TY - JOUR
T1 - Using BERT to identify drug-target interactions from whole PubMed
AU - Aldahdooh, Jehad
AU - Vähä-Koskela, Markus
AU - Tang, Jing
AU - Tanoli, Ziaurrehman
PY - 2022/6/21
Y1 - 2022/6/21
N2 - Drug-target interactions (DTIs) are critical for drug repurposing and elucidation of drug mechanisms, and are manually curated by large databases, such as ChEMBL, BindingDB, DrugBank and DrugTargetCommons. However, the number of curated articles likely constitutes only a fraction of all the articles that contain experimentally determined DTIs. Finding such articles and extracting the experimental information is a challenging task, and there is a pressing need for systematic approaches to assist the curation of DTIs. To this end, we applied Bidirectional Encoder Representations from Transformers (BERT) to identify such articles. Because DTI data intimately depends on the type of assays used to generate it, we also aimed to incorporate functions to predict the assay format.
AB - Drug-target interactions (DTIs) are critical for drug repurposing and elucidation of drug mechanisms, and are manually curated by large databases, such as ChEMBL, BindingDB, DrugBank and DrugTargetCommons. However, the number of curated articles likely constitutes only a fraction of all the articles that contain experimentally determined DTIs. Finding such articles and extracting the experimental information is a challenging task, and there is a pressing need for systematic approaches to assist the curation of DTIs. To this end, we applied Bidirectional Encoder Representations from Transformers (BERT) to identify such articles. Because DTI data intimately depends on the type of assays used to generate it, we also aimed to incorporate functions to predict the assay format.
KW - BERT
KW - BERT for biomedical data
KW - Bidirectional encoder representations from transformers
KW - Bioactivity data
KW - Biomedical text mining
KW - Drug repurposing
KW - Drug target interaction prediction
KW - INFORMATION
KW - Mining drug target interactions
KW - PREDICTION
KW - 3111 Biomedicine
U2 - 10.1186/s12859-022-04768-x
DO - 10.1186/s12859-022-04768-x
M3 - Article
VL - 23
JO - BMC Bioinformatics
JF - BMC Bioinformatics
SN - 1471-2105
IS - 1
M1 - 245
ER -