smftools 0.1.7__py3-none-any.whl → 0.2.3__py3-none-any.whl

{smftools-0.1.7.dist-info → smftools-0.2.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: smftools
-Version: 0.1.7
+Version: 0.2.3
 Summary: Single Molecule Footprinting Analysis in Python.
 Project-URL: Source, https://github.com/jkmckenna/smftools
 Project-URL: Documentation, https://smftools.readthedocs.io/
@@ -43,9 +43,11 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Classifier: Topic :: Scientific/Engineering :: Visualization
-Requires-Python: >=3.9
+Requires-Python: <3.13,>=3.9
 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
@@ -57,15 +59,18 @@ 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: 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: docs
 Requires-Dist: ipython>=7.20; extra == 'docs'
@@ -98,12 +103,9 @@ While most genomic data structures handle low-coverage data (<100X) along large
 
 ## Dependencies
 The following CLI tools need to be installed and configured before using the informatics (smftools.inform) module of smftools:
-1) [Dorado](https://github.com/nanoporetech/dorado) -> For standard/modified basecalling and alignment. Can be attained by downloading and configuring nanopore MinKnow software.
-2) [Samtools](https://github.com/samtools/samtools) -> For working with SAM/BAM files
-3) [Minimap2](https://github.com/lh3/minimap2) -> The aligner used by Dorado
-4) [Modkit](https://github.com/nanoporetech/modkit) -> Extracting summary statistics and read level methylation calls from modified BAM files
-5) [Bedtools](https://github.com/arq5x/bedtools2) -> For generating Bedgraphs from BAM alignment files.
-6) [BedGraphToBigWig](https://genome.ucsc.edu/goldenPath/help/bigWig.html) -> For converting BedGraphs to BigWig files for IGV sessions.
+1) [Dorado](https://github.com/nanoporetech/dorado) -> Basecalling, alignment, demultiplexing.
+2) [Minimap2](https://github.com/lh3/minimap2) -> Alignment if not using dorado.
+3) [Modkit](https://github.com/nanoporetech/modkit) -> Extracting read level methylation metrics from modified BAM files.
 
 ## Modules
 ### Informatics: Processes raw Nanopore/Illumina data from SMF experiments into an AnnData object.
@@ -118,6 +120,9 @@ The following CLI tools need to be installed and configured before using the inf
 
 ## Announcements
 
+### 11/05/25 - Version 0.2.1 is available through PyPI
+Version 0.2.1 makes the core workflow (smftools load) a command line tool that takes in an experiment_config.csv file for input/output and parameter management.
+
 ### 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.
 

