Machine learning articles from across Nature Portfolio

Nellie is a user-friendly tool that streamlines organelle analysis by providing automated segmentation, tracking and feature extraction across any intracellular structure, without the need for deep-learning models or manual parameter adjustment.

DeepGEM, an artificial intelligence (AI)-based model, accurately predicts the presence of key genomic alterations in histological slides prepared from samples obtained from patients with lung cancer. This approach provides a cost-effective alternative to genomic testing, generates spatial mutation maps and might support personalized treatment strategies. Validated in diverse datasets, DeepGEM highlights the potential of AI to transform precision oncology and improve global healthcare equity.

Pycytominer is a user-friendly, open-source Python package that carries out key bioinformatics steps in image-based profiling.

Cell2fate improves RNA velocity analysis of single-cell and spatial transcriptomics data by module decomposition of realistic biophysical models of transcription dynamics.

This study presents a method that decode representation from brain recordings as input to a large language model, enabling the generation of language that reflects humans’ perceived semantic content.

Insights from artificial intelligence could eventually transform drug development, if the quality and quantity of biological and chemical data can be improved.

Nellie is a user-friendly tool that streamlines organelle analysis by providing automated segmentation, tracking and feature extraction across any intracellular structure, without the need for deep-learning models or manual parameter adjustment.

A machine learning framework — trained on B cell and T cell receptor sequences from thousands of people — can detect a range of infectious and autoimmune diseases.

The machine learning algorithm picks up sudden loss of pulse and automatically alerts emergency services — plus, the latest from the Nature Briefing.

Measuring poverty is the first step to delivering support, but it has long been a costly, time-intensive and contentious endeavour.