Research Briefing |
Featured
-
-
Article
| Open AccessAn atlas of healthy and injured cell states and niches in the human kidney
A high-resolution kidney cellular atlas of 51 main cell types, including rare and previously undescribed cell populations, represents a comprehensive benchmark of cellular states, neighbourhoods, outcome-associated signatures and publicly available interactive visualizations.
- Blue B. Lake
- , Rajasree Menon
- & Sanjay Jain
-
Article
| Open AccessMega-scale experimental analysis of protein folding stability in biology and design
Large-scale assays using cDNA display proteolysis are used to measure the folding stabilities of protein domains, providing a method to quantify the effects of mutations on protein folding, with applications in protein design.
- Kotaro Tsuboyama
- , Justas Dauparas
- & Gabriel J. Rocklin
-
Career Column |
Fourteen things you need to know about collaborating with data scientists
Experimentalists often need help to analyse data. Here’s how to ensure your collaboration is productive.
- Michele Tobias
- , Nick Ulle
- & Tyler Shoemaker
-
News |
ChatGPT gives an extra productivity boost to weaker writers
The AI program allows people with limited writing skills to create higher-quality texts — but makes little difference to proficient writers’ work quality.
- Mariana Lenharo
-
Article
| Open AccessSpatially resolved multiomics of human cardiac niches
Single-cell and spatial transcriptomic analysis of eight human heart tissues reveals the cellular profiles and tissue architecture of niches including the cardiac conduction system, and a new tool, drug2cell, identifies drug target expression.
- Kazumasa Kanemaru
- , James Cranley
- & Sarah A. Teichmann
-
-
News Feature |
AI tools are designing entirely new proteins that could transform medicine
Digital art techniques can now devise custom, working biomolecules on demand.
- Ewen Callaway
-
Article
| Open AccessDe novo design of protein structure and function with RFdiffusion
Fine-tuning the RoseTTAFold structure prediction network on protein structure denoising tasks yields a generative model for protein design that achieves outstanding performance on a wide range of protein structure and function design challenges.
- Joseph L. Watson
- , David Juergens
- & David Baker
-
Career Column |
Computer algorithms infer gender, race and ethnicity. Here’s how to avoid their pitfalls
Demographic-prediction algorithms have various challenges, following best practices can minimize the harms.
- Jeffrey W. Lockhart
- , Molly M. King
- & Christin L. Munsch
-
News & Views |
The outlook for AI weather prediction
Two models demonstrate the enormous potential that artificial intelligence holds for weather prediction. But the risks involved demand that meteorologists learn to design, evaluate and interpret such systems.
- Imme Ebert-Uphoff
- & Kyle Hilburn
-
Article
| Open AccessLoss of CDK4/6 activity in S/G2 phase leads to cell cycle reversal
We uncover the mechanism underlying the restriction point phenomenon, suggest a role for cyclin-dependent kinase 4 and 6 activity in S and G2 phases, and explain the behaviour of cells following loss of mitogen signalling.
- James A. Cornwell
- , Adrijana Crncec
- & Steven D. Cappell
-
Nature Video |
A robotic raspberry teaches machines how to pick fruit
This fake raspberry allows researchers to train fruit-picking robots in the lab before field tests.
- Shamini Bundell
-
Technology Feature |
Foldseek gives AlphaFold protein database a rapid search tool
The structural search program makes finding proteins with similar 3D shapes easy.
- Matthew Hutson
-
Article |
Cancer aneuploidies are shaped primarily by effects on tumour fitness
A study reports the development of an algorithm, BISCUT, that detects genomic loci under selective pressure by relying on the distribution of breakpoints across chromosome arms, and uses it to explore how aneuploidies affect tumorigenesis.
- Juliann Shih
- , Shahab Sarmashghi
- & Rameen Beroukhim
-
Article |
A spatially resolved single-cell genomic atlas of the adult human breast
The Human Breast Cell Atlas identifies 12 major breast cell types and 58 biological cell states, revealing abundant pericyte, endothelial and immune cell populations, and highly diverse luminal epithelial cell states.
- Tapsi Kumar
- , Kevin Nee
- & Nicholas Navin
-
-
Editorial |
Stop talking about tomorrow’s AI doomsday when AI poses risks today
Talk of artificial intelligence destroying humanity plays into the tech companies’ agenda, and hinders effective regulation of the societal harms AI is causing right now.
