smftools 0.1.3__py3-none-any.whl → 0.1.7__py3-none-any.whl

smftools/tools/train_hmm.py

@@ -0,0 +1,78 @@
+def train_hmm(
+    data,
+    emission_probs=[[0.8, 0.2], [0.2, 0.8]],
+    transitions=[[0.9, 0.1], [0.1, 0.9]],
+    start_probs=[0.5, 0.5],
+    end_probs=[0.5, 0.5],
+    device=None,
+    max_iter=50,
+    verbose=True,
+    tol=50,
+    pad_value=0,
+):
+    """
+    Trains a 2-state DenseHMM model on binary methylation data.
+
+    Parameters:
+        data (list or np.ndarray): List of sequences (lists) with 0, 1, or NaN.
+        emission_probs (list): List of emission probabilities for two states.
+        transitions (list): Transition matrix between states.
+        start_probs (list): Initial state probabilities.
+        end_probs (list): End state probabilities.
+        device (str or torch.device): "cpu", "mps", "cuda", or None (auto).
+        max_iter (int): Maximum EM iterations.
+        verbose (bool): Verbose output from pomegranate.
+        tol (float): Convergence tolerance.
+        pad_value (int): Value used to pad shorter sequences.
+
+    Returns:
+        hmm: Trained DenseHMM model
+    """
+    import torch
+    from pomegranate.hmm import DenseHMM
+    from pomegranate.distributions import Categorical
+    import numpy as np
+    from tqdm import tqdm
+
+    # Auto device detection
+    if device is None:
+        device = torch.device("mps") if torch.backends.mps.is_available() else torch.device("cpu")
+    elif isinstance(device, str):
+        device = torch.device(device)
+    print(f"Using device: {device}")
+
+    # Ensure emission probs on correct device
+    dists = [
+        Categorical(torch.tensor([p], device=device))
+        for p in emission_probs
+    ]
+
+    # Create DenseHMM
+    hmm = DenseHMM(
+        distributions=dists,
+        edges=transitions,
+        starts=start_probs,
+        ends=end_probs,
+        verbose=verbose,
+        max_iter=max_iter,
+        tol=tol,
+    ).to(device)
+
+    # Convert data to list if needed
+    if isinstance(data, np.ndarray):
+        data = data.tolist()
+
+    # Preprocess data (replace NaNs + pad)
+    max_length = max(len(seq) for seq in data)
+    processed_data = []
+    for sequence in tqdm(data, desc="Preprocessing Sequences"):
+        cleaned_seq = [int(x) if not np.isnan(x) else np.random.choice([0, 1]) for x in sequence]
+        cleaned_seq += [pad_value] * (max_length - len(cleaned_seq))
+        processed_data.append(cleaned_seq)
+
+    tensor_data = torch.tensor(processed_data, dtype=torch.long, device=device).unsqueeze(-1)
+
+    # Fit HMM
+    hmm.fit(tensor_data)
+
+    return hmm

smftools/tools/training/__init__.py

@@ -0,0 +1 @@
+from .train_lightning_model import train_lightning_model

smftools/tools/training/train_lightning_model.py

@@ -0,0 +1,47 @@
+import torch
+from pytorch_lightning import Trainer
+from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
+
+def train_lightning_model(
+    model,
+    datamodule,
+    max_epochs=20,
+    patience=5,
+    monitor_metric="val_loss",
+    checkpoint_path=None,
+):
+    # Device logic
+    if torch.cuda.is_available():
+        accelerator = "gpu"
+        devices = 1
+    elif torch.backends.mps.is_available():
+        accelerator = "mps"
+        devices = 1
+    else:
+        accelerator = "cpu"
+        devices = 1
+
+    # Callbacks
+    callbacks = [
+        EarlyStopping(monitor=monitor_metric, patience=patience, mode="min"),
+    ]
+    if checkpoint_path:
+        callbacks.append(ModelCheckpoint(
+            dirpath=checkpoint_path,
+            filename="{epoch}-{val_loss:.4f}",
+            monitor=monitor_metric,
+            save_top_k=1,
+            mode="min",
+        ))
+
+    # Trainer setup
+    trainer = Trainer(
+        max_epochs=max_epochs,
+        callbacks=callbacks,
+        accelerator=accelerator,
+        devices=devices,
+        log_every_n_steps=10,
+    )
+    trainer.fit(model, datamodule=datamodule)
+    
+    return trainer

smftools/tools/utils/__init__.py

@@ -0,0 +1,2 @@
+from .device import detect_device
+from .grl import GradReverse

smftools/tools/utils/device.py

@@ -0,0 +1,10 @@
+import torch
+
+def detect_device():
+    device = (
+        torch.device('cuda') if torch.cuda.is_available() else
+        torch.device('mps') if torch.backends.mps.is_available() else
+        torch.device('cpu')
+    )
+    print(f"Detected device: {device}")
+    return device

smftools/tools/utils/grl.py

@@ -0,0 +1,14 @@
+import torch
+
+class GradReverse(torch.autograd.Function):
+    @staticmethod
+    def forward(ctx, x, alpha):
+        ctx.alpha = alpha
+        return x.view_as(x)
+
+    @staticmethod
+    def backward(ctx, grad_output):
+        return -ctx.alpha * grad_output, None
+
+def grad_reverse(x, alpha=1.0):
+    return GradReverse.apply(x, alpha)

{smftools-0.1.3.dist-info → smftools-0.1.7.dist-info}/METADATA

@@ -1,12 +1,32 @@
 Metadata-Version: 2.3
 Name: smftools
-Version: 0.1.3
+Version: 0.1.7
 Summary: Single Molecule Footprinting Analysis in Python.
 Project-URL: Source, https://github.com/jkmckenna/smftools
 Project-URL: Documentation, https://smftools.readthedocs.io/
 Author: Joseph McKenna
 Maintainer-email: Joseph McKenna <jkmckenna@berkeley.edu>
-License-Expression: MIT
+License: MIT License
+        
+        Copyright (c) 2024 jkmckenna
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        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
@@ -26,12 +46,18 @@ Classifier: Topic :: Scientific/Engineering :: Visualization
 Requires-Python: >=3.9
 Requires-Dist: anndata>=0.10.0
 Requires-Dist: biopython>=1.79
-Requires-Dist: cython>=0.29.28
+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: pomegranate>1.0.0
+Requires-Dist: pomegranate>=1.0.0
 Requires-Dist: pyfaidx>=0.8.0
 Requires-Dist: pysam>=0.19.1
 Requires-Dist: scanpy>=1.9
@@ -40,6 +66,7 @@ Requires-Dist: scipy>=1.7.3
 Requires-Dist: seaborn>=0.11
 Requires-Dist: torch>=1.9.0
 Requires-Dist: tqdm
+Requires-Dist: wandb
 Provides-Extra: docs
 Requires-Dist: ipython>=7.20; extra == 'docs'
 Requires-Dist: matplotlib!=3.6.1; extra == 'docs'
@@ -67,7 +94,7 @@ Description-Content-Type: text/markdown
 A Python tool for processing raw sequencing data derived from single molecule footprinting experiments into [anndata](https://anndata.readthedocs.io/en/latest/) objects. Additional functionality for preprocessing, analysis, and visualization.
 
