Evolutionary-scale prediction of atomic-level protein structure with a language model

Zeming Lin, Halil Akin, Roshan Rao, +12

Science

EngineeringMachine LearningStructural BioinformaticsBiomolecular Structure PredictionGenetics +15

Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences

Alexander Rives, Joshua Meier, Tom Sercu, +8

Proceedings of the National Academy of Sciences

Language models enable zero-shot prediction of the effects of mutations on protein function

Joshua Meier, Roshan Rao, Robert Verkuil, +3

Structured PredictionEngineeringMachine LearningGeneticsMolecular Biology +19

Evolutionary-scale prediction of atomic level protein structure with a language model

Zeming Lin, Halil Akin, Roshan Rao, +12

EngineeringStructural BioinformaticsBiomolecular Structure PredictionMolecular BiologyLarge Language Model +15

Simulating 500 million years of evolution with a language model

Thomas Hayes, Roshan Rao, Halil Akin, +22

Science

Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences

Alexander Rives, Joshua Meier, Tom Sercu, +8

Artificial IntelligenceEngineeringAmino AcidsStructural BioinformaticsMolecular Biology +19

Learning inverse folding from millions of predicted structures

Chloe Hsu, Robert Verkuil, Jason Liu, +5

Structured PredictionInverse FoldingGeometric LearningEngineeringMachine Learning +20

Transformer protein language models are unsupervised structure learners

Roshan Rao, Joshua Meier, Tom Sercu, +2

Structured PredictionEngineeringStructural BioinformaticsContact PredictionMolecular Biology +18

MSA Transformer

Roshan Rao, Jason Liu, Robert Verkuil, +5

Natural Language ProcessingSequence ModellingEngineeringNatural SciencesComputational Linguistics +11

Very deep multilingual convolutional neural networks for LVCSR

Tom Sercu, Christian Puhrsch, Brian Kingsbury, +1

Natural Language ProcessingLarge Ai ModelConvolutional Neural NetworkEngineeringMachine Learning +13