VARIDT 3.0: the phenotypic and regulatory variability of drug transporter.

The phenotypic and regulatory variability of drug transporter (DT) are vital for the understanding of drug responses, drug-drug interactions, multidrug resistances, and so on. The ADME property of a drug is collectively determined by multiple types of variability, such as: microbiota influence (MBI), transcriptional regulation (TSR), epigenetics regulation (EGR), exogenous modulation (EGM) and post-translational modification (PTM). However, no database has yet been available to comprehensively describe these valuable variabilities of DTs. In this study, a major update of VARIDT was therefore conducted, which gave 2072 MBIs, 10 610 TSRs, 46 748 EGRs, 12 209 EGMs and 10 255 PTMs. These variability data were closely related to the transportation of 585 approved and 301 clinical trial drugs for treating 572 diseases. Moreover, the majority of the DTs in this database were found with multiple variabilities, which allowed a collective consideration in determining the ADME properties of a drug. All in all, VARIDT 3.0 is expected to be a popular data repository that could become an essential complement to existing pharmaceutical databases, and is freely accessible without any login requirement at: https://idrblab.org/varidt/.

Decoding Drug Response with Structurized Gridding Map-based Cell Representation.

A thorough understanding of cell-line drug response mechanisms is crucial for drug development, repurposing, and resistance reversal. While targeted anticancer therapies have shown promise, not all cancers have well-established biomarkers to stratify drug response. Single-gene associations only explain a small fraction of the observed drug sensitivity, so a more comprehensive method is needed. However, while deep learning models have shown promise in predicting drug response in cell lines, they still face significant challenges when it comes to their application in clinical applications. Therefore, this study proposed a new strategy called DD-Response for cell-line drug response prediction. First, a limitation of narrow modeling horizons was overcome to expand the model training domain by integrating multiple datasets through source-specific label binarization. Second, a modified representation based on a two-dimensional structurized gridding map (SGM) was developed for cell lines & drugs, avoiding feature correlation neglect and potential information loss. Third, a dual-branch, multi-channel convolutional neural network-based model for pairwise response prediction was constructed, enabling accurate outcomes and improved exploration of underlying mechanisms. As a result, the DD-Response demonstrated superior performance, captured cell-line characteristic variations, and provided insights into key factors impacting cell-line drug response. In addition, DD-Response exhibited scalability in predicting clinical patient responses to drug therapy. Overall, because of DD-response's excellent ability to predict drug response and capture key molecules behind them, DD-response is expected to greatly facilitate drug discovery, repurposing, resistance reversal, and therapeutic optimization.

State-of-the-art Application of Artificial Intelligence to Transporter-centered Functional and Pharmaceutical Research.

Protein transporters not only have essential functions in regulating the transport of endogenous substrates and remote communication between organs and organisms, but they also play a vital role in drug absorption, distribution, and excretion and are recognized as major determinants of drug safety and efficacy. Understanding transporter function is important for drug development and clarifying disease mechanisms. However, the experimental-based functional research on transporters has been challenged and hinged by the expensive cost of time and resources. With the increasing volume of relevant omics datasets and the rapid evolution of artificial intelligence (AI) techniques, next-generation AI is becoming increasingly prevalent in the functional and pharmaceutical research of transporters. Thus, a comprehensive discussion on the state-of-the-art application of AI in three cutting-edge directions was provided in this review, which included (a) transporter classification and function annotation, (b) structure discovery of membrane transporters, and (c) drug-transporter interaction prediction. This study provides a panoramic view of AI algorithms and tools applied to the field of transporters. It is expected to guide a better understanding and utilization of AI techniques for in-depth studies of transporter-centered functional and pharmaceutical research.

GPX4 deficiency-dependent phospholipid peroxidation drives motor deficits of ALS.

Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease characterized by oxidative stress that triggers motor neurons loss in the brain and spinal cord. However, the mechanisms underlying the exact role of oxidative stress in ALS-associated neural degeneration are not definitively established. Oxidative stress-generated phospholipid peroxides are known to have extensive physiological and pathological consequences to tissues. Here, we discovered that the deficiency of glutathione peroxidase 4 (GPX4), an essential antioxidant peroxidase, led to the accumulation of phospholipid peroxides and resulted in a loss of motor neurons in spinal cords of ALS mice. Mutant human SOD1G93A transgenic mice were intrathecally injected with neuron-targeted adeno-associated virus (AAV) expressing GPX4 (GPX4-AAV) or phospholipid peroxidation inhibitor, ferrostatin-1. The results showed that impaired motor performance and neural loss induced by SOD1G93A toxicity in the lumbar spine were substantially alleviated by ferrostatin-1 treatment and AAV-mediated GPX4 delivery. In addition, the denervation of neuron-muscle junction and spinal atrophy in ALS mice were rescued by neural GPX4 overexpression, suggesting that GPX4 is essential for the motor neural maintenance and function. In comparison, conditional knockdown of Gpx4 in the spinal cords of Gpx4fl/fl mice triggered an obvious increase of phospholipid peroxides and the occurrence of ALS-like motor phenotype. Altogether, our findings underscore the importance of GPX4 in maintaining phospholipid redox homeostasis in the spinal cord and presents GPX4 as an attractive therapeutic target for ALS treatment.