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
-
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
-
ResearchComputer vision accelerates self-driving reaction workups from being automated to autonomous
Platform understands significance of solid residues, liquid levels, homogeneity, turbidity and colours
-
OpinionOne year on from ChatGPT’s launch does it offer hope or hype for science?
Chatbots could help chemists but their limitations need to be understood
-
ResearchMachine learning tool fed red wines’ chemical profiles can deduce where they’re from
Statistical tool matches wines to their estates with 100% accuracy
-
ResearchRobotic chemistry lab joins forces with Google AI to predict then make new inorganic materials
Algorithm discovered more than 2 million inorganic structures
-
ResearchFleeting phenomenon of water autoionisation pinned down by neural network simulations
Modelling sheds light on a process that has been known for over a century but was tricky to understand
-
OpinionSlow march of the retrosynthesis robots
Software synthesis suggestions are hampered by biased and incomplete datasets
-
WebinarCO₂ storage, magic doors and machine learning
Learn how machine learning based simulations with Matlantis help rationalise long-time CO₂ storage experimental results