Ruth-Anne Pai, PhD
The case for any disease

Two agents that take any disease from data to a drug program — and a manuscript.

The molecules on this site are demonstrations. The real deliverable is the engine that produced them: a pair of human-in-the-loop AI specialists that a non-coding scientist can point at any disease. Part 1 turns a disease into a full, decision-gated drug-development program. Part 2 turns that program into a written, peer-review-style manuscript. Together they take one person from “here is a disease” to a program and the paper that documents it — the same path this site walked three times, across two diseases.

Two-agent pipeline: any disease feeds the Therapeutic Program Architect (10-stage, human-in-the-loop) which produces a full drug-development program dossier; the Manuscript Architect then turns it into a bioRxiv-style preprint hardened by two rounds of synthetic peer review Two-agent pipeline: any disease feeds the Therapeutic Program Architect (10-stage, human-in-the-loop) which produces a full drug-development program dossier; the Manuscript Architect then turns it into a bioRxiv-style preprint hardened by two rounds of synthetic peer review
Part 1 — the Therapeutic Program Architect turns any disease into a full, decision-gated drug-development program. Part 2 — the Manuscript Architect turns that program into a peer-review-hardened preprint. The same path this site walked three times, across two diseases.

Why it matters. I am one person, living with the disease I started on, and I do not write production code. In one week these two agents let me run a credible, honest, end-to-end drug-discovery program — and then generalize it to a second disease I have no personal stake in. That is the case: not a single result, but a repeatable, inspectable method that puts a full program within reach of any motivated researcher or patient community.

Part 1 · disease → program

The Therapeutic Program Architect

Give it any disease — common, rare, or genetic — and it runs a ten-stage, human-in-the-loop program: from unmet need and patient priorities, through data- and literature-mined target and modality selection, AI/ML design and in-silico pressure-testing, to scientific, regulatory, and commercial strategy. It stops and asks you at every consequential decision, and it flags its own over-claims.

  1. Indication & unmet need Epidemiology, biology, standard of care, and precedent.
  2. Patient priorities / PFDD What patients actually want fixed — with an optional community survey.
  3. Literature + competitive pipeline Mechanism map plus who is developing what, and why they succeeded or failed.
  4. Data mining → targets Omics meta-analysis and single-cell → ranked druggable targets.
  5. Target & modality selection The pivotal fork: a scored rubric, then you confirm the pick.
  6. Design & pressure-test Modality-routed AI/ML design plus in-silico validation.
  7. Scientific development plan AI-to-first-in-human assay cascade, CMC, biomarkers.
  8. Regulatory strategy FDA / EMA path, designations, endpoints.
  9. Commercial & financing TAM/SAM/SOM, whitespace, financial model, and the Ask.
  10. Deliverables & synthesis Business plan, scientific plan, deck, manuscript, peer review.

See the full ten-stage walkthrough →

Part 2 · program → manuscript

The Manuscript Architect

A program is only useful if others can read, check, and build on it. The Manuscript Architect turns a completed program dossier into a structured, bioRxiv-style preprint — then hardens it through two rounds of synthetic peer review, generating reviewer critiques and point-by-point responses so the weak claims surface before a human reviewer ever sees them.

Draft

Dossier → preprint

Assembles the program's targets, designs, methods, and figures into a complete manuscript with the sections and rigor a preprint server expects.

Review

Two rounds of synthetic peer review

Generates independent reviewer critiques and the author responses to them — a self-correcting loop that catches over-claims and gaps early.

Harden

Honest by construction

Every computational result is labeled in-silico, never “validated.” The honesty line is enforced in the writing, not bolted on afterward.

The three manuscripts on this site were produced this way — read them →

The proof

One engine, three programs, two diseases

The same two agents produced every program on this site. The clearest evidence that the method generalizes is that it re-ran cleanly on a disease with entirely different biology and a different modality.

EoE · tolerance

pMHC-II antigen engine

Personalized antigen selection for eosinophilic esophagitis — 4,640 peptide×allele evaluations → 832 strong binders.

EoE · effector axis

CCL26 / POSTN binders

A 9-cohort meta-analysis to two no-trial targets, then 80→1,920→60 de novo designs with an honest negative-control calibration.

Esophageal cancer

GUCY2C / DKK1 dual arm

The generalization test: public genomics → two nominated targets → 16 binders, 15/16 clearing the interface line.

Open source

Both agents are open

Both specialists and the skills behind them are public, installable, and reproducible — part of twelve open repositories spanning target mining, epitope mapping, protein design, patient-org navigation, market analysis, peer review, and media.

These agents assist a human researcher; they do not replace scientific, clinical, or regulatory judgment. Every output on this site is computational and has not been experimentally validated. Not medical advice.