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

smftools/preprocessing/flag_duplicate_reads.py

@@ -1,51 +1,64 @@
+from __future__ import annotations
+
 # duplicate_detection_with_hier_and_plots.py
 import copy
 import math
 import os
 import warnings
 from collections import defaultdict
-from typing import Any, Dict, List, Optional, Sequence, Tuple, Union
+from importlib.util import find_spec
+from typing import TYPE_CHECKING, Any, Dict, List, Optional, Sequence, Tuple, Union
 
-import anndata as ad
-import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
-import torch
+from scipy.cluster import hierarchy as sch
+from scipy.spatial.distance import pdist, squareform
+from scipy.stats import gaussian_kde
 
 from smftools.logging_utils import get_logger
+from smftools.optional_imports import require
 
 from ..readwrite import make_dirs
 
 logger = get_logger(__name__)
 
-# optional imports for clustering / PCA / KDE
-try:
-    from scipy.cluster import hierarchy as sch
-    from scipy.spatial.distance import pdist, squareform
-
-    SCIPY_AVAILABLE = True
-except Exception:
-    sch = None
-    pdist = None
-    squareform = None
-    SCIPY_AVAILABLE = False
+plt = require("matplotlib.pyplot", extra="plotting", purpose="duplicate read plots")
+torch = require("torch", extra="torch", purpose="duplicate read detection")
 
-try:
-    from sklearn.cluster import DBSCAN, KMeans
-    from sklearn.decomposition import PCA
-    from sklearn.metrics import silhouette_score
-    from sklearn.mixture import GaussianMixture
+if TYPE_CHECKING:
+    import anndata as ad
 
-    SKLEARN_AVAILABLE = True
-except Exception:
-    PCA = None
-    KMeans = DBSCAN = GaussianMixture = silhouette_score = None
-    SKLEARN_AVAILABLE = False
+SCIPY_AVAILABLE = True
+SKLEARN_AVAILABLE = find_spec("sklearn") is not None
 
-try:
-    from scipy.stats import gaussian_kde
-except Exception:
-    gaussian_kde = None
+PCA = None
+KMeans = DBSCAN = GaussianMixture = silhouette_score = None
+if SKLEARN_AVAILABLE:
+    sklearn_cluster = require(
+        "sklearn.cluster",
+        extra="ml-base",
+        purpose="duplicate read clustering",
+    )
+    sklearn_decomp = require(
+        "sklearn.decomposition",
+        extra="ml-base",
+        purpose="duplicate read PCA",
+    )
+    sklearn_metrics = require(
+        "sklearn.metrics",
+        extra="ml-base",
+        purpose="duplicate read clustering diagnostics",
+    )
+    sklearn_mixture = require(
+        "sklearn.mixture",
+        extra="ml-base",
+        purpose="duplicate read clustering",
+    )
+    DBSCAN = sklearn_cluster.DBSCAN
+    KMeans = sklearn_cluster.KMeans
+    PCA = sklearn_decomp.PCA
+    silhouette_score = sklearn_metrics.silhouette_score
+    GaussianMixture = sklearn_mixture.GaussianMixture
 
 
 def merge_uns_preserve(orig_uns: dict, new_uns: dict, prefer: str = "orig") -> dict:
@@ -153,24 +166,6 @@ def flag_duplicate_reads(
     import numpy as np
     import pandas as pd
 
