Pulmonology

SHEST: Single-cell-level artificial intelligence from haematoxylin and eosin morphology for cell type prediction and spatial transcriptomics reconstruction

A comprehensive understanding of cancer progression requires integrating tissue morphol-ogy with spatial molecular profiles. We present SHEST, a multi-task profiling framework that leverages haematoxylin and eosin morphology to predict cellular composition and re-construct spatial gene expression at single-cell resolution. SHEST employs a quadruple-tile input capturing nuclear and contextual infor...

SARS-CoV-2 Variant-Dependent Alterations in Nasopharyngeal Microbiota and Host Inflammatory Response

The SARS-CoV-2 pandemic saw multiple outbreaks occur over short periods. This was linked to the virus’s high infectivity and rapid mutation rate, which hindered the development of effective treatments and a comprehensive understanding of COVID-19 pathophysiology. The nasopharyngeal tract, the main entry site of SARS-CoV-2, interacts with angiotensin-converting enzyme 2 (ACE2) receptors via the vir...

Sequence-aware Prediction of Point Mutation-induced Effects on Protein-Protein Binding Affinity using Deep Learning

Amino acid mutations may lead to significant changes in the binding affinity of protein complexes, thereby causing a series of cellular dysfunctions. ...

An integrated platform for high-throughput phenospace learning of 3D multilineage organoid systems

Complex multilineage organoid systems lack quantitative phenotyping methods preserving spatial architecture at high throughput. Current approaches com...

Using Large Language Models to Assemble, Audit, and Prioritize the Therapeutic Landscape

We present an AI-assisted pipeline for disease-specific drug landscape analysis. Given a disease name, the system assembles a comprehensive, evidence-...

Self-supervised AI reveals a lethal discohesive phenotype in lung adenocarcinoma

Applications of artificial intelligence (AI) to histopathology are now common, but most require supervision which inherently limits their scope. By us...

Diffusion Models vs. DCGANs for Class-Imbalanced Lung Cancer CT Classification: A Comparative Study

Effective lung cancer detection from CT scans remains critically challenged by class imbalance where benign and normal cases are underrepresented, lea...

Comparative Single-Cell Transcriptomics Uncovers Shared and Distinct Molecular Signatures in Cystic Fibrosis and Primary Ciliary Dyskinesia

Cystic Fibrosis (CF) and Primary Ciliary Dyskinesia (PCD) are both inherited respiratory disorders that result in impaired mucociliary clearance, and ...

GenVS-TBDB: A Target-Aware AI-Generated and Virtual-Screened Small-Molecule Library for Tuberculosis Drug Discovery

Tuberculosis (TB) remains a leading global health threat, with over 10 million new cases and 1.25 million deaths reported in 2023. Current TB therapie...

Machine Learning Reveals Proteome-Encoded Growth Predictors of Rhodopseudomonas palustris CGA009 on Lignin Aromatics

Microbial utilization of lignin-derived aromatics requires extensive metabolic flexibility, yet growth outcomes vary sharply with substrate chemistry ...

ROSIE-Enabled Spatial Mapping Reveals Architectural Fragmentation and Immune Reprogramming in Lung Adenocarcinoma Evolution

The progression of lung adenocarcinoma (LUAD) from precancerous lesions to invasive carcinoma entails extensive remodeling of tissue architecture and ...

Redefining the topology of the human bone marrow using augmented spatial transcriptomic analysis

The bone marrow (BM) is the main site of haematopoiesis in adult life. Our understanding of the pathogenesis of BM-derived blood cancers is limited by...

AI-based Predictive Signaling Pathway Profiling in Cardiac Fibrosis Suggests a Novel Combinatorial Treatment Strategy

Cardiovascular disease (CVD) remains the leading cause of global mortality, with myocardial fibrosis characterized by excessive extracellular matrix (...

Closing the Sim-to-Real Gap: An End-to-End Robotic Ultrasound System Leveraging In Vivo Reinforcement Learning and 3D-Prior Guided Hybrid Control

Abdominal ultrasound is a crucial first-line diagnostic tool, yet its efficacy is inherently constrained by a strong dependency on operator skill, lea...

RamanOmics Decodes Spatial Vibrational-Molecular Architecture and Rewiring in Aging and Repair

Aging and tissue repair involve multilayered and spatially heterogeneous remodeling across transcriptional, biochemical, and cellular dimensions, yet ...

Phenotypic Screening Coupled with AI-Driven Target Deconvolution Identifies α-Terthienyl as a Dual DPP-IV/HSD17β13 Modulator with Efficacy in a Mouse Model of MASLD

Metabolic dysfunction-associated steatotic liver disease (MASLD) is a highly prevalent condition characterized by fat build-up in the liver and ranges...

A Druggable Tumor Suppressor and Leukemic Stem Cell Marker

Acute myeloid leukemia (AML) often enters remission after chemotherapy but frequently relapses due to chemotherapy-resistant leukemic stem cells (LSCs...

Airborne Nanoplastics Perturb Mitochondrial Complex I via the ND6 Axis: Polymer-Specific Mitoepigenetic Remodeling Integrating Experimental, In Silico, and Machine Learning Analyses

Airborne nanoplastics constitute an emerging class of environmental contaminants, but their mitoepigenetic effects on human immune cells have not been...

Protocol for the development and validation of machine-learning models for predicting the risk of hypertriglyceridemia in critically ill patients receiving propofol sedation using retrospective data

Propofol is a widely used sedative-hypnotic agent for critically-ill patients requiring invasive mechanical ventilation (IMV). Despite its clinical be...

Care Phenotypes In Critical Care

The Social Determinants of Health (SDoH) have long been recognised as significant drivers of health inequalities. Within healthcare settings, large EH...