feature_names
['f_string_core_partner_score', 'f_string_core_degree', 'f_string_core_score_sum', 'f_reactome_ad_pathway_overlap', 'f_reactome_pathway_count', 'f_mygene_ad_mention']
benchmark_name
OT-AD Target Ranking Benchmark v1
benchmark_notes
Z-score weighted sum rule baseline; 5-feature model; 80/20 train/test stratified split
evaluation_metrics
{'n_test': 99, 'n_genes': 495, 'n_train': 396, 'auroc_full': 0.7998, 'auroc_test': 0.8156, 'n_positives': 49, 'recall_at_50': 0.3878, 'recall_at_100': 0.6327, 'spearman_full': 0.3236, 'spearman_test': 0.2971}