in the Reference name.')
+                logger.error(
+                    "Top or bottom strand of conversion could not be determined. Ensure this value is in the Reference name."
+                )
 
         for site_type in site_types:
             # Site context annotations for each reference
-            adata.var[f'{ref}_{site_type}'] = boolean_dict[f'{ref}_{site_type}'].astype(bool)
+            adata.var[f"{ref}_{site_type}"] = boolean_dict[f"{ref}_{site_type}"].astype(bool)
             # Restrict the site type labels to only be in positions that occur at a high enough frequency in the dataset
-            if adata.uns["calculate_coverage_performed"] == True:
-                adata.var[f'{ref}_{site_type}'] = (adata.var[f'{ref}_{site_type}']) & (adata.var[f'position_in_{ref}'])
+            if adata.uns.get("calculate_coverage_performed", False):
+                adata.var[f"{ref}_{site_type}_valid_coverage"] = (
+                    (adata.var[f"{ref}_{site_type}"]) & (adata.var[f"position_in_{ref}"])
+                )
+                if native:
+                    adata.obsm[f"{ref}_{site_type}_valid_coverage"] = adata[
+                        :, adata.var[f"{ref}_{site_type}_valid_coverage"]
+                    ].layers["binarized_methylation"]
+                else:
+                    adata.obsm[f"{ref}_{site_type}_valid_coverage"] = adata[
+                        :, adata.var[f"{ref}_{site_type}_valid_coverage"]
+                    ].X
             else:
                 pass
-            
+
             if native:
-                adata.obsm[f'{ref}_{site_type}'] = adata[:, adata.var[f'{ref}_{site_type}'] == True].layers['binarized_methylation']
+                adata.obsm[f"{ref}_{site_type}"] = adata[:, adata.var[f"{ref}_{site_type}"]].layers[
+                    "binarized_methylation"
+                ]
             else:
-                adata.obsm[f'{ref}_{site_type}'] = adata[:, adata.var[f'{ref}_{site_type}'] == True].X
+                adata.obsm[f"{ref}_{site_type}"] = adata[:, adata.var[f"{ref}_{site_type}"]].X
 
     # mark as done
     adata.uns[uns_flag] = True
 
-    return None
+    return None

smftools/preprocessing/append_binary_layer_by_base_context.py

@@ -1,29 +1,47 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
 import numpy as np
 import scipy.sparse as sp
 
+from smftools.logging_utils import get_logger
+
+if TYPE_CHECKING:
+    import anndata as ad
+
+logger = get_logger(__name__)
+
+
 def append_binary_layer_by_base_context(
-    adata,
+    adata: "ad.AnnData",
     reference_column: str,
     smf_modality: str = "conversion",
     verbose: bool = True,
     uns_flag: str = "append_binary_layer_by_base_context_performed",
     bypass: bool = False,
-    force_redo: bool = False
-):
-    """
-    Build per-reference C/G-site masked layers:
-      - GpC_site_binary
-      - CpG_site_binary
-      - GpC_CpG_combined_site_binary (numeric sum where present; NaN where neither present)
-      - C_site_binary
-      - other_C_site_binary
-
-    Behavior:
-      - If X is sparse it will be converted to dense for these layers (keeps original adata.X untouched).
-      - Missing var columns are warned about but do not crash.
-      - Masked positions are filled with np.nan to make masked vs unmasked explicit.
-      - Requires append_base_context to be run first
+    force_redo: bool = False,
+    from_valid_sites_only: bool = False,
+    valid_site_col_suffix: str = "_valid_coverage",
+) -> "ad.AnnData":
+    """Build per-reference masked layers for base-context sites.
+
+    Args:
+        adata: AnnData object to annotate.
+        reference_column: Obs column containing reference identifiers.
+        smf_modality: SMF modality identifier.
+        verbose: Whether to log layer summary information.
+        uns_flag: Flag in ``adata.uns`` indicating prior completion.
+        bypass: Whether to skip processing.
+        force_redo: Whether to rerun even if ``uns_flag`` is set.
+        from_valid_sites_only: Whether to use valid-coverage site masks only.
+        valid_site_col_suffix: Suffix for valid-coverage site columns.
+
+    Returns:
+        anndata.AnnData: AnnData object with new masked layers.
     """
+    if not from_valid_sites_only:
+        valid_site_col_suffix = ""
 
     # Only run if not already performed
     already = bool(adata.uns.get(uns_flag, False))
@@ -46,17 +64,25 @@ def append_binary_layer_by_base_context(
 
