Ruth-Anne Pai, PhD
Project Tolera · programming T‑cell tolerance

Programming T‑cell tolerance, one patient at a time.

A citizen-scientist's roadmap for a personalized pMHC-II tolerance vaccine in eosinophilic esophagitis — from AI/ML design to first-in-patient. EoE is, at its root, antigen-specific: a food peptide presented on an MHC-II molecule to a pathogenic T-cell clone. Yet every approved and pipeline therapy is a broad, chronically-dosed symptom suppressor. Project Tolera maps the path to a one-course therapy that reprograms the pathogenic clone toward tolerance and retires it.

Project Tolera pipeline: public omics to target generation, then two arms — a direct drug-candidate arm (CCL26/POSTN binders) and a personalized-tolerance arm (pMHC construct), with the Gladstone CD4+ Perturb-seq dataset feeding reprogramming drug targets into the tolerance arm Project Tolera pipeline: public omics to target generation, then two arms — a direct drug-candidate arm (CCL26/POSTN binders) and a personalized-tolerance arm (pMHC construct), with the Gladstone CD4+ Perturb-seq dataset feeding reprogramming drug targets into the tolerance arm
One engine runs from public omics to target generation, then branches into a direct drug-candidate arm and a personalized-tolerance arm. The Gladstone CD4+ T-cell Perturb-seq dataset nominates reprogramming targets that prime committed clones for pMHC-induced tolerance.

Two ways to reprogram the pathogenic T cell

Tolera's reprogramming work runs on two complementary axes. The lead program engineers a personalized pMHC-II construct that re-educates the food-specific T-cell clone toward tolerance based purely on its TCR — regardless of the cell's activation state. In parallel, we mined a genome-scale CD4+ T-cell CRISPRi Perturb-seq resource to identify drug targets that reprogram T-cell state: knockdowns that dampen pathogenic Th2 output (lowering IL-13/IL-5/IL-4, the upstream drivers of the CCL26/POSTN tissue axis) and co-targets that improve amenability to pMHC-induced tolerance, making committed effector clones more convertible to a regulatory fate.

Perturb-seq resource: genome-scale CRISPRi in primary human CD4+ T cells, from the laboratories of Alex Marson (Gladstone Institutes / UCSF) and his collaborator Jonathan Pritchard (Stanford University), made publicly available through the CZI Virtual Cells Platform.

Read the target-mining report (PDF)

Commercial strategy

Two paths to the clinic — and a molecular reason to pursue the combination

The Perturb-seq mining did more than nominate targets: 33 dual-program hits converge on the LKB1→AMPK/SIK→CREB energy-sensing axis, with the kinase SIK3 as the standout (pMHC-adjunct utility score 0.815; high cross-donor robustness across five EoE donors). SIK3 inhibition blocks CREB–c-FOS at the IL-2 promoter while a pMHC-II construct drives FOXP3+CD39+CD73+ iTreg/Tr1 differentiation — a mechanistic rationale for co-dosing that a monotherapy cannot access.

Path A · monotherapy

pMHC-II nanoparticle, orphan indication

The lead antigen-specific construct as a single agent, developed down a rare-disease/orphan pathway for the HLA-restricted subgroup.

Reach: single-HLA subgroup (≈70k patients) · Deal shape: $2–5M upfront + $20–30M milestones + 5–8% royalties · Peak sales $100–200M/yr

Path B · combination (recommended)

pMHC-II construct + SIK3 inhibitor

Co-dosing the tolerizing construct with a transient, isoform-selective SIK3 inhibitor to prime committed effector clones for conversion — broadening reach beyond a single HLA.

Reach: 70–100% of EoE (140–200k patients) · Deal shape: $5–10M upfront + $50–100M milestones + 3–5% royalties · Peak sales $400–800M/yr

Market and deal figures are illustrative scenarios for strategic planning, not forecasts; they depend on clinical success, HLA coverage, and partnering terms that remain to be established.

Phase 1b go/no-go gate. A 14-day co-culture of the pMHC-II construct plus transient SIK3 inhibition in freshly isolated EoE-patient CD4+ T cells, reading iTreg/Tr1 conversion and suppressive function. The combination must increase conversion >2× over either agent alone — if it does not, Path B reverts to the Path A monotherapy plan.

