smftools 0.3.0__py3-none-any.whl → 0.3.2__py3-none-any.whl

smftools/tools/sequence_alignment.py

@@ -0,0 +1,140 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Literal
+
+
+@dataclass(frozen=True)
+class AlignmentMismatch:
+    """Record a mismatch or gap between two aligned sequences."""
+
+    event: Literal["substitution", "insertion", "deletion"]
+    seq1_pos: int | None
+    seq1_base: str | None
+    seq2_pos: int | None
+    seq2_base: str | None
+
+
+def align_sequences_with_mismatches(
+    seq1: str,
+    seq2: str,
+    match_score: int = 1,
+    mismatch_score: int = -1,
+    gap_score: int = -1,
+    ignore_n: bool = True,
+) -> tuple[str, str, list[AlignmentMismatch]]:
+    """Globally align two sequences and return mismatch positions/bases.
+
+    The alignment uses a simple Needleman-Wunsch dynamic programming approach
+    with configurable scores. Mismatch reporting is based on the aligned
+    sequences and returns 0-based coordinates in each sequence. Gap events
+    are represented with a ``None`` coordinate for the gapped sequence.
+
+    Args:
+        seq1: First sequence (treated as reference for positions).
+        seq2: Second sequence.
+        match_score: Score for matching bases.
+        mismatch_score: Score for mismatching bases.
+        gap_score: Score for introducing a gap.
+        ignore_n: Whether to ignore mismatches involving the base ``N``.
+
+    Returns:
+        Tuple of (aligned_seq1, aligned_seq2, mismatches).
+    """
+    seq1 = seq1.upper()
+    seq2 = seq2.upper()
+    n, m = len(seq1), len(seq2)
+
+    scores = [[0] * (m + 1) for _ in range(n + 1)]
+    traceback = [[None] * (m + 1) for _ in range(n + 1)]
+
+    for i in range(1, n + 1):
+        scores[i][0] = scores[i - 1][0] + gap_score
+        traceback[i][0] = "up"
+    for j in range(1, m + 1):
+        scores[0][j] = scores[0][j - 1] + gap_score
+        traceback[0][j] = "left"
+
+    for i in range(1, n + 1):
+        for j in range(1, m + 1):
+            diag_score = scores[i - 1][j - 1] + (
+                match_score if seq1[i - 1] == seq2[j - 1] else mismatch_score
+            )
+            up_score = scores[i - 1][j] + gap_score
+            left_score = scores[i][j - 1] + gap_score
+
+            best_score = max(diag_score, up_score, left_score)
+            scores[i][j] = best_score
+            if best_score == diag_score:
+                traceback[i][j] = "diag"
+            elif best_score == up_score:
+                traceback[i][j] = "up"
+            else:
+                traceback[i][j] = "left"
+
+    aligned1: list[str] = []
+    aligned2: list[str] = []
+    i, j = n, m
+    while i > 0 or j > 0:
+        direction = traceback[i][j]
+        if direction == "diag":
+            aligned1.append(seq1[i - 1])
+            aligned2.append(seq2[j - 1])
+            i -= 1
+            j -= 1
+        elif direction == "up":
+            aligned1.append(seq1[i - 1])
+            aligned2.append("-")
+            i -= 1
+        else:
+            aligned1.append("-")
+            aligned2.append(seq2[j - 1])
+            j -= 1
+
+    aligned_seq1 = "".join(reversed(aligned1))
+    aligned_seq2 = "".join(reversed(aligned2))
+
+    mismatches: list[AlignmentMismatch] = []
+    seq1_index = 0
+    seq2_index = 0
+    for base1, base2 in zip(aligned_seq1, aligned_seq2, strict=True):
+        if base1 == "-":
+            if not (ignore_n and base2 == "N"):
+                mismatches.append(
+                    AlignmentMismatch(
+                        event="insertion",
+                        seq1_pos=None,
+                        seq1_base=None,
+                        seq2_pos=seq2_index,
+                        seq2_base=base2,
+                    )
+                )
+            seq2_index += 1
+            continue
+        if base2 == "-":
+            if not (ignore_n and base1 == "N"):
+                mismatches.append(
+                    AlignmentMismatch(
+                        event="deletion",
+                        seq1_pos=seq1_index,
+                        seq1_base=base1,
+                        seq2_pos=None,
+                        seq2_base=None,
+                    )
+                )
+            seq1_index += 1
+            continue
+        if base1 != base2 and not (ignore_n and "N" in (base1, base2)):
+            mismatches.append(
+                AlignmentMismatch(
+                    event="substitution",
+                    seq1_pos=seq1_index,
+                    seq1_base=base1,
+                    seq2_pos=seq2_index,
+                    seq2_base=base2,
+                )
+            )
+        seq1_index += 1
+        seq2_index += 1
+
+    return aligned_seq1, aligned_seq2, mismatches

smftools/tools/tensor_factorization.py

@@ -0,0 +1,217 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Iterable, Sequence
+
+import numpy as np
+
+from smftools.constants import MODKIT_EXTRACT_SEQUENCE_BASE_TO_INT
+from smftools.logging_utils import get_logger
+from smftools.optional_imports import require
+
+if TYPE_CHECKING:
+    import anndata as ad
+
+logger = get_logger(__name__)
+
+
+def build_sequence_one_hot_and_mask(
+    encoded_sequences: np.ndarray,
+    *,
+    bases: Sequence[str] = ("A", "C", "G", "T"),
+    dtype: np.dtype | type[np.floating] = np.float32,
+) -> tuple[np.ndarray, np.ndarray]:
+    """Build one-hot encoded reads and a seen/unseen mask.
