Hit-finding, docking, co-folding, MD, and FEP — the open-source CADD stack (GROMACS, OpenFE, Boltz-2, OpenFold3) run as one managed Slurm cluster inside your own AWS account. One queue, the right GPU on spot, your data never leaving your VPC. Not a pip install — a cluster operated for you.
3 design-partner slots · $4K pilot, then $1,500/mo · live in 30 days or we work free
Docking, co-folding, and MM-GBSA rank fast for triage — but still swap rank order within a scaffold, enough noise to advance the wrong compound and burn $400K–1.5M finding out. For the lead-opt call, FEP tracks experiment to 0.38 kcal/mol on the TYK2 benchmark. The hard part was never the algorithm — it was the cluster.
sbatch to ranked hits — watch a full campaign.A 1,000-compound hit-discovery funnel — structure → dock → co-fold → MD, end-to-end in your AWS. One command. 73 minutes. $1.16.
sbatch, unedited wall-clock.
The open-source CADD stack your comp chem team already cites
A managed Slurm cluster in your AWS, the full CADD suite operated end-to-end, and every campaign's ΔΔG history accreting as your program's computational book-of-record.
Perturbation networks, ΔΔG history, MBAR bundles, and per-job cost stamps accumulate in your own EFS — a cost-stamped record that lives in your account, not ours, and compounds into a system no competitor can pull out of your VPC.
Structure prediction (OpenFold3), docking (Uni-Dock, AutoDock-GPU, GNINA), affinity rescoring (Boltz-2), MD (GROMACS, AMBER), and RBFE campaigns (OpenFE, FEP multidir) — the same job queue, Karpenter picks the hardware. No partition routing in your scripts.
Pre-IND structure data is program IP. It stays in your IAM perimeter — not on our infra, not routed through our control plane. BYOC means you see every dollar on your AWS bill, and your Savings Plans apply.
Submit from the web console if you'd rather not touch Slurm. SSH in and sbatch if you live in the terminal. Wire the REST API into your orchestrator if you automate everything.
Browse the CADD template catalog, fill the campaign form, hit submit. Live logs, per-job cost stamp, run history, ΔΔG records. For scientists who'd rather not write sbatch.
sbatch fep-campaign --network edges.csvSlurm-native. SSH in and submit the way you would on any HPC system — same sbatch, squeue, sacct, scancel. For comp chemists who already live in the terminal.
POST /v1/jobs/submitWire Clusterra into your in-house pipeline, Airflow DAG, or Slack bot. JSON in, JSON out. For platform teams that want Clusterra as the compute backend, not the front door.
The same managed Slurm cluster runs all three verticals. Start with the pain that's blocking you now and expand as your program grows.
For the lone comp chemist at a Series A/B small-molecule biotech. OpenFold3 + Uni-Dock + Boltz-2 + GROMACS hit funnel in 73 min at $1.16. RBFE campaigns on the same cluster — no partition routing, no HPC hire.
For structural-biology biotechs running RELION-5 / AreTomo / Warp·M / IsoNet / MemBrain pipelines. Multi-TB tilt-series stay in your VPC. CryoCloud covers SPA — we cover STA. No academic-cluster waitlist.
If you're running nf-core/sarek, AlphaDIA cohorts, MAPPs, single-cell, or a custom Slurm pipeline — the platform substrate is the same. New workloads onboard in days. Send us what you're running.
Not a log file. A tarball any reviewer can rerun end-to-end — with ΔΔG history, MBAR bundles, and per-job cost stamps accreting in your own EFS.
campaign_provenance.tar.gz ├── manifest.json # run metadata + hashes ├── perturbation_network.json # Lomap edge list ├── ddg_estimates.csv # per-edge ΔΔG + MBAR ├── slurm.sbatch # exact submit script ├── container.sha256 # image digest ├── input/ │ └── ligands.sdf / protein.pdb ├── output/ │ └── ranked_hits.tsv / ddg.csv ├── cost.json # per-job AWS cost stamp └── provenance.log # signed, append-only
{ "run_id": "clst-21047", "git_sha": "a3f9e21", "workflow": "fep-campaign@0.3.0", "container": "sha256:4c8a…d9f2", "submitted_at": "2026-06-01T09:14:22Z", "edges": 24, "wall_clock_s": 18420, "cost_usd": 11.40, "nodes": "g5.12xlarge × 1", "protocol_hash": "b91c…d47e", "signed_by": "clusterra-prod" }
Finance can expense it. A new scientist joining next year can clusterra rerun a 2026 campaign and get the same ΔΔG estimates. The SAR history your program accumulates becomes the switching cost that makes the cluster worth keeping.