 ## Philosophy
-While most genomic data structures handle low-coverage data (<100X) along large references, smftools prioritizes high-coverage data (scalable to at least 1 million X coverage) of a few genomic loci at a time. This enables efficient data storage, rapid data operations, hierarchical metadata handling, seamless integration with various machine-learning packages, and ease of visualization. Furthermore, functionality is modularized, enabling analysis sessions to be saved, reloaded, and easily shared with collaborators. Analyses are centered around the [anndata](https://anndata.readthedocs.io/en/latest/) object, and are heavily inspired by the work conducted within the single-cell genomics community.
+While most genomic data structures handle low-coverage data (<100X) along large references, smftools prioritizes high-coverage data (scalable to >1,000,000X coverage) of a few genomic loci at a time. This enables efficient data storage, rapid data operations, hierarchical metadata handling, seamless integration with various machine-learning packages, and ease of visualization. Furthermore, functionality is modularized, enabling analysis sessions to be saved, reloaded, and easily shared with collaborators. Analyses are centered around the [anndata](https://anndata.readthedocs.io/en/latest/) object, and are heavily inspired by the work conducted within the single-cell genomics community.
 
 ## Dependencies
 The following CLI tools need to be installed and configured before using the informatics (smftools.inform) module of smftools:
@@ -81,14 +108,23 @@ The following CLI tools need to be installed and configured before using the inf
 ## Modules
 ### Informatics: Processes raw Nanopore/Illumina data from SMF experiments into an AnnData object.
 ![](docs/source/_static/smftools_informatics_diagram.png)
-### Preprocessing: Appends QC metrics to the AnnData object and perfroms filtering.
+### Preprocessing: Appends QC metrics to the AnnData object and performs filtering.
 ![](docs/source/_static/smftools_preprocessing_diagram.png)
-- Tools: Appends various analyses to the AnnData object.
-- Plotting: Visualization of analyses stored within the AnnData object.
+### Tools: Appends analyses to the AnnData object.
+- Currently Includes: Position X Position correlation matrices, Hidden Markov Model feature detection, clustering, dimensionality reduction, peak calling, train/test workflows for various ML classifiers.
+- To do: Additional ML methods for learning predictive single molecule features on condition labels: Autoencoders, Variational Autoencoders, Transformers.
+### Plotting: Visualization of analyses stored within the AnnData object.
+- Most analyses appended to the adata object by a tools method have, or will have, an accompanying plotting method.
 
 ## Announcements
-### 09/09/24 - The pre-alpha phase package ([smftools-0.1.1](https://pypi.org/project/smftools/))
+
+### 05/29/25 - Version 0.1.6 is available through PyPI.
+Informatics, preprocessing, tools, plotting modules have core functionality that is approaching stability on MacOS(Intel/Silicon) and Linux(Ubuntu). I will work on improving documentation/tutorials shortly. The base PyTorch/Scikit-Learn ML-infrastructure is going through some organizational changes to work with PyTorch Lightning, Hydra, and WanDB to facilitate organizational scaling, multi-device usage, and logging.
+
+### 10/01/24 - More recent versions are being updated frequently. Installation from source over PyPI is recommended!
+
+### 09/09/24 - The version 0.1.1 package ([smftools-0.1.1](https://pypi.org/project/smftools/)) is installable through pypi!
 The informatics module has been bumped to alpha-phase status. This module can deal with POD5s and unaligned BAMS from nanopore conversion and direct SMF experiments, as well as FASTQs from Illumina conversion SMF experiments. Primary output from this module is an AnnData object containing all relevant SMF data, which is compatible with all downstream smftools modules. The other modules are still in pre-alpha phase. Preprocessing, Tools, and Plotting modules should be promoted to alpha-phase within the next month or so.
 
-### 08/30/24 - The pre-alpha phase package ([smftools-0.1.0](https://pypi.org/project/smftools/)) is installable through pypi!
-Currently, this package (smftools-0.1.0) is going through rapid improvement (dependency handling accross Linux and Mac OS, testing, documentation, debugging) and is still too early in development for standard use. The underlying functionality was originally developed as a collection of scripts for single molecule footprinting (SMF) experiments in our lab, but is being packaged/developed to facilitate the expansion of SMF to any lab that is interested in performing these styles of experiments/analyses. The alpha-phase package is expected to be available within a couple months, so stay tuned!
+### 08/30/24 - The version 0.1.0 package ([smftools-0.1.0](https://pypi.org/project/smftools/)) is installable through pypi!
+Currently, this package (smftools-0.1.0) is going through rapid improvement (dependency handling accross Linux and Mac OS, testing, documentation, debugging) and is still too early in development for widespread use. The underlying functionality was originally developed as a collection of scripts for single molecule footprinting (SMF) experiments in our lab, but is being packaged/developed to facilitate the expansion of SMF to any lab that is interested in performing these styles of experiments/analyses. The alpha-phase package is expected to be available within a couple months, so stay tuned!

