Altrove uses AI models and lab automation to create new materials | TechCrunch

Innovation in the development of new materials has been growing rapidly over the past few years. And a new French startup called Altrov plans to play a role in this innovation cycle. The deep tech startup has already raised €3.7 million (about $4 million at current exchange rates).

If you are interested in the development of new materials, you may have noticed that several teams have shared significant breakthroughs with the research community regarding materials prediction.

“Historically, over the past 50 years, research and development to find new materials has moved very slowly,” Thibaud Martin, co-founder and CEO of Altrov, told TechCrunch. “There have been many bottlenecks. And an important one is the starting point — how can you predict that a material made from a handful of elements could theoretically exist?”

When you combine two different chemical elements, there are thousands of possibilities. When you want to work with three different elements, there are thousands of combinations. With four elements, you get millions of possibilities.

Teams working for DeepMind, Microsoft, Meta or Orbital material Artificial intelligence models are being developed to overcome computational bottlenecks and predict new materials that may potentially exist in a stable state. “More stable materials have been predicted in the last nine months than in the previous 49 years,” Martin said.

But solving this bottleneck is only part of the equation. When it comes to creating new content, knowing that new content can exist is not enough. You have to find the recipe.

“A recipe is not just about what you mix together. It’s also about the ratios, what temperatures, what order, for how long. So there are a lot of factors, a lot of variables involved in how you make new materials,” Martin said.

Altrov is focusing on inorganic materials and more specifically rare earth elements, starting with them. There is a market opportunity here with rare earth elements because they are hard to source, pricing varies greatly and they often come from China. Many companies try to be less dependent on China as part of their supply chain to avoid regulatory uncertainties.

Creating automatic iteration loop

The company doesn’t invent new substances from scratch, but rather selects interesting candidates from all the new substances that have been predicted. Altrov then uses its own AI models to generate potential prescriptions for these substances.

Right now, the company tests these recipes one by one and produces a small sample of each material. After that, Altrov has developed a proprietary characterization technology that uses an X-ray diffractometer to understand whether the output material works as expected.

“It sounds like a simple thing, but examining what you’ve built and understanding why you did it is actually very complex,” Martin said. “In most cases, what you’ve built is not exactly what you initially wanted.”

This is where Altrove shines because the company’s co-founder and CTO Jonathan Laulainen has a PhD in materials science and is an expert in characterization. The startup has IP related to characterization.

When it comes to creating new materials, learning from the characterization step is crucial to improving your recipes. This is why Altrov wants to automate his lab so he can test more recipes at once and speed up the feedback loop.

“We want to create the first high-throughput method. In other words, pure prediction only takes you about 30% of the way to getting materials that can actually be used industrially. The remaining 70% involves replication in real life. That’s why having an automated lab is very important because you increase throughput and you can parallelize more experiments,” Martin said.

Altrove defines itself as a hardware-enabled AI company. It thinks it will sell licenses for its newly produced materials or create those materials itself with third-party partners. The company raised €3.7 million in a round Contrarian Ventures with Sign are also participating. Several business angels have also invested in the startup, such as Thomas Clozel (Okin CEO), Julien Chaumond (Hugging Face CTO) and Nicolaj Deichmann (3Shape founder).

The startup takes inspiration from biotech companies that have resorted to AI to find new drugs and treatments – but this time for new materials. Altrov plans to build its automated laboratory by the end of the year and sell its first property within 18 months.