Researchgene prioritizationgwasgenomicsopen source
CALDERA Simplifies Causal Gene Identification In GWAS
8.8
Schipper et al. (published March 17, 2026) present CALDERA, a logistic regression–based gene prioritization tool trained on a data-driven truth set of 200 GWAS loci that uses just four input features. In independent benchmarks CALDERA matched or outperformed FLAMES, L2G, and cS2G, produced well-calibrated causal probabilities, and when applied to 93 UK Biobank traits predicted 11,956 putative causal genes, resolving up to 52% of loci.
Key Points
- 1Shows logistic regression matches XGBoost performance for gene prioritization using a simple four-feature model
- 2Reduces model complexity and mitigates training biases by using a data-driven truth set and interpretable coefficients
- 3Enables scalable transparent causal gene prediction across 93 traits, identifying 11,956 genes and resolving 52% loci
Scoring Rationale
Strong practical advance with open-source validation; scope primarily limited to GWAS gene prioritization applications.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