smftools-0.2.3.dist-info/RECORD

@@ -0,0 +1,173 @@
+smftools/__init__.py,sha256=aZlrZBVexf_nEnzQeZu7NU_Kp6OnxcYpLo1KPImi7sI,599
+smftools/_settings.py,sha256=Ed8lzKUA5ncq5ZRfSp0t6_rphEEjMxts6guttwTZP5Y,409
+smftools/_version.py,sha256=X0PliCRFAeVnSTceUeHX1eM0j1HFhGFDWCRxLdde2Bs,21
+smftools/cli_entry.py,sha256=_QdtEKcVK5o-e5s9ETB9sOIdftPVlrDxvvjBKcP6YNk,14680
+smftools/readwrite.py,sha256=ExKZHNZ0QB-PtSck08drXfHTqbPeSUTHiYhv951SH1s,45994
+smftools/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+smftools/cli/cli_flows.py,sha256=xRiFUThoAL3LX1xdXaHVg4LjyJI4uNpGsc9aQ_wVCto,4941
+smftools/cli/hmm_adata.py,sha256=PApUJW0lO4kcLjsiqqQopXgL3Dg-AascIqJrgvSY1Rg,15916
+smftools/cli/load_adata.py,sha256=Qt1ej-osyJ47fpBkGaSDgR1F8E4aBNAdcXeBAGM-Lqg,29100
+smftools/cli/preprocess_adata.py,sha256=EKGbSTli7qvL44OQUmMalYJjsH9vn3w4Rx7U7BL0ybs,20991
+smftools/cli/spatial_adata.py,sha256=AX6iyBfbXud9actteTvDuaQUU_SE3SyBIeknR317g34,30212
+smftools/config/__init__.py,sha256=ObUnnR7aRSoD_uvpmsxA_BUFt4NOOfWNopDVCqjp7tg,69
+smftools/config/conversion.yaml,sha256=HrFz2f9QRe1RuhmgU6ZtMHaM4ZzY61_aLcugsmpV40Q,969
+smftools/config/deaminase.yaml,sha256=mw2aY222y2xg08Rs5CWvjlrXo3vaEim7JwBThA80y4o,1349
+smftools/config/default.yaml,sha256=3IrX0OrUyjhVc3CqTjM8uiprKWrrBdVtil4YhtVzKdQ,10233
+smftools/config/direct.yaml,sha256=SBhdtG7PKm-z5xxQmA7JV3NQsGnUJ4p58fGH8BnoMrM,2137
+smftools/config/discover_input_files.py,sha256=G9vyAmK_n_8Ur5dOnumevVLG3ydHchMy_JQrJdiuuz0,3892
+smftools/config/experiment_config.py,sha256=d_6f_Uv3CY-1orHbxpHtAZDsY2gwxw079_pNgR9wDUg,58837
+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/hmm/HMM.py,sha256=K8rt-EHn3ylIHpQ3dHf_OZCXxCBVSS2UWTgSGOatwHw,71046
+smftools/hmm/__init__.py,sha256=BkX145eGVy-kFOtyqOcu-Hzv9ZJLDQ3cfDe51eKBTwY,585
+smftools/hmm/apply_hmm_batched.py,sha256=BBeJ8DiIuuMWzLwtDdk2DO2vvrfLCrVe4JtRYPFItIU,10648
+smftools/hmm/calculate_distances.py,sha256=KDWimQ6u-coyxCKrbTm42Fh_Alf_gURBZ0vfFaem848,644
+smftools/hmm/call_hmm_peaks.py,sha256=T-3Ld8H4t3Mgg2whBTYP9s2QL7rY-9RIzVCgB6avKhE,4625
+smftools/hmm/display_hmm.py,sha256=3WuQCPvM3wPfzAdgbhfiBTd0g5mQdx9HTUdqAxs2aj4,825
+smftools/hmm/hmm_readwrite.py,sha256=DjJ3hunpBQ7N0GVvxL7-0QUas_SkA88LVgL72mVK2cI,359
+smftools/hmm/nucleosome_hmm_refinement.py,sha256=nQWimvse6dclcXhbU707rGbRVMKHM0mU_ZhH9g2yCMA,4641
+smftools/hmm/train_hmm.py,sha256=srzRcB9LEmNuHyBM0R5Z0VEnxecifQt-MoaJhADxGT8,2477
+smftools/informatics/__init__.py,sha256=vLvSrCtCVYRUCCNLW7fL3ltPr3h_w8FhT--V6el3ZkQ,1191
+smftools/informatics/bam_functions.py,sha256=otgl3TRPLn5Fnsx1jXX75du90k3XB3RHGzlfamvETsU,32670
+smftools/informatics/basecalling.py,sha256=jc39jneaa8Gt1azutHgBGWHqCoPeTVSGBu3kyQwP7xM,3460
+smftools/informatics/bed_functions.py,sha256=uETVxT5mRWDNn7t0OqhDi8kDiq7uDakeHB1L2JsP4PA,13377
+smftools/informatics/binarize_converted_base_identities.py,sha256=yOepGaNBGfZJEsMiLRwKauvsmaHn_JRrxaGp8LmKAXs,7778
+smftools/informatics/complement_base_list.py,sha256=k6EkLtxFoajaIufxw1p0pShJ2nPHyGLTbzZmIFFjB4o,532
+smftools/informatics/converted_BAM_to_adata.py,sha256=Y2kQNWly0WjjGN9El9zL1nLfjVxmPLWONvX5VNgZUh0,22554
+smftools/informatics/fasta_functions.py,sha256=5IfTkX_GIj5gRJB9PjL_WjyEktpBHwGsmS_nnO1ETjI,9790
+smftools/informatics/h5ad_functions.py,sha256=iAOxJjhaDslTUC78kjUHlCELigDl73sWo0fvXcKuFoI,7824
+smftools/informatics/modkit_extract_to_adata.py,sha256=TrgrL_IgfqzNJ9qZ_2EvF_B38_Syw8mP38Sl7v0Riwo,55278
+smftools/informatics/modkit_functions.py,sha256=lywjeqAJ7Cdd7k-0P3YaL_9cAZvEDTDLh91rIRcSMWE,5604
+smftools/informatics/ohe.py,sha256=MEmh3ps-ZSSyXuIrr5LMzQvCsDJRCYiy7JS-WD4TlYs,5805
+smftools/informatics/pod5_functions.py,sha256=vxwhD_d_iWpJydIpbf0uce7VGHm8sBnCwb7tLNpYBc8,9859
+smftools/informatics/run_multiqc.py,sha256=n6LvQuGQpLfsutVGmgvHfV0SV5PqTQ8wa_SeKOjRssM,1052
+smftools/informatics/archived/bam_conversion.py,sha256=I8EzXjQixMmqx2oWnoNSH5NURBhfT-krbWHkoi_M964,3330
+smftools/informatics/archived/bam_direct.py,sha256=jbEFtUIiUR8Wlp3po_sWkr19AUNS9WZjglojb9j28vo,3606
+smftools/informatics/archived/basecall_pod5s.py,sha256=Ynmxscsxj6qp-zVY0RWodq513oDuHDaHnpqoepB3RUU,3930
