Jie Xia

Antibiotics with new mechanisms are highly pursued to address the threat of infections caused by drug-resistant Gram-negative bacteria. Targeting MsbA, a key protein of the lipopolysaccharide biosynthesis pathway, represents a promising strategy to discover new classes of antibiotics. However, currently available MsbA-targeted molecules either lack sufficient potency or have unfavorable properties, necessitating expansion of chemical space. In this study, we chose the most promising cerastecin Cpd 4 as the template, and used two Artificial Intelligence (AI)-based tools, i.e. Link-INVENT and AutoMolDesigner for molecular design, performed chemical derivatization and antibacterial activity evaluation, which led to the discovery of Y-11 (MIC for A. baumannii: 0.5 μg/mL). Encouragingly, Y-11 showed equivalent potency to Cpd4 for carbapenem-resistant A. baumannii, and less cytotoxicity and hemolysis as well as lower spontaneous resistance frequency. In vivo efficacy study demonstrated that Y-11 could effectively reduce bacterial loads in the mice infected by A. baumannii. The following mechanism study including molecular dynamics simulation, biochemical assay, and transmission electron microscope (TEM) analysis suggested that Y-11 inhibited the transport of lipooligosaccharide and impaired the formation of outer membrane, probably by competitively binding to the substrate binding site of MsbA and modulating ATPase activity. Taken together, we have discovered a MsbA-targeted small molecule Y-11 via AI-driven drug design, which provides a foundation for future antibiotic development.

Alzheimer’s disease (AD) is a neurodegenerative disorder characterized by the pathological accumulation of amyloid-β (Aβ) plaques and neuro

Gram-negative pathogens are difficult to treat because their outer membrane, enriched with lipid A-anchored lipopolysaccharide, serves as a protective barrier to many antibiotics. LpxH, an essential dimanganese hydrolase in lipid A biosynthesis, represents a promising antimicrobial target, but its distinct L-shaped binding pocket has limited inhibitor development, with only the sulfonylpiperazine chemotype reported to date. To broaden the chemical space, we developed a multistage virtual screening workflow combining HipHop-based pharmacophore modeling, ROCS-based query matching, and FRED docking. This pipeline identified F523-0608, an acetylpiperazine-containing compound, as a moderate Klebsiella pneumoniae LpxH (KpLpxH) inhibitor. Substructure searching and optimization yielded compound 7, a potent inhibitor (IC₅₀: 0.17 μM) with moderate antibacterial activity (MIC: 5.3 μg/mL). The crystal structure of the KpLpxH-compound 7 complex revealed its binding mode, validating virtual screening analysis. These studies establish acetylpiperazine derivatives as a new class of LpxH inhibitors and provide a foundation for future antibiotic development.

MsbA, a bacterial ABC transporter essential for lipopolysaccharide (LPS) transport, is a promising target for treating multidrug-resistant infections. However, developing potent MsbA inhibitors remains challenging. Recently, cerastecin C, representing a class of bivalent inhibitors targeting the MsbA dimer interface, demonstrated in vivo efficacy against multidrug-resistant Gram-negative bacteria, despite high plasma protein binding, by blocking LPS translocation essential for bacterial survival. In this study, we developed a bivalent molecular generative model, BL-INVENT, focusing on linker design to optimize the structure of cerastecin C. Several generative model designed compounds were synthesized and exhibited antibacterial activity. Further optimization led to the identification of compound 12, which showed enhanced potency and lower plasma protein binding compared with cerastecin C. These findings demonstrate an effective AI-driven strategy for the development of next-generation MsbA inhibitors.

Recent advancements in large-scale self-supervised pretraining have significantly improved molecular representation learning, yet challenges persist, particularly when addressing distributional shifts (e.g., under scaffold-split). Drawing inspiration from the success of Mixture-of-Experts (MoE) networks in NLP, we introduce H-MoE, a hierarchical MoE model tailored for molecular representation learning. Since conventional routing strategies struggle to capture global molecular information—such as scaffold structures, which are crucial for enhancing generalization—we propose a hierarchical routing mechanism. This mechanism first utilizes scaffold-level structural guidance before refining molecular characteristics at the atomic level. To optimize expert assignment, we incorporate scaffold routing contrastive loss, ensuring scaffold-consistent routing while preserving discriminability across molecular categories. Furthermore, a curriculum learning approach and dynamic expert allocation strategy are employed to enhance adaptability. Extensive experiments on molecular property prediction tasks demonstrate the effectiveness of our method in capturing molecular diversity and improving generalization across different tasks.

We have discovered a potent DYRK1A inhibitor Y16-5 by virtual screening and in vitro biological evaluation. This compound showed strong in vitro neuroprotective activity and favorable druglikeness.

Accurate assessment of drug combination risk levels is crucial for guiding rational clinical medication and avoiding adverse reactions. However, most existing methods are limited to binary classification, which fails to quantify distinctions between risk levels and struggles with imbalanced data distribution and insufficient semantic alignment of heterogeneous features. To address these challenges, we propose MSFCL, a drug combination risk level prediction based on multisource feature fusion and contrastive learning. MSFCL integrates molecular structural features extracted by TrimNet with high-order topological relationships captured via a graph convolutional network. To enhance feature robustness, we fuse Morgan fingerprint similarity matrices with identity matrix-based prior constraints. To tackle data imbalance issues, we design an adaptive gradient-noise hybrid perturbation strategy to dynamically balance gradient direction guidance and Gaussian noise injection, enabling contrastive learning without requiring data augmentation. In addition, we implement multihead attention mechanisms and residual connections to improve multisource feature alignment while label smoothing and focal loss functions sharpen the training objectives. Extensive experiments on three benchmark data sets demonstrated that MSFCL outperformed baseline methods across all evaluation metrics. Specifically, on the DDInter data set, MSFCL achieved an average improvement of 9.84% in accuracy, 14.97% in macro-F1, 11.91% in macro-recall, and 12.94% in macro-precision. MSFCL also demonstrated superior generalization in multiclass classification tasks on the DrugBank and MDF-SA-DDI data sets.

To date, the abuse of antibiotics and a gradual decline in novel antibiotic discovery enlarge the threat of drug-resistant bacterial infections, especially methicillin-resistant Staphylococcus aureus (MRSA). Herein, inspired by the unique structures and antibacterial activities of 2-quinolones, a class of novel 2-quinolones with substituted pyridines was synthesized. Notably, compound 11, the derivative with a methylpyridine fragment, showed potent antibacterial and antibiofilm activities, especially for MRSA strains (MIC = 0.02-0.04 mu g/mL). A mechanistic study of compound 11 revealed that the increase of intracellular ROS and acceleration of the TCA cycle, which reprogrammed the bacterial metabolism, eventually triggered membrane damage and bacterial death. Most importantly, compound 11, with antibacterial and anti-inflammatory properties, accelerated the reconstruction and healing of MRSA-infected cutaneous wounds by decreasing bacterial loads, attenuating inflammation, and promoting angiogenesis. Overall, these findings provide a novel multifunctional chemotype with broad-spectrum antibacterial activity and highlight a promising strategy for MRSA-infected wound healing.