-
Article |
B-cell-specific checkpoint molecules that regulate anti-tumour immunity
Manipulation of TIM-1-expressing B cells enables engagement of the second arm of adaptive immunity to promote anti-tumour immunity and inhibit tumour growth.
- Lloyd Bod
- , Yoon-Chul Kye
- & Vijay K. Kuchroo
-
-
News |
Open-source AI chatbots are booming — what does this mean for researchers?
Freely accessible large language models have accelerated the pace of innovation, computer scientists say.
- Davide Castelvecchi
-
Where I Work |
Teaching robots how to touch
Through better sensing, Yuhan Hu hopes to bring robots and humans closer together.
- James Mitchell Crow
-
Article
| Open AccessA pangenome reference of 36 Chinese populations
A study reports data from the first phase of the Chinese Pangenome Consortium including 116 de novo assemblies from 58 core samples representing 36 minority Chinese ethnic groups.
- Yang Gao
- , Xiaofei Yang
- & Shuhua Xu
-
Editorial |
Why Nature will not allow the use of generative AI in images and video
Saying ‘no’ to this kind of visual content is a question of research integrity, consent, privacy and intellectual-property protection.
-
News & Views |
AI learns to write sorting software on its own
Deep reinforcement learning has been used to improve computer code by treating the task as a game — with no special knowledge needed on the part of the player. The result has already worked its way into countless programs.
- Armando Solar-Lezama
-
News |
DeepMind AI creates algorithms that sort data faster than those built by people
The technology developed by DeepMind that plays Go and chess can also help to write code.
- Matthew Hutson
-
Correspondence |
ChatGPT: standard reporting guidelines for responsible use
- Giovanni E. Cacciamani
- , Gary S. Collins
- & Inderbir S. Gill
-
Technology Feature |
Six tips for better coding with ChatGPT
Although powerful, the tools are not as intelligent as they seem. Use them with caution, computer scientists warn.
- Jeffrey M. Perkel
-
Research Briefing |
Machine-learning model makes predictions about network biology
A deep-learning model called Geneformer has been developed and pretrained using about 30 million single-cell gene-expression profiles to enable it to make predictions about gene-network biology in instances in which gene-expression data are limited. Geneformer can be tuned for many downstream applications to accelerate discovery of key gene-network regulators and candidate therapeutic targets.
-
Article |
Transfer learning enables predictions in network biology
A context-aware, attention-based deep learning model pretrained on single-cell transcriptomes enables predictions in settings with limited data in network biology and could accelerate discovery of key network regulators and candidate therapeutic targets.
- Christina V. Theodoris
- , Ling Xiao
- & Patrick T. Ellinor
-
Nature Podcast |
AI identifies gene interactions to speed up search for treatment targets
How an AI overcomes data-scarcity to map gene networks, and assessing the impact of rocket noise on wildlife.
- Nick Petrić Howe
- & Benjamin Thompson
-
Article
| Open AccessDeterministic evolution and stringent selection during preneoplasia
We model occult preneoplasia by biallelic inactivation of TP53, a common early event in gastric cancer, in human gastric organoids, the results implying predictability in the earliest stages of tumorigenesis.
- Kasper Karlsson
- , Moritz J. Przybilla
- & Christina Curtis
-
Spotlight |
Towards quantum machine learning
Jungsang Kim discusses his interest in the pioneering technology.
- Michael Brooks
-
Outlook |
Listening for neurological symptoms
Unusual vocal patterns can give clues that help to detect conditions such as Alzheimer’s disease.
- Michael Eisenstein
-
Outlook |
Disrupting protein folding to tackle cancer
Intermediate states show promise as drug targets.
- Elie Dolgin
-
Article
| Open AccessUbiquitination regulates ER-phagy and remodelling of endoplasmic reticulum
Ubiquitination of the receptor FAM134B regulates ER-phagy and remodelling of the endoplasmic reticulum in response to cellular demands.
- Alexis González
- , Adriana Covarrubias-Pinto
- & Ivan Dikić
-
Correspondence |
Social media: generative AI could harm mental health
- David Greenfield
- & Shivan Bhavnani
-
Career Feature |
Why AI’s diversity crisis matters, and how to tackle it
Machine-learning researchers from under-represented groups say the field desperately needs more people like them to ensure the technologies deliver for all.
