Built with Claude: Life Sciences Hackathon · 2026

Open therapeutic science, from target to a fundable plan.

I'm Ruth-Anne Pai, PhD — an immunologist, protein designer, and person living with eosinophilic esophagitis (EoE). In one week I built an end-to-end body of work: mining EoE omics to nominate targets, designing antigen-specific protein therapeutics with ESM-family and folding models, and packaging it all into reusable software, manuscripts, and a development plan. Everything here is open.

9
pMHC-II tolerance constructs designed & folded
0.87–0.90
ipTM across the structural panel
8
open-source repositories
2
manuscripts drafted
Find your path

Where would you like to start?

The work spans data mining, protein design, software, and a full biotech plan. Pick the entry point that fits you — each card points to the pages built for you.

Patient-led nonprofit & advocates

Tools that work for any disease

The Therapeutic Program Architect turns your community's disease into a full, human-in-the-loop drug program. And the EoE plan was written patient-voice-first.

Scientists using protein models

pMHC-II design & effector-target binders

Read the methods and structures behind the antigen-specific tolerance work and the CCL26/POSTN binder designs.

Biotech, investors & partners

Project Tolera — a roadmap to patients

The full package: platform thesis, market, competitive whitespace, regulatory path, budget, and milestones.

Developers & Claude Science users

Reusable skills & pipelines

Eight open repositories — skills for target mining, epitope mapping, market analysis, peer review, and media.

Academics & data scientists

Omics-mined targets, reproducibly

A ten-stage pipeline from public GEO/PRIDE/CELLxGENE data to a ranked, druggability-annotated target shortlist.

Just curious?

The one-week story

How a citizen-scientist took EoE from "here is a disease" to IND-ready design and a plan — all in public.

What the week produced

Three integrated streams

Data mining

Targets from public omics

Transcriptomic, proteomic, and single-cell EoE datasets mined for dysregulated genes, pathways, and cell populations — surfacing high-evidence, low-competition targets like CCL26 and POSTN.

Protein design

Antigen-specific therapeutics

A 9-construct pMHC-II tolerance panel across dairy, wheat, and soy triggers — folded, groove-validated, and formulated on a multivalent nanoparticle — plus CCL26/POSTN effector-target binders.

Plan & tools

From design to fundable plan

A disease-agnostic drug-program pipeline, a patient-voice-first business and scientific plan, and open repositories anyone can pick up and run.

EoE target landscape: literature evidence versus clinical maturity, sized by opportunity score
The EoE target landscape that anchored the week: strong biology, thin pipeline. High-evidence, no-trial targets (CCL26, POSTN, IL-13, CAPN14) mark the unexploited biology this work set out to address.