AI and biotech
Accurate prediction of drug-target affinity (DTA) is crucial for accelerating drug discovery, but it remains a significant challenge. While deep learning methods have shown promise, many existing models struggle with representing long-range protein relationships within protein-protein interaction (P…
Background: Pancreatic ductal adenocarcinoma (PDAC) has one of the poorest treatment responses since it contains desmoplastic stroma, lacks good vascularity, and has high interstitial fluid pressures, which are the most damaging factors depriving chemotherapy. Liposomal doxorubicin is much better in…
Accurate prediction of protein-ligand bound poses and their affinities is essential in structure-based drug discovery. Here, we present an integrated deep-learning framework that disentangles the two core tasks─affinity estimation and pose evaluation─within complementary graph neural n…
Vascular and lymphatic vessel regeneration is crucial for tissue repair and organ function restoration. However, conventional biomaterials are often constrained by poor biocompatibility and unpredictable degradation behavior. Engineered short peptides, typically comprising 2-50 amino acids, offer a …
Small-molecule drug discovery requires balancing potency, selectivity, solubility, safety, and synthetic feasibility, among other interdependent properties. Yet most computational workflows address these properties sequentially or collapse them into fixed weighted scores. Although artificial intelli…
Peptide-based therapeutics show promising potential in treating a range of diseases, such as diabetes, cancer, and chronic pain. However, critical challenges, including peptide toxicity, immunogenicity, and stability deficiencies of peptides, have become major obstacles to their direct clinical appl…
Early-stage drug discovery often suffers from data scarcity and out-of-distribution (OOD) shifts, which constrain the reliability of predictive models. While deep learning has advanced representation learning from molecular and biological data, tabular modeling remains indispensable, particularly in…
The performance of machine-learning models in drug discovery is highly dependent on the quality and consistency of the training data. Due to limitations in data set sizes, many models are trained by aggregating bioactivity data from diverse sources, including public databases such as ChEMBL. However…
LiBRe: A Ligand-Aware Sequence-Based Binding Residue Prediction Model for Virtual Screening.
2026-03-19
Identifying protein-ligand binding residues is fundamental to unlocking molecular recognition and advancing therapeutic development. Sequence-based deep learning models for predicting protein-ligand binding residues have gained attention due to their scalability and ability to operate without relyin…
Accurately predicting the binding affinity between ribonucleic acid (RNA) and small molecules (RSMA) is crucial for RNA-targeted drug discovery, yet existing computational methods face challenges in fully leveraging multisource feature information and modeling complex interactions. To address these …
Accurate prediction of half-maximal inhibitory concentration (IC50) values is critical for accelerating drug discovery, yet traditional quantitative structure-activity relationship (QSAR) models often have limited ability to capture both local structural patterns and global physicochemical propertie…
Visceral leishmaniasis caused by Leishmania infantum remains a lethal disease with few therapeutic options, necessitating innovative computational methods and approaches to accelerate drug discovery. Here, we present a graph neural network (GNN) framework incorporating well-established multiscale me…
Drug discovery
Multiscale analysis and optimal glioma therapeutic candidate discovery using the CANDO platform.
2026-04-12
Glioma is a highly malignant brain tumor with limited treatment options. We employed the Computational Analysis of Novel Drug Opportunities (CANDO) platform for multiscale therapeutic discovery to predict new glioma therapies. We began by computing interaction scores between extensive libraries of d…
Gene editing
Prime editing has emerged as a precise and powerful genome editing tool, offering a favorable gene editing profile compared to other Cas9-based approaches. Here we report several nCas9-DNA polymerase fusion proteins and their engineered versions to create a simple and efficient two-component chimeri…
Immunotherapy
To characterize the magnetic resonance imaging (MRI) lesion dynamics, comorbidities, predictors of relapse, and outcomes in anti-γ-aminobutyric acid type A receptor (GABAAR) encephalitis, and assess the utility of LIM-domain-only-protein 5 (LMO5) antibodies as tumor markers….
Targeted drug conjugates (TDCs) have transformed cancer therapy by enabling selective delivery of cytotoxic agents, yet most existing designs rely on single-antigen targeting and single-payload architectures that limit efficacy in heterogeneous tumors and restrict opportunities for integrating ortho…
Immune checkpoint inhibitors (ICIs) are essential in advanced cancer treatments; however, they can cause severe immune-related adverse events (irAEs). Herein, we aimed to investigate the effectiveness of electronic patient-reported outcomes (ePROs) in monitoring the symptoms of patients with advance…
Programmed Cell Death Protein 1 (PD-1) / Programmed Cell Death Ligand 1 (PD-L1) inhibitors have revolutionized cancer immunotherapy but are limited by low response rates and drug resistance. Interleukin-2 (IL-2), a potent T-cell activator, is clinically restricted due to regulatory T cell (Treg…
Gene fusions generated by chromosomal rearrangements function as oncogenic drivers in human cancers. We previously showed that EWSR1-ETS oncofusions of Ewing sarcoma (EwS) directly induce surface expression of IL1 receptor accessory protein (IL1RAP), which along with limited expression in healthy ti…
The phase II axitinib plus avelumab trial in recurrent/metastatic adenoid cystic carcinoma (ACC) demonstrated favorable response rates and progression-free survival (PFS), leading to its inclusion in NCCN guidelines as the first immunotherapy-based option for ACC. We sought to identify biomarkers pr…
The potential of the immune system to decrease cancer progression is widely recognized and has led to the development of innovative anti-cancer immunotherapies. Here, we studied human macrophages derived from genetically engineered iPSCs (iMac) with angiotensin-converting enzyme (ACE) expression reg…
The endoplasmic reticulum (ER) is essential for protein folding, lipid metabolism, calcium homeostasis, and cellular stress signaling. Cancer cells endure chronic ER stress from elevated metabolic demands and oxidative conditions, adapting ER pathways to evade apoptosis, while promoting growth, surv…
Cancer immunotherapy has significantly advanced the field of oncology. However, effectiveness of immunotherapy remains limited by tumor heterogeneity, immune evasion, and immunosuppressive tumor microenvironments. Immunogenic cell death (ICD) and autophagy are two interconnected biological mechanism…
Longevity
Complete macroscopic tumor resection is the strongest prognostic factor in advanced epithelial tubo-ovarian and primary peritoneal cancer, yet benefit from maximum-effort cytoreductive surgery may vary with tumor distribution and site-specific resections. We aimed to identify predictors of long-term…
Mitochondria
Acute liver failure (ALF) represents a critical clinical challenge with limited therapeutic options beyond liver transplantation, urgently requires novel therapeutic strategies. Here, we show that a cinnamic acid derivative, CA7, confers significant protection in mouse models of ALF. The therapeutic…