ProQR Therapeutics has cracked a major bottleneck in AI-powered drug discovery by partnering with Ginkgo Bioworks to automate the experimental data generation that trains AI models. The partnership, announced in April 2026, pairs ProQR's artificial intelligence models for RNA editing with Ginkgo's autonomous laboratory system, enabling the biotech company to accelerate the discovery of new medicines based on its proprietary Axiomer RNA editing technology .

The collaboration addresses a fundamental challenge in AI drug discovery: while machine learning models can predict promising drug candidates quickly, generating the experimental data needed to train and validate those models has remained slow and labor-intensive. Ginkgo's 50-plus instrument autonomous laboratory, called Nebula, removes this constraint by dramatically increasing the speed and scale of data generation .

Why This Partnership Matters for RNA Medicine Development?

ProQR has spent the last 18 months developing an AI model that significantly accelerates and improves the discovery of editing oligonucleotides, which are short RNA molecules designed to correct disease-causing mutations. The company's Axiomer platform uses a cell's own molecular machinery called ADAR (Adenosine Deaminase Acting on RNA) to make precise single-nucleotide edits in RNA, potentially correcting mutations or modulating protein expression to treat disease .

Without access to high-throughput experimental data, even the best AI models hit a wall. By integrating Ginkgo's autonomous lab capabilities, ProQR can now feed its AI system with vastly more experimental results, allowing the models to learn patterns faster and make better predictions about which RNA edits will work in real patients. This creates a virtuous cycle: better data leads to better predictions, which leads to better drug candidates .

"Over the last 18 months we have developed an AI model that leads to significant acceleration and improvement of editing oligonucleotides in drug discovery," said Daniel A. de Boer, Founder and Chief Executive Officer of ProQR. "We're pleased to have announced the partnership with Ginkgo Bioworks, providing us access to their state-of-the-art autonomous lab enabling high throughput data generation to further scale up our AI-enabled drug discovery."

Daniel A. de Boer, Founder and Chief Executive Officer of ProQR Therapeutics

How to Understand ProQR's AI-Driven Discovery Timeline?

• Current Status: ProQR has already developed AI models that accelerate the discovery of RNA editing oligonucleotides, with the partnership announced in April 2026 to scale up data generation.
• Near-Term Milestone: The company expects to file a clinical trial application (CTA) for its first AI-discovered drug candidate by mid-2026, with initial clinical data anticipated by year-end 2026.
• Strategic Advantage: Ginkgo's autonomous lab removes a major bottleneck by increasing experimental throughput, enabling ProQR's AI models to predict drug candidates more efficiently and improve discovery timelines.
• Advisory Support: ProQR established an AI Advisory Board comprising leaders from industry and academia to guide the company's AI strategy and ensure best practices in applying machine learning to Axiomer discovery.

The advisory board includes prominent figures from the AI and biotech sectors, such as Thomas Wolf, Co-Founder and Chief Science Officer of Hugging Face, a leading open-source AI platform; David Ruau, Head of Business Development for Healthcare and Life Sciences at NVIDIA, a major AI chip manufacturer; and Gerard van Westen, Full Professor of AI and Medicinal Chemistry at Leiden University . These advisors bring expertise in machine learning, computational chemistry, and translating AI research into practical drug discovery applications.

Ginkgo Bioworks, a synthetic biology company known for engineering microorganisms and biological systems, made a strategic equity investment in ProQR as part of the partnership. This financial commitment signals confidence in the approach and aligns the two companies' long-term interests in advancing AI-enabled drug discovery .

What Makes This Different From Previous AI Drug Discovery Efforts?

Many AI drug discovery initiatives have focused on predicting which molecules might work as drugs, but they've often struggled with the practical reality of actually generating the experimental data needed to validate those predictions. ProQR's approach tackles this head-on by integrating autonomous lab capabilities directly into the discovery pipeline. Rather than treating data generation as a separate, bottlenecked step, the partnership makes it a continuous, high-throughput process that feeds directly into AI model training .

The focus on RNA editing also represents a narrower, more specialized application of AI compared to some broader drug discovery platforms. By concentrating on optimizing Axiomer editing oligonucleotides, ProQR's AI models can develop deeper expertise in a specific therapeutic modality rather than trying to predict drug candidates across all possible chemical space. This specialization may make the AI more accurate and practical for clinical development .

ProQR's timeline is notably aggressive. The company expects to advance its first AI-discovered programs into clinical trials within months, with clinical data readouts anticipated by the end of 2026. This compressed timeline reflects confidence in both the AI models and the autonomous lab partnership to accelerate discovery beyond what traditional methods could achieve .

The formation of the AI Advisory Board also underscores a lesson learned from earlier AI drug discovery efforts: successful translation of AI predictions into real medicines requires guidance from experts who understand both cutting-edge machine learning and the practical constraints of drug development and clinical trials. By assembling advisors from NVIDIA, Hugging Face, Leiden University, and other leading organizations, ProQR is positioning itself to avoid common pitfalls and maximize the impact of its AI strategy .