A computational workflow designs proteins with catalytic efficiencies comparable to those of some natural enzymes — a landmark result for the field.

The morphology of fragmented cellular structures can be captured by converting microscopy images to 3D point clouds and analyzing them with rotation-invariant deep-learning models. These compact models represent a powerful alternative to conventional pixel-based analysis pipelines because they achieve high reconstruction and classification accuracies while remaining fast and biologically interpretable.

We developed group technical effects (GTE) as a quantitative metric for evaluating gene-level batch effects in single-cell data. It identifies highly batch-sensitive genes — the primary contributors to batch effects — that vary across datasets, and whose removal effectively mitigates the batch effects.

A generative model provides a dataset of registered disease and healthy image pairs for chest X-ray interpretation and clinical diagnosis.

The use of deep learning in medical image segmentation is limited by the low availability of annotated images. Here, the authors develop GenSeg, a generative deep learning framework that can generate high-quality paired segmentation masks and medical images that can improve the performance of segmentation models under ultra low-data regimes across multiple scenarios.

Artificial intelligence (AI) has primarily enhanced individual primary care visits, yet its potential for population health management remains untapped. Effective AI should integrate longitudinal patient data, automate proactive outreach, and mitigate disparities by addressing barriers such as transportation and language. Properly deployed, AI can significantly reduce administrative burden, facilitate early intervention, and improve equity in primary care, necessitating rigorous evaluation and adaptive design to realize sustained population-level benefits.

Some studies containing instructions in white text or small font — visible only to machines — will be withdrawn from preprint servers.

As life sciences research becomes enmeshed in the age of AI, real experimental data are more valuable than ever.

A computational workflow designs proteins with catalytic efficiencies comparable to those of some natural enzymes — a landmark result for the field.

The publication of ever-larger numbers of problematic papers, including fake ones generated by artificial intelligence, represents an existential crisis for the established way of doing evidence synthesis. But with a new approach, AI might also save the day.