RELION-5, AreTomo, Warp/M, IsoNet, MemBrain, MotionCor3, CTFFIND4, Topaz — verified containers, multi-GPU, Slurm-orchestrated. Multi-TB tilt-series stay in your VPC. We containerize the new methods that drop quarterly so your team doesn't have to.
First reference customer free · $4K paid pilot otherwise · $750/mo BYOC after
Clusterra runs benchmarked proteomics and structure-prediction workflows on customer AWS today. The cryo-ET stack — RELION-5, AreTomo, IsoNet, MemBrain — is containerized and runs on the same managed Slurm. We don't yet have a published cryo-ET case study with real tilt-series numbers.
If you're a structural-biology biotech or core facility tired of waiting for academic-cluster slots, we'd love to benchmark your tilt series as the first cryo-ET reference deployment. Free pilot, joint case study, your data in your VPC.
Pinned versions, GPU-tuned, multi-node where applicable. The exact things you'd install on a fresh academic cluster, minus the install.
Tilt-series and reconstructed tomograms stay in your S3 bucket. Cross-account IAM, your KMS keys, your audit trail. We never see the data.
Skip the 2-week academic-cluster waitlist. Pay only for the GPU-hours you use. Multi-GPU NCCL + EFA for large refinements; spot checkpoint-restart for long jobs.
IsoNet, MemBrain, AreTomo, Warp/M — we track the field. When the next denoiser or picker drops, we container-build and ship it. You don't maintain a custom RELION install with five patches.
· 5–50 person structural-biology biotech (cellular cryo-ET, drug-target structure)
· Or a cryo-EM core facility serving industry users
· Running RELION / AreTomo / Warp pipelines on aging on-prem GPUs or shared academic clusters
· Need GPU + fast scratch for tomogram reconstruction and subtomogram averaging
· Want a managed catalog of frontier OSS tools (IsoNet, MemBrain, etc.) without maintaining containers yourself
· Your pipeline is fully on cryoSPARC and the license is happy
· You have an in-house cryo-EM IT team running your own cluster
· You only do SPA (single-particle), not cryo-ET — the wedge here is in-cell tomography
· You need SOC 2 / FedRAMP in month one
· Microscope time is your only bottleneck and processing turnaround doesn't matter
These published benchmarks demonstrate the same managed-Slurm-on-AWS substrate that would run your cryo-ET pipeline. Same containers, same orchestration, same BYOC model.
11 reference TCR-pMHC complexes, Boltz-2 on A10G, DockQ 0.59-0.62 against published crystals. Demonstrates GPU-driven structure prediction at ~$0.13/complex.
EGFR target → 1,000-compound docking → Boltz-2 rescore → GROMACS MD. End-to-end in 73 min for $1.16 on EC2 GPUs. Demonstrates multi-stage GPU + MPI orchestration.
30× WGS in 2h 32m for ~$2.59/sample. Parabricks GPU alignment + DeepVariant. F1=0.9966 against GIAB. Demonstrates large-input pipelines at scale with reliability under spot.
30 minutes to scope your pipeline. 4 weeks of free pilot on your tilt series in exchange for a published joint case study. After that, $750/mo BYOC.