A deep learning based multi-model approach for predicting drug-like chemical compound's toxicity.

Ensuring the safety and efficacy of chemical compounds is crucial in small-molecule drug development. In the later stages of drug development, toxic compounds pose a significant challenge, losing valuable resources and time. Early and accurate prediction of compound toxicity using deep learning models offers a promising solution to mitigate these risks during drug discovery. In this study, we present the development of several deep-learning models aimed at evaluating different types of compound toxicity, including acute toxicity, carcinogenicity, hERG_cardiotoxicity (the human ether-a-go-go related gene caused cardiotoxicity), hepatotoxicity, and mutagenicity. To address the inherent variations in data size, label type, and distribution across different types of toxicity, we employed diverse training strategies. Our first approach involved utilizing a graph convolutional network (GCN) regression model to predict acute toxicity, which achieved notable performance with Pearson R 0.76, 0.74, and 0.65 for intraperitoneal, intravenous, and oral administration routes, respectively. Furthermore, we trained multiple GCN binary classification models, each tailored to a specific type of toxicity. These models exhibited high area under the curve (AUC) scores, with an impressive AUC of 0.69, 0.77, 0.88, and 0.79 for predicting carcinogenicity, hERG_cardiotoxicity, mutagenicity, and hepatotoxicity, respectively. Additionally, we have used the approved drug dataset to determine the appropriate threshold value for the prediction score in model usage. We integrated these models into a virtual screening pipeline to assess their effectiveness in identifying potential low-toxicity drug candidates. Our findings indicate that this deep learning approach has the potential to significantly reduce the cost and risk associated with drug development by expediting the selection of compounds with low toxicity profiles. Therefore, the models developed in this study hold promise as critical tools for early drug candidate screening and selection.

Kidney tubular transcription co-activator, Yes-associated protein 1 (YAP), controls the expression of collecting duct aquaporins and water homeostasis.

Final urine volume and concentration are defined by water reabsorption through the water channel proteins aquaporin (AQP)-2, -3 and -4 in the collecting duct. However, the transcriptional regulation of these AQPs is not well understood. The Hippo/Yes-associated protein 1 (YAP) pathway plays an important role in organ size control and tissue homeostasis. When the Hippo pathway including the Mst1/Mst2 kinases is inhibited, YAP is activated and functions as a transcription co-activator. Our previous work revealed a pathological role of tubular YAP activation in chronic kidney disease, but the physiological role of YAP in the kidney remains to be established. Here, we found that tubule-specific Yap knockout mice showed increased urine output and decreased urinary osmolality. Decreases in Aqp2, -3 and -4 mRNA and protein abundance in the kidney were evident in Yap knockout mice. Analysis of Mst1/Mst2 double knockout and Mst1/Mst2/Yap triple knockout mice showed that expression of Aqp2 and Aqp4 but not Aqp3 was dependent on YAP. Furthermore, YAP was recruited to the promoters of the Aqp2 and Aqp4 genes and stimulated their transcription. Interestingly, YAP was found to interact with transcription factors GATA2, GATA3 and NFATc1. These three factors promoted Aqp2 transcription in a YAP dependent manner in collecting duct cells. These three factors also promoted Aqp4 transcription whereas only GATA2 and GATA3 enhanced Aqp3 transcription. Thus, our results suggest that YAP promotes Aqp2 and Aqp4 transcription, interacts with GATA2, GATA3 and NFATc1 to control Aqp2 expression, while Aqp-2, -3 and -4 exploit overlapping mechanisms for their baseline transcriptional regulation.

Network Pharmacology and Molecular Docking Analysis Reveal Insights into the Molecular Mechanism of Shengma-Gegen Decoction on Monkeypox.

BACKGROUND: A new viral outbreak caused by monkeypox has appeared after COVID-19. As of yet, no specific drug has been found for its treatment. Shengma-Gegen decoction (SMGGD), a pathogen-eliminating and detoxifying agent composed of four kinds of Chinese herbs, has been demonstrated to be effective against several viruses in China, suggesting that it may be effective in treating monkeypox, however, the precise role and mechanisms are still unknown. METHODS: Network pharmacology was used to investigate the monkeypox-specific SMGGD targets. These targets were analyzed via String for protein-to-protein interaction (PPI), followed by identification of hub genes with Cytoscape software. Function enrichment analysis of the hub targets was performed. The interactions between hub targets and corresponding ligands were validated via molecular docking. RESULTS: Through screening and analysis, a total of 94 active components and 8 hub targets were identified in the TCM-bioactive compound-hub gene network. Molecular docking results showed that the active components of SMGGD have strong binding affinity for their corresponding targets. According to functional analysis, these hub genes are mainly involved in the TNF, AGE-RAGE, IL-17, and MAPK pathways, which are linked to the host inflammatory response to infection and viral replication. Therefore, SMGGD might suppress the replication of monkeypox virus through the MAPK signaling pathway while also reducing inflammatory damage caused by viral infection. CONCLUSION: SMGGD may have positive therapeutic effects on monkeypox by reducing inflammatory damage and limiting virus replication.

Antitumor effect and mechanism of an ellagic acid derivative on the HepG2 human hepatocellular carcinoma cell line.

In the present study, to identify the effective components of Chinese traditional herbs, Euphorbia hylonoma Hand.-Mazz. (Euphorbiaceae), a folk herb that has been used among the Qinling mountain area for hundreds of years, was investigated. 3,3'-Di-O-methyl ellagic acid-4'-O-ß-d-xylopyranoside (JNE2), an ellagic acid derivative, was isolated from the acetone extract of the herb and its antitumor activity against human hepatoma HepG2 cells was detected in vitro. The results showed that JNE2 inhibited the proliferation of HepG2 cells in a dose- and time-dependent manner and blocked the cell cycle at the G1/S phase. A high dosage of JNE2 induced apoptosis of the tumor cells, but no significant differences were identified between the treatment groups. The invasiveness of HepG2 cells was also inhibited by JNE2. The mechanism of the antitumor effect of JNE2 at the molecular level was presumed to be due to the upregulation of the protein expression of Bax and caspase-3, and the downregulation of the protein expression of Bcl-2 and CCND1. The results suggested that JNE2 is a potential antitumor agent that merits further investigation.

[Analysis of petroleum fraction from flower, stem and leaf of Aconitum taipeicum by GC-MS].

OBJECTIVE: To analyze the chemical constituents of petroleum fraction of Aconitum taipeicum. METHODS: The methanol extract of Aconitum taipeicum were extracted by petroleum and then analyzed by GC-MS. The compounds were quantitatively determined by normalization method. RESULTS: Twenty eight compounds were separated and identified. Most of them were alkane, fat acids and their esters and alkenes. The Nonacosane covered 13.057% of the total peaks, while 19-methyl-18,21-Hexatriacontanediether 8.180%, Ethylen eglycol monooctadecy ether 7.851%, 3,7,11,15-Tetramethyl-2-hexadecen-1-ol 7.805%, Metahyl Palmitate 6.676% and so on. CONCLUSION: This is the first report of constituents from the flower, stem and leaf of Aconitum taipeicum. The results will provide foundation for further exploitation and use of Aconitum taipeicum.