+smftools/informatics/archived/basecalls_to_adata.py,sha256=-Nag6lr_NAtU4t8jo0GSMdgIAIfmDge-5VEUPQbEatE,3692
+smftools/informatics/archived/conversion_smf.py,sha256=QhlISVi3Z-XqFKyDG_CenLojovAt5-ZhuVe9hus36lg,7177
+smftools/informatics/archived/deaminase_smf.py,sha256=mNeg1mIYYVLIiW8powEpz0CqrGRDsrmY5-aoIgwMGHs,7221
+smftools/informatics/archived/direct_smf.py,sha256=ylPGFBvRLdxLHeDJjAwq98j8Q8_lfGK3k5JJnQxrwJw,7485
+smftools/informatics/archived/fast5_to_pod5.py,sha256=TRG_FYYGCGWUPzZCt0ZqzB8gQv_HKvkssp9nTctWzXU,1398
+smftools/informatics/archived/print_bam_query_seq.py,sha256=8Z2ZJEOOlfWYUXiZGjteLWU4yTgvV8KQzEIBHUmamGM,838
+smftools/informatics/archived/subsample_fasta_from_bed.py,sha256=7YTKhXg_mtP4KWpnD-TB4nuFEL4crOa9_d84IJKllyQ,1633
+smftools/informatics/archived/subsample_pod5.py,sha256=zDw9tRcrFRmPI62xkcy9dh8IfsJcuYm7R-FVeBC_g3s,4701
+smftools/informatics/archived/helpers/archived/__init__.py,sha256=DiiBerFJAxZeG5y0ScpJSaVBJ8b4XWdfEJCh8Q7k8jU,2783
+smftools/informatics/archived/helpers/archived/align_and_sort_BAM.py,sha256=yaRfhQDh3HpsSTme6QnSqBgElCS0kv2G6TunhvR1weY,5493
+smftools/informatics/archived/helpers/archived/aligned_BAM_to_bed.py,sha256=N3NAOaoSt_M4V48vtTP_m_iF1tRuNIPS_uNJ3Y0IA4E,3391
+smftools/informatics/archived/helpers/archived/bam_qc.py,sha256=PWl3dViCHGOcjB4UKkxBFz34Gc0PXHVTHjpYVNckVH0,7975
+smftools/informatics/archived/helpers/archived/bed_to_bigwig.py,sha256=Bg9wFsavUU9Ha57n_99vYlYpVcbDUz3tLtYJ7ZFVR9k,2986
+smftools/informatics/archived/helpers/archived/canoncall.py,sha256=5WS6lwukc_xYTdPQy0OSj-WLbx0Rg70Cun1lCucY7w8,1741
+smftools/informatics/archived/helpers/archived/concatenate_fastqs_to_bam.py,sha256=6GTHXG1dfaC8rBin5NthG3xgyGqOsT6wIGxJVCmCq58,9774
+smftools/informatics/archived/helpers/archived/converted_BAM_to_adata.py,sha256=sRmOtn0kNosLYfogqslDHg1Azk51l6nfNOLgQOnQjlA,14591
+smftools/informatics/archived/helpers/archived/count_aligned_reads.py,sha256=ZF_kkzAf1RvM4PwDYhxD36UiuVuMM_MBvZgiXom1NQ0,2176
+smftools/informatics/archived/helpers/archived/demux_and_index_BAM.py,sha256=KmU7nqGQ-MfDrp8h3txbToGn4h95Rkvg0WEiuext-vY,2000
+smftools/informatics/archived/helpers/archived/extract_base_identities.py,sha256=CaFqNBjkDujYlyiUnOeRock1OQWs3CeiD3yTL96sjIs,3043
+smftools/informatics/archived/helpers/archived/extract_mods.py,sha256=Mrs7mrLFgCTiRGfPFSyvJm6brq--LGzZrNDiFB-jynI,3895
+smftools/informatics/archived/helpers/archived/extract_read_features_from_bam.py,sha256=SYAb4Q1HxiJzCx5bIz86MdH_TvVPsRAVodZD9082HGY,1491
+smftools/informatics/archived/helpers/archived/extract_read_lengths_from_bed.py,sha256=Cw39wgp1eBTV45Wk1l0c9l-upBW5N2OcgyWXTAXln90,678
+smftools/informatics/archived/helpers/archived/extract_readnames_from_BAM.py,sha256=3FxSNqbZ1VsOK2RfHrvevQTzhWATf5E8bZ5yVOqayvk,759
+smftools/informatics/archived/helpers/archived/find_conversion_sites.py,sha256=JPlDipmzeCBkV_T6esGD5ptwmbQmk8gJMTh7NMaSYd4,2480
+smftools/informatics/archived/helpers/archived/generate_converted_FASTA.py,sha256=Us6iH1cIhsXDnTvDxI-FEHB6ndbB30hd1ss-9dIoWVE,3819
+smftools/informatics/archived/helpers/archived/get_chromosome_lengths.py,sha256=BEroXshYSpjf5wt_vrEAFiTJmSuf-kvD-Z1B_1gusME,1000
+smftools/informatics/archived/helpers/archived/get_native_references.py,sha256=fRuyEm9UJkfd5DwHmFb1bxEtNvtSI1_BxGRmrCymGkw,981
+smftools/informatics/archived/helpers/archived/index_fasta.py,sha256=w6xHFSaoXVk-YWZWftZ9Xv8rywZ_IuuIouLQ12KL3ro,779
+smftools/informatics/archived/helpers/archived/informatics.py,sha256=gKb2ZJ_LcAeEXuQqn9e-QDF_sS4tMpMTr2vZlqa7n54,14572
+smftools/informatics/archived/helpers/archived/load_adata.py,sha256=DhvYYqO9VLsZqhL1WjN9sd-e3fgvdXGlgTP18z1h0L0,33654
+smftools/informatics/archived/helpers/archived/make_modbed.py,sha256=Wh0UCSOL4fMZbWYK-3oGGHwJtqPurJ3Bl6wJWBaTXoM,923
+smftools/informatics/archived/helpers/archived/modQC.py,sha256=pz2EscFgO-j-9dfNgNDseweXXqM5-a-Rj2abBLErLd0,1051
+smftools/informatics/archived/helpers/archived/modcall.py,sha256=LVPrdMNVp2gyQTJ4BNp8NJNm89AueDjsKaY7Gqkluho,1777
