Skip to main content
Search

# SHAP Feature Attribution

2 related articles

Subscribe to updates
  1. A CRISPRi guide-efficacy model nearly fails on a new library; swapping the within-gene percentile label lifts transfer correlation from 0.008 to 0.136

    A CRISPRi guide-efficacy model trained in K562 cells barely transferred to the independent Dolcetto library from Sanson et al. 2018 in HT29 and A375 cells, reaching Spearman correlations of only 0.008 and 0.012. Keeping the same 101 features, architecture and hyperparameters but replacing the within-gene percentile label with a continuous cross-study z-score raised transfer to 0.136 in HT29 and 0.158 in A375, and leave-one-chromosome-out performance in K562 from 0.375 to 0.429. The transfer failure therefore traces mainly to label design rather than missing chromatin features.

  2. Pain Management

    Determination of Candidate Predictors for Chiropractic Treatment Outcome of Spinal Pain Using a Machine Learning Framework for Small Datasets

    In this prospective cohort study, 96 patients with spinal pain completed an extensive questionnaire covering pain, mood, sleep, lifestyle, and treatment expectations at baseline and at 1 and 3 months, with binary recovery outcomes defined at 3 months for pain intensity, disability, quality of life, and Patient Global Impression of Change; a three-step machine learning framework combining SHAP-based candidate feature selection, Leave-One-Out Cross-Validation with permutation testing, and generalization testing yielded AUC values of 0.93-0.99 in LOOCV and 0.62-0.

You’re all caught up