Competitive whitespace: every EoE therapy clusters in the broad-mechanism, chronic-dosing corner; TOL-EoE occupies the antigen-specific, durable/one-course corner alone
The whitespace. Every approved and pipeline EoE therapy clusters in one corner — broad mechanism, chronic dosing. No agent is both antigen-specific and durable off-therapy. Tolera occupies the opposite corner alone.
The platform

PACT™ — the N-of-1 manufacturing thesis

Personalized therapy is only investable if manufacturing is tractable. PACT uses a shared, GPU-validated MHC-II backbone with a swappable peptide cassette — only the peptide changes per patient, so the expensive, regulated components are standardized and validated once. Vein-to-vaccine target: 6–10 weeks.

PACT platform: from an esophageal biopsy and blood draw through HLA typing, trigger profiling, epitope selection, construct assembly, GMP manufacture, to dosing
From one biopsy and blood draw to a patient-specific tolerance vaccine: read the patient's HLA×food×TCR triad, select the epitope, assemble on the shared backbone, formulate on nanoparticle, dose. Signal-1 (peptide) drives clonal anergy; Signal-2 (multivalent display) drives antigen-specific Tr1 (IL-10) induction.
Market

A ~$2.2B unmet need, sized against a real precedent

LayerDefinitionPatients (US)
PrevalenceUS EoE (~1 in 2,000)~167,500
DiagnosedClinically diagnosed (~60%)~100,500
SAMBiologic-eligible (moderate–severe / failing conventional care)~55,300
SOM (mature)Realistic annual serviceable share (~12% of SAM)~6,600 / yr
US market funnel and mature-year revenue by adoption scenario at $150k per course: conservative $0.66B, base $0.99B, upside $1.49B
Base-case SOM revenue ~$1.0B/yr at maturity (~6,600 patients × $150k one-course price). The adoption range is anchored to Tzield's real-world, screening-gated uptake — the bottleneck is screening infrastructure, not demand, which is why a companion diagnostic is a day-one deliverable.
Patient-centered differentiation

The voice-first thesis

Antigen-specific tolerance is a hard, worthwhile problem, and the field has built the groundwork Tolera stands on. EoE has no dedicated patient-focused drug-development (PFDD) meeting and no pMHC program yet — an opening to bring patient priorities in early, capturing them before the trial is designed rather than after.

Five cross-disease patient priorities mapped to the specific design requirements they demand of a tolerance vaccine
Five cross-disease patient priorities (from celiac, T1D, and EoE communities) mapped directly to the design choices they demand — one course over lifelong dosing, tolerogenic delivery over bare allergen, a low-burden schedule, an equitable companion diagnostic, and PRO instruments co-designed with patients.
Regulatory strategy

A platform IND, not one per patient

An EoE pMHC vaccine follows the trail blazed by Tzield (T1D), KAN-101 (celiac), and dupilumab (EoE). The plan pursues an expedited-designation sequence and engages FDA early on whether histologic remission can serve as a registration-enabling surrogate.

Regulatory and value-inflection timeline: Orphan Drug filing, INTERACT and Pre-IND meetings, GLP tox and GMP lots, IND submission, first-in-human, and Phase 2 proof-of-concept
The regulatory and value-inflection path across the seed-to-IND and Series-A-to-Phase-2 runways — a single platform IND built on the individualized-product framework validated by neoantigen cancer vaccines, with the companion diagnostic co-developed in parallel.
What it would take

Capital mapped to value inflections

~$8M carries the concept from validated in-silico design to a cleared IND and first-in-human dosing — the single largest de-risking step available today. A further ~$35M funds through the Phase 2 durable-remission proof-of-concept. These figures scope the work, not a raise.

Use of proceeds: $8M seed to IND plus first-in-human, and $35M Series A to Phase 2 proof-of-concept, broken down by category
Seed ($8M → IND + FIH) and Series A ($35M → Phase 2 PoC), allocated across functional validation, murine PoC, GLP tox, GMP/IND lots, the companion diagnostic, regulatory, and team.
Value-inflection timeline with each milestone tagged by the de-risking it delivers, across seed and Series A runways
Each milestone tagged with the de-risking it delivers — from Orphan Drug Designation through the IND clearance step-up to the Phase 2 durable-remission inflection where a dedicated organization and partnering make sense.
The full package

Documents

The complete Project Tolera package — business plan, scientific plan, financial model, market analysis, and investor deck. Everything below is downloadable.

This is an independent research roadmap, not a company prospectus or an offer to invest. It maps what a credible path from AI/ML design to first-in-patient could look like — a scoped brief for any biotech partner or funder who wants to take it forward. Preclinical-stage concept. Financial and market figures are illustrative planning assumptions grounded in public data, not guidance. Non-dairy epitope activity is a computational prior pending wet-lab validation. The food-trigger assay concept is patented (Hill/Spergel) — a freedom-to-operate / licensing consideration for anyone taking this forward. Not medical advice.