-    # optional imports already guarded at module import time, but re-check
-    try:
-        from scipy.cluster import hierarchy as sch
-        from scipy.spatial.distance import pdist
-
-        SCIPY_AVAILABLE = True
-    except Exception:
-        sch = None
-        pdist = None
-        SCIPY_AVAILABLE = False
-    try:
-        from sklearn.decomposition import PCA
-
-        SKLEARN_AVAILABLE = True
-    except Exception:
-        PCA = None
-        SKLEARN_AVAILABLE = False
-
     # -------- helper: demux-aware keeper selection --------
     def _choose_keeper_with_demux_preference(
         members_idx: List[int],
@@ -1577,13 +1572,6 @@ def _run_clustering(
     Run clustering on 2D points (x,y). Returns labels (len = npoints) and diagnostics dict.
     Labels follow sklearn conventions (noise -> -1 for DBSCAN/HDBSCAN).
     """
-    try:
-        from sklearn.cluster import DBSCAN, KMeans
-        from sklearn.metrics import silhouette_score
-        from sklearn.mixture import GaussianMixture
-    except Exception:
-        KMeans = DBSCAN = GaussianMixture = silhouette_score = None
-
     pts = np.column_stack([x, y])
     diagnostics: Dict[str, Any] = {"method": method, "n_input": len(x)}
     if len(x) < min_points:

smftools/preprocessing/make_dirs.py

@@ -1,5 +1,6 @@
-## make_dirs
+from __future__ import annotations
 
+## make_dirs
 from smftools.logging_utils import get_logger
 
 logger = get_logger(__name__)

smftools/preprocessing/min_non_diagonal.py

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

smftools/preprocessing/recipes.py

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

smftools/tools/__init__.py

@@ -1,19 +1,27 @@
-from .calculate_umap import calculate_umap
-from .cluster_adata_on_methylation import cluster_adata_on_methylation
-from .general_tools import combine_layers, create_nan_mask_from_X, create_nan_or_non_gpc_mask
-from .position_stats import calculate_relative_risk_on_activity, compute_positionwise_statistics
-from .read_stats import calculate_row_entropy
-from .spatial_autocorrelation import *
-from .subset_adata import subset_adata
+from __future__ import annotations
 
-__all__ = [
-    "compute_positionwise_statistics",
-    "calculate_row_entropy",
-    "calculate_umap",
-    "calculate_relative_risk_on_activity",
-    "cluster_adata_on_methylation",
-    "create_nan_mask_from_X",
-    "create_nan_or_non_gpc_mask",
-    "combine_layers",
-    "subset_adata",
-]
+from importlib import import_module
+
+_LAZY_ATTRS = {
+    "calculate_umap": "smftools.tools.calculate_umap",
+    "cluster_adata_on_methylation": "smftools.tools.cluster_adata_on_methylation",
+    "combine_layers": "smftools.tools.general_tools",
+    "create_nan_mask_from_X": "smftools.tools.general_tools",
+    "create_nan_or_non_gpc_mask": "smftools.tools.general_tools",
+    "calculate_relative_risk_on_activity": "smftools.tools.position_stats",
+    "compute_positionwise_statistics": "smftools.tools.position_stats",
+    "calculate_row_entropy": "smftools.tools.read_stats",
+    "subset_adata": "smftools.tools.subset_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/tools/archived/apply_hmm.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import numpy as np
 import pandas as pd
 import torch

smftools/tools/archived/classifiers.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 ## Train CNN, RNN, Random Forest models on double barcoded, low contamination datasets
 import torch
 import torch.nn as nn

smftools/tools/archived/classify_methylated_features.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # classify_methylated_features
 
 def classify_methylated_features(read, model, coordinates, classification_mapping={}):

smftools/tools/archived/classify_non_methylated_features.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # classify_non_methylated_features
 
 def classify_non_methylated_features(read, model, coordinates, classification_mapping={}):

smftools/tools/archived/subset_adata_v1.py

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

smftools/tools/archived/subset_adata_v2.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # subset_adata
 
 def subset_adata(adata, columns, cat_type='obs'):

smftools/tools/calculate_umap.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 from typing import TYPE_CHECKING, Sequence
 
 from smftools.logging_utils import get_logger
+from smftools.optional_imports import require
 
 if TYPE_CHECKING:
     import anndata as ad
@@ -36,7 +37,8 @@ def calculate_umap(
     import os
 
     import numpy as np
-    import scanpy as sc
+
+    sc = require("scanpy", extra="scanpy", purpose="UMAP calculation")
     from scipy.sparse import issparse
 
     os.environ["OMP_NUM_THREADS"] = str(threads)

