Durham’s Snthesis Smooths The Path Between Data Collection And Analysis

Emerson Huitt (top left) leads Durham's Snthesis.

Being organized is important. For a scientist running experiments in a lab, keeping track of the 100,000 samples that can be done per day is a headache. And worse, spending time organizing that massive amount of data takes precious time away from the actual science.

Emerson Huitt observed this problem firsthand working in a lab for a vaccine research company, and he used his 15 years of background in developing software to solve it.

In 2018, Huitt founded Durham-based Snthesis, a SaaS startup that uses automated tools to aggregate and sort data, thereby speeding and smoothing the path between data collection and data analysis. 

“What Snthesis boils down to is a mechanism to enable any organization that’s generating large quantities of data to turn that data into a searchable database that enables you to quickly gain insight into what’s happening in your business or research workflow,” Huitt said. 

Current data management processes in the life sciences industry are laborious and ripe for disruption, Huitt said. The increasing reliance on automated processes in the last 10 years means scientists can collect up to 100,000 samples a day rather than, say, 100, Huitt said. 

“So there’s a huge amount of data flowing through these discovery pipelines now,” Huitt said, “but it’s not well-curated and it’s not easy to analyze. And a lot of that data still ends up being in spreadsheets, unfortunately, even at very large institutions.”

Snthesis aggregates data in real time, whether the source is Excel spreadsheets, automated lab instruments, handwritten notes or even thousands of spreadsheets created by different people over many years. Automated tools are used to classify the data, and after the Snthesis Comprehension Engine accounts for any anomalies or validation problems in the data, the bulk of the data is processed by the system so scientists do not have to touch it until they need it for analysis.

Unlike many of its competitors, whose software may require users to classify their data before inputting it, Snthesis captures all the data that is generated at the onset, and users can sort it out later if needed.

“So scientific time is free to focus on analysis and areas where there are problems that the machines can’t automatically figure out,” Huitt said. 

Snthesis’ current customers are large-scale life science enterprises in the Triangle. While that industry is their primary focus right now, Huitt said they are having conversations with companies in other industries and plan to expand in the near future. For example, Huitt said investigative law enforcement agencies also collect massive amounts of data and could benefit from the fully searchable database created by Snthesis’ software.

In February, Snthesis released a General Availability commercial version of the software for the general marketplace. 

Since being founded in late 2018, Snthesis has generated about $2 million in revenue, which they hope to double by the end of the year, Huitt said.

Huitt said they are in an unusual position for startups because they have been completely bootstrapped and revenue-funded since opening their doors to customers in 2019. Eventually they will raise growth funding, but for now Huitt said they are taking advantage of the fact that they can focus on creating transformative software without worrying about delivering immediate results to investors.

“The majority of investment activity in software, at least in the Triangle area, has historically been for quick turnarounds and the problem that Snthesis solving is a big problem, it’s a hard problem,” Huitt said. “And so right now we’re kind of very happy to be revenue-funded because that gives us the freedom to solve that problem in a way that we think is most effective for the long term.”