A study on pharmaceutical text relationship extraction based on heterogeneous graph neural networks.

Effective information extraction of pharmaceutical texts is of great significance for clinical research. The ancient Chinese medicine text has streamlined sentences and complex semantic relationships, and the textual relationships may exist between heterogeneous entities. The current mainstream relationship extraction model does not take into account the associations between entities and relationships when extracting, resulting in insufficient semantic information to form an effective structured representation. In this paper, we propose a heterogeneous graph neural network relationship extraction model adapted to traditional Chinese medicine (TCM) text. First, the given sentence and predefined relationships are embedded by bidirectional encoder representation from transformers (BERT fine-tuned) word embedding as model input. Second, a heterogeneous graph network is constructed to associate words, phrases, and relationship nodes to obtain the hidden layer representation. Then, in the decoding stage, two-stage subject-object entity identification method is adopted, and the identifier adopts a binary classifier to locate the start and end positions of the TCM entities, identifying all the subject-object entities in the sentence, and finally forming the TCM entity relationship group. Through the experiments on the TCM relationship extraction dataset, the results show that the precision value of the heterogeneous graph neural network embedded with BERT is 86.99% and the F1 value reaches 87.40%, which is improved by 8.83% and 10.21% compared with the relationship extraction models CNN, Bert-CNN, and Graph LSTM.

EGFR signaling-dependent inhibition of glioblastoma growth by ginsenoside Rh2.

Glioblastoma is the most common and most aggressive malignant primary brain tumor in humans, accounting for 52 % of all functional tissue brain tumor cases and 20 % of all intracranial tumors. The typical treatment involves a combination of chemotherapy, radiation, and surgery, whereas it still achieves fairly poor patient survival. Ginsenoside Rh2 has been reported to have a therapeutic effect on some tumors, but its effect on glioblastoma has not been extensively evaluated. Here, we show that ginsenoside Rh2 can substantially inhibit the growth of glioblastoma in vitro and in vivo in a mouse model. Moreover, the inhibition of the tumor growth appears to result from combined effects on decreased tumor cell proliferation and increased tumor cell apoptosis. Further analyses suggest that ginsenoside Rh2 may have its antiglioblastoma effect through inhibition of the epidermal growth factor receptor (EGFR) signaling pathway in tumor cells. In a lose-of-function experiment, recombinant EGFR was given together with ginsenoside Rh2 to the tumor cells in vitro and in vivo, which completely blocked the antitumor effects of ginsenoside Rh2. Thus, our data not only reveal an anti-glioblastoma effect of ginsenoside Rh2 but also demonstrate that this effect may function via inhibition of EGFR signaling in glioblastoma cells.