Biology subjects

Nguyen, A. T. N.

Publications and source records attributed to Nguyen, A. T. N..

4 recordsLinked to original sources

bioRxiv2026

Bioactivity foundation model for hit identification and hit-to-lead optimization from sequence data

Learning from large-scale bioactivity archives is complicated by heterogeneous assay readouts and differences in data reliability. Here we show that a model that predicts probability distributions over binding affinities from sequence data opens model training to vast and diverse troves of heterogeneous bioactivity data. We develop PSICHIC+, a bioactivity foundation model trained on approximately 82 million protein-ligand records using a distributional objective that preserves quantitative resolution while incorporating variation in data reliability. Given a protein sequence and ligand SMILES, PSICHIC+ predicts binding affinity in milliseconds. In zero-shot virtual-screening benchmarks without target-specific training data, it improves enrichment over regression- and classification-based approaches and performs competitively with leading structure-based methods. In lab-in-the-loop campaigns, distribution-guided acquisition improves recovery of high-activity compounds under fixed screening budgets. Combining PSICHIC+ with Boltz-2 improves hit-to-lead affinity prediction over Boltz-2 alone, with mean correlation approaching that of FEP+ on the evaluated benchmarks, without requiring high-resolution protein structures. These results support distributional learning as a scalable approach to using heterogeneous bioactivity data for hit identification and hit-to-lead optimization.

bioinformatics↗

bioRxiv2025

Molecular basis of ligand binding and receptor activation at the human A3 adenosine receptor

Adenosine receptors (ARs: A1AR, A2AAR, A2BAR, and A3AR) are crucial therapeutic targets, yet developing selective, efficacious drugs remains challenging. Here, we present high-resolution cryo-electron microscopy (cryo-EM) structures of the human A3AR in three distinct functional states: bound to the endogenous agonist adenosine, the clinically relevant agonist Piclidenoson, and the covalent antagonist LUF7602. These structures, complemented by mutagenesis and pharmacological studies, reveal a unique A3AR activation mechanism involving an extensive hydrogen bond network from the extracellular surface down to the orthosteric binding site. In addition, we identify a cryptic pocket that accommodates the N6-iodobenzyl group of Piclidenoson through a ligand-dependent conformational change of M1745.35. Our comprehensive structural and functional characterization of A3AR advances understanding of adenosine receptor pharmacology and establishes a foundation for developing more selective therapeutics for various disorders including inflammatory diseases, cancer, and glaucoma. TeaserStructures of the A3AR in different conformations reveal a unique activation mechanism and cryptic binding pocket.

pharmacology and toxicology↗

bioRxiv2023

PSICHIC: physicochemical graph neural network for learning protein-ligand interaction fingerprints from sequence data

In drug discovery, determining the binding affinity and functional effects of small-molecule ligands on proteins is critical. Current computational methods can predict these protein-ligand interaction properties but often lose accuracy without high-resolution protein structures and falter in predicting functional effects. We introduce PSICHIC (PhySIcoCHemICal graph neural network), a framework uniquely incorporating physicochemical constraints to decode interaction fingerprints directly from sequence data alone. This enables PSICHIC to attain first-of-its-kind emergent capabilities in deciphering mechanisms underlying protein-ligand interactions, achieving state-of-the-art accuracy and interpretability. Trained on identical protein-ligand pairs without structural data, PSICHIC matched and even surpassed leading structure-based methods in binding affinity prediction. In a library screening for adenosine A1 receptor agonists, PSICHIC discerned functional effects effectively, ranking the sole novel agonist within the top three. PSICHICs interpretable fingerprints identified protein residues and ligand atoms involved in interactions. We foresee PSICHIC reshaping virtual screening and deepening our understanding of protein-ligand interactions.

bioinformatics↗

bioRxiv2020

A novel equilibrative nucleoside transporter 1 inhibitor alleviates Tau-mediated neurodegeneration

Tau hyperphosphorylation favors the formation of neurofibrillary tangles and triggers the gradual loss of neuronal functions in tauopathies, including Alzheimers disease. Herein, we demonstrated that chronic treatment with an inhibitor (J4) of equilibrative nucleoside transporter 1 (ENT1), which plays a critical role in controlling adenosine homeostasis and purine metabolism in the brain, exerted beneficial effects in a mouse model of tauopathy (Thy-Tau22, Tau22). Chronic treatment with J4 improved spatial memory deficits, mitochondrial dysfunction, synaptic plasticity impairment, and gliosis. Immunofluorescence assays showed that J4 not only reduced Tau hyperphosphorylation but also normalized the reduction in mitochondrial mass and suppressed the abnormal activation of AMP-activated protein kinase (AMPK), a pathogenic feature that is also observed in the brains of patients with tauopathies. Given that AMPK is an important energy sensor, our findings suggest that energy dysfunction is associated with tauopathy and that J4 may exert its protective effect by improving energy homeostasis. Bulk RNA-seq analysis revealed that J4 also mitigated immune signature associated with Tau pathology including C1q upregulation and A1 astrocyte markers. Collectively, our findings suggest that identifying strategies for normalizing energy and neuroimmune dysfunctions in tauopathies through adenosinergic signaling modulation may pave the way for the development of treatments for Alzheimers disease.

neuroscience↗