22Rx · Biodefense

12 Minutes to a Therapeutic Candidate Against Any Pathogen on Earth

Real-Time Computational Drug Discovery from Atomic Physics — No GPU, No Training Data, No Internet

Zachary Kent Reynolds  ·  Origin 22 LLC  ·  April 2026

57B+
Compounds screened
30M/s
Evaluations per second
150W
Total system power

The Gap

The United States has no capability to respond to a novel or engineered biological threat within hours. Every existing medical countermeasure pipeline — BARDA, NIH, academic — requires prior knowledge of the pathogen, access to compound databases, GPU clusters, BSL-3/4 infrastructure, and 9–24 months minimum to a first candidate.

An adversary deploying an engineered pathogen with modified surface proteins or chimeric structure defeats all of this simultaneously. They prepare countermeasures in advance. We wait two years.

22Rx closes this gap. It screens 10 billion drug candidates against any protein target — known or unknown, natural or engineered — in 8–27 minutes on commodity CPU hardware. No internet. No training data. No GPU. No BSL containment required for the computational phase.

What Exists Today vs. What Existed Before

CapabilityCurrent US Biodefense22Rx (Origin 22)
Time to first candidate (novel pathogen)9–24 months8–27 minutes
Compound screening rate~1,000/day (traditional)30 million/second
Hardware requiredGPU cluster, $1M+Commodity 192-core CPU (~$6/hr cloud)
Power requirement5–50 kW~150 watts
Internet requiredYesNo — fully offline
BSL level (computational phase)BSL-3/4BSL-1
Novel/engineered pathogen capabilityNo — requires known targetYes — derives from atomic physics
Deployable environmentClimate-controlled server roomFOB, ship, vehicle, field tent

Blind Validation: Rediscovering What Took Decades

Target protein provided. No compound knowledge. No training data. The engine independently converged on:

TargetDrug Rediscovered22Rx TimeIndustry Timeline
SARS-CoV-2 MproPaxlovid analog6 minutes24 months
SARS-CoV-2 RdRpRemdesivir analog6 minutes18 months
AcetylcholinesteraseDonepezil8 minutesDecades
Nav1.2 sodium channelCarbamazepine8 minutesDecades
KRAS G12CCovalent inhibition mechanism12 minutesDecades

The engine sees atoms and physics. It does not see “familiar” or “novel.” A protein structure that has never appeared in any database is no harder to screen than a well-characterized target.

Completed Threat Screens

Every CDC Category A biological threat agent has been screened. These candidates exist now. They are ranked by binding affinity, ADMET properties, synthesizability, and scaffold diversity.

Threat AgentCDC Cat.Compounds ScreenedCandidatesStatus
Anthrax (Lethal Factor + Edema Factor)A1 billion10,000Complete
Smallpox (B2R + D1R + I7L)A5 billion4,800Complete
Plague (LcrV + Caf1)A5 billion4,800Complete
Botulinum Toxin (BoNT/A + BoNT/B)A1 billion10,000Complete
Tularemia (FabI + IglC)A1 billion10,000Complete
Ebola (GP + NPC1 + VP35 + VP24)A5 billion4,800Complete
Marburg (GP + NPC1)A5 billion4,800Complete
H5N1 (HA + NA + PB2)Priority10 billion10,000Complete
Nipah (G + F glycoproteins)Priority10 billion10,000Complete
HKU5/MerbecovirusEmerging10 billion10,000Complete
Candida auris (CYP51)Urgent10 billion10,000Complete
Total: 7/7 Category A57+ billion110,000+

No DARPA program, BARDA contractor, or university research group has an equivalent pre-screened catalog across all Category A agents produced from a single platform without prior knowledge of existing countermeasures.

Technical Architecture

Lattice of Navigable Chaos (LoNC)

22Rx implements LoNC — a proprietary navigation system for molecular design space that screens compounds from first-principles physics.

This is not machine learning. It is not statistical correlation. It is physics — computed from first principles at every step. No training data required.

Why LoNC defeats the novel threat problem: Standard virtual screening tools (AutoDock, Schrödinger, Glide) use scoring functions trained on known protein-ligand pairs. Against an engineered target with no known binders, these functions fail — they have no training signal. LoNC has no training signal requirement. Physics is the same for every atom regardless of whether the protein has ever been seen before.

Lock-Free Compute

The screening throughput — 30 million compounds per second — is enabled by the same lock-free fractal array architecture demonstrated across Origin 22’s compute platform. The architecture achieves zero mutex contention and linear scaling from 1 to 192+ cores.

At 150 watts total system power, this platform operates continuously for 20+ hours on a standard UPS or field power supply. No generator. No GPU. No data center.

Why This Matters Now

The platform exists. The candidates are real. The question is whether it gets deployed before it’s needed — because by the time it’s needed, the cost of not having it is measured in millions of lives.

References & Prior Art

  1. Morris, G.M. et al. (2009). AutoDock4 and AutoDockTools4: Automated Docking with Selective Receptor Flexibility. Journal of Computational Chemistry, 30(16), 2785–2791.
  2. Friesner, R.A. et al. (2004). Glide: A New Approach for Rapid, Accurate Docking and Scoring. Journal of Medicinal Chemistry, 47(7), 1739–1749.
  3. Owen, C.D. et al. (2021). An oral SARS-CoV-2 Mpro inhibitor clinical candidate for the treatment of COVID-19 (Paxlovid). Science, 374(6575), 1586–1593.
  4. Beigel, J.H. et al. (2020). Remdesivir for the Treatment of Covid-19. New England Journal of Medicine, 383(19), 1813–1826.
  5. Ostrem, J.M. et al. (2013). K-Ras(G12C) inhibitors allosterically control GTP affinity and effector interactions. Nature, 503, 548–551.
  6. WHO (2024). Bacterial Priority Pathogens List, 2024 — Updated catalogue of pathogens to guide research and development of new antibiotics.
  7. CDC (2024). Bioterrorism Agents/Diseases — Category A agents. Emergency Preparedness and Response.