Causal GRN inference methods outperform correlation baselines in clean simulated regimes but lose their advantage under dropout and latent confounders, as revealed by 6120 experiments isolating seven pathologies with sub-additive joint effects.
Nature , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
When Does Gene Regulatory Network Inference Break? A Controlled Diagnostic Study of Causal and Correlational Methods on Single-Cell Data
Causal GRN inference methods outperform correlation baselines in clean simulated regimes but lose their advantage under dropout and latent confounders, as revealed by 6120 experiments isolating seven pathologies with sub-additive joint effects.