Deep learning perturbation models can outperform baselines on calibrated metrics
Nature Biotechnology says the finding comes from a calibration-aware evaluation of perturbation models.
TLDR
Nature Biotechnology reports that deep learning perturbation models can outperform baselines on calibrated metrics, based on a calibration-aware evaluation.
Combined views
785
1 Source, first seen 49m ago
6 likes2 saves3 reposts
