A Danish startup Hoping to help R&D teams automate lab experiments that require visual inspection, it raised $20 million in Series A funding to expand its technology in the U.S.

Founded in Copenhagen in 2018, Reshape develops a robotic imaging system packed with software and artificial intelligence models that helps scientists track visual changes, such as color or cell growth rates, in petri dishes and petri dish-like formats. Its machines have built-in incubation capabilities that can be set to specific temperatures and record corresponding data to ensure experiments can be easily repeated.

The benefit is that these experiments can run 24/7 without direct supervision, freeing up technicians to perform other critical tasks.

Reshape's machine is running

Reshape’s machine is running Image Source:Reshape

“Decoding Nature”

The concept of “decoding nature” is at the heart of what Reshape aims to achieve, building on a wider trend where the lines between the natural and man-made worlds are blurring. Silicon Valley has not lost sight of these opportunities, as evidenced by the countless dollars being poured into technologies seeking to “engineer” biology.

“Biology as a whole is transitioning from a science to an engineering discipline, and I think one of the most important things we want to do is make some very ‘intangible’ things — how does an object grow, how does it behave? — easier to describe,” Reshape CEO Carl-Emil Grøn told TechCrunch. “Ideally, we want to figure out how to create a translation layer between what’s happening in the real world and what’s happening in the DNA.”

The genesis of Reshape was that Grøn, who has an engineering background himself, started dating someone who worked in the biotech industry, which gave him insight into the amount of physical labor involved in laboratory experiments.

“I just assumed biotech was mass-automated, but every eight hours a day for five months she had to go into the lab and take a picture of a petri dish,” Glenn said. “When you come from the tech world, it seems crazy.”

After talking to some local biotech companies in Copenhagen, Grøn realized that his initial experience wasn’t surprising: the way labs sequence DNA, measure chemical composition, and all the other stuff is still happening, more or less. It has been the same way for more than a century.

So Grøn recruited two co-founders, Daniel Storgaard and Magnus Madsen, and set out to build a full-stack platform, equipped with high-resolution cameras and lighting to capture visual data points and time-lapses and record the conditions of different components in a given environment. Experiments respond to the conditions in which they are exposed.

under the hood

Reshape has developed its own AI models, trained on in-house data in its own labs, and these models can be used from the outset for some of the more common types of experiments, such as those involving fungal or bacterial hosts, seeds, and insects. But the company can also help customers train models for specific use cases, such as tracking how specific microorganisms behave under specific conditions.

“The Reshape data science team used our custom MLops architecture to handle this end-to-end problem, starting from understanding the required outputs and quantifications, annotating the required datasets at scale, developing and benchmarking the models, and then deploying them on our of products for our customers,” says Grøn.

For example, agricultural companies can use Reshape to test seed germination rates or the severity of specific diseases. Alternatively, food companies can conduct ingredient characterization to test quality, freshness, or how ingredients mature over time—anything that typically requires visual assessment.

Remodeling: Growth detected in assay

Growth detected in assay Image Source:Reshape

Some Reshape customers are using the platform technology to transition from chemical pesticides to biopesticides—essentially finding out which new compounds work best and documenting how they are made. Speed ​​is ultimately the main attraction for customers.

“They will conduct four to ten times more experiments than before, which means they can bring products to market much faster,” Grøn said.

Reshape enables results to be viewed in a cloud-based interface, but the platform also supports data export in formats such as LIMS or CSV, allowing users to export data to other biotech software such as Benchling or even just Excel.

Results are presented via a cloud-based interface

Results are presented via a cloud-based interface Image Source:Reshape

In terms of accuracy, Grøn said it compared the base model to human performance in the same experiment, covering metrics such as false negatives. This helps avoid situations where an experiment might be cut short because scientists think it is ineffective.

“We’ve helped reduce false negatives by about 80 percent,” Grøn says. “We’ve also helped customers reduce the time it takes to get results. Instead of relying on remembering how an experiment was performed years ago, we can track it perfectly. So , every time you run an experiment on the platform, we track it; reproducibility is extremely important.”

In terms of business model, Reshape sells the entire platform, including hardware, machine learning and underlying software, on a subscription basis. Pricing uses a “value-based” pricing model, which may vary for each customer.

Currently, Reshape only offers one size of machine, which means that if customers conduct a large number of experiments, they must obtain a large number of machines. So in order to scale it up to large, industrial-scale experiments, Reshape will likely need a larger machine; Grøn remains somewhat coy on the matter, but he suggested they might “scale up” to larger equipment in the future.

Reshape's Imaging Machine

Reshape’s Imaging Machine Image Source:Reshape


Reshape, a graduate of Y Combinator (YC)’s Winter 2021 batch, has amassed a pretty impressive client list, including Swiss agtech giant Syngenta and the University of Oxford. Reshape, which has secured an additional $20 million in funding following an $8.1 million seed round last year, said it plans to use the new infusion of cash to expand its operations in the U.S., where it said it generates about two-thirds of its revenue. Already from the United States. Mainly from American factories for European customers.

“We’ve proven that our technology works—now we want to scale it up and help as many labs as possible accelerate biological transformation,” Glenn said.

Other companies are also bringing automation to science labs, including London-based Automata, which raised $40 million last year to work on broader lab workflows. Several companies offer products similar to what Reshape is trying to do, such as Singer Instruments’ Phenobooth and Interscience’s ScanStation.

But Grøn believes that this is what sets Reshape apart by providing a complete, full-stack platform with end-to-end data management capabilities.

“This is a costly problem that many companies have been trying to solve for a long time,” Glenn said. “We provide incubation, image capture and analysis in a closed-loop system. Our pre-trained models are ready for immediate use and require no time-consuming training.”

Reshape’s Series A round was led by European venture capital firm Astanor Ventures, with participation from YC, R7, ACME, 21stBio and Unity co-founder Nicholas Francis.

#Reshape #hopes #decode #nature #automating #visual #part #lab #experiments

Leave a Reply

Your email address will not be published. Required fields are marked *