Bioinformatics teams face a common challenge: delivering reliable, reproducible data products to downstream teams, models, and customers. For CytoReason, whose computational disease models depend on complex bioinformatics pipelines, clean orchestration was only part of the answer. Pipeline outputs needed to be traceable, governed, and easy to consume as data products.
Learn how the Cytoreason bioinformatics team orchestrates reproducible workflows at scale with Nextflow and the Seqera Platform in combination with lakeFS to capture their pipeline outputs as governed, versioned data. As a result, every disease model traces back to the exact inputs and code that produced it. Disease models become data products: reproducible, auditable, and ready to ship.
About
-
How CytoReason treats disease models as data products.
-
Why reproducible pipelines weren't enough and where productizing the outputs broke down.
-
How pairing Nextflow and Seqera Platform with lakeFS unlocked faster, and more reproducible model releases.
-
How this impacts bioinformatics teams converting pipeline outputs into governed data products.
CytoReason
CytoReason is a technology company transforming drug development from trial and error to predictable outcomes, using computational disease models. Research and therapeutic area teams, including disease, asset, and computational leaders, use CytoReason’s platform to better inform target prioritization, combinations, indication prioritization, and patient subpopulation selection. CytoReason’s models are trusted, validated, and used at scale by top pharma companies. The CytoReason disease modeling platform is supported by scientific services and by an AI research assistant (LINA). Customers enhance the models they subscribe to through ingesting their data. CytoReason is backed by NVIDIA, Thermo Fisher Scientific, Pfizer, and others. Learn more at www.cytoreason.com.
lakeFS
lakeFS is the control plane for AI-ready data, bridging the infrastructure gap that slows down enterprise AI initiatives. Built on a highly scalable data version control architecture, lakeFS accelerates AI delivery, ensures data quality, makes AI training and agent runs reproducible, and reduces data access friction for tools, users, and AI agents. lakeFS is trusted by AI/MLOps teams, data engineers, and data scientists at thousands of organizations including Arm, Bosch, Lockheed Martin, NASA, Volvo, and the U.S. Department of Energy. Learn more at lakefs.io.
Seqera
Seqera is the intelligent engine for the life sciences, from the creators of Nextflow — the gold standard workflow engine for modern bioinformatics. Seqera is the enterprise platform for scalable bioinformatics. Designed by bioinformaticians, it powers agentic science with reproducible workflows, seamless infrastructure integration, and built-in compliance. Trusted by 14 of the top 20 pharma companies and over 150 leading life sciences teams worldwide, Seqera helps organizations take their science further, faster. Learn more at https://seqera.io/
Speakers
Ron Poches
System Architect, CytoReason
Iddo Avneri
Chief Business Officer, lakeFS
Florian Wuennemann
Senior Bioinformatics Engineer at Seqera
Rob Newman
Product Manager Lead at Seqera