Our client had mathematical models of the in vivo behavior of their patented, FDA-approved molecule, and wanted a detailed understanding of the molecule’s effects on individual patients to further increase clinical effectiveness and reduce side effects. Each run of the complex dynamical systems model required substantial CPU time to numerically solve the differential equations and simulate time-series results. They also needed hundreds or thousands of runs per patient using a Monte Carlo approach to account for intra-patient variability across a range of dimensions. Multiplied by thousands of patients, millions of CPU-intensive runs were needed. Finally, to satisfy regulators, our client wanted demonstrable correctness at the source-code level as well as in the clinical trial.
The client had exhausted its internal IT resources and had been frustrated by the lack of progress from its normal external vendors. They turned to FP Complete for a comprehensive solution.
Our solution was to deploy the model on a high-performance cloud of multiple 36-core virtual compute servers, automatically adding machines according to the workload requirements. We used our High Performance Computing (HPC) system based on Redis to distribute computations transparently across all of the machines, creating very large computing power.
To get the most out of these big computers, we helped the client improve the model’s concurrent performance using Haskell for high-performance parallel programming.
To accelerate experimentation, we configured container software including Docker and Kubernetes to automatically bring up whole clusters — so test, research, and production runs could each have their own systems on demand running different versions of the model. Each cluster was put into its own Amazon Private Cloud (VPC) and four logically distinct subnets, each replicated for scalability and fault tolerance:
The system massively increased the throughput of the client’s pharmacodynamic model, scaling it from a desktop implementation to a 360-CPU virtual supercomputer available as a Web service. This delivered huge amounts of computation to the R&D team, completing ultra-detailed dynamical and probabilistic analysis of a large set of clinical data.
Access to so many runs on demand enabled the team to identify important mediating factors that were never before known to clinicians. They used this knowledge to improve the model, and used on-demand cloud deployment to test and retest improved models in a very short cycle time.
The completed and scaled-up system achieved significant predictive power, far exceeding any previous predictive model of this molecule’s effects on individual patients.
The resulting software is so safe and effective, and developed with FP Complete under such strong engineering controls, that the client is preparing a regulatory submission to use it in a clinical medical device.