smftools 0.1.7__py3-none-any.whl → 0.2.1__py3-none-any.whl

{smftools-0.1.7.dist-info → smftools-0.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: smftools
-Version: 0.1.7
+Version: 0.2.1
 Summary: Single Molecule Footprinting Analysis in Python.
 Project-URL: Source, https://github.com/jkmckenna/smftools
 Project-URL: Documentation, https://smftools.readthedocs.io/
@@ -46,6 +46,8 @@ Classifier: Topic :: Scientific/Engineering :: Visualization
 Requires-Python: >=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
@@ -64,8 +66,10 @@ 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'

smftools-0.2.1.dist-info/RECORD

@@ -0,0 +1,161 @@
+smftools/__init__.py,sha256=OXW2_b5NUGZhTXsH8qY0PzfJnaz8T2y6lCqMnSVSuIk,676
+smftools/_settings.py,sha256=Ed8lzKUA5ncq5ZRfSp0t6_rphEEjMxts6guttwTZP5Y,409
+smftools/_version.py,sha256=tC9CwL4Nm8brVXJnZNGk_eoZaJj6eOtLKtOrdJMrpoI,21
+smftools/cli.py,sha256=MNObu279y322JHkmugssM0rVHo0UQ1zboTG9MlqnMgQ,7033
+smftools/load_adata.py,sha256=VJMUBqRC8InIj48JMnkZKLuqEz1u8uSTNx_ARl0cn7M,74313
+smftools/readwrite.py,sha256=ObNxBj6Y_zIHqQpAvmHAddAypLjg7F3qARF-sH-V3do,42706
+smftools/config/__init__.py,sha256=ObUnnR7aRSoD_uvpmsxA_BUFt4NOOfWNopDVCqjp7tg,69
+smftools/config/conversion.yaml,sha256=rJGhrVd95p6_6OVxLq2lvobJu8SGzNYI80jU0fLeK_g,795
+smftools/config/deaminase.yaml,sha256=Vh3Wg0bCb88S20Ob-8zi3eQJ1g_pcBulR9pPbAX9U1o,1138
+smftools/config/default.yaml,sha256=0DYIvvdbzoB2eJgsoxEzx4Rc0TVGaiHa85nxo1VwCqQ,9704
+smftools/config/direct.yaml,sha256=2F_fGploWW3f88Y7sTZ68Vk9fgNaO-sb5AK-Cutc2TQ,735
+smftools/config/experiment_config.py,sha256=zQhWaag9hPuexnTOqZ-Od--c3iHs18c4Wc2sU-LOyts,52872
+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=8tvVG08L_Z-bP28PusBtVt1UTnHxuKi0lImLNcP7qso,338
+smftools/informatics/basecall_pod5s.py,sha256=Ynmxscsxj6qp-zVY0RWodq513oDuHDaHnpqoepB3RUU,3930
+smftools/informatics/fast5_to_pod5.py,sha256=h-cUZX5sWwPCkQ4g3kyz3koSBjZOWI6EjSpWO8zib1I,862
+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/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/print_bam_query_seq.py,sha256=8Z2ZJEOOlfWYUXiZGjteLWU4yTgvV8KQzEIBHUmamGM,838
+smftools/informatics/helpers/__init__.py,sha256=EgCIcJ6o3_R3vzsFwhtvOcKKWnmmMmN_GZXDQ_K_-NI,2693
+smftools/informatics/helpers/align_and_sort_BAM.py,sha256=gy_BU6KfDd584LPFybJ7JzNwfCD95dZXx6MccnT4Qro,3725
+smftools/informatics/helpers/aligned_BAM_to_bed.py,sha256=e6yg5-yHcw0QPFI3oRVHrhfAUj7US77Ir2VVzE3c-x8,3374
+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=yOepGaNBGfZJEsMiLRwKauvsmaHn_JRrxaGp8LmKAXs,7778
+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=0jy4H1ORuqaarsznv9tS1SM8CCRjaaD20NMknNvQPv0,16212
+smftools/informatics/helpers/converted_BAM_to_adata.py,sha256=sRmOtn0kNosLYfogqslDHg1Azk51l6nfNOLgQOnQjlA,14591
+smftools/informatics/helpers/converted_BAM_to_adata_II.py,sha256=9Tz-qWtK9v1DTlK6yManvhOlMcaHFQUmmrRZQ5eiECw,22229
+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/discover_input_files.py,sha256=hUes2iKBQW_sVmAYD-1JnLD9Ub-COEHzrRKWNFipl0g,3725
+smftools/informatics/helpers/extract_base_identities.py,sha256=2yvr5uff9ah0jylFjNMt7oRJb1z_YdhvM6htSxI0frg,3038
