Normalized claim
Simulation speedup: 2 x increase
2x faster molecular simulation times on modern hardware
Ryvu Therapeutics scales molecular dynamics simulations on Google Cloud, cutting processing time from weeks to hours and reducing false positives by 50%
Use case typeDrug discoveryUpdated 3 days ago
Ryvu Therapeutics is an oncology biotech company that relies on computational methods such as molecular docking, molecular dynamics, protein structure prediction, and physics-based free energy perturbation calculations to prioritize chemical compounds for drug discovery. The company needed to overcome an on-premises compute bottleneck that pushed simulation turnarounds from hours into weeks and slowed down medicinal chemistry synthesis cycles. It built an automated in silico evaluation pipeline on Google Cloud using Google Batch, Compute Engine GPUs, Cloud Storage, and Nextflow orchestration, with Gemini also mentioned among products in the source.
- Organization
- Ryvu Therapeutics
- Industry
- Pharma
- Location
- Poland
- Published
- July 2026
Reported outcomes
2x
simulation speedupTime & speed
5-10 hours per weekmanual data preparation time saved per week−50%false positives reduced
Strategic outcomes
Speed & agilityCompressed discovery cyclesOther strategic outcomeFreed scientists from manual overheadScale & capacityEnabled broader chemical-space exploration
Catalog median for time & speed deployments: +60% across 143 reported metrics. Compare benchmarks →
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Manual data preparation time saved per week: 5-10 hours per week decrease
5-10 hours saved per week on manual data preparation
Normalized claim
False positives reduced: 50% decrease
reducing false positives by 50%
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Ryvu Therapeutics
- Provider
- GCP
- Maturity
- Exploring
- Linked source
- Google Cloud Customers
It built an automated in silico evaluation pipeline on Google Cloud using Google Batch, Compute Engine GPUs, Cloud Storage, and Nextflow orchestration, with Gemini also mentioned among products in the source
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 2 of 2
- 1Drug discovery
- 2Workflow orchestration
- Fixed on-premises hardware could not keep up with hundreds of parallel molecular dynamics simulations and caused long turnarounds for medicinal chemists.
- Scientists needed standardized results by the next morning to map out lab synthesis cycles without delay.
- Built a modern, automated in silico evaluation pipeline using Google Batch as the backend for Nextflow orchestration.
- Automatically spins up hundreds of GPU instances simultaneously, stores and caches terabytes of trajectory files in Cloud Storage, and generates standardized morning reports.
- Reduced processing time from weeks to days, with a standard 100-compound campaign completing in a single night.
- Saved 5-10 hours per week on manual data preparation.
- Reduced false positives by 50% and shaved months off the development lifecycle by filtering candidates before lab synthesis.
Sources & evidence1
Evidence: Medium65/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: Jul 25, 2026Publisher: Google CloudEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.