smftools-0.1.7.dist-info/RECORD

@@ -0,0 +1,136 @@
+smftools/__init__.py,sha256=0Llj2kZuzB0PvwcQV5RjvMC0KgFW6F__eceV2eYR4TU,551
+smftools/_settings.py,sha256=Ed8lzKUA5ncq5ZRfSp0t6_rphEEjMxts6guttwTZP5Y,409
+smftools/_version.py,sha256=GmypIHlw9-BaSEaoucCIwm0ut1DUut0hUvsyTCr17qk,21
+smftools/readwrite.py,sha256=Y-6ehzoEMUIBWp3WQtyX2Vhe9aHwY1tsoNsVApRJRy4,7303
+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=xkSTlPuakVYVCuRurif9BceNBDt6bsngJvvjI8757QI,142
+smftools/datasets/dCas9_m6A_invitro_kinetics.h5ad.gz,sha256=niOcVHaYY7h3XyvwSkN-V_NMBaRt2vTP5TrJO0CwMCs,8385050
+smftools/datasets/datasets.py,sha256=0y597Ntp707bOgDwN6O-JEt9yxgplj66p0aj6Zs_IB4,779
+smftools/informatics/__init__.py,sha256=Iz5Jyzln5wKRJ2yu4AWbUx0sMavpMy8XZtGOaLECVmE,391
+smftools/informatics/basecall_pod5s.py,sha256=Ynmxscsxj6qp-zVY0RWodq513oDuHDaHnpqoepB3RUU,3930
+smftools/informatics/conversion_smf.py,sha256=QhlISVi3Z-XqFKyDG_CenLojovAt5-ZhuVe9hus36lg,7177
+smftools/informatics/direct_smf.py,sha256=ylPGFBvRLdxLHeDJjAwq98j8Q8_lfGK3k5JJnQxrwJw,7485
+smftools/informatics/fast5_to_pod5.py,sha256=xfdZU3QluaAcR-q2uBRz8hcBwYt73nCnrFeahvi0OKQ,704
+smftools/informatics/load_adata.py,sha256=90eseT30qkKc9TCwBQ6UvoLbR7_oQ9foLniSxv-x8Q0,10563
+smftools/informatics/readwrite.py,sha256=DgVisHYdkjzaO7suPbUvluImeTc3jqGDlioNveHUxPc,4158
+smftools/informatics/subsample_fasta_from_bed.py,sha256=YqYV09rvEQdeiS5hTTrKa8xYmJfeM3Vk-UUqwpw0qBk,1983
+smftools/informatics/subsample_pod5.py,sha256=zDw9tRcrFRmPI62xkcy9dh8IfsJcuYm7R-FVeBC_g3s,4701
+smftools/informatics/archived/bam_conversion.py,sha256=I8EzXjQixMmqx2oWnoNSH5NURBhfT-krbWHkoi_M964,3330
+smftools/informatics/archived/bam_direct.py,sha256=jbEFtUIiUR8Wlp3po_sWkr19AUNS9WZjglojb9j28vo,3606
+smftools/informatics/archived/basecalls_to_adata.py,sha256=-Nag6lr_NAtU4t8jo0GSMdgIAIfmDge-5VEUPQbEatE,3692
+smftools/informatics/archived/print_bam_query_seq.py,sha256=8Z2ZJEOOlfWYUXiZGjteLWU4yTgvV8KQzEIBHUmamGM,838
+smftools/informatics/helpers/LoadExperimentConfig.py,sha256=6K8AmwWVapx5XbZdhIRLB7tNSr6szpPtzM78hbEts7k,2891
+smftools/informatics/helpers/__init__.py,sha256=-PuxmsaS_IrFndAVNwyd13UqSZ4OawvxK87s2gbZIcU,2803
+smftools/informatics/helpers/align_and_sort_BAM.py,sha256=Ce-_m9wQrLS7MPy-sA4yEHNjBPNmmzoLjLbjjJYkvwM,2470
+smftools/informatics/helpers/aligned_BAM_to_bed.py,sha256=5-5fpE7ovDTwF7FZSwpfTNGcgxFKKE-ANxAxGuVH1ks,2887
+smftools/informatics/helpers/bam_qc.py,sha256=IlrXXpCdTYIv_89SE8D5tJ1wtTzxWGjk9vc-rbC1UjU,2430
+smftools/informatics/helpers/bed_to_bigwig.py,sha256=AazYEZzKgKgukSFwCpeiApzxh1kbt11X4RFqRIiBIaY,1466
+smftools/informatics/helpers/binarize_converted_base_identities.py,sha256=VqXXm61KL2z2xK1AcohvezY69bYHI3uL8RTnDDjOOgI,3756
+smftools/informatics/helpers/canoncall.py,sha256=5WS6lwukc_xYTdPQy0OSj-WLbx0Rg70Cun1lCucY7w8,1741
+smftools/informatics/helpers/complement_base_list.py,sha256=k6EkLtxFoajaIufxw1p0pShJ2nPHyGLTbzZmIFFjB4o,532
+smftools/informatics/helpers/concatenate_fastqs_to_bam.py,sha256=uSWazdNRCa_Cc1SOMreJZBchPIcII4DNluB9PJF_rA8,2713
+smftools/informatics/helpers/converted_BAM_to_adata.py,sha256=sRmOtn0kNosLYfogqslDHg1Azk51l6nfNOLgQOnQjlA,14591
+smftools/informatics/helpers/converted_BAM_to_adata_II.py,sha256=yYjCc5tJ0_-HgcPziccjNXCe8A7kmD5mFfNWcEDcA3o,16482
+smftools/informatics/helpers/count_aligned_reads.py,sha256=uYyUYglF1asiaoxr-LKxPMUEbfyD7FS-dumTg2hJHzQ,2170
+smftools/informatics/helpers/demux_and_index_BAM.py,sha256=2B_UiU05ln3gYvcN9aC_w6qs8j_WAF4pHWZekAYsXm4,2114
+smftools/informatics/helpers/extract_base_identities.py,sha256=cWcAcWK0vhHl-jRpMX2YMLtYezhSdhMfyj4E7rm2VEU,1833
+smftools/informatics/helpers/extract_mods.py,sha256=MbSIiyj3zx7WlSSWMRPriLMkBtxYc1EWZiAAirMVgqA,3865
+smftools/informatics/helpers/extract_read_features_from_bam.py,sha256=nJxGjVe7LtPi8Eu5HuFFQuDi5ZnvDxLMsPfFc5bLfx4,1275
+smftools/informatics/helpers/extract_read_lengths_from_bed.py,sha256=Cw39wgp1eBTV45Wk1l0c9l-upBW5N2OcgyWXTAXln90,678
+smftools/informatics/helpers/extract_readnames_from_BAM.py,sha256=3FxSNqbZ1VsOK2RfHrvevQTzhWATf5E8bZ5yVOqayvk,759
+smftools/informatics/helpers/find_conversion_sites.py,sha256=e7gRmvZSakwhnFJkhfgg9i_85rYEXtbGv4_oS8RoNlE,2329
+smftools/informatics/helpers/generate_converted_FASTA.py,sha256=UniQfERNt4FC5L8T1tzr4cLQOJc3wMBPhuWmC-lC8Fs,3747
+smftools/informatics/helpers/get_chromosome_lengths.py,sha256=sLumLrGsU_Xg_oJcdOpQyjUGpJoT2HbcmxWwbwzXUlE,1036
+smftools/informatics/helpers/get_native_references.py,sha256=fRuyEm9UJkfd5DwHmFb1bxEtNvtSI1_BxGRmrCymGkw,981