+
+    Args:
+        encoded_sequences: Integer-encoded sequences shaped (n_reads, seq_len).
+        bases: Bases to one-hot encode.
+        dtype: Output dtype for the one-hot tensor.
+
+    Returns:
+        Tuple of (one_hot_tensor, mask) where:
+            - one_hot_tensor: (n_reads, seq_len, n_bases)
+            - mask: (n_reads, seq_len) boolean array indicating seen bases.
+    """
+    encoded = np.asarray(encoded_sequences)
+    if encoded.ndim != 2:
+        raise ValueError(
+            f"encoded_sequences must be 2D with shape (n_reads, seq_len); got {encoded.shape}."
+        )
+
+    base_values = np.array(
+        [MODKIT_EXTRACT_SEQUENCE_BASE_TO_INT[base] for base in bases],
+        dtype=encoded.dtype,
+    )
+
+    if np.issubdtype(encoded.dtype, np.floating):
+        encoded = encoded.copy()
+        encoded[np.isnan(encoded)] = -1
+
+    mask = np.isin(encoded, base_values)
+    one_hot = np.zeros((*encoded.shape, len(base_values)), dtype=dtype)
+
+    for idx, base_value in enumerate(base_values):
+        one_hot[..., idx] = encoded == base_value
+
+    return one_hot, mask
+
+
+def calculate_sequence_cp_decomposition(
+    adata: "ad.AnnData",
+    *,
+    layer: str,
+    var_mask: np.ndarray | None = None,
+    var_mask_name: str | None = None,
+    rank: int = 5,
+    n_iter_max: int = 100,
+    random_state: int = 0,
+    overwrite: bool = True,
+    embedding_key: str = "X_cp_sequence",
+    components_key: str = "H_cp_sequence",
+    uns_key: str = "cp_sequence",
+    bases: Iterable[str] = ("A", "C", "G", "T"),
+    backend: str = "pytorch",
+    show_progress: bool = False,
+    init: str = "random",
+    non_negative: bool = False,
+) -> "ad.AnnData":
+    """Compute CP decomposition on one-hot encoded sequence data with masking.
+
+    Args:
+        adata: AnnData object to update.
+        layer: Layer name containing integer-encoded sequences.
+        var_mask: Optional boolean mask over variables to include in the CP fit.
+        var_mask_name: Optional label describing the provided ``var_mask``.
+        rank: CP rank.
+        n_iter_max: Maximum number of iterations for the solver.
+        random_state: Random seed for initialization.
+        overwrite: Whether to recompute if the embedding already exists.
+        embedding_key: Key for embedding in ``adata.obsm``.
+        components_key: Key for position factors in ``adata.varm``.
+        uns_key: Key for metadata stored in ``adata.uns``.
+        bases: Bases to one-hot encode (in order).
+        backend: Tensorly backend to use (``numpy`` or ``pytorch``).
+        show_progress: Whether to display progress during factorization if supported.
+        non_negative: Whether to request a non-negative CP decomposition.
+
+    Returns:
+        Updated AnnData object containing the CP decomposition outputs.
+    """
+    if embedding_key in adata.obsm and components_key in adata.varm and not overwrite:
+        logger.info("CP embedding and components already present; skipping recomputation.")
+        return adata
+
+    if backend not in {"numpy", "pytorch"}:
+        raise ValueError(f"Unsupported backend '{backend}'. Use 'numpy' or 'pytorch'.")
+
+    tensorly = require("tensorly", extra="ml-base", purpose="CP decomposition")
+    from tensorly.decomposition import parafac
+
+    try:
+        from tensorly.decomposition import non_negative_parafac
+    except ImportError:
+        non_negative_parafac = None
+
+    tensorly.set_backend(backend)
+
+    if layer not in adata.layers:
+        raise KeyError(f"Layer '{layer}' not found in adata.layers.")
+
+    layer_data = adata.layers[layer]
+    mask_indices = None
+    if var_mask is not None:
+        var_mask_array = np.asarray(var_mask, dtype=bool)
+        if var_mask_array.shape[0] != adata.n_vars:
+            raise ValueError(
+                "var_mask must match adata.n_vars; "
+                f"got {var_mask_array.shape[0]} vs {adata.n_vars}."
+            )
+        if not var_mask_array.any():
+            raise ValueError("var_mask must include at least one variable.")
+        mask_indices = var_mask_array
+        layer_data = layer_data[:, var_mask_array]
+
+    one_hot, mask = build_sequence_one_hot_and_mask(layer_data, bases=tuple(bases))
+    mask_tensor = np.repeat(mask[:, :, None], one_hot.shape[2], axis=2)
+
+    device = "numpy"
+    if backend == "pytorch":
+        torch = require("torch", extra="ml-base", purpose="CP decomposition backend")
+        if torch.cuda.is_available():
+            device = torch.device("cuda")
+        elif getattr(torch.backends, "mps", None) and torch.backends.mps.is_available():
+            device = torch.device("mps")
+        else:
+            device = torch.device("cpu")
+
+        one_hot = torch.tensor(one_hot, dtype=torch.float32, device=device)
+        mask_tensor = torch.tensor(mask_tensor, dtype=torch.float32, device=device)
+
+    parafac_kwargs = {
+        "rank": rank,
+        "n_iter_max": n_iter_max,
+        "init": init,
+        "mask": mask_tensor,
+        "random_state": random_state,
+    }
+    import inspect
+
+    decomposition_fn = parafac
+    if non_negative:
+        if non_negative_parafac is not None:
+            decomposition_fn = non_negative_parafac
+        elif "non_negative" in inspect.signature(parafac).parameters:
+            parafac_kwargs["non_negative"] = True
+        else:
+            raise ValueError(
+                "Non-negative CP decomposition requested but tensorly does not support it."