+smftools/informatics/helpers/extract_mods.py,sha256=MbSIiyj3zx7WlSSWMRPriLMkBtxYc1EWZiAAirMVgqA,3865
+smftools/informatics/helpers/extract_read_features_from_bam.py,sha256=SYAb4Q1HxiJzCx5bIz86MdH_TvVPsRAVodZD9082HGY,1491
+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=JPlDipmzeCBkV_T6esGD5ptwmbQmk8gJMTh7NMaSYd4,2480
+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=yjG_Onh6YgwpE11I8mgQyN6F-8yStJgvDcI38L13i4A,52098
+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_bed_histograms.py,sha256=sdtz_ieU_5rz8WyfAzjxbzY_w8kLdE_Rklvjax1hl3Q,10442
+smftools/informatics/helpers/run_multiqc.py,sha256=qkw48DeBdTEqzhKFGjMUlvNmTehp8wRPkcxdkwERkHc,980
+smftools/informatics/helpers/separate_bam_by_bc.py,sha256=WJZwKCYODUvzFaVWwX3SUE8sxEXmeYmSi7Dl9h2J2EY,1802
+smftools/informatics/helpers/split_and_index_BAM.py,sha256=yowMusTGoC7uRD0jAwOHzBegX6MV7f-uY-XSzkX5cBw,1253
+smftools/informatics/helpers/archived/informatics.py,sha256=gKb2ZJ_LcAeEXuQqn9e-QDF_sS4tMpMTr2vZlqa7n54,14572
+smftools/informatics/helpers/archived/load_adata.py,sha256=DhvYYqO9VLsZqhL1WjN9sd-e3fgvdXGlgTP18z1h0L0,33654
+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=wdqQ4dawibgZeXRs_G4WterkqOgxHWrJlgZ4PdtO-OA,27456
+smftools/plotting/classifiers.py,sha256=8_zabh4NNB1_yVxLD22lfrfl5yfzbEoG3XWqlIqdtrQ,13786
+smftools/plotting/general_plotting.py,sha256=JOeF_lq2hCDt1Vgy8KYLKSzNj8SXGi3z6qMt2P68TDU,31458
+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=VqhiwJg57m0ePCRAGfX3cJniNLV2jNJpoXZEM2j-0wU,1687
+smftools/preprocessing/add_read_length_and_mapping_qc.py,sha256=zD_Kxw3DvyOypfuSMGv0ESyt-02w4XlAAMqQxb7yDNQ,5700
+smftools/preprocessing/append_base_context.py,sha256=ohtdHNS1Y9ttLvhLKSwrOyar7HyU2Dw0Ach9WVx5QM8,6221
+smftools/preprocessing/append_binary_layer_by_base_context.py,sha256=I3iiZkVqqB1KqSiA-s-ctl-ESkuTpd7Ot82M0xv_Cm4,6202
+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_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=9GY_WWwaxpB2Xppck3WT1zHtFOhTXrpuDIgbxLC9A7E,7450
+smftools/preprocessing/calculate_read_length_stats.py,sha256=gNNePwMqYZJidzGgT1ZkfSlvc5Y3I3bi5KNYpP6wQQc,4584
+smftools/preprocessing/calculate_read_modification_stats.py,sha256=fQYtwsGt6zq7QBlWtAEaFOkbV_4yXjrj9GnBryEEztc,4779
+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=wOmHhQj3xQALQdtQ4-v4POEOat5bEJa-BVmzEE_yrKA,19403
+smftools/preprocessing/flag_duplicate_reads.py,sha256=D7KrDuyy_TSgGvB5aRRmY01k36p92n48YEwmwsUd3IY,65595
+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-0.2.1.dist-info/METADATA,sha256=MXyiJbt1w_Ln4ENxQNbLU0JWwE-S6z1oNZkd8gkf3J8,8958
+smftools-0.2.1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+smftools-0.2.1.dist-info/entry_points.txt,sha256=NflK6zRv2zlvnjCnDSHycp9w9CczHLfGz9zAc4FtI0I,46
+smftools-0.2.1.dist-info/licenses/LICENSE,sha256=F8LwmL6vMPddaCt1z1S83Kh_OZv50alTlY7BvVx1RXw,1066
+smftools-0.2.1.dist-info/RECORD,,

smftools-0.2.1.dist-info/entry_points.txt

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

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/plot_read_length_and_coverage_histograms.py

