Machine learning – Page 6
-
ResearchMachine learning concocts carbon dioxide conversion catalyst
Computation guides experiments towards a de-alloyed copper–aluminium catalyst
-
ResearchQuantum chemistry simulations offers beguiling possibility of ‘solving chemistry’
Academics and tech giants are using neural networks to represent electronic behaviour
-
NewsOpen source antiviral dataset released to aid fight against Covid-19
CAS collection hosts 50,000 compounds with potential to treat coronavirus infections
-
ResearchProgram that automatically interprets NMR spectra is boon for structure elucidation
Raw NMR data takes 60 seconds, rather than eight hours, to go from spectrometer to structure
-
Research‘Liquid biopsy’ blood test accurately spots cancer by detecting DNA methylation
Power of AI harnessed to identify 50 different cancers before symptoms have even begun to emerge
-
ResearchStructure-based AI tool can predict wide range of very different reactions
Molecular properties, enantioselectivities, yields and relative conversion can all be modelled by the same program
-
ResearchAI tool screens 107 million molecules, discovers potent new antibiotics
Deep learning approach could help in fight against drug-resistant bacteria
-
PodcastYou Look Like a Thing and I Love You by Janelle Shane – Book club
We talk about Janelle Shane’s dive into the depths of AI weirdness
-
ResearchProgram finds 5 million synthetic routes to complex chemicals
Only around five hundred ‘tactical combinations’ for advanced organic synthesis existed – until Chematica was let loose on the problem
-
ArticleArtificial intelligence: on the cusp of a digital revolution
AI is transforming the pharma industry and its drug discovery pipeline
-
ResearchMachine learning predicts electron densities with DFT accuracy
Non-covalent interactions and electron densities can be explored quickly without the need for expensive and time-consuming quantum chemical calculations
-
ResearchLanguage-based software’s accurate predictions translate to benefits for chemists
State-of-the-art design for computer language processing results in improved models for predicting chemistry
-
ResearchHuman biases cause problems for machines trying to learn chemistry
Including ‘unpopular’ reagents and reaction conditions into datasets could lead to better machine-learning models
-
ResearchRetrosynthetic algorithm broadened to design similar, but different, molecules
Chematica can now design efficient syntheses for large compound libraries
-
ResearchAre synthetic chemists out of a job as AI meets automation?
Platform can weigh up a synthetic route, plan it and then carry out it
-
ResearchUncertainty metric builds confidence in machine learned-chemistry
Calculation will help users recognise when they need to retrain a neural network
-
OpinionMachine-learning Mendeleevs have rediscovered the periodic table
Exposing new dimensions in the relationships between elements
-
ResearchTranslating molecules into music helps humans and AI understand proteins
Scientists make amino acids’ vibrations audible to train artificial intelligence programs in protein design
-
ResearchAlgorithm accurately predicts mechanical properties of existing and theoretical MOFs
Machine learning could speed up the production and use of coordination polymers in industry
-
BusinessFighting fake medicines
RxAll’s handheld scanner assesses drug quality in real time via a smartphone