+smftools/informatics/archived/helpers/archived/ohe_batching.py,sha256=QVOiyl9fYHNIFWM23afYnQo0uaOjf1NR3ASKGVSrmuw,2975
+smftools/informatics/archived/helpers/archived/ohe_layers_decode.py,sha256=gIgUC9L8TFLi-fTnjR4PRzXdUaH5D6WL2Hump6XOoy0,1042
+smftools/informatics/archived/helpers/archived/one_hot_decode.py,sha256=3n4rzY8_aC9YKmgrftsguMsH7fUyQ-DbWmrOYF6la9s,906
+smftools/informatics/archived/helpers/archived/one_hot_encode.py,sha256=5hHigA6-SZLK84WH_RHo06F_6aTg7S3TJgvSr8gxGX8,1968
+smftools/informatics/archived/helpers/archived/plot_bed_histograms.py,sha256=78i0mYFuElTPGA2Dt1feO6Z4Grh1Nro3m-F8D5FRBOw,9914
+smftools/informatics/archived/helpers/archived/separate_bam_by_bc.py,sha256=pCLev0OQji1jBdVr25lI_gt9fsozSG8vh7TQkE_UHnY,1800
+smftools/informatics/archived/helpers/archived/split_and_index_BAM.py,sha256=Q7I5qJ5JjW6mSKysfl9NdlFZ6LIy3C8G5rGmG7cn2eA,1224
+smftools/machine_learning/__init__.py,sha256=cWyGN_QVcssqBr_VVr7xh2Inz0P7ylqUmBBcpMgsK0k,257
+smftools/machine_learning/data/__init__.py,sha256=xbfLE-gNjdgxvZ9LKTdvjAtbIHOcs2TR0Gz3YRFbo38,113
+smftools/machine_learning/data/anndata_data_module.py,sha256=ktrdMVMk5yhIUrnu-G_Xf3y7G-KP9PyhYZhobv8TCVg,10063
+smftools/machine_learning/data/preprocessing.py,sha256=dSs6Qs3wmlccFPZSpOc-uy1nlFSf68wWQKwF1iTqMok,137
+smftools/machine_learning/evaluation/__init__.py,sha256=KHvcC7bTYv-ThptAi6G8wD-hW5Iz1HPgMcQ3AewtK3c,122
+smftools/machine_learning/evaluation/eval_utils.py,sha256=t9WIevIJ6b6HqU6OYaNx7UBAa5TEIPFmZow6n_ZDZeY,1105
+smftools/machine_learning/evaluation/evaluators.py,sha256=KqYHqbVV2WOs0Yo4GIhLS_0h1oKY6nd1yi6piDWYQLg,8184
+smftools/machine_learning/inference/__init__.py,sha256=vWLQD-JNEKKNGuzDtx7vcE4czKKXEO6S-0Zp5-21fPs,172
+smftools/machine_learning/inference/inference_utils.py,sha256=aJuXvTgC8v4BOjLCgOU9vT3S2y1UGoZjq4mQpPswTQU,947
+smftools/machine_learning/inference/lightning_inference.py,sha256=34WVnPfpPDf4KM8ZN5MOsx4tYgsrUclkens6GXgB4Ek,2160
+smftools/machine_learning/inference/sklearn_inference.py,sha256=FomgQF5jFBfAj1-H2Q0_RPmvR9rDJsmUeaWOVRhbpTw,1612
+smftools/machine_learning/inference/sliding_window_inference.py,sha256=8zjQs2hGhj0Dww4gWljLVK0g002_U96dyIqQJiDdSDY,4426
+smftools/machine_learning/models/__init__.py,sha256=bMfPbQ5bDmn_kWv82virLuUhjb12Yow7t_j96afNbyA,421
+smftools/machine_learning/models/base.py,sha256=p3d77iyY8BVx0tYL0TjmOSnPNP1ZrKTzn_J05e2GF0A,9626
+smftools/machine_learning/models/cnn.py,sha256=KKZmJLQ6Bjm_HI8GULnafjz6mRy5BZ6Y0ZCgDSuS268,4465
+smftools/machine_learning/models/lightning_base.py,sha256=3nC3wajPIupFMtOq3YUf24_SHvDoW_9BIGyIvEwzN9w,13626
+smftools/machine_learning/models/mlp.py,sha256=Y2hc_qHj6vpM_mHpreFxBULn4MkR25oEA1LXu5sPA_w,820
+smftools/machine_learning/models/positional.py,sha256=EfTyYnY0pCB-aVJIWf-4DVNpyGlvx1q_09PzfrC-VlA,652
+smftools/machine_learning/models/rnn.py,sha256=uJnHDGpT2_l_HqHGsx33XGF3v3EYZPeOtSQ89uvhdpE,717
+smftools/machine_learning/models/sklearn_models.py,sha256=ssV-mR3rmcjycQEzKccRcbVaEjZp0zRNUL5-R6m1UKU,10402
+smftools/machine_learning/models/transformer.py,sha256=8YXS0vCcOWT-33h-8yeDfFM5ibPHQ-CMSEhGWzR4pm8,11039
+smftools/machine_learning/models/wrappers.py,sha256=HEY2A6-Bk6MtVZ9jOaPT8S1Qi0L98SyEg1nbKqYZoag,697
+smftools/machine_learning/training/__init__.py,sha256=teUmwpnmAl0oNFaqVrfoijEpxBjLwI5YtBwLHT3uXck,185
+smftools/machine_learning/training/train_lightning_model.py,sha256=usEBaQ4vNjfatefP5XDCXkywzgZ2D-YppGmT3-3gTGE,4070
+smftools/machine_learning/training/train_sklearn_model.py,sha256=m1k1Gsynpj6SJI64rl4B3cfXm1SliU0fwMAj1-bAAeE,3166
+smftools/machine_learning/utils/__init__.py,sha256=yOpzBc9AXbarSRfN8Ixh2Z1uWLGpgpjRR46h6E46_2w,62
+smftools/machine_learning/utils/device.py,sha256=GITrULOty2Fr96Bqt1wi1PaYl_oVgB5Z99Gfn5vQy4o,274
+smftools/machine_learning/utils/grl.py,sha256=BWBDp_kQBigrUzQpRbZzgpfr_WOcd2K2V3MQL-aAIc4,334
+smftools/plotting/__init__.py,sha256=7T3-hZFgTY0nfQgV4J6Vn9ogwkNMlY315kguZR7V1AI,866
+smftools/plotting/autocorrelation_plotting.py,sha256=cF9X3CgKiwzL79mgMUFO1tSqdybDoPN1COQQ567InCY,27455
