A next-generation poultry health surveillance and diagnostic platform that combines single-tube multi-pathogen NGS, AI-driven genomic analysis, and cloud-based reporting to rapidly identify and characterize the major viral, bacterial, and protozoal pathogens affecting poultry.

The platform uses a single clinical sample to simultaneously screen for 30–50 pathogens, including respiratory and enteric pathogens, while also identifying virulence factors, antimicrobial-resistance (AMR) genes, pathogen strains, and vaccine versus field strains.

An automated cloud pipeline converts sequencing data into actionable veterinary intelligence — pathogen profiles, strain characterization, co-infection detection, AMR risk, farm-level risk scores, and AI-assisted recommendations. A longitudinal surveillance dashboard lets producers and integrators track pathogen trends, emerging variants, and outbreaks across farms.

A regional One Health platform for the surveillance, detection, genomic characterization, risk assessment, and early prediction of vector-borne diseases across Southeast Asia. It integrates data from mosquito vectors, humans, livestock, wildlife, and the environment with pathogen genomics, spatial-temporal analytics, and AI to understand how diseases emerge, spread, and evolve at the human–animal–environment interface.

Ongoing work in the Philippines, Laos, and across Southeast Asia is building an integrated surveillance network that combines field-based vector and sentinel-animal surveillance with molecular diagnostics, whole-genome sequencing, environmental and ecological data, and advanced analytics — identifying circulating pathogens and variants, mapping transmission hotspots, and developing early-warning signals for emerging outbreaks.

Starting with diseases such as Japanese encephalitis and other mosquito-borne infections, the platform is designed to evolve into a regional Pathogen and Vector Intelligence System for public health agencies, veterinary services, researchers, and communities.

Moving vector-borne disease control from reactive outbreak response to proactive, predictive prevention.

We combine digital pathology, AI, and clinical data to develop intelligent tools for cancer detection and diagnosis. Our current project uses deep-learning analysis of whole-slide histopathology images to predict key breast cancer biomarkers, supported by structured cancer data through the CMDN Cancer Database.

These capabilities can be applied across hospitals, pathology laboratories, pharmaceutical companies, and CROs to support automated image analysis, diagnostic decision support, biomarker assessment, and precision medicine.

Connecting clinical data, pathology, genomics, and AI to deliver smarter, scalable healthcare solutions.