@@ -1,53 +0,0 @@
-# plot_read_length_and_coverage_histograms
-
-def plot_read_length_and_coverage_histograms(bed_file, plotting_directory):
-    """
-    Plots read length and coverage statistics for each record.
-
-    Parameters:
-        bed_file (str): Path to the bed file to derive read lengths and coverage from.
-        plot_directory (str): Path to the directory to write out historgrams.
-
-    Returns:
-        None
-    """
-    import pandas as pd
-    import matplotlib.pyplot as plt
-    import numpy as np
-    import os
-
-    bed_basename = os.path.basename(bed_file).split('.bed')[0]
-    # Load the BED file into a DataFrame
-    print(f"Loading BED to plot read length and coverage histograms: {bed_file}")
-    df = pd.read_csv(bed_file, sep='\t', header=None, names=['chromosome', 'start', 'end', 'length', 'read_name'])
-    
-    # Group by chromosome
-    grouped = df.groupby('chromosome')
-
-    for chrom, group in grouped:
-        # Plot read length histogram
-        plt.figure(figsize=(12, 6))
-        plt.hist(group['length'], bins=50, edgecolor='k', alpha=0.7)
-        plt.title(f'Read Length Histogram of reads aligned to {chrom}')
-        plt.xlabel('Read Length')
-        plt.ylabel('Count')
-        plt.grid(True)
-        save_name = os.path.join(plotting_directory, f'{bed_basename}_{chrom}_read_length_histogram.png')
-        plt.savefig(save_name)
-        plt.close()
-
-        # Compute coverage
-        coverage = np.zeros(group['end'].max())
-        for _, row in group.iterrows():
-            coverage[row['start']:row['end']] += 1
-        
-        # Plot coverage histogram
-        plt.figure(figsize=(12, 6))
-        plt.plot(coverage, color='b')
-        plt.title(f'Coverage Histogram for {chrom}')
-        plt.xlabel('Position')
-        plt.ylabel('Coverage')
-        plt.grid(True)
-        save_name = os.path.join(plotting_directory, f'{bed_basename}_{chrom}_coverage_histogram.png')
-        plt.savefig(save_name)
-        plt.close()

