New AI genomics platform targets kidney and cardiorenal disease
Posted: 9 January 2026 | Drug Target Review | No comments yet
Seattle-based biotech company, Variant Bio, have launched Inference, an AI-powered genomics platform designed to accelerate drug discovery and identify genetically supported targets.


Variant Bio, a genomics-driven AI drug discovery company, have announced Inference, the world’s first agentic genomic drug discovery platform. Developed over seven years with more than $100 million invested in data and infrastructure, Inference is designed to transform how pharmaceutical R&D teams harness human genetic data to discover and validate therapeutic targets.
The company have also announced a multi-year research collaboration and licence agreement with Boehringer Ingelheim to accelerate the discovery of novel targets for cardiorenal and kidney diseases using this new platform.
Transforming genomic drug discovery
Variant Bio built Inference to be the definitive solution for genomic drug discovery. As a company that generates proprietary human genomic data from global studies, processes large multi-omic datasets and advances its own drug development programmes, Variant Bio want to continuously improve the platform through real-world application.
Automation now plays a central role in discovery. From self-driving laboratories to real-time bioprocessing
This report explores how data-driven systems improve reproducibility, speed decisions and make scale achievable across research and development.
Inside the report:
- Advance discovery through miniaturised, high-throughput and animal-free systems
- Integrate AI, robotics and analytics to speed decision-making
- Streamline cell therapy and bioprocess QC for scale and compliance
- And more!
This report unlocks perspectives that show how automation is changing the scale and quality of discovery. The result is faster insight, stronger data and better science – access your free copy today
The platform is designed for dynamic, real-time analysis rather than static, precomputed results.
Using the platform, Variant have harmonised data from major genetic and multi-omic studies, global biobanks and their own studies involving underrepresented populations. They have also processed hundreds of billions of genetic associations across tens of thousands of genome-wide association studies, which has created the largest unified source of human genomic data for drug discovery.
Additionally, Inference provides dynamic, real-time analysis rather than static, precomputed results, with its proprietary API allowing for instant retrieval of gene and variant-level data across hundreds of millions of data points.
“With Inference, we built the tool we wished existed when we started Variant Bio. Enterprise software design principles, applied by people who actually do genomic research. When you’re solving your own problems, you build something real,” said Stephane Castel, co-founder and chief technology officer of Variant Bio.
AI-powered discovery and agentic analysis
Inference incorporates two AI capabilities to accelerate target discovery. VB-Predict creates molecular models of disease using transcriptomic, proteomic and metabolomic data alongside neural networks, predicting traits and identifying disease-correlated targets. VB-Atlas learns embeddings from thousands of association studies, mapping genome-wide gene–phenotype relationships and making massive datasets accessible to large language models (LLMs).
What Variant Bio has built stands out as one of the most impressive applications of agentic AI.
Most notably, Inference Agents are autonomous AI agents capable of executing complex analyses and interpreting results. They can validate therapeutic targets, assess causality, determine effect direction, scan for safety liabilities and rank putative causal genes across hundreds of loci using first principles rather than literature reviews.
“As early AI investors, we’ve seen countless approaches to drug discovery. What Variant Bio has built stands out as one of the most impressive applications of agentic AI. They’re avoiding artificial hype and building autonomous systems doing actual scientific research, with real implications for patients,” said Josh Wolfe, co-founder and managing partner of Lux Capital.
Partnership with Boehringer Ingelheim
The collaboration with Boehringer Ingelheim will focus on discovering and validating novel targets for cardiorenal and kidney disease, which affects more than 850 million people globally. By combining Variant Bio’s AI-driven platform with Boehringer Ingelheim’s expertise in cardiovascular and renal research, the two companies can accelerate the development of new therapies.
The collaboration with Boehringer Ingelheim will focus on discovering and validating novel targets for cardiorenal and kidney disease, which affects more than 850 million people globally.
“This strategic partnership with Boehringer Ingelheim marks another key milestone for Variant Bio and demonstrates the power of our Inference platform,” said Andrew Farnum, CEO of Variant Bio. “Combining our AI-driven discovery engine and unique data resources with Boehringer Ingelheim’s unparalleled expertise in cardiovascular and renal conditions gives us an exceptional opportunity to make a real difference for patients with kidney disease.”
Under the agreement, Variant Bio will also receive an upfront payment and is eligible for potential licence and milestone payments exceeding $120 million.
“We look forward to working with Variant’s scientists and harnessing their unique platform,” said Søren Tullin, global head of cardiovascular-renal-metabolic diseases research at Boehringer Ingelheim. “Discovering novel, genetically validated targets is pivotal to developing next–generation, first-in-class treatments that can transform the lives of people with kidney disease.”
Advancing the mission
Inference is now available to research partners, enabling secure upload of proprietary data and supporting collaborations with pharmaceutical companies in multi-year discovery alliances valued at over $200 million. Variant Bio is continuing to expand its data resources, fulfilling its goal of maximising genomic data for drug discovery whilst sharing the benefits with partner communities worldwide.
Related topics
Artificial Intelligence, Bioinformatics, Computational techniques, Drug Discovery, Drug Discovery Processes, Drug Targets, Genomics, Metabolomics, Proteomics, Sequencing, Target Validation, Targets, Translational Science
Related conditions
Cardiorenal Disease, Kidney disease
Related organisations
Boehringer Ingelheim, Variant Bio


