Computational chemistry
The latest chemistry news and research on computational chemistry, including machine learning, artificial intelligence, molecular dynamics and density functional theory, from the Royal Society of Chemistry's magazine, Chemistry World
-
FeatureThe evolution of chemical notation
Chemical notation has come a long way since the cryptic symbols of the alchemists – but agreeing on how to represent molecules, bonds and reactions has never been straightforward, and the challenge is far from over
-
ResearchMicrosoft’s split-personality retrosynthetic AI is a fast learner
Retrochimera combines two deep learning algorithms from different classes, outperforming their individual success rates on datasets from Novartis and GSK
-
ResearchAI helps chemists consider more options when it comes to picking the best reactants for an experiment
Algorithm can standardise substrate selection to improve performance and structural diversity
-
OpinionScientists must be trained to work without AI, as well as working with it
As AI and autonomous labs become more capable, human reasoning must be preserved
-
ResearchTagging AI-generated proteins during design process will let scientists know who made them
Google DeepMind researchers who developed the method say that this will help uphold scientific integrity and prevent misuse of protein designs
-
WebinarEl Agente: ask me anything! A live demonstration
Join us as we tackle your chemistry challenges live with the El Agente team on 24 November
-
ResearchGoogle DeepMind’s mutation Atlas shines a light on our dark DNA
AI’s predictions on the impact of changing each and every base of the human genome will help scientists understand genetic basis of disease
-
OpinionFeeding AI’s appetite for data
Tapping companies’ archives makes for better predictions of how proteins bind drugs, but any data inputs need to be transparent and attributed
-
ResearchCan we predict what happens in a molecular movie?
A seemingly impossible challenge revealed how close theorists are to truly predicting the future in computational photochemistry
-
ResearchMolecular dyes outside of the sRGB colour gamut present a challenge for digital chemistry
Researchers warn that colour clipping could mean camera-based reaction monitoring setups misinterpret measurements, with implications for increasingly automated laboratories
-
ResearchBenchmark flaws may be distorting AI drug-discovery leaderboards
Audit identifies subtle but consequential issues, such as conflicting labels and train–test leakage, in numerous benchmark datasets
-
OpinionArtificial intelligence or clever artifice?
It’s important to be realistic about what AI can, and can’t, achieve, across the chemistry enterprise
-
BusinessCombining AI with experiments to solve real-world materials problems
CuspAI’s Materials Foundry partner network includes 45 technology, data and materials chemistry companies to make and test its predictions
-
NewsUS National Science Foundation putting $380 million into building ‘self-driving’ labs
North Carolina State is one of the institutes receiving a $20 million grant aims to advance an autonomous chemistry lab
-
FeatureHow AI is transforming the world of analytical chemistry
Analytical chemists have been using machine learning long before ChatGPT made headlines. Now, as generative AI enters the laboratory, the discipline faces both opportunities and risks
-
WebinarOne goal, three industries: retrosynthesis for pharma, agrochemicals and flavours & fragrances
Explore the latest in expertly-coded retrosynthetic software, as we look at its performance across three different industries
-
ResearchOne-electron bonds may be more common than chemists thought
Researchers identify one-electron behaviour in systems traditionally described as covalent, ionic and dative bonding
-
ResearchProtein wrappers designed by AI solve membrane proteins’ solubility problem
Protein sheaths encapsulate membrane proteins while preserving their structure and function making them easier to study
-
OpinionCould AI undermine our (belief in the truth of) scientific theories?
Artificial intelligence models that make predictions based solely on data present problems for philosophers
-
ResearchAI model fills in the gaps in crystal structures by placing missing hydrogen atoms
Model may help fix existing structures in the database or better simulate new materials