+smftools/plotting/classifiers.py,sha256=8_zabh4NNB1_yVxLD22lfrfl5yfzbEoG3XWqlIqdtrQ,13786
+smftools/plotting/general_plotting.py,sha256=2JzE7agm_tILpQ67BHs5pdyPRsHBwcENZe7n4gfMWgM,61350
+smftools/plotting/hmm_plotting.py,sha256=3Eq82gty_0b8GkSMCQgUlbKfzR9h2fJ5rZkB8yYGX-M,10934
+smftools/plotting/position_stats.py,sha256=4XukYIWeWZ_aGSZg1K0t37KA2aknjNNKT5kcKFfuz8Q,17428
+smftools/plotting/qc_plotting.py,sha256=q5Ri0q89udvNUFUNxHzgk9atvQYqUkqkS5-JFq9EqoI,10045
+smftools/preprocessing/__init__.py,sha256=GAQBULUH7fGVabzK5Cq5Wj-0ew0vNA-jWQtR5LAowvs,1746
+smftools/preprocessing/add_read_length_and_mapping_qc.py,sha256=zD_Kxw3DvyOypfuSMGv0ESyt-02w4XlAAMqQxb7yDNQ,5700
+smftools/preprocessing/append_base_context.py,sha256=wGBAADePnys8DLUR15MpRe2BUcfCMDJWaCDDNyjn6AU,6209
+smftools/preprocessing/append_binary_layer_by_base_context.py,sha256=s-7t-VKCs9Y67pX7kH6DNCEkC-RW4nM-UPsBQV2ZwtE,6186
+smftools/preprocessing/binarize.py,sha256=6Vr7Z8zgtJ5rS_uPAx1n3EnQR670V33DlZ_95JmOeWc,484
+smftools/preprocessing/binarize_on_Youden.py,sha256=HGs4p7XiOSYU3_z8QswNHIA9HlrI-7Pp1Kggrn6yUnI,1834
+smftools/preprocessing/binary_layers_to_ohe.py,sha256=Lxd8knelNTaUozfGMFNMlnrOb6uP28Laj3Ymw6cRHL0,1826
+smftools/preprocessing/calculate_complexity.py,sha256=cXMpFrhkwkPipQo2GZGT5yFknMYUMt1t8gz0Cse1DrA,3288
+smftools/preprocessing/calculate_complexity_II.py,sha256=DGfl0jkuBPUpzhKVItN0W7EPzh-QYuR4IxRObPE6gAQ,9301
+smftools/preprocessing/calculate_consensus.py,sha256=6zRpRmb2xdfDu5hctZrReALRb7Pjn8sy8xJZTm3o0nU,2442
+smftools/preprocessing/calculate_coverage.py,sha256=4WTILzKLzxGLSsQrZkshXP-IRQpoVu3Fkqc0QTpux3Y,2132
+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=yaSd6UDXPCddoN1UR6LgTqE5teJ79Ldw0BAlemc9fB4,7453
+smftools/preprocessing/calculate_read_length_stats.py,sha256=gNNePwMqYZJidzGgT1ZkfSlvc5Y3I3bi5KNYpP6wQQc,4584
+smftools/preprocessing/calculate_read_modification_stats.py,sha256=mIlLBqNflVIkuoLxhbyujq3JEKyPl8iebhUlikB9brM,4775
+smftools/preprocessing/clean_NaN.py,sha256=IOcnN5YF05gpPQc3cc3IS83petCnhCpkYiyT6bXEyx0,1937
+smftools/preprocessing/filter_adata_by_nan_proportion.py,sha256=GZcvr2JCsthX8EMw34S9-W3fc6JElw6ka99Jy6f2JvA,1292
+smftools/preprocessing/filter_reads_on_length_quality_mapping.py,sha256=93LgTy_vsPnOZgoiXhZ1-w_pix2oFdBk-dsBUoz33Go,7379
+smftools/preprocessing/filter_reads_on_modification_thresholds.py,sha256=4TUvChkSH8R4p_0TpRCh7TounkdUgQHh71TGNmsZ29A,19355
+smftools/preprocessing/flag_duplicate_reads.py,sha256=MySI9En6xVp0FqL7hfiLw0EP3JnGVJWM_yZfkvN-m1U,65585
+smftools/preprocessing/invert_adata.py,sha256=HYMJ1sR3Ui8j6bDjY8OcVQOETzZV-_rrpIYaWLZL6S4,1049
+smftools/preprocessing/load_sample_sheet.py,sha256=AjJf2MrqGHJJ2rNjYi09zV1QkLTq8qGaHGVklXHnPuU,1908
+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=QV3asy5_lP9wcRzpNTfxGTCcpykkbNYvzxSMpFw4KXU,719
+smftools/tools/calculate_umap.py,sha256=2arbAQdFOtnWoPq22TWicyr6fLYZ5PTNeZv_jdwuk_I,2491
+smftools/tools/cluster_adata_on_methylation.py,sha256=UDC5lpW8fZ6O-16ETu-mbflLkNBKuIg7RIzQ9r7knvA,5760
+smftools/tools/general_tools.py,sha256=YbobB6Zllz6cUq50yolGH9Jr6uuAMvEI4m3hiJ6FmAI,2561
+smftools/tools/position_stats.py,sha256=Z7VW54wUVzH1RQ9xhP6KO7ewp-xeLybd07I5umV_aqM,24369
+smftools/tools/read_stats.py,sha256=w3Zaim6l__Kt8EPCJKXTlMgO51Iy2Milj6yUb88HXiI,6324
+smftools/tools/spatial_autocorrelation.py,sha256=uQkuPi2PJCj5lZzb33IWTL-e-p3J6PdMeM88rUFfQRw,21212
+smftools/tools/subset_adata.py,sha256=nBbtAxCNteZCUBmPnZ9swQNyU74XgWM8aJHHWg2AuL0,1025
+smftools/tools/archived/apply_hmm.py,sha256=pJXCULay0zbmubrwql368y7yiHAZr2bJhuGx2QUuKnE,9321
+smftools/tools/archived/classifiers.py,sha256=mwSTpWUXBPjmUuV5i_SMG1lIPpHSMCzsKhl8wTbm-Og,36903
+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-0.2.3.dist-info/METADATA,sha256=w_PRsBPndPoTQZviW9WTuiZV1Pk3ukeJ155OvC4E57M,8787
+smftools-0.2.3.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+smftools-0.2.3.dist-info/entry_points.txt,sha256=q4hg4w-mKkI2leekM_-YZc5XRJzp96Mh1FcU3hac82g,52
+smftools-0.2.3.dist-info/licenses/LICENSE,sha256=F8LwmL6vMPddaCt1z1S83Kh_OZv50alTlY7BvVx1RXw,1066
+smftools-0.2.3.dist-info/RECORD,,