smftools/informatics/load_adata.py

@@ -1,182 +0,0 @@
-## load_adata
-
-def load_adata(config_path):
-    """
-    High-level function to call for converting raw sequencing data to an adata object. 
-    Works for nanopore pod5, fast5, and unaligned modBAM data types for direct SMF workflows.
-    Works for nanopore pod5, fast5, unaligned BAM for conversion SMF workflows.
-    Also works for illumina fastq and unaligned BAM for conversion SMF workflows.
-
-    Parameters:
-        config_path (str): A string representing the file path to the experiment configuration csv file.
-
-    Returns:
-        None
-    """
-    # Lazy importing of packages
-    from .helpers import LoadExperimentConfig, make_dirs, concatenate_fastqs_to_bam, extract_read_features_from_bam
-    from .fast5_to_pod5 import fast5_to_pod5
-    from .subsample_fasta_from_bed import subsample_fasta_from_bed
-    import os
-    import numpy as np
-    import anndata as ad
-    from pathlib import Path
-
-    # Default params
-    bam_suffix = '.bam' # If different, change from here.
-    split_dir = 'demultiplexed_BAMs' # If different, change from here.
-    strands = ['bottom', 'top'] # If different, change from here. Having both listed generally doesn't slow things down too much.
-    conversions = ['unconverted'] # The name to use for the unconverted files. If different, change from here.
-
-    # Load experiment config parameters into global variables
-    experiment_config = LoadExperimentConfig(config_path)
-    var_dict = experiment_config.var_dict
-
-    # These below variables will point to default_value if they are empty in the experiment_config.csv or if the variable is fully omitted from the csv.
-    default_value = None
-
-    # General config variable init
-    smf_modality = var_dict.get('smf_modality', default_value) # needed for specifying if the data is conversion SMF or direct methylation detection SMF. Necessary.
-    input_data_path = var_dict.get('input_data_path', default_value) # Path to a directory of POD5s/FAST5s or to a BAM/FASTQ file. Necessary.
-    output_directory = var_dict.get('output_directory', default_value) # Path to the output directory to make for the analysis. Necessary.
-    fasta = var_dict.get('fasta', default_value) # Path to reference FASTA.
-    fasta_regions_of_interest = var_dict.get("fasta_regions_of_interest", default_value) # Path to a bed file listing coordinate regions of interest within the FASTA to include. Optional.
-    mapping_threshold = var_dict.get('mapping_threshold', default_value) # Minimum proportion of mapped reads that need to fall within a region to include in the final AnnData.
-    experiment_name = var_dict.get('experiment_name', default_value) # A key term to add to the AnnData file name.
-    model_dir = var_dict.get('model_dir', default_value) # needed for dorado basecaller
-    model = var_dict.get('model', default_value) # needed for dorado basecaller
-    barcode_kit = var_dict.get('barcode_kit', default_value) # needed for dorado basecaller
-    barcode_both_ends = var_dict.get('barcode_both_ends', default_value) # dorado demultiplexing
-    trim = var_dict.get('trim', default_value) # dorado adapter and barcode removal
-    input_already_demuxed = var_dict.get('input_already_demuxed', default_value) # If the input files are already demultiplexed.
-    threads = var_dict.get('threads', default_value) # number of cpu threads available for multiprocessing
-    # Conversion specific variable init
-    conversion_types = var_dict.get('conversion_types', default_value)
-    # Direct methylation specific variable init
-    filter_threshold = var_dict.get('filter_threshold', default_value)
-    m6A_threshold = var_dict.get('m6A_threshold', default_value)
-    m5C_threshold = var_dict.get('m5C_threshold', default_value)
-    hm5C_threshold = var_dict.get('hm5C_threshold', default_value)
-    thresholds = [filter_threshold, m6A_threshold, m5C_threshold, hm5C_threshold]
-    mod_list = var_dict.get('mod_list', default_value)
-    batch_size = var_dict.get('batch_size', default_value)
-    device = var_dict.get('device', 'auto')
-    make_bigwigs = var_dict.get('make_bigwigs', default_value)
-    skip_unclassified = var_dict.get('skip_unclassified', True)
-    delete_batch_hdfs = var_dict.get('delete_batch_hdfs', True)
-
-    # Make initial output directory
-    make_dirs([output_directory])
-    os.chdir(output_directory)
-    # Define the pathname to split BAMs into later during demultiplexing.
-    split_path = os.path.join(output_directory, split_dir)
-
-    # If fasta_regions_of_interest is passed, subsample the input FASTA on regions of interest and use the subsampled FASTA.
-    if fasta_regions_of_interest and '.bed' in fasta_regions_of_interest:
-        fasta_basename = os.path.basename(fasta).split('.fa')[0]
-        bed_basename_minus_suffix = os.path.basename(fasta_regions_of_interest).split('.bed')[0]
-        output_FASTA = fasta_basename + '_subsampled_by_' + bed_basename_minus_suffix + '.fasta'
-        subsample_fasta_from_bed(fasta, fasta_regions_of_interest, output_directory, output_FASTA)
-        fasta = os.path.join(output_directory, output_FASTA)
-
-    # If conversion_types is passed:
-    if conversion_types:
-        conversions += conversion_types
-
-    # Get the input filetype
-    if Path(input_data_path).is_file():
