Transforming Computational Drug Discovery
Chemspace and Fovus
Chemspace
Chemspace is a leader in the chemical compound marketplace and end-to-end computational chemistry services. Home to Enamine xREAL and Freedom Spaces — the world’s most extensive collection of commercially available chemical compounds with over 5 trillion molecules — Chemspace supports industries spanning biotechnology, life sciences, chemistry, and pharmaceuticals. By leveraging its vast database of building blocks, reagents, and screening compounds, Chemspace delivers integrated drug discovery services powered by the Design-Make-Test-Analyze (DMTA) cycle, cementing its position as an innovator in computational chemistry and drug discovery.
Fovus
Fovus is an AI-powered, serverless high-performance computing (HPC) platform delivering intelligent, scalable, and cost-efficient supercomputing power at the scientists’ and engineers’ fingertips. Fovus uses AI to optimize HPC strategies and orchestrates cloud logistics, making cloud HPC a no-brainer and ensuring sustained time-cost optimality for digital innovation amid quickly evolving cloud infrastructure. By accelerating time-to-insights and optimizing cloud costs, Fovus helps Biotech clients accelerate Design-Make-Test-Analyze (DMTA) cycles and discover more with less.
Molecular Dynamics Simulation
Molecular Dynamics Simulation helps study the dynamic interactions and behaviors of protein-ligand systems. It enables the exploration of the structural changes induced by ligand binding and energetic fluctuations within the protein-ligand complex, offering valuable insights into the stability and affinity of the complex. One of the applications of this method is to obtain a range of protein conformations that are used to create a better model for molecular docking, as it allows for protein flexibility to be accounted for. Another vital utilization is calculating the binding free energy between protein and ligand. For this purpose, we use Molecular Mechanics Poisson-Boltzmann Surface Area or Generalized Born Surface Area (MM/PB (GB)SA) calculations at the Fovus platform. For each protein-ligand complex, MD simulation is run for 10 ns, after which hundreds of frames from the trajectory are analyzed using the gmx_MMPBSA tool to estimate binding affinity. Moreover, it is possible to perform free energy decomposition analysis to evaluate contributions from individual residues or energy components, which allows the detection of key interactions driving the binding process. MM/PB (GB)SA calculations with a proper parameter adjustment outperform classical docking score functions and might considerably improve the enrichment rate. We use it as an additional metric to select the best compounds for further synthesis.
Serverless HPC Model
Fovus simplifies cloud HPC with AI-driven autonomous automation for cluster setup and infrastructure provisioning, allowing chemists to focus on discovery. Workloads deploy in a single CLI command or a few clicks via web UI, with Fovus handling logistics, optimization, scaling, maintenance, and many more. No cloud or cluster management is needed — pay only for workload runtime.
Free Automated Benchmarking
Free automated benchmarking evaluates how different HPC strategies (CPUs, GPUs, memory, storage, and networking configurations, as well as parallel computing and cloud configurations) quantitively impact the overall runtime and cost of each computational chemistry workload, providing Fovus the visibility of their respective HPC strategy space.
AI-driven Strategy Optimization
Driven by custom benchmarking data, Fovus automatically determines the optimal HPC strategy to minimize runtime and costs for each computational chemistry workload, including GROMACS, docking simulations, and other AI/ML workloads.
Dynamic Multi-Cloud-Region Auto-Scaling
Fovus dynamically scales GPU clusters and parallel tasks across multiple cloud zones and regions, automatically leveraging abundant cloud resources to accelerate large-scale tasks with massive parallelization. Multi-region auto-scaling reduces the time needed for computational chemistry and accelerates DMTA cycles.
Intelligent Spot Instance Utilization
Fovus intelligently auto-leverages spot instances using low-cost cloud resources to reduce headaches and costs for GPU-heavy simulations. Failover capabilities ensure task result integrity, making large-scale computations affordable and reliable.
Continuous Improvement
Fovus auto-updates benchmarking data and auto-refines HPC strategies as cloud infrastructure evolves, ensuring sustained efficiency and cost-effectiveness with up-to-date performance metrics.
Discover how Fovus can optimize your computational workflows and how Chempace delivers drug discovery solutions:
