Leading discovery service provider accelerated DMTA cycles and project delivery at reduced costs
Fovus reduced the time-to-insight for our large-scale compound screening workloads from weeks to hours while slashing our cloud HPC cost by 85%, helping us operate more efficiently and deliver projects faster.
Olga Tarkhanova
Head Of Discovery Services
Optimal
HPC
strategy
Massive
task-level
parallelism
Spot
instance
auto-leveraged
112x
faster
time-2-insight
85%
lower
cloud cost
Optimal
HPC strategy
Massive
task-level parallelism
Spot
instance auto-leveraged
112x
faster time-2-insight
85%
lower cloud cost
| Self-managed AWS Time | Self-managed AWS Cost | Fovus Time | Fovus Cost | Time Reduction | Cost Saving | |
|---|---|---|---|---|---|---|
| Compound screening (molecular dynamics) | 4 weeks | $5,550 | 6 hrs | $750 | 112x | 7x |
About Chemspace
Chemspace is a leading online marketplace for chemical compounds, offering the world’s largest database of building blocks, reagents, and screening compounds. Chemspace offers a comprehensive Integrated Drug Discovery service utilizing a key component – Design-Make-Test-Analyze cycle.
Industry
Contract research organization (CRO) serving the biotechnology, life science, chemistry, and pharmaceutical industries.
HPC Workloads
Molecular dynamics and docking simulations, compound screening, ML/AI-based drug discovery, etc.
Pains
- Cloud logistics is too complex and time-consuming for the computational chemist to manage. They want to focus on science and discovery rather than wasting time on cloud hassles.
- Cloud offerings are too diverse and heterogeneous, making it impossible to find the optimal HPC strategies for various computational chemistry workloads.
- A suitable HPC strategy for workload A could be bad for workload B. Without proper HPC strategies, Computational chemists experience high cloud HPC costs, especially for GPU workloads.
- Scaling up cluster size is difficult due to a lack of cloud expertise, especially for GPU workloads. This limits the computation scale and leads to unbearably long time-to-insight for large-scale compound screening, slowing project delivery.
Solution
Serverless HPC experience, ease-of-everything
- Fovus uses AI to automatically orchestrate all the cloud logistics and optimize the HPC strategies so the computational chemists focus on science and discovery.
- The computational chemists deploy their HPC workloads in a single command via CLI or with just a few clicks using the web UI, and Fovus takes care of everything else.
- Easy to integrate, deploy, scale, optimize, and sustain.
- No cloud management is needed. Pay only for the runtime of workloads.
Free automated benchmarking
- Fovus auto-benchmarked each type of Chemspace’s computational chemistry workload for free to explore their HPC strategy space effectively.
- This reveals how the choice of CPUs/GPUs, hyperthreading, memory, and storage configurations impact the performance and cost of each Chemspace’s computational chemistry workload.
- Such benchmarking data provides the foundation for optimizing the HPC strategy tailored to each Chemspace’s computational chemistry workload.
AI-optimized HPC strategy
- Based on the custom benchmarking data, Fovus auto-determines the optimal HPC strategy to minimize the total runtime and cloud cost for each Chemspace’s computational chemistry workload.
- This ensures the time-cost optimality of computational drug discovery with zero user effort needed.
Multi-cloud-zone auto-scaling
- Fovus auto-scales the cluster size and the tasks running in parallel across multiple cloud availability zones according to their availability dynamics to leverage abundant cloud resources best to accelerate computational drug discovery.
- This massively parallelized the computation for Chemspace’s large-scale compound screening tasks and accelerated the critical insight delivery in DMTA cycles by over 110x.
Continuously improve HPC strategy
- Fovus auto-updates the custom benchmarking data and continuously improves the HPC strategies for each Chemspace’s computational chemistry workload as cloud infrastructure constantly upgrades.
- This sustains the time-cost optimality of computational drug discovery as cloud infrastructure quickly evolves.
Auto-leverage spot instance
- For each Chemspace’s computational chemistry workload, Fovus intelligently analyzes the expected savings for each applicable spot strategy according to the availability and pricing dynamics of spot instances, their frequency of interruption, and workload runtime predictions.
- Fovus automatically leverages spot instances by applying the best spot strategy to further reduce the cloud cost by another 3-4x. This makes computational drug discovery highly affordable at scale, especially for GPU-based molecular dynamics simulations in large batches.
- Fovus automatically re-queues any disrupted tasks due to reclaiming spot instances for re-execution to assure the integrity of simulation results with failover capabilities.
Results
- No more cloud hassles, allowing computational chemists to focus their valuable time on science and discovery.
- Significantly faster and cheaper computational drug discovery (see table below)
- For large-scale compound screening, time-to-insight was reduced from weeks to hours—112x faster. Cloud cost was reduced from $5,550 to $750 per launch—7x lower expense.
- Ability to consistently leverage state-of-the-art hardware technology to supercharge computational drug discovery and stay ahead of the game.
- Faster DMTA cycles, more efficient discovery service.
- Faster project delivery, more customer success.
Other case studies
Stealth Series-B Startup
Success Story
Trailblazing Biotech startup accelerated DMTA cycles at reduced cloud expense
Success Story
World’s 2nd largest heavy equipment manufacturer accelerated digital innovation
