Case Study

Novozymes Delivers Four Breakthrough Biofuels Products To Market in Half the Development Time

In 2017, Novozymes implemented Riffyn SDE to enable advanced lab automation, custom data processing and a revamped analytics pipeline in support of their advanced biofuels yeast product portfolio. This digital R&D infrastructure enhancement resulted in transformative workflows.


  • Contextualization of exponentially scaled data
  • Required data structure, context, integration, governance, and scalability
  • Shifting time spent on routine tasks to time spent critically analyzing and doing science


  • Slash product development time by 50%
  • Increase in strain build and screening throughput by an order of magnitude
  • Enhance real-time collaboration on experiment design and data analytics across sites

About the Project


5001-10000 Employees
Process Riffyn Addressed
Advanced lab automation and custom data processing for biofuels development

Technical Details

White biotechnology
Molecular biologyCell culture / ScreeningBioassays

Download the full case study

Get the PDF

As the saying goes, “with great risk often comes great reward.” It sounds cliché, but anyone responsible for industrial R&D is painfully aware that for any company to remain at the forefront of its field, it must take a leap of faith every now and then.

Novozymes, a global leader in biological solutions, recently took a leap of faith that provided substantial reward. At the core of this achievement was an innovative data analytics system harnessing wet lab automation in novel ways, a paradigm-shifting scientific process data system called Riffyn, and a dedicated group of researchers and data scientists that made it all work.


Turning data-driven research up a notch

Novozymes has a long history of data-driven research — and in 2015, the company further advanced their journey. The transformation began with a fluid ecosystem of data tools centered around a central data repository, the “Data Lake.” In parallel, Novozymes implemented and expanded wet lab automation capabilities that expanded exponentially the scale of data they needed to analyze. Quality and contextualization of this data were critical for success.

“We had to change how we were handling data and make it a more scalable and more efficient approach,” says Michael, Data Scientist at Novozymes. They found what they needed in a flexible tool that provided data structure, context, integration, governance, and scalability, all in one package: Riffyn Nexus.

In a radical departure from existing systems, such as ELNs or LIMS, Riffyn Nexus offered a process-centric approach to data capture, which could deliver data primed for advanced analytics and machine learning directly into the Data Lake through a seamless API.

To achieve game changing results — like cutting time to market in half — you must succeed in shifting time spent on routine tasks to time spent critically analyzing and doing science. Integrating Riffyn Nexus into Novozymes’ Data Lake-centered ecosystem enabled the yeast R&D teams to do just that – and the numbers speak for themselves.

“In the early strain construction phase, we realized an order of magnitude increase in build capacity, and in subsequent application screening flows we enabled a many-fold increase in bandwidth,” says Mads, Digital Officer, Biorefining and Feed R&D at Novozymes.


Dozens of improved yeast strains were identified in a Novozymes screening campaign using lab automation, Riffyn SDE, and the Novozymes data analytics pipeline.

Riffyn Nexus provided a framework to capture and harmonize people, process, terminology and data. Using Riffyn Nexus ensured that everybody was always looking at the same data. Scientists now spend more time analyzing results, making discoveries, and designing new experiments with significantly less time spent preparing data for analytics.

“The cross-functional communication gets the project moving along in such a way that the next experiment design is natural because we already discussed it. Many people have their eyes on the data enabling a well-informed decision,” adds Brianna, a researcher in the Biorefining R&D team.

Contextualizing experimental data with structured metadata also “future proofs” your experiments, says Ryan, Associate Data Scientist at Novozymes. “The data context and structure that Riffyn provides is a massive benefit for scientific research. It becomes a force multiplier by enabling the application of the data to new questions.”

In a world of incremental change, Novozymes’ decision to fully digitalize their R&D processes was a big step that paid off in the ways they expected and in many that they didn’t. Digitalizing their processes and democratizing their data have moved human capital away from time-consuming manual tasks and toward science and analysis — the real innovation behind a data-driven approach to R&D.

With their Riffyn-supported data ecosystem, Novozymes has further bolstered their decades-long inspiration to build a better tomorrow.

Download the full case study

Get the PDF