smftools-0.2.3.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+smftools = smftools.cli_entry:cli

smftools/informatics/fast5_to_pod5.py

@@ -1,21 +0,0 @@
-# fast5_to_pod5
-
-def fast5_to_pod5(fast5_dir, output_pod5='FAST5s_to_POD5.pod5'):
-    """
-    Convert Nanopore FAST5 files to POD5 file
-
-    Parameters:
-        fast5_dir (str): String representing the file path to a directory containing all FAST5 files to convert into a single POD5 output.
-        output_pod5 (str): The name of the output POD5.
-    
-    Returns:
-        None
-    
-    """
-    import subprocess
-    from pathlib import Path
-
-    if Path(fast5_dir).is_file():
-        subprocess.run(["pod5", "convert", "fast5", fast5_dir, "--output", output_pod5])
-    elif Path(fast5_dir).is_dir():
-        subprocess.run(["pod5", "convert", "fast5", f".{fast5_dir}*.fast5", "--output", output_pod5])

smftools/informatics/helpers/LoadExperimentConfig.py

@@ -1,75 +0,0 @@
-## LoadExperimentConfig
-
-class LoadExperimentConfig:
-    """
-    Loads in the experiment configuration csv and saves global variables with experiment configuration parameters.
-    Parameters:
-        experiment_config (str): A string representing the file path to the experiment configuration csv file.
-    
-    Attributes:
-        var_dict (dict): A dictionary containing experiment configuration parameters.
-
-    Example:
-        >>> import pandas as pd
-        >>> from io import StringIO
-        >>> csv_data = '''variable,value,type
-        ... mapping_threshold,0.05,float
-        ... batch_size,4,int
-        ... testing_bool,True,bool
-        ... strands,"[bottom, top]",list
-        ... split_dir,split_bams,string
-        ... pod5_dir,None,string
-        ... pod5_dir,,string
-        ... '''
-        >>> csv_file = StringIO(csv_data)
-        >>> df = pd.read_csv(csv_file)
-        >>> df.to_csv('test_config.csv', index=False)
-        >>> config_loader = LoadExperimentConfig('test_config.csv')
-        >>> config_loader.var_dict['mapping_threshold']
-        0.05
-        >>> config_loader.var_dict['batch_size']
-        4
-        >>> config_loader.var_dict['testing_bool']
-        True
-        >>> config_loader.var_dict['strands']
-        ['bottom', 'top']
-        >>> config_loader.var_dict['split_dir']
-        'split_bams'
-        >>> config_loader.var_dict['pod5_dir'] is None
-        True
-        >>> config_loader.var_dict['pod5_dir'] is None
-        True
-    """
-    def __init__(self, experiment_config):
-        import pandas as pd
-        print(f"Loading experiment config from {experiment_config}")
-        # Read the CSV into a pandas DataFrame
-        df = pd.read_csv(experiment_config)
-        # Initialize an empty dictionary to store variables
-        var_dict = {}
-        # Iterate through each row in the DataFrame
-        for _, row in df.iterrows():
-            var_name = str(row['variable'])
-            value = row['value']
-            dtype = row['type']
-            # Handle empty and None values
-            if pd.isna(value) or value in ['None', '']:
-                value = None
-            else:
-                # Handle different data types
-                if dtype == 'list':
-                    # Convert the string representation of a list to an actual list
-                    value = value.strip('()[]').replace(', ', ',').split(',')
-                elif dtype == 'int':
-                    value = int(value)
-                elif dtype == 'float':
-                    value = float(value)
-                elif dtype == 'bool':
-                    value = value.lower() == 'true'
-                elif dtype == 'string':
-                    value = str(value)
-            # Store the variable in the dictionary
-            var_dict[var_name] = value
-        # Save the dictionary as an attribute of the class
-        self.var_dict = var_dict
-