+            )
+
+    if "verbose" in inspect.signature(decomposition_fn).parameters:
+        parafac_kwargs["verbose"] = show_progress
+
+    cp = decomposition_fn(one_hot, **parafac_kwargs)
+
+    if backend == "pytorch":
+        weights = cp.weights.detach().cpu().numpy()
+        read_factors, position_factors, base_factors = [
+            factor.detach().cpu().numpy() for factor in cp.factors
+        ]
+    else:
+        weights = np.asarray(cp.weights)
+        read_factors, position_factors, base_factors = [np.asarray(f) for f in cp.factors]
+
+    adata.obsm[embedding_key] = read_factors
+    if mask_indices is None:
+        adata.varm[components_key] = position_factors
+    else:
+        full_components = np.full(
+            (adata.n_vars, position_factors.shape[1]),
+            np.nan,
+            dtype=position_factors.dtype,
+        )
+        full_components[mask_indices] = position_factors
+        adata.varm[components_key] = full_components
+    adata.uns[uns_key] = {
+        "rank": rank,
+        "n_iter_max": n_iter_max,
+        "random_state": random_state,
+        "layer": layer,
+        "components_key": components_key,
+        "weights": weights,
+        "base_factors": base_factors,
+        "base_labels": list(bases),
+        "backend": backend,
+        "device": str(device),
+        "non_negative": non_negative,
+        "var_mask_name": var_mask_name,
+        "var_mask_count": int(np.sum(mask_indices)) if mask_indices is not None else None,
+    }
+
+    logger.info(
+        "Stored: adata.obsm['%s'], adata.varm['%s'], adata.uns['%s']",
+        embedding_key,
+        components_key,
+        uns_key,
+    )
+    return adata

{smftools-0.3.0.dist-info → smftools-0.3.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: smftools
-Version: 0.3.0
+Version: 0.3.2
 Summary: Single Molecule Footprinting Analysis in Python.
 Project-URL: Source, https://github.com/jkmckenna/smftools
 Project-URL: Documentation, https://smftools.readthedocs.io/
@@ -65,16 +65,19 @@ 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: pynndescent>=0.5.10; 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: tensorly; extra == 'all'
 Requires-Dist: torch>=1.9.0; extra == 'all'
+Requires-Dist: umap-learn>=0.5.5; extra == 'all'
 Requires-Dist: upsetplot; extra == 'all'
 Requires-Dist: wandb; extra == 'all'
 Provides-Extra: cluster
 Requires-Dist: fastcluster; extra == 'cluster'
+Requires-Dist: igraph; extra == 'cluster'
 Requires-Dist: leidenalg; extra == 'cluster'
 Provides-Extra: dev
 Requires-Dist: pre-commit; extra == 'dev'
@@ -103,6 +106,7 @@ 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: tensorly; extra == 'ml-base'
 Requires-Dist: torch>=1.9.0; extra == 'ml-base'
 Provides-Extra: ml-extended
 Requires-Dist: captum; extra == 'ml-extended'
@@ -124,11 +128,11 @@ 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'
+Provides-Extra: umap
+Requires-Dist: pynndescent>=0.5.10; extra == 'umap'
+Requires-Dist: umap-learn>=0.5.5; extra == 'umap'
 Description-Content-Type: text/markdown
 
 [![PyPI](https://img.shields.io/pypi/v/smftools.svg)](https://pypi.org/project/smftools)

{smftools-0.3.0.dist-info → smftools-0.3.2.dist-info}/RECORD

@@ -1,34 +1,38 @@
 smftools/__init__.py,sha256=Wun5eO3FHy7sAelTLlLdFj3NurqZFQxfO3U5YHJ3KcY,1247