Spot pricing, checkpoint-restart on, us-east-1. Reproducible benchmarks on public datasets — fork the repo, verify the numbers.
n=1 run verified June 2026, job 2958, TYK2. Spot evictions mid-run; checkpoint-resume recovered every leg with zero lost work. n=3 is required for per-ligand ΔG estimates and error bars — that’s the number we quote. Every dollar lands on your AWS bill, not ours.
Every named competitor has a hard constraint that excludes them from the lone CADD scientist at a Series A/B biotech. Here is the honest map.
| Capability | Clusterra | Rowan | Schrödinger | BioTeam | AWS PCS |
|---|---|---|---|---|---|
| Full CADD suite: hit-find → FEP — operated end-to-end | ✓ | hit-find + docking, no BYOC FEP | FEP+ only with Maestro license | consulting, not SaaS | substrate — you build it |
| Open tools (GROMACS / OpenFE — no proprietary force fields) | ✓ | proprietary TMD engine | OPLS3e, Maestro | ✓ | ✓ |
| BYOC — compute and data in customer’s own AWS | ✓ | VPC tier is bespoke enterprise | virtual cluster, enterprise contract | — | ✓ |
| Flat price (no per-seat, no compute markup) | $1,500/mo | $200 solo / $50K org / $25 per-cpd | ~$100K+ / year | project billing | per-hr mgmt fee |
| One queue — any job gets the right hardware, no partition routing | ✓ | — | — | — | 10-partition cap, no cross-family |
| Campaign system-of-record (ΔΔG + cost history in your EFS) | ✓ | results on Rowan infra | Maestro project files | — | — |
Rowan wins where the browser UX matters and budget is tight at the per-seat level — it’s a great product for early exploration. Schrödinger wins where the Maestro + OPLS3e stack is already licensed. BioTeam wins where you need custom consulting. AWS PCS is the substrate we’re built on. Clusterra wins when you want the open-source CADD suite operated in your own AWS account at a flat price a Series A biotech can actually afford.
Three steps. All in your AWS account.
BYOC via a cross-account IAM role. Your VPC, your billing, your data. We deploy the Slurm + Karpenter control plane into your account — nothing routes through ours.
Hit-discovery funnel, RBFE campaign, GROMACS FEP multidir, AMBER REMD, OpenFold3 batch — or submit your own Slurm job. The cluster knows what hardware each step needs; you never write a partition name.
sbatch, REST, or the console. Karpenter provisions the right instance family on Spot. Checkpoint-restart on eviction. Live cost meter. Per-job cost stamp. Campaign provenance bundle on every run.
A scoped 30-day pilot to get your first RBFE campaign running in your AWS account. Then a flat monthly fee — your VPC, your compute, your AWS bill.
Pilot covers: cluster deployment in your VPC, a CDK2 smoke campaign that proves the GROMACS FEP stack is running correctly in your account before your compound IP goes in, and 30 days of infra support. You bring the chemistry. We make the cluster work. After the pilot, flat $1,500/month — compute runs in your AWS account, not ours. No per-seat fee, no compute markup.
72-hour affinity guarantee: once live, submit a valid RBFE campaign and get a complete results.csv within 72 business hours — or that month is free and we finish at our compute cost. If the FEP stack isn’t validated in your account within 30 days, the pilot fee is refunded in full.
DIY GROMACS on AWS is “free” — minus the 4–8 weeks of MPI, EFA, spot-recovery and orchestration work before your first campaign runs.
Production pricing (customer #4 onward): $8K pilot → $2,500/mo. Design-partner rate is open now for the first three accounts.
30 minutes to scope. 30-day pilot with your first RBFE campaign running in your AWS account. FEP Launchpad: $4K pilot, $1,500/mo BYOC. Three design-partner slots — closes when filled.