+smftools/informatics/helpers/index_fasta.py,sha256=N3IErfSiavYldeaat8xcQgA1MpykoQHcE0gHUeWuClE,267
+smftools/informatics/helpers/make_dirs.py,sha256=lWHXpwC76MFM5sSme9i_WeYUaxutzybendokhny03ds,537
+smftools/informatics/helpers/make_modbed.py,sha256=cOQ97gPfRiCcw_fqboxousXIiOYjp78IFYLbu749U1Y,939
+smftools/informatics/helpers/modQC.py,sha256=LeOBObG8gAVVdgESIMceYhd5AW1gfN7ABo91OQtOzTM,1041
+smftools/informatics/helpers/modcall.py,sha256=LVPrdMNVp2gyQTJ4BNp8NJNm89AueDjsKaY7Gqkluho,1777
+smftools/informatics/helpers/modkit_extract_to_adata.py,sha256=uU5p9A1C9ZSEqU5P9Dc_ssDTGrZlh5uXVYlS0RRKdj0,51833
+smftools/informatics/helpers/ohe_batching.py,sha256=QVOiyl9fYHNIFWM23afYnQo0uaOjf1NR3ASKGVSrmuw,2975
+smftools/informatics/helpers/ohe_layers_decode.py,sha256=gIgUC9L8TFLi-fTnjR4PRzXdUaH5D6WL2Hump6XOoy0,1042
+smftools/informatics/helpers/one_hot_decode.py,sha256=3n4rzY8_aC9YKmgrftsguMsH7fUyQ-DbWmrOYF6la9s,906
+smftools/informatics/helpers/one_hot_encode.py,sha256=5hHigA6-SZLK84WH_RHo06F_6aTg7S3TJgvSr8gxGX8,1968
+smftools/informatics/helpers/plot_read_length_and_coverage_histograms.py,sha256=3PmxZJGjIyPLkJvL7VIILrkE9JzB6Kdxh0IJfoJ0e5k,1942
+smftools/informatics/helpers/run_multiqc.py,sha256=qkw48DeBdTEqzhKFGjMUlvNmTehp8wRPkcxdkwERkHc,980
+smftools/informatics/helpers/separate_bam_by_bc.py,sha256=Fsi8OEmv5Ny13cWoHVV9JmEjVFEXT_ZxbBOlRdmyPbE,1742
+smftools/informatics/helpers/split_and_index_BAM.py,sha256=tLAhLoPfiVJhLYGr3LVcjo0xQ_8-yb60hR46EQUpL-s,1570
+smftools/informatics/helpers/archived/informatics.py,sha256=gKb2ZJ_LcAeEXuQqn9e-QDF_sS4tMpMTr2vZlqa7n54,14572
+smftools/informatics/helpers/archived/load_adata.py,sha256=DhvYYqO9VLsZqhL1WjN9sd-e3fgvdXGlgTP18z1h0L0,33654
+smftools/plotting/__init__.py,sha256=MKT8y7Wq1X1CCDhLxyzYQfqXpEXQZFpZzhi25qGOul4,707
+smftools/plotting/classifiers.py,sha256=8_zabh4NNB1_yVxLD22lfrfl5yfzbEoG3XWqlIqdtrQ,13786
+smftools/plotting/general_plotting.py,sha256=LjN85KyXtuLbDpryMweSps2vFX9GEfc5flmLybLVdn8,9483
+smftools/plotting/position_stats.py,sha256=4XukYIWeWZ_aGSZg1K0t37KA2aknjNNKT5kcKFfuz8Q,17428
+smftools/preprocessing/__init__.py,sha256=2s_46L2qDmM_YoaG3j9YvZ6nTu1T_IF0czhlzC2emQQ,1349
+smftools/preprocessing/append_C_context.py,sha256=mmXju79pKYwrz7WP6v8rztDis4KHHhllBqJCmKky7lk,4414
+smftools/preprocessing/binarize_on_Youden.py,sha256=O5E3vFc2zXMfKW0p0JGDlmRKEx2_VP6dAqfvrumzz00,1797
+smftools/preprocessing/binary_layers_to_ohe.py,sha256=Lxd8knelNTaUozfGMFNMlnrOb6uP28Laj3Ymw6cRHL0,1826
+smftools/preprocessing/calculate_complexity.py,sha256=cXMpFrhkwkPipQo2GZGT5yFknMYUMt1t8gz0Cse1DrA,3288
+smftools/preprocessing/calculate_consensus.py,sha256=6zRpRmb2xdfDu5hctZrReALRb7Pjn8sy8xJZTm3o0nU,2442
+smftools/preprocessing/calculate_converted_read_methylation_stats.py,sha256=CWS3yoDTceZ8kDMWdy9eEo9Nd-yEbr2OehNovyoLR8w,5822
+smftools/preprocessing/calculate_coverage.py,sha256=XhtOo73ZL1kOvpzEaZAkOCtSD870zBPm0H9D7Kpv190,1867
+smftools/preprocessing/calculate_pairwise_differences.py,sha256=5zJbNNaFld5qgKRoPyplCmMHflbvAQ9eKWCXPXPpJ60,1774
+smftools/preprocessing/calculate_pairwise_hamming_distances.py,sha256=e5Mzyex7pT29H2PY014uU4Fi_eewbut1JkzC1ffBbCg,961
+smftools/preprocessing/calculate_position_Youden.py,sha256=9GY_WWwaxpB2Xppck3WT1zHtFOhTXrpuDIgbxLC9A7E,7450
+smftools/preprocessing/calculate_read_length_stats.py,sha256=gNNePwMqYZJidzGgT1ZkfSlvc5Y3I3bi5KNYpP6wQQc,4584
+smftools/preprocessing/clean_NaN.py,sha256=6eWSFFLxipiejcR_BeYJ4sVaayMuiEIoscd0eLvJuL0,1557
+smftools/preprocessing/filter_adata_by_nan_proportion.py,sha256=GZcvr2JCsthX8EMw34S9-W3fc6JElw6ka99Jy6f2JvA,1292
+smftools/preprocessing/filter_converted_reads_on_methylation.py,sha256=LOyBho1ltD2HXWrpO2xEeHk4aiHJxxWuG7_lr2NHSJk,2042
+smftools/preprocessing/filter_reads_on_length.py,sha256=Y4WQO5Mna4Xm9hFYKk66hEQb67GnzCTXPOokebRnV-g,2625
+smftools/preprocessing/flag_duplicate_reads.py,sha256=8izI9ekC8oOY1gf500hg8lM0UQFs0_2j2PFUQwgXES8,6276
+smftools/preprocessing/invert_adata.py,sha256=FS-Yo8o70pIT39CoxRtt73dFr1SGZiZqU1HcIj8zDQg,782
+smftools/preprocessing/load_sample_sheet.py,sha256=cRrf-6FDWu6t0eqZufHaF5qn1DLww3DcN5IEncj5K6k,1497
+smftools/preprocessing/make_dirs.py,sha256=lWHXpwC76MFM5sSme9i_WeYUaxutzybendokhny03ds,537
+smftools/preprocessing/min_non_diagonal.py,sha256=hx1asW8CEmLaIroZISW8EcAf_RnBEC_nofGD8QG0b1E,711
+smftools/preprocessing/recipes.py,sha256=cfKEpKW8TtQLe1CMdSHyPuIgKiWOPn7uP6uMIoRlnaQ,7063
+smftools/preprocessing/subsample_adata.py,sha256=ivJvJIOvEtyvAjqZ7cwEeVedm4QgJxCJEI7sFaTuI3w,2360