 smftools/_settings.py,sha256=QqZzjz6Y_-gZH4VJAPRCL68HRlGjzl3hXU7d-dMi8-M,418
-smftools/_version.py,sha256=KdHlm9KKc9XEB182bG2710ZrIpNwJdS5TBcAjXA8U_M,58
-smftools/cli_entry.py,sha256=wTjwx520HJIez2I1CGXAHhWXUC-nsRBZ6yUFJd_84XM,10519
-smftools/constants.py,sha256=SWOJ76KTP2p3geyVkNQ8LB96NOmDDtjFEur2hSw7iyU,1289
-smftools/logging_utils.py,sha256=jOptBgSW7NQcw7JTnw2-oWcN2qyrtfJkDpIZsfcU1Mk,1323
-smftools/metadata.py,sha256=yGTMof2hAUR43QfgRSwK9mnOiTAznV3Usxzsvt185s4,14898
+smftools/_version.py,sha256=xm1u7RHIf6fYv7ou5-vxQ9OiaAwZ0vJK7AngPQ7IBek,58
+smftools/cli_entry.py,sha256=rFd_rSY8KA28LdHGS5wnSY1nCaiSZMSlhG4bm2Dn1w0,11675
+smftools/constants.py,sha256=NZjUgTD57StBaktxPIpUGoAmNjNB6D68Yr6ueAQJ8KY,4111
+smftools/logging_utils.py,sha256=OpDul2P5FCWhjJqunYK2MrSaYtbKEPGFE0Z7vZhSX0Y,2193
+smftools/metadata.py,sha256=-U8jVzjBsXbZ2SKRcyPHMCDPnsQQRR4djzerjpeQvzU,14917
 smftools/optional_imports.py,sha256=PpjWa-H-rlxwXJjkPLSHkiuim922xwDVsqlgFY8wWqw,1039
-smftools/readwrite.py,sha256=GCCBAWXQezTtXMBr-2NeV-jJfdnl_yB_x5nuz7Bt11c,52413
+smftools/readwrite.py,sha256=fvCJsIZ6Idjp0QIzbxXTPSXmQOb6ggx8idRaTbDck7w,54876
 smftools/cli/__init__.py,sha256=U4S_2y3zgLZVfMenHRaJFBW8yqh2mUBuI291LGQVOJ8,35
-smftools/cli/helpers.py,sha256=Euf0e3rNgKAlnghlJvr5fKaiMxqPum1HD6CYI__Z3Ko,1435
-smftools/cli/hmm_adata.py,sha256=2W1OLU_KaEtwUzkL_ZaecK4rQA9XyHJEurZEKQqnU00,40795
-smftools/cli/load_adata.py,sha256=mVsXQQB8sRIIettJhC1Y1xnrBcSTrRs-p-O72TlhO1o,32453
-smftools/cli/preprocess_adata.py,sha256=m_IWvUEBwIA5goJ2W7FQdqaA8tqQZB7gAXjjCWrcFCU,22632
-smftools/cli/spatial_adata.py,sha256=rzEPJ5pM78zE27rp-Sgif0fw_I6NiPK71xyGnZnXYcc,32001
+smftools/cli/chimeric_adata.py,sha256=roX2qpIg_84lpRFCHgD9MPLTh_Qv8XQU0250_RLyhtI,73758
+smftools/cli/helpers.py,sha256=LGiQyJfqB8mTQ6BhJWG1vc4hkZv0BmxBCbCzY7vAE2A,2932
+smftools/cli/hmm_adata.py,sha256=ZGzU9cfLaYUrUTtGFzUvmgFNQHHzBTkN1jXsGMEpZzE,49363
+smftools/cli/latent_adata.py,sha256=q4PupWWPR8ZY-Qsmj6Ug2WoTRf8SUA4-caNq5Vie2-M,26523
+smftools/cli/load_adata.py,sha256=RSgX1kvEcqSx3JRXL055m2u4hro8uM-sNvA5jVVxOr8,31539
+smftools/cli/preprocess_adata.py,sha256=D2LGNto2aeAvPjMwSPKR9CzxTIewhTtBUL3n47gE5Pw,25161
+smftools/cli/recipes.py,sha256=v3CnuNOyizD_tdNlHF2Qv9LsUkNMYDIVlqr_I3275QA,735
+smftools/cli/spatial_adata.py,sha256=MLsCo8PTYw1jxxXh9bdUG1Ftjuk2bp36oSGmnw7GvF8,30149
+smftools/cli/variant_adata.py,sha256=RNV0WyLVOdJhFAaM6XjUVh__kLMD7kv1BTSym7HIezY,16889
 smftools/cli/archived/cli_flows.py,sha256=w1rPHSH8WzZn7owz0ra7WOUGlJSEsaRw_W3x-9Ra42k,4977
 smftools/config/__init__.py,sha256=rcI3qG1DGfRcvQzh8bffiHuRPcmPsas5T8MN6uhScxA,106
-smftools/config/conversion.yaml,sha256=N7lUO7-yAaJR6VhxRGCRc-ceAi0cp5xNASSIsXl9KwI,1242
-smftools/config/deaminase.yaml,sha256=JCE1nF39AX436-3RyvuZN24gdJfriDijNv5XNHrMT8I,1357
-smftools/config/default.yaml,sha256=yhcMASjqqccuHpTFepyjt6KHfNNR6IDNSH0rmEERXm4,13933
+smftools/config/conversion.yaml,sha256=djZTJ1EwHc1Ax_fIsZo1UnERDpyER15rgo8APrOtAwE,1243
+smftools/config/deaminase.yaml,sha256=uZZzWeNc3TcBGY7o58lqQb3XOMAi3kIpHsUBqWUuM9g,1388
+smftools/config/default.yaml,sha256=gCWhoemO97zyaNTrt0A40RWnaHJ6R65mJJ4gEMUjgC4,16242
 smftools/config/direct.yaml,sha256=Jw8Nj3QKQrCfJpVl8sGgCKdRvjk5cV66dzRlNfoDOzI,2269
 smftools/config/discover_input_files.py,sha256=NcOqNYoXggLDieam8UMJAc2sWmoYOZ_Wqp2mApnlBfs,4015
-smftools/config/experiment_config.py,sha256=IqSN7JwnnWWjOoDZWbQ2zATwjm_uywSSs8mhagII6ms,67521