-        input_data_filetype = '.' + os.path.basename(input_data_path).split('.')[1].lower()
-        input_is_pod5 = input_data_filetype in ['.pod5','.p5']
-        input_is_fast5 = input_data_filetype in ['.fast5','.f5']
-        input_is_fastq = input_data_filetype in ['.fastq', '.fq']
-        input_is_bam = input_data_filetype == bam_suffix
-        if input_is_fastq:
-            fastq_paths = [input_data_path]
-    elif Path(input_data_path).is_dir():
-        # Get the file names in the input data dir
-        input_files = os.listdir(input_data_path)
-        input_is_pod5 = sum([True for file in input_files if '.pod5' in file or '.p5' in file])
-        input_is_fast5 = sum([True for file in input_files if '.fast5' in file or '.f5' in file])
-        input_is_fastq = sum([True for file in input_files if '.fastq' in file or '.fq' in file])
-        input_is_bam = sum([True for file in input_files if bam_suffix in file])
-        if input_is_fastq:
-            fastq_paths = [os.path.join(input_data_path, file) for file in input_files if '.fastq' in file or '.fq' in file]
-
-    # If the input files are not pod5 files, and they are fast5 files, convert the files to a pod5 file before proceeding.
-    if input_is_fast5 and not input_is_pod5:
-        # take the input directory of fast5 files and write out a single pod5 file into the output directory.
-        output_pod5 = os.path.join(output_directory, 'FAST5s_to_POD5.pod5')
-        print(f'Input directory contains fast5 files, converting them and concatenating into a single pod5 file in the {output_pod5}')
-        fast5_to_pod5(input_data_path, output_pod5)
-        # Reassign the pod5_dir variable to point to the new pod5 file.
-        input_data_path = output_pod5
-        input_is_pod5 = True
-        input_is_fast5 = False
-    
-    elif input_is_fastq:
-        output_bam = os.path.join(output_directory, 'FASTQs_concatenated_into_BAM.bam')
-        concatenate_fastqs_to_bam(fastq_paths, output_bam, barcode_tag='BC', gzip_suffix='.gz')
-        input_data_path = output_bam
-        input_is_bam = True
-        input_is_fastq = False
-
-    if input_is_pod5:
-        basecall = True
-    elif input_is_bam:
-        basecall = False
-    else:
-        print('Error, can not find input bam or pod5')
-
-    if smf_modality == 'conversion':
-        from .conversion_smf import conversion_smf
-        final_adata, final_adata_path, sorted_output, bam_files = conversion_smf(fasta, output_directory, conversions, strands, model_dir, model, input_data_path, split_path
-                                                         , barcode_kit, mapping_threshold, experiment_name, bam_suffix, basecall, barcode_both_ends, trim, device, make_bigwigs, threads, input_already_demuxed)
-    elif smf_modality == 'direct':
-        from .direct_smf import direct_smf
-        # need to add input_already_demuxed workflow here.
-        final_adata, final_adata_path, sorted_output, bam_files = direct_smf(fasta, output_directory, mod_list,model_dir, model, thresholds, input_data_path, split_path
-                                                     , barcode_kit, mapping_threshold, experiment_name, bam_suffix, batch_size, basecall, barcode_both_ends, trim, device, make_bigwigs, skip_unclassified, delete_batch_hdfs, threads)
-    else:
-            print("Error")
-            
-    # Read in the final adata object and append final metadata
-    #print(f'Reading in adata from {final_adata_path} to add final metadata')
-    # final_adata = ad.read_h5ad(final_adata_path)
-    
-    # Adding read query length metadata to adata object.
-    read_metrics = {}
-    for bam_file in bam_files:
-        bam_read_metrics = extract_read_features_from_bam(bam_file)
-        read_metrics.update(bam_read_metrics)
-    #read_metrics = extract_read_features_from_bam(sorted_output)
-
-    query_read_length_values = []
-    query_read_quality_values = []
-    reference_lengths = []
-    # Iterate over each row of the AnnData object
-    for obs_name in final_adata.obs_names:
-        # Fetch the value from the dictionary using the obs_name as the key
-        value = read_metrics.get(obs_name, np.nan)  # Use np.nan if the key is not found
-        if type(value) is list:
-            query_read_length_values.append(value[0])
-            query_read_quality_values.append(value[1])
-            reference_lengths.append(value[2])
-        else:
-            query_read_length_values.append(value)
-            query_read_quality_values.append(value)
-            reference_lengths.append(value) 
-                       
-    # Add the new column to adata.obs
-    final_adata.obs['query_read_length'] = query_read_length_values
-    final_adata.obs['query_read_quality'] = query_read_quality_values
-    final_adata.obs['query_length_to_reference_length_ratio'] = np.array(query_read_length_values) / np.array(reference_lengths)
-
-    final_adata.obs['Raw_methylation_signal'] = np.nansum(final_adata.X, axis=1)
-    final_adata.obs['Raw_per_base_methylation_average'] = final_adata.obs['Raw_methylation_signal'] / final_adata.obs['query_read_length']
-
-    print('Saving final adata')
-    if ".gz" in final_adata_path:
-        final_adata.write_h5ad(f"{final_adata_path}", compression='gzip')
-    else:
-        final_adata.write_h5ad(f"{final_adata_path}.gz", compression='gzip')
-    print('Final adata saved')