+smftools/preprocessing/archives/mark_duplicates.py,sha256=kwfstcWb7KkqeNB321dB-NLe8yd9_hZsSmpL8pCVBQg,8747
+smftools/preprocessing/archives/preprocessing.py,sha256=4mLT09A7vwRZ78FHmuwtv38mH9TQ9qrZc_WjHRhhkIw,34379
+smftools/preprocessing/archives/remove_duplicates.py,sha256=Erooi5_1VOUNfWpzddzmMNYMCl1U1jJryt7ZtMhabAs,699
+smftools/tools/__init__.py,sha256=jnO_-xJyt9Q86QKCZa6GvFCtacx9G4rW_HJtSyeiook,1717
+smftools/tools/apply_hmm.py,sha256=pJXCULay0zbmubrwql368y7yiHAZr2bJhuGx2QUuKnE,9321
+smftools/tools/apply_hmm_batched.py,sha256=1_36BK3ie7lPU4pD93TOBYltmsbdE3VJPqZydiw8I5s,10410
+smftools/tools/calculate_distances.py,sha256=KDWimQ6u-coyxCKrbTm42Fh_Alf_gURBZ0vfFaem848,644
+smftools/tools/calculate_umap.py,sha256=SoZvvnCBjCdshgkW0ODH1lUY97AHkrPXTxWDdYZO8VY,2513
+smftools/tools/call_hmm_peaks.py,sha256=ixnO-KwFYtLiXt8dSa1dEjNR0RO6b-Eswziz1AA647A,4933
+smftools/tools/classifiers.py,sha256=mwSTpWUXBPjmUuV5i_SMG1lIPpHSMCzsKhl8wTbm-Og,36903
+smftools/tools/cluster_adata_on_methylation.py,sha256=UDC5lpW8fZ6O-16ETu-mbflLkNBKuIg7RIzQ9r7knvA,5760
+smftools/tools/display_hmm.py,sha256=4yM-4wpQnWQiim16cUV4ITI-USEEEtaLHqK3LPu5YCg,840
+smftools/tools/general_tools.py,sha256=P9Ecq2SxzmhwLBvWaMpqGGzSPjOiMmG-AspCb0QaaPk,2573
+smftools/tools/hmm_readwrite.py,sha256=DjJ3hunpBQ7N0GVvxL7-0QUas_SkA88LVgL72mVK2cI,359
+smftools/tools/nucleosome_hmm_refinement.py,sha256=yzkx1i3ez678SS_mOMbg6sbI-yHXaUq5eJdaEF43S1w,4649
+smftools/tools/position_stats.py,sha256=FNR5JaD4e3ykrieN922IIyM4GHvwybz--_bgNPhAkNs,9500
+smftools/tools/read_stats.py,sha256=ze-1kuEnFR7UhNzuPB-UgJ_YIHCfDhOgs6oWAo90VaI,2546
+smftools/tools/subset_adata.py,sha256=nBbtAxCNteZCUBmPnZ9swQNyU74XgWM8aJHHWg2AuL0,1025
+smftools/tools/train_hmm.py,sha256=TCzvHlKLoQnKhflZOsXyXlgPhtk54k9EAoP89kUbQ1U,2465
+smftools/tools/archived/classify_methylated_features.py,sha256=Z0N2UKw3luD3CTQ8wcUvdnMY7w-8574OJbEcwzNsy88,2897
+smftools/tools/archived/classify_non_methylated_features.py,sha256=IJERTozEs7IPL7K-VIjq2q2K36wRCW9iiNSYLAXasrA,3256
+smftools/tools/archived/subset_adata_v1.py,sha256=qyU9iCal03edb5aUS3AZ2U4TlL3uQ42jGI9hX3QF7Fc,1047
+smftools/tools/archived/subset_adata_v2.py,sha256=OKZoUpvdURPtckIQxGTWmOI5jLa-_EU62Xs3LyyehnA,1880
+smftools/tools/data/__init__.py,sha256=DEEeRUbOOaeqvy1swkUWPK_TPcjmkU6CcoZAqSa5cfs,91
+smftools/tools/data/anndata_data_module.py,sha256=ReAdYxwPR446eeNRKYCrt9OEhlQ9woY_4qxncJbUh4c,4425
+smftools/tools/data/preprocessing.py,sha256=dSs6Qs3wmlccFPZSpOc-uy1nlFSf68wWQKwF1iTqMok,137
+smftools/tools/evaluation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+smftools/tools/inference/__init__.py,sha256=VJCamuKjcucG7RPFsjd8vECd_kwPlIz92u64gdPePDY,56
+smftools/tools/inference/lightning_inference.py,sha256=8SXbJWLDgbWiZW0bpC3IMkU01S1d_2zyzB__KxIAuBk,1469
+smftools/tools/models/__init__.py,sha256=bMfPbQ5bDmn_kWv82virLuUhjb12Yow7t_j96afNbyA,421
+smftools/tools/models/base.py,sha256=TRJMyKHGLLUkhEbzRMKIaNf-6yFyCEf5s0Xs0QUeG-0,505
+smftools/tools/models/cnn.py,sha256=M7SYPL-7f2Cyf0zQGmnV2vI6-KCz6rfikHV81XLy-lA,1169
+smftools/tools/models/lightning_base.py,sha256=8Zoj-ij5fSsFAn30hJfdUv-pZGuJLGtwj8HoHK3Msws,1354
+smftools/tools/models/mlp.py,sha256=YXVf1Pix-S2aqOMvmsVzbF_igsf9_MjKbuZw6FBo_nk,561
+smftools/tools/models/positional.py,sha256=7g93nyxnvWTYrfrdvIMWa74DG0obn5FbC2-ngWmCBVo,631
+smftools/tools/models/rnn.py,sha256=DVhG1mJ47ObqaHiLHEwHTpme1vR_uNeTnaaKzC6whgQ,656
+smftools/tools/models/sklearn_models.py,sha256=rFDrq7nJXHd4yCrc5oAvB76m04vdHQRNqWh3RCCOBQ0,1289
+smftools/tools/models/transformer.py,sha256=d0v7vtXNXOHDgOsXMyRkMLObpPpWjLvbFntGnh924g8,4896
+smftools/tools/models/wrappers.py,sha256=HEY2A6-Bk6MtVZ9jOaPT8S1Qi0L98SyEg1nbKqYZoag,697
+smftools/tools/training/__init__.py,sha256=PxAsc6UhXYyZkmwewhYK3OPVZG_se_YfSq75fqc0EBM,56
+smftools/tools/training/train_lightning_model.py,sha256=dtx1lJzgP8eMR1VyXsQo8KnzB6bhF2VY3kHhkEqVV58,1157
+smftools/tools/utils/__init__.py,sha256=yOpzBc9AXbarSRfN8Ixh2Z1uWLGpgpjRR46h6E46_2w,62
+smftools/tools/utils/device.py,sha256=GITrULOty2Fr96Bqt1wi1PaYl_oVgB5Z99Gfn5vQy4o,274
+smftools/tools/utils/grl.py,sha256=BWBDp_kQBigrUzQpRbZzgpfr_WOcd2K2V3MQL-aAIc4,334
+smftools-0.1.7.dist-info/METADATA,sha256=xb2e-EdaGquNERQ-0Pcs3SR4yTi5V_ua10ITchFjTkI,8870
+smftools-0.1.7.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+smftools-0.1.7.dist-info/licenses/LICENSE,sha256=F8LwmL6vMPddaCt1z1S83Kh_OZv50alTlY7BvVx1RXw,1066
+smftools-0.1.7.dist-info/RECORD,,

