The Platform for Population Genomics

Optimized through 20 years of experience

Built for scale, speed, and security

The core of WuXi NextCODE’s platform is our proprietary Genomically Ordered Relational database (GORdb).  Proven over more than two decades, with extensive testing and input from our partners, GORdb is developed specifically to be scalable and efficient for genomics in today’s big data world.  GORdb can be easily used with your own software and databases to provide faster and even more advanced analysis capabilities. The GORdb is fully interoperable with your existing cloud, and other data sources.

Scale from patients to cohort to populations

Query 100,000 whole-genome dataset in seconds. Our platform was built for populations and scales to conduct your analysis faster with more power and computational efficiency.

Speed to uncover insights

Ask the questions you want and get the answers you need. Integrated view of your data extendable to global reference data. Quickly identify and validate biomarkers, solve cases, and uncover new genomic insights.

Anywhere, any time

Access your data across the globe in a secure Cloud. Collaborate with colleagues and partners on one common platform with full control of your data privileges.

Flexible and interoperable

Our platform works with your existing tools and solutions.

DNA sequence


Our genomically ordered relational database (GORdb) uses the world’s most scalable and efficient architecture for genomic data. Similar to BAM files, GOR follows and leverages the genome’s own structure. Whether you are delivering healthcare or managing a worldwide clinical trial, GOR gives you unrivaled capabilities for deriving the full value from all your sequence data.


Purpose-built for translational research, the GOR API gives bioinformaticians the power to ingest and query NGS data at biobank scale. Petabyte-performant speedTM is made possible by GOR’s genomically-ordered, yet index-free nature.

Learn more
Tom Chittenden, WuXi NextCODE executive


Our DeepCODE variant detection model is based on deep learning of known molecular annotations.  Annotation is obtained from CADD (the Combined Annotation Dependent Depletion) data and UCSC exonic coordinate regions.  The deepCODEscore is a statistical probability measure of “functional biological relevance” of missense changes in protein coding sequences.

Learn more


WuXi NextCODE has partnered with leading cloud services providers to ensure you have the utmost flexibility, speed, and storage capacity for managing all of your data. We partner with Google Cloud, AWS, Microsoft Azure, NetApp, and Alibaba for all your cloud needs.