- Rachel Crowell
-
Editorial |
For chemists, the AI revolution has yet to happen
Machine-learning systems in chemistry need accurate and accessible training data. Until they get it, they won’t achieve their potential.
-
Comment |
Create an IPCC-like body to harness benefits and combat harms of digital tech
Emerging information technologies, including ChatGPT, require proper stewardship. An intergovernmental panel to synthesize the evidence offers the best path forward.
- Joseph Bak-Coleman
- , Carl T. Bergstrom
- & Timmons Roberts
-
Research Briefing |
A continuous measure for understanding the accuracy of genetically based predictions
Polygenic scores can estimate the likelihood of an individual having a certain trait by using the contributions of thousands of genetic variants in their genome. An analysis shows that the accuracy of these scores varies between individuals across a continuum of genetic ancestry, even in populations conventionally considered homogeneous.
-
Article
| Open AccessPolygenic scoring accuracy varies across the genetic ancestry continuum
Using two large biobank datasets, a study shows that the accuracy of polygenic scores decreases as a function of relatedness at the individual level when modelling genetic ancestry as a continuum.
- Yi Ding
- , Kangcheng Hou
- & Bogdan Pasaniuc
-
World View |
Audit AI search tools now, before they skew research
Generative AI could be a boon for literature search, but only if independent groups scrutinize its biases and limitations.
- Michael Gusenbauer
-
Article
| Open AccessA draft human pangenome reference
An initial draft of the human pangenome is presented and made publicly available by the Human Pangenome Reference Consortium; the draft contains 94 de novo haplotype assemblies from 47 ancestrally diverse individuals.
- Wen-Wei Liao
- , Mobin Asri
- & Benedict Paten
-
Nature Careers Podcast |
Unlocking the mysteries of the brain’s neocortex
Entrepreneur Jeff Hawkins explains how our knowledge of the brain can help us to better understand artificial intelligence.
- Dom Byrne
-
Research Briefing |
Brain dynamics uncovered using a machine-learning algorithm
CEBRA is a machine-learning method that can be used to compress time series in a way that reveals otherwise hidden structures in the variability of the data. It excels at processing behavioural and neural data recorded simultaneously, and it can decode activity from the visual cortex of the mouse brain to reconstruct a viewed video.
-
Article
| Open AccessStructural atlas of a human gut crassvirus
A cryo-electron microscopy reconstruction of the virus ΦcrAss001 provides insights into the functions of the viral gene products in capsid assembly and infection.
- Oliver W. Bayfield
- , Andrey N. Shkoporov
- & Alfred A. Antson
-
Article
| Open AccessLearnable latent embeddings for joint behavioural and neural analysis
A new encoding method, CEBRA, jointly uses behavioural and neural data in a (supervised) hypothesis- or (self-supervised) discovery-driven manner to produce both consistent and high-performance latent spaces.
- Steffen Schneider
- , Jin Hwa Lee
- & Mackenzie Weygandt Mathis
-
News Explainer |
Mind-reading machines are here: is it time to worry?
Neuroethicists are split on whether a study that uses brain scans and AI to decode imagined speech poses a threat to mental privacy.
- Sara Reardon
-
News |
‘Remarkable’ AI tool designs mRNA vaccines that are more potent and stable
Software from Baidu Research yields jabs for COVID that have greater shelf stability and that trigger a larger antibody response in mice than conventionally designed shots.
- Elie Dolgin
Browse broader subjects
Browse narrower subjects
- Biochemical reaction networks
- Cellular signalling networks
- Classification and taxonomy
- Communication and replication
- Computational models
- Computational neuroscience
- Computational platforms and environments
- Data acquisition
- Data integration
- Data mining
- Data processing
- Data publication and archiving
- Databases
- Functional clustering
- Gene ontology
- Gene regulatory networks
- Genome informatics
- Hardware and infrastructure
- High-throughput screening
- Image processing
- Literature mining
- Machine learning
- Microarrays
- Network topology
- Phylogeny
- Power law
- Predictive medicine
- Probabilistic data networks
- Programming language
- Protein analysis
- Protein design
- Protein folding
- Protein function predictions
- Protein structure predictions
- Proteome informatics
- Quality control
- Scale invariance
- Sequence annotation
- Software
- Standards
- Statistical methods
- Virtual drug screening