Machine learning
The latest chemistry news and research on machine learning, including reaction prediction, synthesis planning and drug and material discovery, from the Royal Society of Chemistry's magazine, Chemistry World
-
OpinionThis year’s chemistry Nobel proves it’s hard to make predictions
It’s been a long journey from the myoglobin model
-
NewsTwenty ways AI is advancing chemistry
List reveals how machine learning is already changing the central science
-
NewsProtein design and structure prediction wins chemistry Nobel prize
David Baker, Demis Hassabis and John Jumper were rewarded for creating computational tools to design proteins and predict their structures that have ‘revolutionised biological chemistry’
-
NewsPhysics Nobel prize goes to artificial neural networks and machine learning
Research inspired by how brains learn now powers cutting-edge technology in smartphones and scientific research
-
WebinarPurposeful simulation: Maximising impact in surface chemistry modelling
Learn how to select appropriate computational models to deliver impact in surface chemistry research – join us 12 November
-
ResearchProteins with multiple structures open up AlphaFold’s black box
AI prediction model often fails to identify fold-switching, helping show how it works and the limits of its usefulness
-
ResearchElectrochemical series for materials makes predicting oxidation states easy
Machine-learning trained model could open up new opportunities in materials discovery
-
NewsDisappointing AI judgment could have a ‘catastrophic effect’ on UK science
Warnings that loose legal definitions in case could also threaten innovation in chemistry
-
ResearchAlgorithm predicts bitterness from mass spectra data alone
New tool could find use in food science and drug development
-
OpinionOur hunger for data could be an unhealthy diet
Synthetic data is both an answer and a problem
-
FeatureWhy are computational chemists making up their data?
‘Synthetic data’ is being used in chemistry, but is it something we should worry about? Hayley Bennett explains
-
ResearchAI predicts vape flavours can break down into potentially harmful compounds when heated
Flavours may decompose into harmful carbonyls, alkenes and aromatics when heated
-
NewsAre we rushing ahead with AI in the lab?
Patience will be key to making machine learning indispensable – and practical – for chemistry
-
ResearchAlgorithm designs proteins from scratch that can bind drugs and small molecules
Strategy could stop an overdose or produce an antidote to a poison
-
ResearchBrewing better Belgian beer with artificial intelligence
Machine learning tool can predict a beer’s taste and quality and which flavour compounds could improve it
-
ResearchAI could provide new approach to assessing chemical toxicity thresholds in aquatic organisms
Model showed excellent predicative ability and could cut animal testing in pollution research
-
ResearchGPT-3 trained and tuned to predict molecular properties
A better understanding of Smiles helps GPT-3 recognise chemically relevant patterns
-
ArticleMicrosoft’s AI and high-performance computing system powers new battery discovery
Azure Quantum Elements platform speeds up discovery of solid-state electrolyte from decades to weeks
-
ResearchNew analysis raises doubts over autonomous lab’s materials ‘discoveries’
Experimental and computational issues flagged as researchers conclude that a fully automated lab failed to make new materials
-
ResearchFirst GPT-4-powered AI lab assistant independently directs key organic reactions
Large language model takes control after being prompted to do Suzuki and Sonogashira couplings