Automatic annotation of protein residues in published papers

• Published in: Acta crystallographica. Section F, Structural biology communications Vol. 75; no. 11; pp. 665 - 672
• Main Authors: Firth, Robert, Talo, Francesco, Venkatesan, Aravind, Mukhopadhyay, Abhik, McEntyre, Johanna, Velankar, Sameer, Morris, Chris
• Format: Journal Article
• Language: English
• Published: 5 Abbey Square, Chester, Cheshire CH1 2HU, England International Union of Crystallography 01.11.2019; Wiley Subscription Services, Inc
• Subjects: Amino Acids - chemistry; Annotations; Automation; Method Communications; Molecular Sequence Annotation; Mutation - genetics; named entity recognizer; natural language processing; NLP; Proteins; Proteins - chemistry; Proteins - genetics; residue; Residues; Software; NLP; named entity recognizer; natural language processing; residue
• ISSN: 2053-230X; 2053-230X
• DOI: 10.1107/S2053230X1901210X

This work presents an annotation tool that automatically locates mentions of particular amino‐acid residues in published papers and identifies the protein concerned. These matches can be provided in context or in a searchable format in order for researchers to better use the existing and future literature. An annotation tool is presented that automatically locates amino‐acid residues in published papers and matches them to protein structures within the paper. These matches can be provided in context or in a searchable format in order for researchers to better use the existing and future literature.