DeepMPF: deep learning framework for predicting drug-target interactions based on multi-modal representation with meta-path semantic analysis.

BACKGROUND: Drug-target interaction (DTI) prediction has become a crucial prerequisite in drug design and drug discovery. However, the traditional biological experiment is time-consuming and expensive, as there are abundant complex interactions present in the large size of genomic and chemical spaces. For alleviating this phenomenon, plenty of computational methods are conducted to effectively complement biological experiments and narrow the search spaces into a preferred candidate domain. Whereas, most of the previous approaches cannot fully consider association behavior semantic information based on several schemas to represent complex the structure of heterogeneous biological networks. Additionally, the prediction of DTI based on single modalities cannot satisfy the demand for prediction accuracy. METHODS: We propose a multi-modal representation framework of 'DeepMPF' based on meta-path semantic analysis, which effectively utilizes heterogeneous information to predict DTI. Specifically, we first construct protein-drug-disease heterogeneous networks composed of three entities. Then the feature information is obtained under three views, containing sequence modality, heterogeneous structure modality and similarity modality. We proposed six representative schemas of meta-path to preserve the high-order nonlinear structure and catch hidden structural information of the heterogeneous network. Finally, DeepMPF generates highly representative comprehensive feature descriptors and calculates the probability of interaction through joint learning. RESULTS: To evaluate the predictive performance of DeepMPF, comparison experiments are conducted on four gold datasets. Our method can obtain competitive performance in all datasets. We also explore the influence of the different feature embedding dimensions, learning strategies and classification methods. Meaningfully, the drug repositioning experiments on COVID-19 and HIV demonstrate DeepMPF can be applied to solve problems in reality and help drug discovery. The further analysis of molecular docking experiments enhances the credibility of the drug candidates predicted by DeepMPF. CONCLUSIONS: All the results demonstrate the effectively predictive capability of DeepMPF for drug-target interactions. It can be utilized as a useful tool to prescreen the most potential drug candidates for the protein. The web server of the DeepMPF predictor is freely available at http://120.77.11.78/DeepMPF/ , which can help relevant researchers to further study.

[Essential oil from Artemisia lavandulaefolia induces apoptosis and necrosis of HeLa cells].

OBJECTIVE: To investigate the effects of Artemisia lavandulaefolia essential oil on apoptosis and necrosis of HeLa cells. METHODS: Cell viability was assayed using MTT method. The morphological and structure alterations in HeLa cells were observed by microscopy. Furthermore, cell apoptosis was measured by DNA Ladder and flow cytometry. DNA damage was measured by comet assay, and the protein expression was examined by Western blot analysis. RESULTS: MTT assay displayed essential oil from Artemisia lavandulaefolia could inhibit the proliferation of HeLa cells in a dose-dependent manner. After treated with essential oil of Artemisia lavadulaefolia for 24 h, HeLa cells in 100 and 200 microg/mL experiment groups exhibited the typical morphology changes of undergoing apoptosis, such as cell shrinkage and nucleus chromatin condensed. However, the cells in the 400 microg/mL group showed the necrotic morphology changes including cytomembrane rupture and cytoplasm spillover. In addition, DNA Ladder could be demonstrated by DNA electrophoresis in each experiment group. Apoptosis peak was also evident in flow cytometry in each experiment group. After treating the HeLa cells with essential oil of Artemisia lavadulaefolia for 6 h, comet tail was detected by comet assay. Moreover, western blotting analysis showed that caspase-3 was activated and the cleavage of PARP was inactivated. CONCLUSION: Essential oil from Artemisia lavadulaefolia can inhibit the proliferation of HeLa cells in vitro. Low concentration of essential oil from Artemisia lavadulaefolia can induce apoptosis, whereas high concentration of the compounds result in necrosis of HeLa cells. And,the mechanism may be related to the caspase-3-mediated-PARP apoptotic signal pathway.

Development and validation of sensitive methods for simultaneous determination of 9 antiviral drugs in different various environmental matrices by UPLC-MS/MS.

Trace antiviral drug contamination in aquatic ecosystems is becoming a significant environmental concern that requires an urgent efficient determination method. Here we developed sensitive and robust multi-residue determination methods to simultaneously extract and analyze 9 commonly used antiviral drugs (abacavir, zidovudine, efavirenz, nevirapine, ritonavir, lopinavir, lamivudine, telbivudine and entecavir) in surface water, wastewater, sediment, and sludge. Water samples were extracted with solid-phase extraction (SPE) technique using tandem hydrophilic-lipophilic balance and graphitized carbon black cartridges, while sediment and sludge samples were extracted using QuEChERS (quick, easy, cheap, effective, rugged, and safe) method. The extraction conditions of SPE (pH and cartridge type) and QuEChERS (acetic acid content, salts reagent, and purification sorbent) methods were carefully optimized. We observed that under optimum conditions, the method quantification limits of the 9 antiviral drugs in water and solid samples ranged from 0.05 to 19.23 ng L-1 and from 0.02 to 7.38 ng g-1, respectively. For environmental samples spiking 3 different concentrations, the recovery values for the most targeted antiviral drugs ranged from 70 to 130%, except for efavirenz. All targeted antiviral drugs were detected in wastewater samples except for entecavir. We also found abacavir, efavirenz, ritonavir, lopinavir, and telbivudine in sediment and sludge samples. Notably, telbivudine was identified in all environmental matrices, with a high concentration of 127 ng L-1 and 222 ng g-1 in water and sediment samples, respectively.