smftools/tools/apply_HMM.py

@@ -1 +0,0 @@
-# apply_HMM

smftools/tools/read_HMM.py

@@ -1 +0,0 @@
-# read_HMM

smftools/tools/train_HMM.py

@@ -1,43 +0,0 @@
-# train_HMM
-
-def train_HMM(adata, model_name='trained_HMM', save_hmm=False):
-    """
-
-    Parameters:
-        adata (AnnData): Input AnnData object
-        model_name (str): Name of the model
-        save_hmm (bool): Whether to save the model
-    
-    """
-    import numpy as np
-    import anndata as ad
-    from pomegranate.distributions import Categorical
-    from pomegranate.hmm import DenseHMM
-
-    bound = Categorical([[0.95, 0.05]])
-    unbound = Categorical([[0.05, 0.95]])
-
-    edges = [[0.9, 0.1], [0.1, 0.9]]
-    starts = [0.5, 0.5]
-    ends = [0.5, 0.5]
-
-    model = DenseHMM([bound, unbound], edges=edges, starts=starts, ends=ends, max_iter=5, verbose=True)
-
-    # define training sets and labels
-    # Determine the number of reads to sample
-    n_sample = round(0.7 * adata.X.shape[0])
-    # Generate random indices
-    np.random.seed(0)
-    random_indices = np.random.choice(adata.shape[0], size=n_sample, replace=False)
-    # Subset the AnnData object using the random indices
-    training_adata_subsampled = adata[random_indices, :]
-    training_sequences = training_adata_subsampled.X
-
-    # Train the HMM without labeled data
-    model.fit(training_sequences, algorithm='baum-welch')
-
-    if save_hmm:
-        # Save the model to a file
-        model_json = model.to_json()
-        with open(f'{model_name}.json', 'w') as f:
-                f.write(model_json)