smftools/tools/cluster_adata_on_methylation.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 from typing import TYPE_CHECKING, Sequence
 
 from smftools.logging_utils import get_logger
+from smftools.optional_imports import require
 
 if TYPE_CHECKING:
     import anndata as ad
@@ -109,7 +110,12 @@ def cluster_adata_on_methylation(
                     )
             elif method == "kmeans":
                 try:
-                    from sklearn.cluster import KMeans
+                    sklearn_cluster = require(
+                        "sklearn.cluster",
+                        extra="ml-base",
+                        purpose="k-means clustering",
+                    )
+                    KMeans = sklearn_cluster.KMeans
 
                     kmeans = KMeans(n_clusters=n_clusters)
                     kmeans.fit(site_subset.layers[layer])

smftools/tools/position_stats.py

@@ -1,41 +1,26 @@
 from __future__ import annotations
 
+import os
 import warnings
+from contextlib import contextmanager
+from itertools import cycle
 from typing import TYPE_CHECKING, Dict, List, Optional, Sequence, Tuple
 
-if TYPE_CHECKING:
-    import anndata as ad
-
-import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
+from scipy.stats import chi2_contingency
+from tqdm import tqdm
 
-# optional imports
-try:
-    from joblib import Parallel, delayed
-
-    JOBLIB_AVAILABLE = True
-except Exception:
-    JOBLIB_AVAILABLE = False
+from smftools.optional_imports import require
 
-try:
-    from scipy.stats import chi2_contingency
+if TYPE_CHECKING:
+    import anndata as ad
 
-    SCIPY_STATS_AVAILABLE = True
-except Exception:
-    SCIPY_STATS_AVAILABLE = False
+plt = require("matplotlib.pyplot", extra="plotting", purpose="position stats plots")
 
 # -----------------------------
 # Compute positionwise statistic (multi-method + simple site_types)
 # -----------------------------
-import os
-from contextlib import contextmanager
-from itertools import cycle
-
-import joblib
-from joblib import Parallel, cpu_count, delayed
-from scipy.stats import chi2_contingency
-from tqdm import tqdm
 
 
 # ------------------------- Utilities -------------------------
@@ -197,6 +182,8 @@ def calculate_relative_risk_on_activity(
 @contextmanager
 def tqdm_joblib(tqdm_object: tqdm):
     """Context manager to patch joblib to update a tqdm progress bar."""
+    joblib = require("joblib", extra="ml-base", purpose="parallel position statistics")
+
     old = joblib.parallel.BatchCompletionCallBack
 
     class TqdmBatchCompletionCallback(old):  # type: ignore
@@ -315,6 +302,8 @@ def compute_positionwise_statistics(
         max_threads: Maximum number of threads.
         reverse_indices_on_store: Whether to reverse indices on output storage.
     """
+    joblib = require("joblib", extra="ml-base", purpose="parallel position statistics")
+
     if isinstance(methods, str):
         methods = [methods]
     methods = [m.lower() for m in methods]
@@ -325,7 +314,7 @@ def compute_positionwise_statistics(
 
     # workers
     if max_threads is None or max_threads <= 0:
-        n_jobs = max(1, cpu_count() or 1)
+        n_jobs = max(1, joblib.cpu_count() or 1)
     else:
         n_jobs = max(1, int(max_threads))
 
@@ -439,13 +428,14 @@ def compute_positionwise_statistics(
                             worker = _relative_risk_row_job
                         out = np.full((n_pos, n_pos), np.nan, dtype=float)
                         tasks = (
-                            delayed(worker)(i, X_bin, min_count_for_pairwise) for i in range(n_pos)
+                            joblib.delayed(worker)(i, X_bin, min_count_for_pairwise)
+                            for i in range(n_pos)
                         )
                         pbar_rows = tqdm(
                             total=n_pos, desc=f"{m}: rows ({sample}__{ref})", leave=False
                         )
                         with tqdm_joblib(pbar_rows):
-                            results = Parallel(n_jobs=n_jobs, prefer="processes")(tasks)
+                            results = joblib.Parallel(n_jobs=n_jobs, prefer="processes")(tasks)
                         pbar_rows.close()
                         for i, row in results:
                             out[int(i), :] = row

