Altrove uses AI models and lab automation to create new materials

Innovation in the development of new materials has accelerated in recent years. A French startup called Altrove plans to participate in this innovation cycle. The deep tech startup has raised €3.7 million (about $4 million at current exchange rates). If you are interested in new materials development, you may have noticed that several groups have shared important breakthroughs with the research community when it comes to materials prediction. "Historically, research and development to find new materials has progressed very slowly over the past 50 years," Altrove co-founder and CEO Thibaud Martin told TechCrunch. An important starting point is - how can one predict whether materials made of some elements theoretically exist?

There are tens of thousands of possibilities when putting two different chemical elements together. When you want to work with three different elements, there are thousands of combinations. There are four factors you get millions of options. Teams at DeepMind, Microsoft, Meta or Orbital Materials have developed artificial intelligence models to overcome computational limitations and predict new materials that can exist in a stable state. "The last nine months are expected to produce more stable material than the last 49 years," Martin said. But solving this bottleneck is only part of the equation. When creating new materials, it's not enough to just know they exist. You must come up with the recipe.

“A recipe is not just about what you put together. This also applies to proportion, temperature, sequence and duration. So there are many factors, many variables involved in creating new materials," Martin said. Altrove focuses on inorganic materials, more specifically starting with rare earth elements. Market opportunities exist for rare earth elements because they are difficult to obtain, have highly variable prices, and often come from China. Many companies are trying to reduce their dependence on Chinese supply chains to avoid regulatory uncertainty.

Create automatic iteration loops

Instead of reinventing new materials, the company selects interesting candidates from all predicted new materials. Altrove then uses its own AI models to generate potential recipes for these materials.

Right now, the company tests these recipes one by one and produces a tiny sample of each material. Altrove then developed a proprietary characterization technology that uses an X-ray diffractometer to understand whether the output material is performing as expected.

"It sounds trivial, but it is actually very complex to examine what you do and understand why. Most of the time, what you end up doing is not exactly what you originally wanted," Martin said.

This is where Altrove shines, as the company's co-founder and chief technology officer, Jonathan Laulainen, has a PhD in materials science and is an expert in characterization. The startup owns intellectual property rights related to the representation.

When making new materials, learning from characterization steps to improve formulations is key. That’s why Altrove wants to automate its lab so more recipes can be tested simultaneously and the feedback loop can be accelerated.

"We wanted to build the first high-throughput method. In other words, pure prediction takes only 30% of the time to obtain materials that can actually be used industrially. The remaining 70% is related to repetitions from real life. That's why it's so important to have an automated lab because you increase throughput and you can run multiple experiments in parallel," Martin said.Altrove defines itself as a hardware-enabled AI company. It believes it will sell licenses for new production materials or work with third-party partners to produce them itself. The company raised €3.7 million in a funding round led by Contrarian Ventures, with participation from Emblem. Several business angels also invested in the startup, such as Thomas Clozel (Owkin CEO), Julien Chaumond (Hugging Face CTO) and Nikolaj Deichmann (3Shape founder).

The startup takes inspiration from biotech companies that use artificial intelligence to find new drugs and treatments, but this time for new materials. Altrove plans to have its automated laboratory ready by the end of this year and sell its first assets within 18 months.