     # expected per-reference var column names
     references = adata.obs[reference_column].astype("category").cat.categories
-    reference_to_gpc_column = {ref: f"{ref}_GpC_site" for ref in references}
-    reference_to_cpg_column = {ref: f"{ref}_CpG_site" for ref in references}
-    reference_to_c_column = {ref: f"{ref}_C_site" for ref in references}
-    reference_to_other_c_column = {ref: f"{ref}_other_C_site" for ref in references}
+    reference_to_gpc_column = {ref: f"{ref}_GpC_site{valid_site_col_suffix}" for ref in references}
+    reference_to_cpg_column = {ref: f"{ref}_CpG_site{valid_site_col_suffix}" for ref in references}
+    reference_to_c_column = {ref: f"{ref}_C_site{valid_site_col_suffix}" for ref in references}
+    reference_to_other_c_column = {
+        ref: f"{ref}_other_C_site{valid_site_col_suffix}" for ref in references
+    }
+    reference_to_a_column = {ref: f"{ref}_A_site{valid_site_col_suffix}" for ref in references}
 
     # verify var columns exist and build boolean masks per ref (len = n_vars)
     n_obs, n_vars = adata.shape
+
     def _col_mask_or_warn(colname):
+        """Return a boolean mask for a var column, or all-False if missing."""
         if colname not in adata.var.columns:
             if verbose:
-                print(f"Warning: var column '{colname}' not found; treating as all-False mask.")
+                logger.warning(
+                    "Var column '%s' not found; treating as all-False mask.",
+                    colname,
+                )
             return np.zeros(n_vars, dtype=bool)
         vals = adata.var[colname].values
         # coerce truthiness
@@ -67,14 +93,17 @@ def append_binary_layer_by_base_context(
 
     gpc_var_masks = {ref: _col_mask_or_warn(col) for ref, col in reference_to_gpc_column.items()}
     cpg_var_masks = {ref: _col_mask_or_warn(col) for ref, col in reference_to_cpg_column.items()}
-    c_var_masks =   {ref: _col_mask_or_warn(col) for ref, col in reference_to_c_column.items()}
-    other_c_var_masks = {ref: _col_mask_or_warn(col) for ref, col in reference_to_other_c_column.items()}
+    c_var_masks = {ref: _col_mask_or_warn(col) for ref, col in reference_to_c_column.items()}
+    other_c_var_masks = {
+        ref: _col_mask_or_warn(col) for ref, col in reference_to_other_c_column.items()
+    }
+    a_var_masks = {ref: _col_mask_or_warn(col) for ref, col in reference_to_a_column.items()}
 
     # prepare X as dense float32 for layer filling (we leave adata.X untouched)
     X = adata.X
     if sp.issparse(X):
         if verbose:
-            print("Converting sparse X to dense array for layer construction (temporary).")
+            logger.info("Converting sparse X to dense array for layer construction (temporary).")
         X = X.toarray()
     X = np.asarray(X, dtype=np.float32)
 
@@ -83,11 +112,12 @@ def append_binary_layer_by_base_context(
     masked_cpg = np.full((n_obs, n_vars), np.nan, dtype=np.float32)
     masked_any_c = np.full((n_obs, n_vars), np.nan, dtype=np.float32)
     masked_other_c = np.full((n_obs, n_vars), np.nan, dtype=np.float32)
+    masked_a = np.full((n_obs, n_vars), np.nan, dtype=np.float32)
 
     # fill row-blocks per reference (this avoids creating a full row×var boolean mask)
     obs_ref_series = adata.obs[reference_column]
     for ref in references:
-        rows_mask = (obs_ref_series.values == ref)
+        rows_mask = obs_ref_series.values == ref
         if not rows_mask.any():
             continue
         row_idx = np.nonzero(rows_mask)[0]  # integer indices of rows for this ref
@@ -95,8 +125,9 @@ def append_binary_layer_by_base_context(
         # column masks for this ref
         gpc_cols = gpc_var_masks.get(ref, np.zeros(n_vars, dtype=bool))
         cpg_cols = cpg_var_masks.get(ref, np.zeros(n_vars, dtype=bool))
-        c_cols   = c_var_masks.get(ref, np.zeros(n_vars, dtype=bool))
+        c_cols = c_var_masks.get(ref, np.zeros(n_vars, dtype=bool))
         other_c_cols = other_c_var_masks.get(ref, np.zeros(n_vars, dtype=bool))
+        a_cols = a_var_masks.get(ref, np.zeros(n_vars, dtype=bool))
 