smftools-0.1.3.dist-info/RECORD

@@ -1,84 +0,0 @@
-smftools/__init__.py,sha256=zy4ckT7hKrLrlm6NiZQoupvc6oSN7wJsyOBCYdzukcQ,401
-smftools/_settings.py,sha256=Ed8lzKUA5ncq5ZRfSp0t6_rphEEjMxts6guttwTZP5Y,409
-smftools/_version.py,sha256=R5TtpJu7Qu6sOarfDpp-5Oyy8Pi2Ir3VewCvsCQiAgo,21
-smftools/readwrite.py,sha256=DgVisHYdkjzaO7suPbUvluImeTc3jqGDlioNveHUxPc,4158
-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=xkSTlPuakVYVCuRurif9BceNBDt6bsngJvvjI8757QI,142
-smftools/datasets/dCas9_m6A_invitro_kinetics.h5ad.gz,sha256=niOcVHaYY7h3XyvwSkN-V_NMBaRt2vTP5TrJO0CwMCs,8385050
-smftools/datasets/datasets.py,sha256=0y597Ntp707bOgDwN6O-JEt9yxgplj66p0aj6Zs_IB4,779
-smftools/informatics/__init__.py,sha256=WQiMBr1yjDrlmHg8UNgW2MJsq4fPrVfh-UBr5tYI9x4,326
-smftools/informatics/conversion_smf.py,sha256=PS-TjgMttr3VRrT0zg5L_L01xMOewB_OXSsQyoM7DWI,4333
-smftools/informatics/direct_smf.py,sha256=ue7p7deuRwaZtEh9EFV1YTE8HKRAmOsx9oaRJdjCrbY,4697
-smftools/informatics/fast5_to_pod5.py,sha256=xfdZU3QluaAcR-q2uBRz8hcBwYt73nCnrFeahvi0OKQ,704
-smftools/informatics/load_adata.py,sha256=i-2YCSaeLzbPfNtKPrLwfkv-9u_TrTAZrbtNAj3FRWY,7271
-smftools/informatics/readwrite.py,sha256=DgVisHYdkjzaO7suPbUvluImeTc3jqGDlioNveHUxPc,4158
-smftools/informatics/subsample_fasta_from_bed.py,sha256=YqYV09rvEQdeiS5hTTrKa8xYmJfeM3Vk-UUqwpw0qBk,1983
-smftools/informatics/subsample_pod5.py,sha256=zDw9tRcrFRmPI62xkcy9dh8IfsJcuYm7R-FVeBC_g3s,4701
-smftools/informatics/archived/bam_conversion.py,sha256=I8EzXjQixMmqx2oWnoNSH5NURBhfT-krbWHkoi_M964,3330
-smftools/informatics/archived/bam_direct.py,sha256=jbEFtUIiUR8Wlp3po_sWkr19AUNS9WZjglojb9j28vo,3606
-smftools/informatics/archived/basecalls_to_adata.py,sha256=-Nag6lr_NAtU4t8jo0GSMdgIAIfmDge-5VEUPQbEatE,3692
-smftools/informatics/helpers/LoadExperimentConfig.py,sha256=gsWGoa9cydwY4Kd-hTXF2gtmxc8glRRD2V1JB88e9js,2822
-smftools/informatics/helpers/__init__.py,sha256=KrfyM08_RgDf3Ajvb4KNTvcOqZiWYSIVhEznCr01Gcc,2255
-smftools/informatics/helpers/align_and_sort_BAM.py,sha256=DouG6nGWXtz2ulZD5p0sEShE-4dbPudHaWcHFm4-oJA,2184
-smftools/informatics/helpers/aligned_BAM_to_bed.py,sha256=eYkGQFSM2gPEauASkY_-9Yvy6727vP8Q4wx_st85Dpc,2638
-smftools/informatics/helpers/bed_to_bigwig.py,sha256=AazYEZzKgKgukSFwCpeiApzxh1kbt11X4RFqRIiBIaY,1466
-smftools/informatics/helpers/binarize_converted_base_identities.py,sha256=iJlDah-YJ0zx0UrlHdtgvrALVNSA0TTTdDoKmNCVg0Q,1846
-smftools/informatics/helpers/canoncall.py,sha256=M7HEqhYsWMUB0tLP3hzMM0L7PhcOTXgetl5lV3GgIaw,1062
-smftools/informatics/helpers/complement_base_list.py,sha256=k6EkLtxFoajaIufxw1p0pShJ2nPHyGLTbzZmIFFjB4o,532
-smftools/informatics/helpers/concatenate_fastqs_to_bam.py,sha256=RXPn7e6Dcwol9tnUsfXJu3EuZcMSOJJo5LNWouovvZs,2715
-smftools/informatics/helpers/converted_BAM_to_adata.py,sha256=Rsnydzpf9lMS3TQjXpbXJSSfCzhVTPn3rBDLiK-8utA,13991
-smftools/informatics/helpers/count_aligned_reads.py,sha256=uYyUYglF1asiaoxr-LKxPMUEbfyD7FS-dumTg2hJHzQ,2170
-smftools/informatics/helpers/extract_base_identities.py,sha256=E-_m9W82N52NjX5kz9Af5YH0S2k58hnq9KTrm4S5vgM,4370
-smftools/informatics/helpers/extract_mods.py,sha256=UBFjXDKz_A6ivjcocYT1_pKjvygY2Fdg0RjQmMS8UuA,2269
-smftools/informatics/helpers/extract_readnames_from_BAM.py,sha256=3FxSNqbZ1VsOK2RfHrvevQTzhWATf5E8bZ5yVOqayvk,759
-smftools/informatics/helpers/find_conversion_sites.py,sha256=5AghDQzEoSvE2Og98VsKoeWUFSLnIGY1LnRu1BtQavM,3700
-smftools/informatics/helpers/generate_converted_FASTA.py,sha256=ueaAsFnBuc7zKwkBivBR3DJg4DtkxkHHIQcVVSWzv-w,5161
-smftools/informatics/helpers/get_chromosome_lengths.py,sha256=sLumLrGsU_Xg_oJcdOpQyjUGpJoT2HbcmxWwbwzXUlE,1036
-smftools/informatics/helpers/get_native_references.py,sha256=fRuyEm9UJkfd5DwHmFb1bxEtNvtSI1_BxGRmrCymGkw,981
-smftools/informatics/helpers/index_fasta.py,sha256=N3IErfSiavYldeaat8xcQgA1MpykoQHcE0gHUeWuClE,267
-smftools/informatics/helpers/make_dirs.py,sha256=lWHXpwC76MFM5sSme9i_WeYUaxutzybendokhny03ds,537
-smftools/informatics/helpers/make_modbed.py,sha256=cOQ97gPfRiCcw_fqboxousXIiOYjp78IFYLbu749U1Y,939
-smftools/informatics/helpers/modQC.py,sha256=LeOBObG8gAVVdgESIMceYhd5AW1gfN7ABo91OQtOzTM,1041