+smftools/config/experiment_config.py,sha256=soaTSwVbZELCDS1D5EQa2MF5RvPFP3lNQAaDhYMIbjM,75729
 smftools/datasets/F1_hybrid_NKG2A_enhander_promoter_GpC_conversion_SMF.h5ad.gz,sha256=q6wJtgFRDln0o20XNCx1qad3lwcdCoylqPN7wskTfI8,2926497
 smftools/datasets/F1_sample_sheet.csv,sha256=9PodIIOXK2eamYPbC6DGnXdzgi9bRDovf296j1aM0ak,259
 smftools/datasets/__init__.py,sha256=_G08ZAMlA9zpY5UjWTVlpAbW2YPS4PLCmz5g1pZdcCw,157
 smftools/datasets/dCas9_m6A_invitro_kinetics.h5ad.gz,sha256=niOcVHaYY7h3XyvwSkN-V_NMBaRt2vTP5TrJO0CwMCs,8385050
 smftools/datasets/datasets.py,sha256=-VOdONP-K_ftLDtLktRKbq3S6vSB4pzRQ6VYBxAy_4A,1074
-smftools/hmm/HMM.py,sha256=_kYhqfmz46XBbx9Y12KF6dKp2XPcSHreZiQgavgx6h4,82437
+smftools/hmm/HMM.py,sha256=Yq7awVwCtTPb4HET1UIx2VTHVvgiwu_2pjEgZTTkTP4,85660
 smftools/hmm/__init__.py,sha256=vs-fjo-v9y8EwdoErK6KDBm-YzD_XmTtflsdTJlRgTg,746
-smftools/hmm/call_hmm_peaks.py,sha256=CzTEz3EP_LNLirIVYzRxbV7_5fCBpLa9azLPSEt6s7s,13529
+smftools/hmm/call_hmm_peaks.py,sha256=jfmo-zzmA57d3pNG1RM1FqjsHue3IErgjOWIf3EuXtQ,13533
 smftools/hmm/display_hmm.py,sha256=N94hmEKZGehPdsB9yLyY7U1_tTWDk2NTMU-PuWnEQqA,1321
 smftools/hmm/hmm_readwrite.py,sha256=n-ok3wH1-anSn90vEA91jWKRbtq0bxM66hp2eYoWk34,687
 smftools/hmm/nucleosome_hmm_refinement.py,sha256=lHB6XVJWhwN-jR1TjBOMIOBQ5soncAJbv3djbkyH1NU,6882
@@ -36,20 +40,21 @@ smftools/hmm/archived/apply_hmm_batched.py,sha256=W2-qx1XbcDJz4q38YCxb1eQn9h-hqA
 smftools/hmm/archived/calculate_distances.py,sha256=MfBhXZNkjQvu9Y8LVMDpiQ4aS9uyfa4TUQbLGjQ1aM0,680
 smftools/hmm/archived/call_hmm_peaks.py,sha256=6SklWXCn4H8LnlGvBncIsLhnf2gaNy8Qro_jxGJn7I0,5249
 smftools/hmm/archived/train_hmm.py,sha256=sYF4RTEKPhE6MwK2eTAv4ghf-f7_33-FvhwUG6tegTU,2513
-smftools/informatics/__init__.py,sha256=jxyzu37yR1lho4LP3WhQ6_Oez4f-un7vCqP80s8xR3g,2885
-smftools/informatics/bam_functions.py,sha256=ErTV3ZrguIaGAqMnLnf-0QmfvvDRix0h_ehSRqKU2Ls,59008
+smftools/informatics/__init__.py,sha256=Q2l7iGOEuZXtGmqWG3NwF-_vNwl4VmJPsElg7-eANO0,3226
+smftools/informatics/bam_functions.py,sha256=b_Vb08HmOl8-hXLbkVNBw-zl-1loXqw-yQJkklJUvyY,73636
 smftools/informatics/basecalling.py,sha256=PgjWoOgfQaUOCoKpyaKO8m8sauMW3el6wdEtzGlvy4s,3699
 smftools/informatics/bed_functions.py,sha256=9y3XNNl6QivqkWEfoH5XszP3Qsj0P-rCopgfd0HpFgs,21268
-smftools/informatics/binarize_converted_base_identities.py,sha256=KRL-KT8MYADadHgRbTgoOFD30LlZazKHe10Hz9nO6Z4,7850
+smftools/informatics/binarize_converted_base_identities.py,sha256=2vncAGQ84GD-yvZpvnbBLj_ex9ABNACOzYAeX9yOPB4,4023
 smftools/informatics/complement_base_list.py,sha256=6DInlD4cdjKJmmUv4Cp4UU9HHLe60Pm8RF9AoBfBfF0,571
-smftools/informatics/converted_BAM_to_adata.py,sha256=YU7KBHgr0ulYZBv0I9PKI-p71JMZRvJbY9SlECWcQ3Q,25741
+smftools/informatics/converted_BAM_to_adata.py,sha256=qDdY5S7oCkH9Ov6a0BADnt2ytZYtcXSU1K2RyoNZxoo,44986
 smftools/informatics/fasta_functions.py,sha256=MD-fL0BkExiDXMUSPkHaHrkOK7aqzOozWREGr5Gzw8w,14111
-smftools/informatics/h5ad_functions.py,sha256=fX4CgO9ZSgYh9VbCmgGPXwNg5uolLJoNPcBZgzNwgMk,13167
-smftools/informatics/modkit_extract_to_adata.py,sha256=wcat5i002BxBpSMPCLENDdu-cnH0K87p6NN1vFSbfc4,63551
+smftools/informatics/h5ad_functions.py,sha256=V-lLmrff4Yv02PiKp9ePjYK7dHZALJInHID3_bSabTY,21178
+smftools/informatics/modkit_extract_to_adata.py,sha256=YF0zeg6k0FiPRCzLLrTcZQ5Q97fI8tZRnzNWco5Jwa0,84581
