Tabular Classification
Scikit-learn
Joblib
genomics
structural-variants
short-tandem-repeats
variant-calling
confidence-calibration
random-forest
Instructions to use khyeom/SVSTR-Score with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use khyeom/SVSTR-Score with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("khyeom/SVSTR-Score", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
| { | |
| "release_version": "1.0", | |
| "model_file": "sv_model.joblib", | |
| "calibrator_file": "sv_calibrator.joblib", | |
| "calibration": "isotonic regression on out-of-fold scores", | |
| "features": [ | |
| "is_pass", | |
| "svtype_DEL", | |
| "svtype_DUP", | |
| "svtype_INS", | |
| "svtype_INV", | |
| "svtype_BND", | |
| "svlen_log", | |
| "cipos_width", | |
| "ciend_width", | |
| "is_imprecise", | |
| "pe_support", | |
| "sr_support", | |
| "total_support", | |
| "vaf", | |
| "gt_hom", | |
| "gq", | |
| "qual_norm", | |
| "local_depth", | |
| "gc_min", | |
| "gc_max", | |
| "entropy_min", | |
| "microhom_max", | |
| "in_segdup_either", | |
| "in_segdup_both", | |
| "in_difficult_either", | |
| "in_difficult_both", | |
| "in_lowmap_either", | |
| "in_tandem_either", | |
| "in_Alu_either", | |
| "in_L1_either", | |
| "in_SVA_either", | |
| "in_LTR_either", | |
| "frac_span_repeat", | |
| "n_neighbors", | |
| "nn_log_dist" | |
| ], | |
| "n_features": 35, | |
| "missing_sentinel": -99999.0, | |
| "tiers": { | |
| "HIGH": "CS>=0.70", | |
| "MODERATE": "0.50<=CS<0.70", | |
| "WARNING": "0.30<=CS<0.50", | |
| "LOW": "CS<0.30" | |
| }, | |
| "tier_edges": [ | |
| 0.3, | |
| 0.5, | |
| 0.7 | |
| ], | |
| "score": "CS = isotonic-calibrated P(call concordant with long-read truth)", | |
| "variant_class": "SV", | |
| "sklearn_version_trained": "1.7.1", | |
| "training": { | |
| "cohort": "HPRC", | |
| "n_samples": 208, | |
| "n_train_rows": 2575116, | |
| "cv": "5-fold GroupKFold by sample", | |
| "oof_auroc": 0.9502, | |
| "oof_auprc": 0.9512 | |
| } | |
| } |