A review of new science, in plain language

Nature Biotechnology  ·  1 October 2026  ·  From issue 45

Deep learning perturbation models can outperform baselines on calibrated metrics

Gene-editing prediction programs beat simple guessing once scientists fixed broken scoring tests.

Henry E. Miller, Gabriel M. Mejia et al.

Integrity screen: passed (3 checks) Checked 6 October 2026. Read the source

The plain-language reading of this paper is in the full issue, for subscribers.

Read the full issue

Get it free, every two days

Five papers free every issue, about 15 emails a month. No spam. Leave in one click.

Also in issue 45 15 papers