{smftools-0.2.5.dist-info → smftools-0.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: smftools
-Version: 0.2.5
+Version: 0.3.0
 Summary: Single Molecule Footprinting Analysis in Python.
 Project-URL: Source, https://github.com/jkmckenna/smftools
 Project-URL: Documentation, https://smftools.readthedocs.io/
@@ -29,7 +29,7 @@ License: MIT License
         SOFTWARE.
 License-File: LICENSE
 Keywords: anndata,chromatin-accessibility,machine-learning,nanopore,protein-dna-binding,single-locus,single-molecule-footprinting
-Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Development Status :: 3 - Alpha
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
@@ -41,38 +41,41 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
-Classifier: Programming Language :: Python :: 3.14
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Classifier: Topic :: Scientific/Engineering :: Visualization
 Requires-Python: >=3.10
 Requires-Dist: anndata>=0.10.0
 Requires-Dist: biopython>=1.79
-Requires-Dist: captum
 Requires-Dist: click
-Requires-Dist: fastcluster
-Requires-Dist: hydra-core
-Requires-Dist: igraph
-Requires-Dist: leidenalg
-Requires-Dist: lightning
-Requires-Dist: multiqc
-Requires-Dist: networkx>=3.2
 Requires-Dist: numpy<2,>=1.22.0
-Requires-Dist: omegaconf
 Requires-Dist: pandas>=1.4.2
-Requires-Dist: pod5>=0.1.21
-Requires-Dist: pybedtools>=0.12.0
-Requires-Dist: pybigwig>=0.3.24
-Requires-Dist: pyfaidx>=0.8.0
-Requires-Dist: pysam>=0.19.1
-Requires-Dist: scanpy>=1.9
-Requires-Dist: scikit-learn>=1.0.2
 Requires-Dist: scipy>=1.7.3
-Requires-Dist: seaborn>=0.11
-Requires-Dist: shap
-Requires-Dist: torch>=1.9.0
 Requires-Dist: tqdm
-Requires-Dist: upsetplot
-Requires-Dist: wandb
+Provides-Extra: all
+Requires-Dist: captum; extra == 'all'
+Requires-Dist: fastcluster; extra == 'all'
+Requires-Dist: hydra-core; extra == 'all'
+Requires-Dist: igraph; extra == 'all'
+Requires-Dist: leidenalg; extra == 'all'
+Requires-Dist: lightning; extra == 'all'
+Requires-Dist: matplotlib>=3.6.2; extra == 'all'
+Requires-Dist: multiqc; extra == 'all'
+Requires-Dist: networkx>=3.2; extra == 'all'
+Requires-Dist: omegaconf; extra == 'all'
+Requires-Dist: pod5>=0.1.21; extra == 'all'
+Requires-Dist: pybedtools>=0.12.0; extra == 'all'
+Requires-Dist: pybigwig>=0.3.24; extra == 'all'
+Requires-Dist: pysam>=0.19.1; extra == 'all'
+Requires-Dist: scanpy>=1.9; extra == 'all'
+Requires-Dist: scikit-learn>=1.0.2; extra == 'all'
+Requires-Dist: seaborn>=0.11; extra == 'all'
+Requires-Dist: shap; extra == 'all'
+Requires-Dist: torch>=1.9.0; extra == 'all'
+Requires-Dist: upsetplot; extra == 'all'
+Requires-Dist: wandb; extra == 'all'
+Provides-Extra: cluster
+Requires-Dist: fastcluster; extra == 'cluster'
+Requires-Dist: leidenalg; extra == 'cluster'
 Provides-Extra: dev
