The past few years have seen an acceleration of innovation in new materials development, and French startup Altrove is set to play its role in this innovation cycle. The deep tech startup has already raised 3.7 million euros (about $4 million at current exchange rates).
If you are interested in developing new materials, you may have noticed that several teams have shared important breakthroughs with the research community when it comes to materials prediction.
“Historically, over the last 50 years, research and development to find new materials has moved at a very slow pace,” Altrove co-founder and CEO Thibaud Martin told TechCrunch. There have been a few bottlenecks, and one of the key ones is the starting point: how can we predict whether a material made of a small number of elements could theoretically exist?
When you combine two different chemical elements, there are tens of thousands of possibilities. When you use three different elements, there are tens of thousands of combinations. With four elements, there are millions of possibilities.
Teams including DeepMind, Microsoft, Meta, and Orbital Materials are developing artificial intelligence models to overcome computational constraints and predict new materials that may exist in stable states. “More stable materials have been predicted in the last nine months than have been predicted in the last 49 years,” Martin said.
But solving this bottleneck is only part of the equation: knowing that a new ingredient might exist isn't enough to make the new ingredient; you have to come up with a recipe.
“A recipe isn't just about putting things together. It's about proportions, temperatures, sequences, times — so there are a lot of factors, a lot of variables involved in how you create a new ingredient,” Martin says.
Altrobe is focused on inorganic materials, specifically starting with rare earth elements. There is a market opportunity here because rare earth elements are difficult to source, have high fluctuations in price and often come from China. Many companies are looking to reduce their reliance on China as part of their supply chain to avoid regulatory uncertainty.
Creating automated repetitive loops
Rather than inventing new ingredients from scratch, the company selects interesting candidates among all predicted new ingredients. Altrove then uses its proprietary AI models to generate potential recipes for these ingredients.
Now the company is testing these recipes one by one, producing small samples of each material. Altrobe has then developed a proprietary characterization technique using an X-ray diffractometer to understand whether the output material performs as expected.
“It sounds like a small thing, but it's really complicated to actually check what you've made and understand why, and most of the time what you've made isn't exactly what you were looking for in the first place,” Martin said.
Altrove shines because its co-founder and CTO, Joonathan Laulainen, has a PhD in materials science and is an expert in characterization, and the startup owns IP related to characterization.
When making new materials, it's important to learn from the characterization step to improve the recipe, so Altrove wants to automate its lab to test many recipes at once and speed up the feedback loop.
“We want to build the first high-throughput method. In other words, pure prediction only gets you 30% of the way to getting materials that can actually be used in industry. The other 70% is repetitive work in real life. That's why having an automated lab is important, because it increases throughput and allows you to parallelize more experiments,” Martin said.
Altrove describes itself as a hardware-enabled AI company. The company envisions selling licenses for its newly manufactured materials or manufacturing the materials in-house in collaboration with third-party partners. The company raised €3.7 million in a round led by Contrarian Ventures with participation from Emblem. Several business angels also invested in the startup, including Thomas Clozel (CEO of Owkin), Julien Chaumond (CTO of Hugging Face) and Nikolaj Deichmann (Founder of 3Shape).
The startup is inspired by biotech companies that use AI to discover new drugs and treatments, but this time it's focusing on new materials. Altrobe plans to build the automated lab by the end of the year and sell its first assets within 18 months.