Cisplatin is a widely used chemotherapeutic agent but its clinical use is often limited by nephrotoxicity. Autophagy is a lysosomal degradation pathway that removes protein aggregates and damaged or dysfunctional cellular organelles for maintaining cell homeostasis. Upon cisplatin exposure, autophagy is rapidly activated in renal tubule cells to protect against acute cisplatin nephrotoxicity. Mechanistically, the protective effect is mainly related to the clearance of damaged mitochondria via mitophagy. The role and regulation of autophagy in chronic kidney problems after cisplatin treatment are currently unclear, despite the significance of research in this area. In cancers, autophagy may prevent tumorigenesis, but autophagy may reduce the efficacy of chemotherapy by protecting cancer cells. Future research should focus on developing drugs that enhance the anti-tumor effects of cisplatin while protecting kidneys during cisplatin chemotherapy.

Cisplatin is a highly effective, broad-spectrum chemotherapeutic drug, yet its clinical use and efficacy are limited by its side effects. Particularly, cancer patients receiving cisplatin chemotherapy have high incidence of kidney problems. Hypoxia-inducible factor (HIF) is the “master” transcription factor that is induced under hypoxia to trans-activate various genes for adaptation to the low oxygen condition. Numerous studies have reported that HIF activation protects against AKI and promotes kidney recovery in experimental models of cisplatin-induced acute kidney injury (AKI). In contrast, little is known about the effects of HIF on chronic kidney problems following cisplatin chemotherapy. Prolyl hydroxylase (PHD) inhibitors are potent HIF inducers that recently entered clinical use. By inducing HIF, PHD inhibitors may protect kidneys during cisplatin chemotherapy. However, HIF activation by PHD inhibitors may reduce the anti-cancer effect of cisplatin in tumors. Future studies should test PHD inhibitors in tumor-bearing animal models to verify their effects in kidneys and tumors.

Relation triple extraction is a combination of named entity recognition and relation prediction. Early works ignore the problem of data overlap when extracting triples, resulting in poor extraction performance. Subsequent works improve the capability of the model to extract overlapping triples through generative and extractive methods. These works achieve considerable performance but still suffer from some defects, such as poor extraction capability for individual triplets and inappropriate spatial distribution of the data. To solve the above problems, we perform sequence-to-matrix transformation and propose the NEDORT model. NEDORT predicts all subjects in the sentence and then completes the extraction of relation–object pairs. There are overlapping parts between relation–object pairs, so we conduct the conversion of sequence to matrix. We design the Differential Amplified Multi-head Attention method to extract subjects. This method highlights the locations of entities and captures sequence features from multiple dimensions. When performing the extraction of relation–object pairs, we fuse subject and sequence information through the Biaffine method and generate relation–sequence matrices. In addition, we design a multi-layer U-Net network to optimize the matrix representation and improve the extraction performance of the model. Experimental results on two public datasets show that our model outperforms other baseline models on triples of all categories