 smftools/informatics/modkit_functions.py,sha256=BvWd_qulVOQKZJFMd4pLTVD3ruo1dT48BmvQsdHB0_E,6103
 smftools/informatics/ohe.py,sha256=fdMEdXG45hiCsHtmYkPsXJKLJ-SBaZktdGx-bmfI3a0,5997
 smftools/informatics/pod5_functions.py,sha256=6_EA2StpslOe0phSwR9TDB_U-Tmx4ykuBcTAiOL0LPU,10327
 smftools/informatics/run_multiqc.py,sha256=M67HhO5FIJl8qn3Qc9YUlnbk7kdDWyYVL0B9SenrqMo,1115
+smftools/informatics/sequence_encoding.py,sha256=9u6E1IcUFL6Cn2BOWW4l_VYY9qQ-6KJo7M1bprMLV30,2244
 smftools/informatics/archived/bam_conversion.py,sha256=Gvy8X8AmCNYQEiwGjnmzs4YRMO3b5Cy6YDuVX8uLwJc,3366
 smftools/informatics/archived/bam_direct.py,sha256=Dj0YGeQzPb2jdFdO6qW6gyTxgdfCHI_c-xpYUc2MARQ,3642
 smftools/informatics/archived/basecall_pod5s.py,sha256=EAGHhKeCkFHybZmJrVR12kInnY5k0TXM__gLuplUOu4,3966
@@ -121,33 +126,42 @@ smftools/machine_learning/training/train_sklearn_model.py,sha256=zQ5SQpu_sl7IVcZ
 smftools/machine_learning/utils/__init__.py,sha256=aiCNpHD08ENEBtz8jzDfVZ8cB7ef9uOE7YaOPDkQUYg,99
 smftools/machine_learning/utils/device.py,sha256=2D5TF6DQIZKTcyNqIcJ7UMFeiWS_kCAvZUBK6XngCXk,432
 smftools/machine_learning/utils/grl.py,sha256=ptr-08dRKAGBZ1cySy_B90GgMn5kXtNXlcUC4PJ5mNA,485
-smftools/plotting/__init__.py,sha256=JrfnlocBQdW2QeP207PDUcx_4DMiOPLszxZBBml9POw,1478
-smftools/plotting/autocorrelation_plotting.py,sha256=gc3iyGgFEvMcyHXE2K8S956Nx6IfduglOOeJj3te8nU,30590
-smftools/plotting/classifiers.py,sha256=9Qt0eixvgE3WXl6jcwPm7O3ATA7Q6mfqRh_B_9M2qTQ,16749
-smftools/plotting/general_plotting.py,sha256=ShN8R0yauo-Br_IDy3ZlM5VR3wuetFaEtLxK5r6Nn8A,69455
-smftools/plotting/hmm_plotting.py,sha256=wPROxP-IJj-lY1I70s5YYy-H-XFfbcVol8PS2aw7srQ,11644
-smftools/plotting/position_stats.py,sha256=yxZx0Hjx4MsKINe9kkq-R7TkjODBGaDrbH9y0mrrTWs,19351
-smftools/plotting/qc_plotting.py,sha256=ODK8UrjVrAJeG8Qfu09DmAJ_o9GJaXRxGwN0pEgbHAU,10358
-smftools/preprocessing/__init__.py,sha256=l_oNlEOjrzoAZbTa66y9prIkEPbGcH4F1J2MyyMmesE,1855
-smftools/preprocessing/append_base_context.py,sha256=Z18Izb9-gZ4_ifXOHFZqcmPOradjCiyJZMZ5oTDfiLQ,7102
+smftools/plotting/__init__.py,sha256=HfDYE0N7ZQSpA6gnFVd1XwEIIAq7Z2U8N4deWtCn1g4,3095
+smftools/plotting/autocorrelation_plotting.py,sha256=fnnvzl_5cD09Jz2wH3iGIZE3UT5oyHQ1OtwPSVk2cbM,31314
+smftools/plotting/chimeric_plotting.py,sha256=j-TMqKg0bzt2Fssi89FWR04WvLYFGkMOyksjN9T-qjo,70200
+smftools/plotting/classifiers.py,sha256=EouBhnrHbBbeL8mJZEPU3GbFyIO1p6aERp0FIqp-3j4,17362
+smftools/plotting/general_plotting.py,sha256=Tj9_V27K0f4mymsNWfwRbgQkPwvgiyoDw7yzM8JVSRo,1809
+smftools/plotting/hmm_plotting.py,sha256=afEAZVknf8wP8yYFA7-tT8Hlwy6sLGKuZKHlu7a-tg8,79999
+smftools/plotting/latent_plotting.py,sha256=vC12rJg-8_luYmX6XI3meMw-oyD3bYYIu0nFTvTiZfQ,28584
+smftools/plotting/plotting_utils.py,sha256=HYNDbCJUMyo_JlIjZ5JtVmv02ncpFoiGzqc1vCRbJKA,7282
+smftools/plotting/position_stats.py,sha256=ITG4tEuZgjn3mCoGCNs2SQfiWAzqfl_cki9VOGD_RAA,19862
+smftools/plotting/preprocess_plotting.py,sha256=VbQWKgO-Tlu2hYT2IOupsATEb6jxgqAwinUbivnNYNw,11736
+smftools/plotting/qc_plotting.py,sha256=h1JGCNzDOTNHq2Zr93mI_qqkdqaNxrragmJyZ9PDIyw,10556
+smftools/plotting/spatial_plotting.py,sha256=uVzpdh7pYRqRoDRvQR_fQaOl44FIMkq8YhfwDRYSbTE,44372
+smftools/plotting/variant_plotting.py,sha256=AGcPZ2WSO4VSWTIn9rbxhOzud7sH4CnmZkxcwPVIo5M,54080
+smftools/preprocessing/__init__.py,sha256=Hcq89k8M2kbzOW7vl7X91PEn4npsOPFShmyrUXeBtmA,2232
