How Mavatar aims to accelerate the path from research to patient

The company is built on 20 years of research in precision medicine, and scientists with backgrounds in molecular biology, bioinformatics, and AI develop the products.

– The core of our technology is DINA (Deep Integrated Network Analysis) – a proprietary data platform that integrates and analyses millions of research studies from around the world to understand how diseases arise, progress, and respond to treatment, says CEO Johan Juhlin.

DINA forms the foundation of their two platforms:

• Mavatar Discovery – their web-based research platform is already on the market. It helps researchers, pharmaceutical companies, and academia quickly identify biomarkers, drug targets, and disease mechanisms through advanced yet user-friendly data analysis.
• Mavatar Precision – their clinical platform launching in 2027. It is based on digital twin technology and provides clinical decision support by simulating how different treatments may work based on a patient’s unique biology.

Today, it often takes months or even years to move from large volumes of research data to true biological understanding. Data is scattered, difficult to compare, and requires advanced bioinformatics expertise – something many research environments lack.

What problems does your product/offer solve?

– With Mavatar Discovery, researchers, pharmaceutical companies, and academic institutions can quickly obtain meaningful, reproducible insights without having to build their own analysis pipelines. The platform makes it possible to:

• Identify new biomarkers and drug targets
• Understand disease mechanisms across multiple tissues and conditions
• Generate pilot data and hypotheses for research grant applications

– Another important aspect is that we use a strictly data-driven approach. Today, most research is based on what is already known in the literature or on experiments that have already been performed, which can often limit discovery. With a data-driven approach, we are not dependent on this, allowing us to uncover new findings and relationships that were previously not possible. In the long term, the same core technology – through Mavatar Precision – will support clinicians in making more accurate treatment decisions using digital twins. But right now, our focus is on giving researchers tools that truly accelerate their work today, says Johan Juhlin.

What kind of research are your products used for?

– Mavatar Discovery is used in early-stage drug discovery, biomarker identification, and systems biology studies. Researchers use it in areas such as oncology, infectious diseases, and more, but the technology is disease-agnostic – it can be applied to any well-defined disease. Because DINA technology integrates and analyzes data from millions of peer-reviewed studies worldwide, the platform can also provide valuable insights into rare diseases, where patient populations are often small, he says.

By combining data from multiple studies and tissues, Mavatar Discovery can reveal biological patterns and mechanisms that would otherwise be difficult to detect – thereby helping to drive research forward even in small or fragmented fields.

What sets your products apart from others on the market?

– What makes Mavatar unique is that we combine deep biological understanding with advanced, 100% data-driven analysis – in a way that is transparent, reproducible, and clinically relevant. At the core is our DINA technology, which analyzes all available peer-reviewed transcriptomic data globally and creates integrated, tissue- and disease-specific networks. The fact that the technology is 100% data-driven means it does not rely on assumptions but instead lets the data itself reveal patterns and relationships – resulting in objective and reliable outcomes, says Johan Juhlin.

In addition, Mavatar is developing digital twins – virtual models of patients and diseases that enable simulation of how different treatments might work before they are administered.

– This technology is unique in its kind and is built directly on DINA’s biological networks. While other tools require users to start from raw data, Mavatar Discovery begins where research really wants to begin – with biological context and pre-analyzed networks ready to explore. In short, we enable researchers and clinicians to go straight to insight – without coding, without delay, and with full traceability to the source, he says.

What are the biggest challenges within AI?

– One of the biggest challenges is that AI in life sciences must be interpretable, verifiable, and scientifically grounded. In medicine, it is not enough for a model to produce the right answer – we must understand why it does so. Today, many players use generative AI to create hypotheses or predictions, but these models often function as black boxes. That is not sufficient in research and healthcare. We cannot base medical decisions on something that cannot be explained or reproduced. That is why we built DINA differently. It is 100% data-driven, built on verified, peer-reviewed research, and delivers traceable and transparent results, says Johan Juhlin.

What are the biggest challenges in precision medicine?

– The biggest challenge in precision medicine is no longer collecting data – it is understanding it. We are drowning in biological information but starving for insight. Today, enormous amounts of knowledge are scattered across databases and publications, but few tools can weave it all together into something clinically useful. To achieve true precision, we must stop thinking in silos – research, healthcare, and the patient need to be connected through data that can communicate with itself. This is where AI- and data-driven technologies like Mavatar’s DINA play a crucial role: they can make the complex understandable and the individual accessible – at scale, he says.

What are your plans for 2026 and beyond?

– In 2026, we are focusing on scaling Mavatar Discovery globally, deepening collaborations with pharmaceutical companies, biotech firms, and academia, and expanding our commercial organization – both in Sweden and internationally. In parallel, we will initiate the first pilot projects with Mavatar Precision, our clinical decision-support platform based on digital twins, he says.

Over the next few years, the goal is to establish the digital backbone of precision medicine – an ecosystem that connects researchers, healthcare providers, and patients through data, insights, and innovation.

– For those who want to test how Mavatar Discovery works in practice, we offer free demos and trial periods so researchers can try it in their own work, Johan Juhlin concludes.