Clear Labs: Disrupting food safety testing with Google Cloud Platform

About Clear Labs

Clear Labs offers the only automated, intelligent next-generation sequencing platform built for food safety testing. Forbes magazine named it one of the 25 most innovative agtech startups of 2018. The company was founded in 2014, has 50 employees, and is headquartered in Menlo Park, California.

Industries: Technology, Healthcare & Life Sciences
Location: United States

Clear Labs is delivering pathogen test results to enterprise food producers in hours instead of days by leveraging Google Cloud Platform services including Google Pipelines API and Compute Engine.

Google Cloud Results

  • Processes terabytes of sequencing data efficiently
  • Scales as needed to support increased processing loads
  • Saves an estimated 20% in infrastructure costs compared to competitive cloud service

Delivers test results in hours not days

Every year, contaminated food sickens one in six Americans, according to the Centers for Disease Control and Prevention. Food safety awareness is on the rise, as nearly every week brings news of Salmonella outbreaks or food product recalls. No surprise, then, that the global food safety testing market is expected to grow to $17.7 billion by 2021, BIS Research reports.

Enter Clear Labs. The Menlo Park, California-based company’s latest offering, Clear Safety, is the first Next-Generation Sequencing (NGS) platform to cost-effectively perform fast, highly accurate, high-volume pathogen tests.

Clear Safety includes cloud software for laboratory management and genetic analysis as well as a fully integrated sample test device deployed at Clear Safety customer locations. The remote device combines Robotic Liquid Handling and DNA Sequencing into a single, fully automated self-service entity. “We’re helping large food companies improve the safety of their food by enabling them to test for pathogens with greater accuracy and faster turnaround time,” says Henrik Gehrmann, Head of Engineering for Clear Labs. “What we’re offering is a game changer for this industry, and ultimately for consumers.”

Technologically speaking, Clear Safety is an ambitious offering that requires a robust infrastructure. For example, with Clear Safety, hundreds of pathogen samples are tested in parallel in a single test run, which means the platform must expediently process terabytes of data per test run. The resulting files are optimized to make them smaller, usually in the hundreds of megabytes, so they can be sent efficiently through Clear Labs’ custom-built bioinformatics analytics pipeline (bio-pipeline). The bio-pipeline consists of multiple, process-intensive steps such as alignment, error correction, and pattern matching, in which sample DNA strains are analyzed and compared to detect pathogens such as Salmonella.

“Google Cloud Platform gives us the infrastructure to scale and quickly process a huge amount of data. No other cloud provider comes close.”

Henrik Gehrmann, Head of Engineering, Clear Labs

To power its product, Clear Labs chose Google Cloud Platform (GCP). “GCP is the only solution that makes it easy to set up a robust environment from scratch and to scale it quickly, that widely supports open source software, and provides super-fast processing power — all at a lower cost than its competitors,” Henrik says.

Clear Labs uses the Google Pipelines API to efficiently process huge volumes of genomic data; Compute Engine as a high-performance virtual machine infrastructure to run its bioinformatics pipeline and Google Kubernetes Engine to run and manage the company’s services and app; Cloud Pub/Sub as a foundation for stream analytics; Cloud SQL for managing databases; and Cloud Storage for unified object storage.

Starting from scratch with ease

From the beginning, Henrik and colleagues were impressed with how easy GCP made it to set up the infrastructure for Clear Safety. “Unlike the other cloud platform that we considered, GCP does a great job of integrating its services, and that makes it so much easier to set up a new environment,” Henrik says. “That’s really important, especially when you have limited resources to build an infrastructure from scratch.”

Henrik adds, “There’s quite a bit of complexity involved in managing all the different pieces we need to make our product work. Having worked with competing cloud providers and briefly reviewing GCP two to three years ago, we had several concerns about managing the operational complexity of such a system. However, we quickly discovered that Google’s offering had advanced on seismic levels since then. We can focus on building enterprise-level software with a solid architecture behind it. At the end of the day, we’re in the business of analyzing food and improving food safety. We’re not in the business of managing infrastructure or building data centers around the world.”

“We compared Google Cloud Platform to a close competitor in terms of price, and we estimate that running our bioinformatics pipeline on Google Cloud Platform costs about 20% less. This is a big plus for us.”

