Featured
-
-
Article |
Host variables confound gut microbiota studies of human disease
The authors use a machine-learning approach to uncover confounding variables in studies that seek to establish an association between the gut microbiota and human disease.
- Ivan Vujkovic-Cvijin
- , Jack Sklar
- & Yasmine Belkaid
-
-
Outlook |
Scailyte: simplifying difficult diagnoses
A firm that combines single-cell analysis and neural networks to identify biomarkers for rare diseases has made it on to the shortlist for The Spinoff Prize.
- Eric Bender
-
News |
How coronavirus dashed Ethiopia’s dream of hosting Africa’s first major AI conference
A meeting planned for Addis Ababa in April was meant to diversify artificial-intelligence conferences, but the push for greater participation continues.
- Davide Castelvecchi
-
News |
Animal source of the coronavirus continues to elude scientists
Computational models, cell studies and animal experiments are being used to pinpoint the viral host that kicked off the pandemic.
- Smriti Mallapaty
-
World View |
Machine learning can help get COVID-19 aid to those who need it most
With pandemic stakes so immediate and consequential, coordinate to share lessons and minimize risks.
- Joshua Blumenstock
-
News |
Artificial intelligence decodes the facial expressions of mice
Neuroscientists also uncover neural circuitry whose activity correlates with particular emotions.
- Alison Abbott
-
Article |
Microbiome analyses of blood and tissues suggest cancer diagnostic approach
Microbial nucleic acids are detected in samples of tissues and blood from more than 10,000 patients with cancer, and machine learning is used to show that these can be used to discriminate between and among different types of cancer, suggesting a new microbiome-based diagnostic approach.
- Gregory D. Poore
- , Evguenia Kopylova
- & Rob Knight
-
Nature Podcast |
Podcast: Improving battery charging, and harnessing energy from the air
Listen to the latest science news, with Nick Howe and Benjamin Thompson.
-
News |
Supercomputer scours fossil record for Earth’s hidden extinctions
Palaeontologists have charted 300 million years of Earth’s history in breathtaking detail.
- Ewen Callaway
-
Article |
Improved protein structure prediction using potentials from deep learning
AlphaFold predicts the distances between pairs of residues, is used to construct potentials of mean force that accurately describe the shape of a protein and can be optimized with gradient descent to predict protein structures.
- Andrew W. Senior
- , Richard Evans
- & Demis Hassabis
-
News Q&A |
This AI researcher is trying to ward off a reproducibility crisis
Joelle Pineau is leading an effort to encourage artificial-intelligence researchers to open up their code.
- Elizabeth Gibney
-
Nature Video |
DeepMind’s new AI masters the online game StarCraft II
'AlphaStar' beat human opponents to reach the top 200 players in Europe.
- Thom Hoffman
-
Article |
Soil nematode abundance and functional group composition at a global scale
High-resolution spatial maps of the global abundance of soil nematodes and the composition of functional groups show that soil nematodes are found in higher abundances in sub-Arctic regions, than in temperate or tropical regions.
- Johan van den Hoogen
- , Stefan Geisen
- & Thomas Ward Crowther
-
Letter |
Dermatologist-level classification of skin cancer with deep neural networks
An artificial intelligence trained to classify images of skin lesions as benign lesions or malignant skin cancers achieves the accuracy of board-certified dermatologists.
- Andre Esteva
- , Brett Kuprel
- & Sebastian Thrun
-
Letter |
Reach and grasp by people with tetraplegia using a neurally controlled robotic arm
Two people with long-standing tetraplegia use neural interface system-based control of a robotic arm to perform three-dimensional reach and grasp movements.
- Leigh R. Hochberg
- , Daniel Bacher
- & John P. Donoghue