+smftools/preprocessing/append_base_context.py,sha256=1C8ZeULZNbAWmD5sZxNh14axI4OZMnsOAaZifjeOZHE,7134
 smftools/preprocessing/append_binary_layer_by_base_context.py,sha256=7mFG7xjAPgm_60AcdCnnjJZK5gJe4VuLohopkrAHmvQ,7640
+smftools/preprocessing/append_mismatch_frequency_sites.py,sha256=cB-lg8GEEoFu2ESSxCyVObIcuMZTFip4Es96a-EJQQ4,7446
+smftools/preprocessing/append_sequence_mismatch_annotations.py,sha256=wa2hMtsAkk3IYz1dAUBfBUS-5fwHZWUH98stujW4E00,6429
+smftools/preprocessing/append_variant_call_layer.py,sha256=dhvIPVWRSv-Tn9JoTKmeAz6kbHg-iocpRGq_YGA0hHM,19098
 smftools/preprocessing/binarize.py,sha256=eDFLybKKIF2wcrtN3JWVjeGXSUayezxLhX76UllAhVc,888
 smftools/preprocessing/binarize_on_Youden.py,sha256=JTHosTDy9-gJ0bPrHkGnz_Ao_AeE8IiutqFA6MksdM8,4887
 smftools/preprocessing/binary_layers_to_ohe.py,sha256=nYvAefdIKGj-JyNtBqHcekJKI4BI2CM9pN-Mq1BT-28,1931
 smftools/preprocessing/calculate_complexity_II.py,sha256=iVh5BcLCPOndVeN4A7Gw74pMBa83UQuxtV5o_sVFUNs,10367
-smftools/preprocessing/calculate_consensus.py,sha256=1_-ldkwQ3JT5Rns9thIfV-HJbSKFW2b1Auida96lhGE,2377
+smftools/preprocessing/calculate_consensus.py,sha256=YbeHFwyhH8MIl_2Acdg5B3DOyFJW8hVqFCZQYSZTLAU,2382
 smftools/preprocessing/calculate_coverage.py,sha256=HZ8rtEmb-z6XCr-EvMfl4rc_9nbTJRztyEk8xUg7feE,2777
 smftools/preprocessing/calculate_pairwise_differences.py,sha256=BRht5E8BtmJp_mxUSH5WfguhXaYV1zdPXZQLL1Wu6lI,1799
 smftools/preprocessing/calculate_pairwise_hamming_distances.py,sha256=86MioHtN6mpH04bj-3UNv2Vistglt8I0ZMALKNEAq7g,999
 smftools/preprocessing/calculate_position_Youden.py,sha256=HKnQAZvff1i8FVSxLkhcGwR2kmAq63izsOBGdCd3ws8,9146
 smftools/preprocessing/calculate_read_length_stats.py,sha256=y2R5lU6ObRBCAhSHKLEZYpgm88woPd9d15NWVthIi_A,4790
-smftools/preprocessing/calculate_read_modification_stats.py,sha256=L1X0LatpjPI5wA1j7MjFgukePYGo75DcgJCYPlhVAGM,5319
+smftools/preprocessing/calculate_read_modification_stats.py,sha256=dc8QWwGqctnk6xbTNUaFy_uA4gg8ZaM6fN_KvEyzm64,5555
 smftools/preprocessing/clean_NaN.py,sha256=hrPhbKfqDpSiXLXXJxvcmtwqFhOecJVC29Z7PMIxi5I,2163
 smftools/preprocessing/filter_adata_by_nan_proportion.py,sha256=5V1PNJISYm92QtEGmS9XSqx456Ult8RY8LMBclNylno,1490
 smftools/preprocessing/filter_reads_on_length_quality_mapping.py,sha256=83G8ovetiAmh8EbikqAUhNnzaX_KnWe0rZ7vfrgeye4,8018
 smftools/preprocessing/filter_reads_on_modification_thresholds.py,sha256=yxYZB9Ran1ZxuZm9iHi5bpLo6xcro5zKyv9rnYUtT6g,21688
-smftools/preprocessing/flag_duplicate_reads.py,sha256=7MooUKnUULJY6IiCNO7P0idE7_6X0usMtX7F9us8n4U,75420
-smftools/preprocessing/invert_adata.py,sha256=-aiidr_PXSf8IIpC4PMRm2RlLAWi-dtZDpr0iSOY-PY,1367
+smftools/preprocessing/flag_duplicate_reads.py,sha256=Khauxw8_stBLmmkM1z4HVVuXpcWIhgTjJwoH-WfOoko,75436
+smftools/preprocessing/invert_adata.py,sha256=QIbNDWra34hp_HHGvYfUYpqwtimIuKys-mVwrb1ChPI,1418
 smftools/preprocessing/load_sample_sheet.py,sha256=rzY76rCYVf3idu2ZRw4pEjVRBB5AyUkSYY-UzpmE_aw,2193
 smftools/preprocessing/make_dirs.py,sha256=SjeiXoWsy_SldM-RoQbpfo2mXdnP78xhHVHywTD7IZI,662
 smftools/preprocessing/min_non_diagonal.py,sha256=2sOWl7zKWltNmv-Jv-ZXb099dYBX28suAOE6DUlUO-U,749
@@ -160,23 +174,30 @@ smftools/preprocessing/archived/mark_duplicates.py,sha256=Acj27Xc8ht8e1HYZFgq57z
 smftools/preprocessing/archived/preprocessing.py,sha256=l0Im9O45kaMYxipyFiPFBA8M7NLiOxWuONf8igmHaPc,34567
 smftools/preprocessing/archived/remove_duplicates.py,sha256=W1Y2ufD2nE9Tnx3NXpEPxso08tiV50iRy77_X3RZkyQ,735