smftools/informatics/helpers/__init__.py

@@ -1,74 +0,0 @@
-from .align_and_sort_BAM import align_and_sort_BAM
-from .aligned_BAM_to_bed import aligned_BAM_to_bed
-from .bam_qc import bam_qc
-from .bed_to_bigwig import bed_to_bigwig
-from .binarize_converted_base_identities import binarize_converted_base_identities
-from .canoncall import canoncall
-from .complement_base_list import complement_base_list
-from .converted_BAM_to_adata_II import converted_BAM_to_adata_II
-from .concatenate_fastqs_to_bam import concatenate_fastqs_to_bam
-from .count_aligned_reads import count_aligned_reads
-from .demux_and_index_BAM import demux_and_index_BAM
-from .extract_base_identities import extract_base_identities
-from .extract_mods import extract_mods
-from .extract_read_features_from_bam import extract_read_features_from_bam
-from .extract_read_lengths_from_bed import extract_read_lengths_from_bed
-from .extract_readnames_from_BAM import extract_readnames_from_BAM
-from .find_conversion_sites import find_conversion_sites
-from .generate_converted_FASTA import convert_FASTA_record, generate_converted_FASTA
-from .get_chromosome_lengths import get_chromosome_lengths
-from .get_native_references import get_native_references
-from .index_fasta import index_fasta
-from .LoadExperimentConfig import LoadExperimentConfig
-from .make_dirs import make_dirs
-from .make_modbed import make_modbed
-from .modcall import modcall
-from .modkit_extract_to_adata import modkit_extract_to_adata
-from .modQC import modQC
-from .one_hot_encode import one_hot_encode
-from .ohe_batching import ohe_batching
-from .one_hot_decode import one_hot_decode
-from .ohe_layers_decode import ohe_layers_decode
-from .plot_read_length_and_coverage_histograms import plot_read_length_and_coverage_histograms
-from .run_multiqc import run_multiqc
-from .separate_bam_by_bc import separate_bam_by_bc
-from .split_and_index_BAM import split_and_index_BAM
-
-__all__ = [
-    "align_and_sort_BAM",
-    "aligned_BAM_to_bed",
-    "bam_qc",
-    "bed_to_bigwig",
-    "binarize_converted_base_identities",
-    "canoncall",
-    "complement_base_list",
-    "converted_BAM_to_adata_II",
-    "concatenate_fastqs_to_bam",
-    "count_aligned_reads",
-    "demux_and_index_BAM",
-    "extract_base_identities",
-    "extract_mods",
-    "extract_read_features_from_bam",
-    "extract_read_lengths_from_bed",
-    "extract_readnames_from_BAM",
-    "find_conversion_sites",
-    "convert_FASTA_record",
-    "generate_converted_FASTA",
-    "get_chromosome_lengths",
-    "get_native_references",
-    "index_fasta",
-    "LoadExperimentConfig",
-    "make_dirs",
-    "make_modbed",
-    "modcall",
-    "modkit_extract_to_adata",
-    "modQC",
-    "one_hot_encode",
-    "ohe_batching",
-    "one_hot_decode",
-    "ohe_layers_decode",
-    "plot_read_length_and_coverage_histograms",
-    "run_multiqc",
-    "separate_bam_by_bc",
-    "split_and_index_BAM"
-]

smftools/informatics/helpers/align_and_sort_BAM.py

@@ -1,59 +0,0 @@
-## align_and_sort_BAM
-
-def align_and_sort_BAM(fasta, input, bam_suffix='.bam', output_directory='aligned_outputs', make_bigwigs=False, threads=None):
-    """
-    A wrapper for running dorado aligner and samtools functions
-    
-    Parameters:
-        fasta (str): File path to the reference genome to align to.
-        input (str): File path to the basecalled file to align. Works for .bam and .fastq files
-        bam_suffix (str): The suffix to use for the BAM file.
-        output_directory (str): A file path to the directory to output all the analyses.
-        make_bigwigs (bool): Whether to make bigwigs
-        threads (int): Number of additional threads to use
-
-    Returns:
-        None
-            The function writes out files for: 1) An aligned BAM, 2) and aligned_sorted BAM, 3) an index file for the aligned_sorted BAM, 4) A bed file for the aligned_sorted BAM, 5) A text file containing read names in the aligned_sorted BAM
-    """
-    import subprocess
-    import os
-
-    input_basename = os.path.basename(input)
-    input_suffix = '.' + input_basename.split('.')[1]
-
-    output_path_minus_suffix = os.path.join(output_directory, input_basename.split(input_suffix)[0])
-    
-    aligned_BAM=f"{output_path_minus_suffix}_aligned"
-    aligned_sorted_BAM=f"{aligned_BAM}_sorted"
-    aligned_output = aligned_BAM + bam_suffix
-    aligned_sorted_output = aligned_sorted_BAM + bam_suffix
-
-    if threads:
-        threads = str(threads)
-    else:
-        pass
-    
-    # Run dorado aligner
-    print(f"Aligning BAM to Reference: {input}")
-    if threads:
-        alignment_command = ["dorado", "aligner", "-t", threads, '--mm2-opts', "-N 1", fasta, input]
-    else:
-        alignment_command = ["dorado", "aligner", '--mm2-opts', "-N 1", fasta, input]
-    subprocess.run(alignment_command, stdout=open(aligned_output, "w"))
-
-    # Sort the BAM on positional coordinates
-    print(f"Sorting BAM: {aligned_output}")
-    if threads:
-        sort_command = ["samtools", "sort", "-@", threads, "-o", aligned_sorted_output, aligned_output]
-    else:
-        sort_command = ["samtools", "sort", "-o", aligned_sorted_output, aligned_output]
-    subprocess.run(sort_command)
-
-    # Create a BAM index file
-    print(f"Indexing BAM: {aligned_sorted_output}")
-    if threads:
-        index_command = ["samtools", "index", "-@", threads, aligned_sorted_output]
-    else:
-        index_command = ["samtools", "index", aligned_sorted_output]
-    subprocess.run(index_command)

