@article{garda2022regel, title={RegEl corpus: identifying DNA regulatory elements in the scientific literature}, author={Garda, Samuele and Lenihan-Geels, Freyda and Proft, Sebastian and Hochmuth, Stefanie and Sch{\"u}lke, Markus and Seelow, Dominik and Leser, Ulf}, journal={Database}, volume={2022}, year={2022}, publisher={Oxford Academic} } # RegEl PubMed Database This database contains the annotations generated by running [HunFlair](https://github.com/flairNLP/flair/blob/master/resources/docs/HUNFLAIR.md) models trained on the [RegEl corpus](https://zenodo.org/record/5776679) over >20M PubMed abstracts. By pairing these annotations with the one provided by PubTator this generates a large text mining database of regulatory elements associated with genes (normalized to NCBI Gene ids) and disease (normalized to either MeSH or OMIM). The tables composing the database are: * abstracts.db: - pmid = PubMed ID of the given abstracts - sid = sentence ID of the given abstracts (from 0 to # of sentences) - text = text of the given sentence * gene.db and disease.db: - pmid = PubMed ID of the given abstracts - sid = sentence ID of the given abstracts (from 0 to # of sentences) - etype = entity type (enhancer, promoter, TFBS) - ann_text = mention of the regulatory element as found in the abstract - start = position (# character) in which the mention begins - end = position (# characters) in which the mention ends - score = model's confidence - cui = gene or disease identifier - cui_symbol = official symbol of cui (if available)