-smftools/informatics/helpers/modcall.py,sha256=9PH7Peq4y-VBqQcMkbv0TwgePBlD5aM4_FmI7H4hbQQ,1142
-smftools/informatics/helpers/modkit_extract_to_adata.py,sha256=duPlRAIz4VWM-jm9iaLY7N6JHQcun_L0nhr2VyUjNTI,38184
-smftools/informatics/helpers/ohe_batching.py,sha256=_Mz2p1We5PVIb8S6Hbq_hREKJ9mGQiADwfFK_NgMGhA,1909
-smftools/informatics/helpers/one_hot_encode.py,sha256=hpZAuwa9ndkhyCm9sO65KVHE0lbFDKqRylfliEKyD4o,632
-smftools/informatics/helpers/plot_read_length_and_coverage_histograms.py,sha256=tAnXFleGzXJNjHRAgZ0NUJuZ0P3aKmUYIrK-V9VoJKY,1860
-smftools/informatics/helpers/separate_bam_by_bc.py,sha256=Fsi8OEmv5Ny13cWoHVV9JmEjVFEXT_ZxbBOlRdmyPbE,1742
-smftools/informatics/helpers/split_and_index_BAM.py,sha256=_TFJ8fcLbIf37JG83hSc1zgs1yxX70-NhA8y-PbhTpo,1966
-smftools/informatics/helpers/archived/informatics.py,sha256=gKb2ZJ_LcAeEXuQqn9e-QDF_sS4tMpMTr2vZlqa7n54,14572
-smftools/informatics/helpers/archived/load_adata.py,sha256=DhvYYqO9VLsZqhL1WjN9sd-e3fgvdXGlgTP18z1h0L0,33654
-smftools/plotting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-smftools/preprocessing/__init__.py,sha256=5FQNrj51KmaDLeAGGBA8iWMkYiSOe7O91ES8mT4aVtE,1399
-smftools/preprocessing/append_C_context.py,sha256=pP5u9o5U4JmHras0PK6yas65u4-U5KlX3sKLb-duo80,3728
-smftools/preprocessing/binarize_on_Youden.py,sha256=slkkt56DZ1FZWy8Un5mNJEZ49JlPnPKow2zU4GoHEr8,2303
-smftools/preprocessing/binary_layers_to_ohe.py,sha256=931eHuVda6pMZTvC7jVTKkY2a_KQWpSfgi-nkA5NmaI,1238
-smftools/preprocessing/calculate_complexity.py,sha256=ut60et8bmIswtiLhctJWHNseIV4ZRQultYdtJPHcRPs,3224
-smftools/preprocessing/calculate_consensus.py,sha256=6zRpRmb2xdfDu5hctZrReALRb7Pjn8sy8xJZTm3o0nU,2442
-smftools/preprocessing/calculate_converted_read_methylation_stats.py,sha256=Si0DcES0lLMvg3XgdKpedxfPnXQ14tEFKrOAFRn3fHs,6059
-smftools/preprocessing/calculate_coverage.py,sha256=ZgRxQGpydxQg1exkvSiy8nHmzDIPGGqL5vL9XQ2PZQ4,2068
-smftools/preprocessing/calculate_pairwise_hamming_distances.py,sha256=e5Mzyex7pT29H2PY014uU4Fi_eewbut1JkzC1ffBbCg,961
-smftools/preprocessing/calculate_position_Youden.py,sha256=mfQ6nFfUaEaKg_icyHA1zZlhh0wHjpLE56BZDXOdP_4,6364
-smftools/preprocessing/calculate_read_length_stats.py,sha256=6m362JaCKlD0QoBUMnM2qsB6Jo_4shl7xFzqU1uZccU,4945
-smftools/preprocessing/clean_NaN.py,sha256=1vieT026p0gDJCbqB_CiLvAGGxlc-5xufoKJgZuBFFk,1150
-smftools/preprocessing/filter_converted_reads_on_methylation.py,sha256=SN5q0rqYtYW9j3i0sVSyTv9EmR_uLKI7GkjmJixeOU0,1307
-smftools/preprocessing/filter_reads_on_length.py,sha256=sAT66bjuI8ZtXyQc9SuPzq1dPIB1CNVx6VfWqVng4Dg,2191
-smftools/preprocessing/invert_adata.py,sha256=u6Y70EH0B5mXb9-HuukIlzpMgZ6rhzcJuy3YZZTx3SA,684
-smftools/preprocessing/load_sample_sheet.py,sha256=uGjzG9x-1t_1lCooH85P8Tfg80GdvVx8Jv1LPl9XNFM,915
-smftools/preprocessing/make_dirs.py,sha256=lWHXpwC76MFM5sSme9i_WeYUaxutzybendokhny03ds,537
-smftools/preprocessing/mark_duplicates.py,sha256=sQuPcTw8JsQoONOk-kMlAF965sIk2Pu-M7rIyfbyGGs,8145
-smftools/preprocessing/min_non_diagonal.py,sha256=hx1asW8CEmLaIroZISW8EcAf_RnBEC_nofGD8QG0b1E,711
-smftools/preprocessing/recipes.py,sha256=KzSw5JW0WJGzSis5Fm7moQY5PxOYl6-uYYf1NDj6nOE,7117
-smftools/preprocessing/remove_duplicates.py,sha256=Erooi5_1VOUNfWpzddzmMNYMCl1U1jJryt7ZtMhabAs,699
-smftools/preprocessing/archives/preprocessing.py,sha256=4mLT09A7vwRZ78FHmuwtv38mH9TQ9qrZc_WjHRhhkIw,34379
-smftools/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-smftools/tools/apply_HMM.py,sha256=AuVtOki69-Xs4mhjhTXJzd49KCVXwixFyWSUgDjtR6s,11
-smftools/tools/cluster.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-smftools/tools/read_HMM.py,sha256=N0MGG494VjlxYJcCVz1jN4OasGtRITZS98SJ2xB_j8k,10
-smftools/tools/subset_adata.py,sha256=qyU9iCal03edb5aUS3AZ2U4TlL3uQ42jGI9hX3QF7Fc,1047
-smftools/tools/train_HMM.py,sha256=x5ZcXj-heWQqDOX86nuuDoj1tPkYKl04fYA1fCKNQ0c,1380
-smftools-0.1.3.dist-info/METADATA,sha256=u26Og8tpAF2TgXZztotk3Q4EuP7Fvf73s1tlIjBDD-A,6410
-smftools-0.1.3.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-smftools-0.1.3.dist-info/licenses/LICENSE,sha256=F8LwmL6vMPddaCt1z1S83Kh_OZv50alTlY7BvVx1RXw,1066
-smftools-0.1.3.dist-info/RECORD,,