smftools/informatics/helpers/aligned_BAM_to_bed.py

@@ -1,74 +0,0 @@
-def aligned_BAM_to_bed(aligned_BAM, out_dir, fasta, make_bigwigs, threads=None):
-    """
-    Takes an aligned BAM as input and writes a BED file of reads as output.
-    Bed columns are: Record name, start position, end position, read length, read name.
-
-    Parameters:
-        aligned_BAM (str): Path to an input aligned_BAM to extract to a BED file.
-        out_dir (str): Directory to output files.
-        fasta (str): File path to the reference genome.
-        make_bigwigs (bool): Whether to generate bigwig files.
-        threads (int): Number of threads to use.
-
-    Returns:
-        None
-    """
-    import subprocess
-    import os
-    import concurrent.futures
-    from concurrent.futures import ProcessPoolExecutor
-    from .bed_to_bigwig import bed_to_bigwig
-    from . import make_dirs
-    from .plot_read_length_and_coverage_histograms import plot_read_length_and_coverage_histograms
-
-    threads = threads or os.cpu_count()  # Use max available cores if not specified
-
-    # Create necessary directories
-    plotting_dir = os.path.join(out_dir, "bed_cov_histograms")
-    bed_dir = os.path.join(out_dir, "beds")
-    make_dirs([plotting_dir, bed_dir])
-
-    bed_output = os.path.join(bed_dir, os.path.basename(aligned_BAM).replace(".bam", "_bed.bed"))
-
-    print(f"Creating BED from BAM: {aligned_BAM} using {threads} threads...")
-
-    # Convert BAM to BED format
-    with open(bed_output, "w") as output_file:
-        samtools_view = subprocess.Popen(["samtools", "view", "-@", str(threads), aligned_BAM], stdout=subprocess.PIPE)
-        awk_process = subprocess.Popen(
-            ["awk", '{print $3 "\t" $4 "\t" $4+length($10)-1 "\t" length($10)-1 "\t" $1}'],
-            stdin=samtools_view.stdout,
-            stdout=output_file
-        )
-
-    samtools_view.stdout.close()
-    awk_process.wait()
-    samtools_view.wait()
-
-    print(f"BED file created: {bed_output}")
-
-    def split_bed(bed):
-        """Splits BED into aligned and unaligned reads."""
-        aligned = bed.replace(".bed", "_aligned.bed")
-        unaligned = bed.replace(".bed", "_unaligned.bed")
-
-        with open(bed, "r") as infile, open(aligned, "w") as aligned_out, open(unaligned, "w") as unaligned_out:
-            for line in infile:
-                (unaligned_out if line.startswith("*") else aligned_out).write(line)
-
-        os.remove(bed)
-        return aligned
-
-    print(f"Splitting BED: {bed_output}")
-    aligned_bed = split_bed(bed_output)
-
-    with ProcessPoolExecutor() as executor:  # Use processes instead of threads
-        futures = []
-        futures.append(executor.submit(plot_read_length_and_coverage_histograms, aligned_bed, plotting_dir))
-        if make_bigwigs:
-            futures.append(executor.submit(bed_to_bigwig, fasta, aligned_bed))
-
-        # Wait for all tasks to complete
-        concurrent.futures.wait(futures)
-
-    print("Processing completed successfully.")

smftools/informatics/helpers/bam_qc.py

@@ -1,66 +0,0 @@
-## bam_qc
-
-def bam_qc(bam_files, bam_qc_dir, threads, modality, stats=True, flagstats=True, idxstats=True):
-    """
-    Performs QC on BAM files by running samtools stats, flagstat, and idxstats.
-    
-    Parameters:
-    - bam_files: List of BAM file paths.
-    - bam_qc_dir: Directory to save QC reports.
-    - threads: Number threads to use.
-    - modality: 'conversion' or 'direct' (affects processing mode).
-    - stats: Run `samtools stats` if True.
-    - flagstats: Run `samtools flagstat` if True.
-    - idxstats: Run `samtools idxstats` if True.
-    """
-    import os
-    import subprocess
-    
-    # Ensure the QC output directory exists
-    os.makedirs(bam_qc_dir, exist_ok=True)
-
-    if threads:
-        threads = str(threads)
-    else:
-        pass
-
-    for bam in bam_files:
-        bam_name = os.path.basename(bam).replace(".bam", "")  # Extract filename without extension
-
-        # Run samtools QC commands based on selected options
-        if stats:
-            stats_out = os.path.join(bam_qc_dir, f"{bam_name}_stats.txt")
-            if threads:
-                command = ["samtools", "stats", "-@", threads, bam]
-            else: 
-                command = ["samtools", "stats", bam]
-            print(f"Running: {' '.join(command)} > {stats_out}")
-            with open(stats_out, "w") as out_file:
-                subprocess.run(command, stdout=out_file)
-
-        if flagstats:
-            flagstats_out = os.path.join(bam_qc_dir, f"{bam_name}_flagstat.txt")
-            if threads:
-                command = ["samtools", "flagstat", "-@", threads, bam]
-            else:
-                command = ["samtools", "flagstat", bam]
-            print(f"Running: {' '.join(command)} > {flagstats_out}")
-            with open(flagstats_out, "w") as out_file:
-                subprocess.run(command, stdout=out_file)
-
-        if idxstats:
-            idxstats_out = os.path.join(bam_qc_dir, f"{bam_name}_idxstats.txt")
-            if threads:
-                command = ["samtools", "idxstats", "-@", threads, bam]
-            else:
-                command = ["samtools", "idxstats", bam]
-            print(f"Running: {' '.join(command)} > {idxstats_out}")
-            with open(idxstats_out, "w") as out_file:
-                subprocess.run(command, stdout=out_file)
-
-        if modality == 'conversion':
-            pass
-        elif modality == 'direct':
-            pass
-
-    print("QC processing completed.")