smftools/preprocessing/append_C_context.py

@@ -1,82 +0,0 @@
-## append_C_context
-
-## Conversion SMF Specific 
-# Read methylation QC
-def append_C_context(adata, obs_column='Reference', use_consensus=False, native=False):
-    """
-    Adds Cytosine context to the position within the given category. When use_consensus is True, it uses the consensus sequence, otherwise it defaults to the FASTA sequence.
-
-    Parameters:
-        adata (AnnData): The input adata object.
-        obs_column (str): The observation column in which to stratify on. Default is 'Reference', which should not be changed for most purposes.
-        use_consensus (bool): A truth statement indicating whether to use the consensus sequence from the reads mapped to the reference. If False, the reference FASTA is used instead.
-        native (bool): If False, perform conversion SMF assumptions. If True, perform native SMF assumptions
-    
-    Returns:
-        None
-    """
-    import numpy as np
-    import anndata as ad
-
-    print('Adding Cytosine context based on reference FASTA sequence for sample')
-    
-    site_types = ['GpC_site', 'CpG_site', 'ambiguous_GpC_CpG_site', 'other_C', 'any_C_site']
-    categories = adata.obs[obs_column].cat.categories
-    for cat in categories:
-        # Assess if the strand is the top or bottom strand converted
-        if 'top' in cat:
-            strand = 'top'
-        elif 'bottom' in cat:
-            strand = 'bottom'
-
-        if native:
-            basename = cat.split(f"_{strand}")[0]
-            if use_consensus:
-                sequence = adata.uns[f'{basename}_consensus_sequence']
-            else:
-                # This sequence is the unconverted FASTA sequence of the original input FASTA for the locus
-                sequence = adata.uns[f'{basename}_FASTA_sequence']
-        else:
-            basename = cat.split(f"_{strand}")[0]
-            if use_consensus:
-                sequence = adata.uns[f'{basename}_consensus_sequence']
-            else:
-                # This sequence is the unconverted FASTA sequence of the original input FASTA for the locus
-                sequence = adata.uns[f'{basename}_FASTA_sequence']
-        # Init a dict keyed by reference site type that points to a bool of whether the position is that site type.    
-        boolean_dict = {}
-        for site_type in site_types:
-            boolean_dict[f'{cat}_{site_type}'] = np.full(len(sequence), False, dtype=bool)
-        
-        if strand == 'top':
-            # Iterate through the sequence and apply the criteria
-            for i in range(1, len(sequence) - 1):
-                if sequence[i] == 'C':
-                    boolean_dict[f'{cat}_any_C_site'][i] = True
-                    if sequence[i - 1] == 'G' and sequence[i + 1] != 'G':
-                        boolean_dict[f'{cat}_GpC_site'][i] = True
-                    elif sequence[i - 1] == 'G' and sequence[i + 1] == 'G':
-                        boolean_dict[f'{cat}_ambiguous_GpC_CpG_site'][i] = True
-                    elif sequence[i - 1] != 'G' and sequence[i + 1] == 'G':
-                        boolean_dict[f'{cat}_CpG_site'][i] = True
-                    elif sequence[i - 1] != 'G' and sequence[i + 1] != 'G':
-                        boolean_dict[f'{cat}_other_C'][i] = True
-        elif strand == 'bottom':
-            # Iterate through the sequence and apply the criteria
-            for i in range(1, len(sequence) - 1):
-                if sequence[i] == 'G':
-                    boolean_dict[f'{cat}_any_C_site'][i] = True
-                    if sequence[i + 1] == 'C' and sequence[i - 1] != 'C':
-                        boolean_dict[f'{cat}_GpC_site'][i] = True
-                    elif sequence[i - 1] == 'C' and sequence[i + 1] == 'C':
-                        boolean_dict[f'{cat}_ambiguous_GpC_CpG_site'][i] = True
-                    elif sequence[i - 1] == 'C' and sequence[i + 1] != 'C':
-                        boolean_dict[f'{cat}_CpG_site'][i] = True
-                    elif sequence[i - 1] != 'C' and sequence[i + 1] != 'C':
-                        boolean_dict[f'{cat}_other_C'][i] = True
-        else:
-            print('Error: top or bottom strand of conversion could not be determined. Ensure this value is in the Reference name.')
-
-        for site_type in site_types:
-            adata.var[f'{cat}_{site_type}'] = boolean_dict[f'{cat}_{site_type}'].astype(bool)
-            adata.obsm[f'{cat}_{site_type}'] = adata[:, adata.var[f'{cat}_{site_type}'] == True].X