The two senior authors (AMC and MM) discussed and modified the article annotation assignments until consensus was reached.
The main objective during the article annotation phase for RegTransBase was to collect experimental evidences of transcriptional regulation and experimentally characterized TF binding sites.
With the customized software in-house, article annotation was fairly swift, individual papers taking 10 30 min, depending on their suitability for mark-up.
Write an article annotation when you are finished.
For the metadata heuristic, error analysis of the 10 documents revealed that the majority of the errors were caused by misspelled toponyms in articles, annotation errors, and some minor deviations from the annotation guidelines.
Table 2 provides an overview of the number of articles and annotations of each subset.
Finally, during the test set prediction phase, registered teams were provided with a collection of articles without annotations for which they had to return predictions within a short period of time, together with a technical system description.
I would also add a column with the number of articles and annotations in each of the data sets (medline, pmc, pdf, etc), and the performance at each of these levels, i.e. calculate the recall on a section (Medline) based on the total annotation present in such section.
The MEDLINE [si] field for the 210 articles selected contained annotations for GenBank (110 articles), PDB (50 articles), GEO (47 articles), RefSeq (4 articles) and GDB (1 article).
In 2011, we implemented eGIFT to assist biocurators with identifying articles for annotation.
