OVEP code

## Overview - Key subpackages/directories include: external tests (AUC), post-analysis with various masks (missing/label/functional/repeat), training/prediction pipelines with 5-fold CV, and plotting utilities. --- ## Directory structure (top-level) - `rate_code/`--- ## Key scripts- `rate_code/post_analysis_maskmissing/category_annotation/calculate_predicted_snp_by_category_maskfunctional.py`Script related to: calculate predicted snp by category maskfunctional.py- `rate_code/revision/JARVIS/modules/jarvis/deep_learn_raw_seq/for_prediction_train_nn_model.py`Arg 'input_features' may take 1 of 3 possible values: - stuctured: using only structured features as input - sequence: using only sequence features as input - both: using both structured and sequence features as inputs- `rate_code/revision/JARVIS/modules/jarvis/variant_classification/plot_gb_feature_importance.py`Script related to: plot gb feature importance.py- `rate_code/external_test/calculate_AUC_dataset1_masksnp.py`Script related to: calculate AUC dataset1 masksnp.py- `rate_code/post_analysis_maskmissing/category_annotation_calibration/calculate_predicted_snp_by_category.py`Script related to: calculate predicted snp by category.py- `rate_code/post_analysis_maskmissing/category_annotation_calibration_masklabel/calculate_predicted_snp_by_category_new.py`Script related to: calculate predicted snp by category new.py- `rate_code/post_analysis_maskmissing/category_annotation_calibration_masklabel/calculate_predicted_snp_by_category.py`Script related to: calculate predicted snp by category.py- `rate_code/post_analysis_maskmissing/category_annotation_calibration_maskfunctional_maskrepeat/calculate_predicted_snp_by_category.py`Script related to: calculate predicted snp by category.py- `rate_code/post_analysis_maskmissing/category_annotation/calculate_predicted_snp_by_category.py`Script related to: calculate predicted snp by category.py- `rate_code/post_analysis_maskmissing/category_annotation/calculate_predicted_snp_by_category_nolabel.py`Script related to: calculate predicted snp by category nolabel.py- `rate_code/post_analysis_maskmissing/exon_analysis_masklabel/calculate_predicted_snp_by_exon_mask.py`Script related to: calculate predicted snp by exon mask.py- `rate_code/post_analysis_maskmissing/category_annotation_calibration_maskfunctional/calculate_predicted_snp_by_category.py`Script related to: calculate predicted snp by category.py- `rate_code/post_analysis_maskmissing/exon_analysis/calculate_predicted_snp_by_exon_mask.py`Script related to: calculate predicted snp by exon mask.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_nonindelonlyintest_masklabel/predict_nucleotide_plot.py`Script related to: predict nucleotide plot.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_nonindelonlyintest_masklabel/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_indelonlyintest_masklabel/predict_nucleotide_plot.py`Script related to: predict nucleotide plot.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_indelonlyintest_masklabel/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/plot/plot_indel_snp_auc.py`!/usr/bin/env python3- `rate_code/code_halftrainmaskmissing_masklabel/plot/plot_auc_nucleotide_length.py`Script related to: plot auc nucleotide length.py- `rate_code/code_halftrainmaskmissing_masklabel/plot/plot_scatter_auc_length.py`Script related to: plot scatter auc length.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_attention/predict_nucleotide_plot.py`Script related to: predict nucleotide plot.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_attention/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_attention/plot_auc_compare_base.py`Script related to: plot auc compare base.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_attention/plot_auc.py`Script related to: plot auc.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_1024/predict_nucleotide_plot.py`Script related to: predict nucleotide plot.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_1024/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_1024/plot_auc_compare_base.py`Script related to: plot auc compare base.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_1024/plot_auc.py`Script related to: plot auc.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_nonbinary_train_and_predict_5fold_masklabel/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_nonindelonlyintrain_masklabel/predict_nucleotide_plot.py`Script related to: predict nucleotide plot.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_nonindelonlyintrain_masklabel/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_nonindelonlyintrain_masklabel/plot_auc_compare_base.py`Script related to: plot auc compare base.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_nonindelonlyintrain_indelonlyintest_masklabel/predict_nucleotide_plot.py`Script related to: predict nucleotide plot.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_nonindelonlyintrain_indelonlyintest_masklabel/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_indelonlyonlyintrain_masklabel/predict_nucleotide_plot.py`Script related to: predict nucleotide plot.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_indelonlyonlyintrain_masklabel/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_indelonlyonlyintrain_masklabel/plot_auc_compare_base.py`Script related to: plot auc compare base.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_nonbinary_5fold_masklabel/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_4096/predict_nucleotide_plot.py`Script related to: predict nucleotide plot.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_4096/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_4096/plot_auc_compare_base.py`Script related to: plot auc compare base.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_4096/plot_auc.py`Script related to: plot auc.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_512/predict_nucleotide_plot.py`Script related to: predict nucleotide plot.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_512/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_512/plot_auc_compare_base.py`Script related to: plot auc compare base.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel_512/plot_auc.py`Script related to: plot auc.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_nonindel_masklabel/predict_nucleotide_plot.py`Script related to: predict nucleotide plot.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_nonindel_masklabel/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_nonindel_masklabel/plot_auc_compare_base.py`Script related to: plot auc compare base.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_nonindel_masklabel/plot_auc.py`Script related to: plot auc.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_indelonlyonlyintrain_nonindelonlyintest_masklabel/predict_nucleotide_plot.py`Script related to: predict nucleotide plot.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_indelonlyonlyintrain_nonindelonlyintest_masklabel/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel/predict_nucleotide_plot.py`Script related to: predict nucleotide plot.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel/plot_auc_compare_base.py`Script related to: plot auc compare base.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_masklabel/plot_auc.py`Script related to: plot auc.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_indelonly_masklabel/predict_nucleotide_plot.py`Script related to: predict nucleotide plot.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_indelonly_masklabel/predict_train.py`Script related to: predict train.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_indelonly_masklabel/plot_auc_compare_base.py`Script related to: plot auc compare base.py- `rate_code/code_halftrainmaskmissing_masklabel/base_excludeN_5fold_indelonly_masklabel/plot_auc.py`Script related to: plot auc.py --- ## Reproducibility hints While this snapshot does not include data/configs, common entry points typically look like: - `*predict_train*.py` — training loop (likely 5-fold CV; see corresponding `predict_nucleotide_plot.py` for visualization).- `external_test/calculate_AUC*.py` — compute AUC on external datasets; expect CLI args for input paths to predictions/labels.- `post_