@article {Goldberg014274, author = {Tatyana Goldberg and Shrikant Vinchurkar and Juan Miguel Cejuela and Lars Juhl Jensen and Burkhard Rost}, title = {Linked annotations: a middle ground for manual curation of biomedical databases and text corpora}, elocation-id = {014274}, year = {2015}, doi = {10.1101/014274}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Annotators of text corpora and biomedical databases carry out the same labor-intensive task to manually extract structured data from unstructured text. Tasks are needlessly repeated because text corpora are widely scattered. We envision that a linked annotation resource unifying many corpora could be a game changer. Such an open forum will help focus on novel annotations and on optimally benefiting from the energy of many experts. As proof-of-concept, we annotated protein subcellular localization in 100 abstracts cited by UniProtKB. The detailed comparison between our new corpus and the original UniProtKB annotations revealed sustained novel annotations for 42\% of the entries (proteins). In a unified linked annotation resource these could immediately extend the utility of text corpora beyond the text-mining community. Our example motivates the central idea that linked annotations from text corpora can complement database annotations.}, URL = {https://www.biorxiv.org/content/early/2015/01/23/014274}, eprint = {https://www.biorxiv.org/content/early/2015/01/23/014274.full.pdf}, journal = {bioRxiv} }