 smftools/schema/__init__.py,sha256=0chkz2Zc3UKSJO4m0MUemfs-WjGUSSghiuuFM28UvsY,293
-smftools/schema/anndata_schema_v1.yaml,sha256=uNFTrsTLNoE3kgJgrcg-hM6iYtDRsu6SHwWCkbcgIuk,7746
-smftools/tools/__init__.py,sha256=MqvwhrFQsTvoSpbJ4HIzV9LWwNLef0RXe9iI3VZReMI,976
-smftools/tools/calculate_umap.py,sha256=oj4EJP4M3cZ50T0bYNVAfZAssEG9ZxKmNgjgKmqxf-g,3594
+smftools/schema/anndata_schema_v1.yaml,sha256=FCMjYIqgt-YxQxehcgkdwWBzqk1k-aSZ3fUcksX1bH4,8310
+smftools/tools/__init__.py,sha256=40LW8N6CiQMyRkujbm12cCJf8X2PdqrLWYwFiFUeNbg,1650
+smftools/tools/calculate_knn.py,sha256=pPnkZpbO6qUD0Te62kB1D_6f7Y5UzUnrIu7b_XhtVNg,3921
+smftools/tools/calculate_leiden.py,sha256=48Y72NIzGb6yxtnUund7gS_2jIFro5lwJC0ycNOoAJI,1867
+smftools/tools/calculate_nmf.py,sha256=E1SCqOycGAdPm_-VLauLtyy4fd5UaFKNiNlVK3nr8Lo,4577
+smftools/tools/calculate_pca.py,sha256=4dm2sEDkKZhW9_0q1e2lfpr6zVgmUNNReuEyCWbOa3g,6444
+smftools/tools/calculate_umap.py,sha256=D5kTWRR6VIvSXWH_6uWC8q8PSnnK5f1g3yN4xxzQXVE,3370
 smftools/tools/cluster_adata_on_methylation.py,sha256=NsU11zFyBB_TZFdVZxjqeSZsiVZgb8iCXaOBY54FA9U,7684
 smftools/tools/general_tools.py,sha256=XO8em-clV4onfbYEH6JTfNj3svLQnwBZ1Tja7s8qsXg,3260
-smftools/tools/position_stats.py,sha256=FiFidt3b5cdEMylFoPPrCZbLAXQHsehxFFcTaHvTtt4,27425
+smftools/tools/position_stats.py,sha256=6tDCgnLNZMU_bKs784ku-gdDZDW-2xbZSsQFdvhpLGQ,27441
 smftools/tools/read_stats.py,sha256=8rV2BXymdPuPihh0Ev-HqPT40lobyt5WExoYjbmrbcI,6534
+smftools/tools/rolling_nn_distance.py,sha256=k0Ut59wc2A0nTIOvocMM6zxHbQwswYE65ZKYXFqnCbA,32388
+smftools/tools/sequence_alignment.py,sha256=KgnDC9Ve66v_xmb4rzGWHsGAlbrPi2K930sSx6NkGkA,4562
 smftools/tools/spatial_autocorrelation.py,sha256=euunec6Mmkm5iBDN7TM4q4NXLl9n8UP77-6GSGYCVOk,25473
 smftools/tools/subset_adata.py,sha256=6xPf6hyKcYwg4L2n0iCnz-Pl84fS4jLgxmD47J-OEco,1012
+smftools/tools/tensor_factorization.py,sha256=c5p2DtltUIUYRUuoPiNQnAj-ms-V2C-WEcwgF1p4-5k,7697
 smftools/tools/archived/apply_hmm.py,sha256=b1DKT_02weiPgkfQ0_Zfk7wN8FRZAMeYvBe74H3QuDU,9357
 smftools/tools/archived/classifiers.py,sha256=iKkK9UyEwEdNwLx-t_r52CURkP3iZ-pFwmQtXF_lnLY,42191
 smftools/tools/archived/classify_methylated_features.py,sha256=uXWXl4t9cP4inRiSvL4MxGbwC2MxT5uT-D1FFdex8oE,2933
 smftools/tools/archived/classify_non_methylated_features.py,sha256=vhfLbR5fqALps5HXxQ91x3lUTGLcfciaEsQkSFeLOgM,3292
 smftools/tools/archived/subset_adata_v1.py,sha256=CBTbHolOil7m4eR0bwIzxS7ZPvo3hmDsPVZGUBzWYrs,1361
 smftools/tools/archived/subset_adata_v2.py,sha256=npic7cuFIOeUiyRjATVrP4A0O7cV0EgHvRXi9aMMOcI,2311
-smftools-0.3.0.dist-info/METADATA,sha256=JuAG9ifECVbhIjC2lKmIqgzosM1Ao2naUcmGh7zgpHk,7840
-smftools-0.3.0.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-smftools-0.3.0.dist-info/entry_points.txt,sha256=q4hg4w-mKkI2leekM_-YZc5XRJzp96Mh1FcU3hac82g,52
-smftools-0.3.0.dist-info/licenses/LICENSE,sha256=F8LwmL6vMPddaCt1z1S83Kh_OZv50alTlY7BvVx1RXw,1066
-smftools-0.3.0.dist-info/RECORD,,
+smftools-0.3.2.dist-info/METADATA,sha256=nOOfJCCWKHQMZU-BSGiipUtnuKEA70esQj-w2Nc_NHE,8036
+smftools-0.3.2.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+smftools-0.3.2.dist-info/entry_points.txt,sha256=q4hg4w-mKkI2leekM_-YZc5XRJzp96Mh1FcU3hac82g,52
+smftools-0.3.2.dist-info/licenses/LICENSE,sha256=F8LwmL6vMPddaCt1z1S83Kh_OZv50alTlY7BvVx1RXw,1066
+smftools-0.3.2.dist-info/RECORD,,