         if gpc_cols.any():
             # assign only the submatrix (rows x selected cols)
@@ -107,6 +138,8 @@ def append_binary_layer_by_base_context(
             masked_any_c[np.ix_(row_idx, c_cols)] = X[np.ix_(row_idx, c_cols)]
         if other_c_cols.any():
             masked_other_c[np.ix_(row_idx, other_c_cols)] = X[np.ix_(row_idx, other_c_cols)]
+        if a_cols.any():
+            masked_a[np.ix_(row_idx, other_c_cols)] = X[np.ix_(row_idx, other_c_cols)]
 
     # Build combined layer:
     # - numeric_sum: sum where either exists, NaN where neither exists
@@ -121,21 +154,26 @@ def append_binary_layer_by_base_context(
     # combined_bool = (~gpc_nan & (masked_gpc != 0)) | (~cpg_nan & (masked_cpg != 0))
     # combined_layer = combined_bool.astype(np.float32)
 
-    adata.layers['GpC_site_binary'] = masked_gpc
-    adata.layers['CpG_site_binary'] = masked_cpg
-    adata.layers['GpC_CpG_combined_site_binary'] = combined_sum
-    adata.layers['C_site_binary'] = masked_any_c
-    adata.layers['other_C_site_binary'] = masked_other_c
+    adata.layers["GpC_site_binary"] = masked_gpc
+    adata.layers["CpG_site_binary"] = masked_cpg
+    adata.layers["GpC_CpG_combined_site_binary"] = combined_sum
+    adata.layers["C_site_binary"] = masked_any_c
+    adata.layers["other_C_site_binary"] = masked_other_c
+    adata.layers["A_site_binary"] = masked_a
 
     if verbose:
+
         def _filled_positions(arr):
+            """Count the number of non-NaN positions in an array."""
             return int(np.sum(~np.isnan(arr)))
-        print("Layer build summary (non-NaN cell counts):")
-        print(f"  GpC: {_filled_positions(masked_gpc)}")
-        print(f"  CpG: {_filled_positions(masked_cpg)}")
-        print(f"  GpC+CpG combined: {_filled_positions(combined_sum)}")
-        print(f"  C: {_filled_positions(masked_any_c)}")
-        print(f"  other_C: {_filled_positions(masked_other_c)}")
+
+        logger.info("Layer build summary (non-NaN cell counts):")
+        logger.info("  GpC: %s", _filled_positions(masked_gpc))
+        logger.info("  CpG: %s", _filled_positions(masked_cpg))
+        logger.info("  GpC+CpG combined: %s", _filled_positions(combined_sum))
+        logger.info("  C: %s", _filled_positions(masked_any_c))
+        logger.info("  other_C: %s", _filled_positions(masked_other_c))
+        logger.info("  A: %s", _filled_positions(masked_a))
 
     # mark as done
     adata.uns[uns_flag] = True

smftools/preprocessing/{archives → archived}/add_read_length_and_mapping_qc.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import numpy as np
 import pandas as pd
 import scipy.sparse as sp

smftools/preprocessing/{archives → archived}/calculate_complexity.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## calculate_complexity
 
 def calculate_complexity(adata, output_directory='', obs_column='Reference', sample_col='Sample_names', plot=True, save_plot=False):
@@ -21,9 +23,11 @@ def calculate_complexity(adata, output_directory='', obs_column='Reference', sam
     from scipy.optimize import curve_fit
 
     def lander_waterman(x, C0):
+        """Lander-Waterman curve for complexity estimation."""
         return C0 * (1 - np.exp(-x / C0))
 
     def count_unique_reads(reads, depth):
+        """Count unique reads in a subsample of the given depth."""
         subsample = np.random.choice(reads, depth, replace=False)
         return len(np.unique(subsample))
 
@@ -69,4 +73,4 @@ def calculate_complexity(adata, output_directory='', obs_column='Reference', sam
                     plt.savefig(save_name, bbox_inches='tight', pad_inches=0.1)
                     plt.close()
                 else:
-                    plt.show()
+                    plt.show()

smftools/preprocessing/{archives → archived}/mark_duplicates.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## mark_duplicates
 
 def mark_duplicates(adata, layers, obs_column='Reference', sample_col='Sample_names', method='N_masked_distances', distance_thresholds={}):