Natural language processing for rapid protein annotation

Over 40 million protein annotations have been added to the UniProt database using a Google Research natural language processing model

Protein structure — Natural language processing for rapid protein annotation. Karen Arnott/EMBL-EBI

Related links

Tags: ai, artificial intelligence, bioinformatics, deep learning, embl-ebi, machine learning, protein, uniprot,

More Technology and innovation

The final set of nodes in a machine learning neural network connect to the first atom of a simplified chemical structure

Machine learning to identify and prioritise drug targets
26 January 2023

Protein structure

Natural language processing for rapid protein annotation
13 October 2022

Protein structure on blue background

AlphaFold predicts structure of almost every catalogued protein known to science
28 July 2022

DNA sequencing data in the background with waves to indicate neural networks. Chromosomes are found in various parts of the image and in circles are different gene symbols.

A machine learning approach for allocating gene function
31 May 2022