Henrik Gehrmann, Head of Engineering, Clear Labs

Scaling as needed

With GCP, Clear Labs has the flexibility to spawn new virtual machine instances on demand to handle increased use of the company’s bio-pipeline. “Google Cloud Platform gives us the infrastructure to scale and quickly process a huge amount of data,” Henrik says. “No other cloud provider comes close.”

A key GCP benefit is the ability to spin up and orchestrate extremely powerful virtual machine instances in Compute Engine of up to 160 vCPUs and 3.75TB of system memory. “Processing speed is an essential component of our business because our bio-pipeline requires a lot of processing power, along with the ability to easily scale,” according to Henrik. “In our tests, our bio-pipelines run faster and more efficiently on GCP than on the other cloud infrastructure we tested.”

The processing power behind GCP plays a leading role in helping Clear Labs dramatically reduce test result sampling times for its customers. “Using Clear Safety, our customers can receive accurate and detailed pathogen test results in under 24 hours,” says Henrik. “That gives us a big competitive edge.”

Leveraging open source software

A strong commitment to open source software is another key differentiator for Google and GCP at Clear Labs. For example, Google has created more than 2,000 open source projects including Kubernetes and many APIs. “Because of my experience in software development, I’ve always been a big proponent of open source software,” says Henrik. “The support for open source is a big part of the attraction to Google. It’s in the Google DNA (no pun intended). And that open source commitment gives companies like us comfort that the infrastructure we build with GCP will be future-proof.”

“Google Cloud Platform has enabled us to create a system that is implicitly secure, saving valuable development time, alleviating potential vulnerabilities, and reducing overall risk.”

Henrik Gehrmann, Head of Engineering, Clear Labs

Saving money

Scaling on demand helps Clear Labs hold down its cloud infrastructure costs. “With GCP, we don’t waste money on infrastructure resources that just sit there, waiting to handle an increase in demand,” Henrik says.

GCP also helps Clear Labs save money in other ways. “We compared Google Cloud Platform to a close competitor in terms of price, and we estimate that running our bioinformatics pipeline on Google Cloud Platform costs about 20% less,” adds Henrik. “This is a big plus for us.”

Achieving peace of mind

The more secure-by-design infrastructure of GCP gives the Clear Labs team peace of mind. “With all the progressive layers built in, we implicitly trust the security that GCP gives us across hardware, user identities, storage, services, and everywhere else,” adds Henrik. “Google Cloud Platform has enabled us to create a system that is implicitly secure, saving valuable development time, alleviating potential vulnerabilities, and reducing overall risk.”

Google has been a valued cloud provider for Clear Labs both in terms of assisting with setting up its infrastructure as well as helping the company move forward in the future.

“We were able to build a solid infrastructure with GCP in a very short timeframe,” Henrik says. “Along the way, we had direct contact with Google engineers and architects, who helped us understand the features and capabilities currently available with GCP and get an idea of what’s coming in the future. The level of support Google gives us is tremendous.”

Clear Labs has big ambitions. Plans include expanding the ability of the Clear Safety platform to test samples for E.coli, Listeria, Campylobacter and other pathogens, to expand its cloud feature to track origination of pathogens and predictive capabilities, and to offer its platform to domestic as well as international customers. The company is also investigating how to employ Cloud Machine Learning Engine to deliver even more value to customers.

“GCP helped us get off the ground quickly, not just running but jumping,” Henrik says. “And it’s going to be a key partner for us to expand and scale our system in the future, so we can keep jumping without missing a beat.”

About Clear Labs

Clear Labs offers the only automated, intelligent next-generation sequencing platform built for food safety testing. Forbes magazine named it one of the 25 most innovative agtech startups of 2018. The company was founded in 2014, has 50 employees, and is headquartered in Menlo Park, California.

Industries: Technology, Healthcare & Life Sciences
Location: United States
Google Cloud Platform logo

12 Months FREE TRIAL

Try Kubernetes Engine, BigQuery, and other Cloud Platform products with $300 in free credit and 12 months.

TRY IT FREE
Google Cloud Platform logo

12 Months FREE TRIAL

Try Kubernetes Engine, BigQuery, and other Cloud Platform products with $300 in free credit and 12 months.

TRY IT FREE