 Requires-Dist: pre-commit; extra == 'dev'
 Requires-Dist: pytest; extra == 'dev'
@@ -81,20 +84,51 @@ Requires-Dist: ruff; extra == 'dev'
 Provides-Extra: docs
 Requires-Dist: ipython>=7.20; extra == 'docs'
 Requires-Dist: matplotlib!=3.6.1; extra == 'docs'
-Requires-Dist: myst-nb>=1; extra == 'docs'
-Requires-Dist: myst-parser>=2; extra == 'docs'
+Requires-Dist: myst-nb<2,>=1; extra == 'docs'
+Requires-Dist: myst-parser<3,>=2; extra == 'docs'
 Requires-Dist: nbsphinx>=0.9; extra == 'docs'
 Requires-Dist: pyyaml; extra == 'docs'
 Requires-Dist: readthedocs-sphinx-search; extra == 'docs'
 Requires-Dist: setuptools; extra == 'docs'
-Requires-Dist: sphinx-autodoc-typehints>=1.25.2; extra == 'docs'
-Requires-Dist: sphinx-book-theme>=1.1.0; extra == 'docs'
-Requires-Dist: sphinx-click; extra == 'docs'
-Requires-Dist: sphinx-copybutton; extra == 'docs'
+Requires-Dist: sphinx-autodoc-typehints<4,>=1.25.2; extra == 'docs'
+Requires-Dist: sphinx-book-theme<2,>=1.1; extra == 'docs'
+Requires-Dist: sphinx-click<7,>=5; extra == 'docs'
+Requires-Dist: sphinx-copybutton<0.6,>=0.5; extra == 'docs'
 Requires-Dist: sphinx-design; extra == 'docs'
-Requires-Dist: sphinx>=7; extra == 'docs'
-Requires-Dist: sphinxcontrib-bibtex; extra == 'docs'
-Requires-Dist: sphinxext-opengraph; extra == 'docs'
+Requires-Dist: sphinx<8,>=7; extra == 'docs'
+Requires-Dist: sphinxcontrib-bibtex<3,>=2; extra == 'docs'
+Requires-Dist: sphinxext-opengraph<0.10,>=0.9; extra == 'docs'
+Provides-Extra: misc
+Requires-Dist: networkx>=3.2; extra == 'misc'
+Requires-Dist: upsetplot; extra == 'misc'
+Provides-Extra: ml-base
+Requires-Dist: scikit-learn>=1.0.2; extra == 'ml-base'
+Requires-Dist: torch>=1.9.0; extra == 'ml-base'
+Provides-Extra: ml-extended
+Requires-Dist: captum; extra == 'ml-extended'
+Requires-Dist: hydra-core; extra == 'ml-extended'
+Requires-Dist: lightning; extra == 'ml-extended'
+Requires-Dist: omegaconf; extra == 'ml-extended'
+Requires-Dist: shap; extra == 'ml-extended'
+Requires-Dist: wandb; extra == 'ml-extended'
+Provides-Extra: ont
+Requires-Dist: pod5>=0.1.21; extra == 'ont'
+Provides-Extra: plotting
+Requires-Dist: matplotlib>=3.6.2; extra == 'plotting'
+Requires-Dist: seaborn>=0.11; extra == 'plotting'
+Provides-Extra: pybedtools
+Requires-Dist: pybedtools>=0.12.0; extra == 'pybedtools'
+Provides-Extra: pybigwig
+Requires-Dist: pybigwig>=0.3.24; extra == 'pybigwig'
+Provides-Extra: pysam
+Requires-Dist: pysam>=0.19.1; extra == 'pysam'
+Provides-Extra: qc
+Requires-Dist: multiqc; extra == 'qc'
+Provides-Extra: scanpy
+Requires-Dist: igraph; extra == 'scanpy'
+Requires-Dist: scanpy>=1.9; extra == 'scanpy'
+Provides-Extra: torch
+Requires-Dist: torch>=1.9.0; extra == 'torch'
 Description-Content-Type: text/markdown
 
 [![PyPI](https://img.shields.io/pypi/v/smftools.svg)](https://pypi.org/project/smftools)