# Genomics England Fuels Critical Genome Research

**Customer:** Genomics England

WEKA® NeuralMesh™ provides Genomics England with the multi-tiered architecture needed to combine commodity flash and disk-based technologies in a single unified platform solution.

## Results

- **5 Million** Genomes Targeted in Five Years
- **41 PB** Dataset in a Single Namespace
- **1.3 PB** High-Performing NVMe-Based Flash Storage

Organisation Overview

## Accelerating Medical Research and Discovery

[Genomics England](https://www.genomicsengland.co.uk/) (GEL) works in partnership with the United Kingdom's National Health Service (NHS) to administer its ambitious 100,000 Genomes Project, which aims to create the world's largest genomic database by gathering genomes from NHS patients with cancer or rare diseases and their families for analysis. Originally launched in 2014, the project's mission was expanded in 2018 with a target of processing an unprecedented 5 million genomes in five years to accelerate medical research and discovery. This landmark public health project is supported by a team of more than 3,000 scientific researchers and is expected to be processing a staggering 140 petabytes of DNA data by 2023.

The Challenge

## Reaching Scale and Performance Limits

Genomics England initially implemented a traditional scale-out NAS solution to support the original 100,000 Genome Project. However, the system was already reaching its scale and performance limits under the strain of the early project parameters.

With its sequencing targets expected to expand from one to 5 million genomes in just five years, Genomics England needed to upgrade its data infrastructure to scale to support the project's projected growth and provide the necessary performance to achieve the new target in an unprecedented amount of time.

Additionally, Genomics England's original data management solution had no viable disaster recovery strategy, leaving sensitive patient health data vulnerable if a security breach or disaster were to occur. Further, backing up the project's more than 20 petabytes (PBs) of data under management was not financially feasible.

The Requirements

## A Flexible, Secure, and Highly Scalable Data Management Solution

**The new solution needed to:**

- Scale capacity in a single namespace to support up to 140PBs of data
- Enhanced data pipeline performance to keep pace with research objectives
- Provide native disaster recovery and data encryption
- Improve cost efficiencies to support tight budget constraints

The Solution

##  NeuralMesh With Quantum ActiveScale Object Storage

NeuralMesh provides Genomics England with the multi-tiered architecture needed to combine commodity flash and disk-based technologies in a single unified platform solution. The primary tier consists of 1.3 PBs of high-performing NVMe-based flash storage to support its researchers' working datasets. The secondary tier consists of 40 PBs of object storage to provide a long-term data lake repository.

NeuralMesh presents Genomics England's entire 41 PB dataset in a single namespace and provides automated data tiering to optimize workload performance and provide better cost efficiency.

NeuralMesh presents Genomic England’s entire 41 PB dataset in a single namespace and provides automated data tiering to optimize workload performance and provide better cost efficiency.

![Genomics England infrastructure diagram with a flash tier, data lake, and application cluster](https://cdn.sanity.io/images/ult5g8gw/production/36d6464edef8334de54bea7282b7e90a852953fb-1027x543.png)

> We needed something that’s much more scalable than existing NAS solutions — an infrastructure that could grow to hundreds of petabytes. Our existing solution couldn’t provide that scale and wasn’t performing as well in these magnitudes — that’s what drove us to NeuralMesh.
>
> — David Ardley, Director of Infrastructure Transformation • Genomics England

The Outcomes

## Accelerating Innovation at Infinite Scale

- Infinite scale to support exponential data growth
- Massive performance improvements to accelerate innovation
- Faster data processing and time to insight
- Significantly improved cost efficiency per genome
- Enhanced security with disaster recovery in place
- Cloud integration for computing elasticity and data mobility

[Download PDF](https://cdn.sanity.io/files/ult5g8gw/production/288228d58d0d8bd6e7a704d6d98b44c71babba3b.pdf)