Urgent.News

What's breaking now, across thousands of outlets.

AI

Deep learning perturbation models can outperform baselines on calibrated metrics

Nature Biotechnology, Published online: 01 October 2026; doi:10.1038/s41587-026-03307-w Calibration-aware evaluation of perturbation models shows that deep learning models can outperform baselines.

We haven't written up this one. Nature Biotechnology has the full story — the link below goes straight to it.

Read the original at nature.com →

More in AI

More from Thursday 1 October →