Motivation Drug-drug interactions (DDIs) are one of the major concerns in pharmaceutical research. Many machine learning based methods have been proposed for the DDI prediction, but most of them predict whether two drugs interact or not. The studies revealed that DDIs could cause different subsequent events, and predicting drug-drug interaction-associated events is more useful for investigating the mechanism hidden behind the combined drug usage or adverse reactions. Results In this paper, we collect DDIs from DrugBank database, and extract 65 categories of DDI events by dependency analysis and events trimming. We propose a multimodal deep learning framework named DDIMDL that combines diverse drug features with deep learning to build a model for predicting drug-drug interaction-associated events. DDIMDL first constructs deep neural network-based sub-models by respectively using four types of drug features: chemical substructures, targets, enzymes and pathways, and then adopts a joint DNN framework to combine the sub-models to learn cross-modality representations of drug-drug pairs and predict DDI events. In computational experiments, DDIMDL produces high-accuracy performances and has high efficiency. Moreover, DDIMDL outperforms state-of-the-art DDI event prediction methods and baseline methods. Among all the features of drugs, the chemical substructures seem to be the most informative. With the combination of substructures, targets and enzymes, DDIMDL achieves an accuracy of 0.8852 and an area under the precision-recall curve of 0.9208. Availability The source code and data are available at https://github.com/YifanDengWHU/DDIMDL Supplementary information Supplementary data are available at Bioinformatics online.
Background Relationships between iron‐dependent ferroptosis and nerve system diseases have been recently revealed. However, the role of ferroptosis in neuropathic pain (NeP) remains to be elucidated. Thus, we aimed to investigate whether ferroptosis in spinal cord contributes to NeP induced by a chronic constriction injury (CCI) of the sciatic nerve. Methods Forty Sprague‐Dawley rats received CCI or sham surgery, and were randomly assigned to the following four groups: sham group; CCI + LIP group; CCI + Veh group; and CCI group. Liproxstatin‐1 or corn oil were separately injected intraperitoneally for three consecutive days after surgery in the CCI + LIP or CCI + Veh group. The mechanical and thermal hypersensitivities were tested after surgery. Biochemical and morphological changes related to ferroptosis in the spinal cord were also assessed. These included iron content, glutathione peroxidase 4 (GPX4) and anti‐acyl‐CoA synthetase long‐chain family member 4 (ACSL4) expression, lipid peroxidation assays, as well as mitochondrial morphology. Results CCI‐induced NeP was followed by iron accumulation, increased lipid peroxidation and dysregulation of ACSL4 and GPX4. Moreover transmission electron microscopy confirmed the presence of aberrant morphological changes on mitochondrial, such as mitochondria shrinkage and membrane rupture. Furthermore, the administration of liproxstatin‐1 on CCI rats attenuated hypersensitivities, lowered the iron level, decreased spinal lipid peroxidation, restored the dysregulations in GPX4 and ACSL4 levels, and protected against CCI induced morphological changes in mitochondria. Conclusions Our findings indicated the involvement of ferroptosis in CCI induced NeP, and point to ferroptosis inhibitors such as liproxstatin‐1 as potential therapies for hypersensitivity induced by peripheral nerve injury. Significance The spinal ferroptosis‐like cell death was involved in the development of neuropathic pain resulted from peripheral nerve injury, and inhibition of ferroptosis by liproxstatin‐1 could alleviate mechanical and thermal hypersensitivities. This knowledge suggested that ferroptosis could represent a potential therapeutic target for neuropathic pain.
Glioblastoma multiforme (GBM) is lethal brain tumor thought to arise from GBM stem cells (GBM-SCs). MicroRNAs carry out post-transcriptional regulation of various cellular processes that modulate the stemness properties of GBM-SCs. Here, we investigated the critical role of miR-153 in GBM-SCs. First, GBM-SCs were isolated from six GBM specimens. These GBM-SCs formed GBM spheres, expressed markers associated with neural stem cells, and possessed the capacity for self-renewal and multilineage differentiation. Then qRT-PCR analysis showed that miR-153 expression was down-regulated in GBM tissues relative to normal brain tissues, and in CD133 positive cells relative to CD133 negative cells. This project demonstrates for the first time that transient transfection of miR-153 into GBM-SCs can inhibit their stemness properties, such as impairing self-renewal ability and inducing differentiation. Meanwhile, miR-153 can also repress GBM-SCs growth and induce apoptosis. Altogether, these results indicate that reactivation of miR-153 expression suggests novel therapeutic strategies for GBM-SCs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.