Novel deep learning-based transcriptome data analysis for drug-drug interaction prediction with an application in diabetes.

BACKGROUND: Drug-drug interaction (DDI) is a serious public health issue. The L1000 database of the LINCS project has collected millions of genome-wide expressions induced by 20,000 small molecular compounds on 72 cell lines. Whether this unified and comprehensive transcriptome data resource can be used to build a better DDI prediction model is still unclear. Therefore, we developed and validated a novel deep learning model for predicting DDI using 89,970 known DDIs extracted from the DrugBank database (version 5.1.4). RESULTS: The proposed model consists of a graph convolutional autoencoder network (GCAN) for embedding drug-induced transcriptome data from the L1000 database of the LINCS project; and a long short-term memory (LSTM) for DDI prediction. Comparative evaluation of various machine learning methods demonstrated the superior performance of our proposed model for DDI prediction. Many of our predicted DDIs were revealed in the latest DrugBank database (version 5.1.7). In the case study, we predicted drugs interacting with sulfonylureas to cause hypoglycemia and drugs interacting with metformin to cause lactic acidosis, and showed both to induce effects on the proteins involved in the metabolic mechanism in vivo. CONCLUSIONS: The proposed deep learning model can accelerate the discovery of new DDIs. It can support future clinical research for safer and more effective drug co-prescription.

Prognostic value of plasma Aß1-40 for Alzheimer's disease.

OBJECTIVE: To investigate the clinical significance of plasma p-amyloid 1-40 (Aß1-40) in patients with Alzheimer's disease (AD). METHODS: In this retrospective study, the clinical data of 305 patients, with or without Alzheimer's disease (AD), who were treated at the Affiliated Hospital of Youjiang Medical University for Nationalities and the People's Hospital of Baise between January 2018 and December 2021 were analyzed. Patients were divided into two groups: an AD group (n=147) and a non-AD group (without AD, n=158 cases). Blood test indices, including serum aspartate aminotransferase (AST), alanine aminotransferase (ALT), creatinine (CRE), high-sensitivity C-reactive protein (hsCRP), and plasma ß-amyloid 1-40 were collected and compared between the two groups. RESULTS: The plasma ß-amyloid 1-40 in the AD group was (3.71±3.45) mol/L, which was significantly higher than (2.8±1.35) mmol/L in the non-AD group (P<0.05). Similarly, hsCRP expression was significantly higher in the AD group than that in the non-AD group (P<0.05). There were no significant differences in AST, ALT, UA, T-tau, NFL or Cr levels between the two groups (all P>0.05). Moreover, univariate regression analysis showed that plasma ß-amyloid 1-40 and hsCRP were significantly correlated with AD. Multiple regression analysis demonstrated that plasma p-amyloid 1-40 (P<0.0001) and hsCRP (P=0.002) were independent predictors of AD. CONCLUSION: Plasma p-amyloid 1-40 and hsCRP are closely related to AD, and may serve as important clinical predictors of AD.

Autophagy Regulation Attenuates Neuroinflammation and Cognitive Decline in an Alzheimer's Disease Mouse Model with Chronic Cerebral Hypoperfusion.

This study investigates the role of autophagy regulation in modulating neuroinflammation and cognitive function in an Alzheimer's disease (AD) mouse model with chronic cerebral hypoperfusion (CCH). Using the APP23/PS1 mice plus CCH model, we examined the impact of autophagy regulation on cognitive function, neuroinflammation, and autophagic activity. Our results demonstrate significant cognitive impairments in AD mice, exacerbated by CCH, but mitigated by treatment with the autophagy inhibitor 3-methyladenine (3-MA). Dysregulation of autophagy-related proteins, accentuated by CCH, underscores the intricate relationship between cerebral blood flow and autophagy dysfunction in AD pathology. While 3-MA restored autophagic balance, rapamycin (RAPA) treatment did not induce significant changes, suggesting alternative therapeutic approaches are necessary. Dysregulated microglial polarization and neuroinflammation in AD+CCH were linked to cognitive decline, with 3-MA attenuating neuroinflammation. Furthermore, alterations in M2 microglial polarization and the levels of inflammatory markers NLRP3 and MCP1 were observed, with 3-MA treatment exhibiting potential anti-inflammatory effects. Our findings shed light on the crosstalk between autophagy and neuroinflammation in AD+CCH and suggest targeting autophagy as a promising strategy for mitigating neuroinflammation and cognitive decline in AD+CCH.

Protein-ligand binding affinity prediction with edge awareness and supervised attention.

Accurate prediction of protein-ligand binding affinity is crucial in structure-based drug design but remains some challenges even with recent advances in deep learning: (1) Existing methods neglect the edge information in protein and ligand structure data; (2) current attention mechanisms struggle to capture true binding interactions in the small dataset. Herein, we proposed SEGSA_DTA, a SuperEdge Graph convolution-based and Supervised Attention-based Drug-Target Affinity prediction method, where the super edge graph convolution can comprehensively utilize node and edge information and the multi-supervised attention module can efficiently learn the attention distribution consistent with real protein-ligand interactions. Results on the multiple datasets show that SEGSA_DTA outperforms current state-of-the-art methods. We also applied SEGSA_DTA in repurposing FDA-approved drugs to identify potential coronavirus disease 2019 (COVID-19) treatments. Besides, by using SHapley Additive exPlanations (SHAP), we found that SEGSA_DTA is interpretable and further provides a new quantitative analytical solution for structure-based lead optimization.