PKU Market Atlas Everything PKU, at your fingertips. Open the atlas
Claude Life Sciences Hackathon Report · July 2026

We ran a hackathon on PKU tools. Here is what we found.

PKU families count the amino acid phenylalanine to the milligram, for life, and AI apps are starting to carry that work. This month, developers across the Claude hackathon are testing those tools with us. The first finding is clear: the AI can do the math, and the nutrition label is what holds accuracy back.

Found it

Sorting the food is the reliable step

Developers gave us strong formulas. The reliable move is to have the AI sort each food into the right protein type first. Sort it right and the phenylalanine number follows by arithmetic, so the same food returns the same answer every time.

Still open

Mixed foods are the hard part

Working out how much of each ingredient sits in a bowl, from a short ingredient list, has no settled method. This is the problem we are handing to every developer in the hackathon for the rest of the month.

Asking for help

Turning kitchen logs into evidence

Families already bridge the gap between the label and the real phenylalanine by hand, with a gram scale and mental math. We are building a way a computer can repeat, so those logs count as clinical research evidence.

Open community testing runs all month, starting at the NPKUA meeting this week.

Decentralized tests

Help us make reliable real-world evidence for PKU.

Open the repo, tell your agent to run AGENTS.md, and walk away. It sorts 719 foods into protein types three times, scores itself against USDA truth, and opens a pull request with the numbers. That is one more data point on which models estimate phenylalanine reliably.

Clone github.com/Cureledger/pku-commons and run AGENTS.md
New · PKU Market Atlas

Phenylketonuria, as a market.

The reliability work above is the science spine. This is the other half: PKU as a market. Coverage law state by state, every medical food and formula and drug, the companies, apps, medical devices, clinics, dietitians, dental, mental health, restaurants, schools, trials, advocacy, and litigation. 433 cited records so investors and innovators can see where the opportunities are.

~16,500 US patients $1-2B market no home phe monitor 15 datasets
Open the Market Atlas

The problem with USDA/FDA food data

Most PKU apps read phenylalanine from the same place, and that place runs out of answers exactly where families need them.

PKU apps generally read phenylalanine from USDA FoodData Central. It has measured phenylalanine for single ingredients like an egg or an apple. It has almost no phenylalanine for packaged, composed foods like a candy bar or a frozen meal.

For those foods, the record is just the Nutrition Facts label: protein rounded to the whole gram, and no amino acids at all. So the app guesses, and different apps guess differently. The result: families, clinicians and researchers do not know if they can rely on app data.

USDA cannot fix this by measuring 350,000 packaged products. The change that scales is to calculate phenylalanine from the recipe, using measured ingredient values, and to say so on every number.

PKU Commons does that. Every phenylalanine value carries how it was found, whether measured, calculated, or estimated, and how far it might be off. Apps get scored on the quality of their data first.

Choose your path

The same infrastructure serves three communities. Pick the door that fits you.

The problem we're solving

PKU (phenylketonuria) is an inborn error of metabolism: the body can't break down phenylalanine (phe), an amino acid in all protein. Left unmanaged, phe builds up and is neurotoxic. The treatment is a "diet for life," a very-low-protein diet that demands daily, gram-level precision.

Families can't use ordinary nutrition labels: protein grams are too coarse, and different protein sources carry different amounts of phe. So parents run an intuitive algorithm, deterministic math plus recipe-science judgment, to turn a label into a phe estimate, then weigh and log every bite.

A new wave of AI phe-estimator apps is taking the labor out of that grind. That's genuinely good news. But there is no standard by which a family can tell if an app is accurate, or by which a clinician can trust its output, and prototype results vary widely.

PKU apps also tend to go unmaintained. When a solo developer stops, the app stalls and families lose a tool their routine depended on.

PKU Commons is the shared spine: open method, open data, and a public accuracy benchmark. Quality lives in the eval, independent of any one author.

Three open building blocks

Each is independently reviewable and independently reusable.

Claude Skill

Phe-estimator Skill

Encodes the "think like a PKU parent" method: is this food countable (<2 g protein/serving)? Which ingredients carry phe? What's the recipe factor? Multiply by portion. Log it.

Knowledge

Living food list

A maintained low-protein foods reference, forked in part from Open Food Facts, that acts as a knowledge graph to raise reliability in the very-low-protein staple range.

Hardware

Bluetooth scale integration

Reverse-engineered gram-scale support so weighing flows straight into logging. Goal: connect the scale you already own instead of buying a new one.

The accuracy standard

The heart of PKU Commons is a public, reproducible benchmark. Every test case pairs a food label with a phe value computed from documented sources (USDA FoodData Central / Open Food Facts). Anyone can re-derive the "true" answer.

Any estimator, our Skill or any app implementing the interface, is scored the same way: error per case, mean absolute error, and percentage of estimates within a clinically-relevant tolerance band.

One benchmark, three jobs:

  • Families & clinicians get the standard for judging an app's accuracy.
  • Contributions are merged only when they improve the score without regressing. Apps stay trustworthy even after a developer leaves.
  • The community gets a leaderboard of performance over time (KPI #1).
How the benchmark works

How we keep it trustworthy: a two-layer review model

PKU Commons answers to two traditions at once. Clinicians and researchers ask "is this defensible?"; engineers and families ask "does it measurably work?" Those map onto two review methods. We use both, on different parts of the system.

Layer 1 · Method & data

Legal-style review, citation to authority

Every estimation rule and every food-list row carries a citation to authority (a USDA FoodData Central id, an Open Food Facts code, or a named clinician / dietitian sign-off), a version, and a reviewer of record. Challenges are filed as issues; resolutions become part of a permanent audit trail. The record shows what is in the knowledge base, why, on whose authority, and who can be asked.

Layer 2 · Estimator outputs

Scientific-style review, settled by measurement

Accuracy claims are settled by measurement against the public benchmark, independent of argument. Ground truth is reproducible from documented sources. Every estimator is scored the same way. Contributions merge only when they improve the score without regressing, enforced in CI. The benchmark above is this layer in action.

Why this makes tools last: quality is guaranteed by the review model, independent of any one author. Knowledge stands on cited authority. Performance stands on a reproducible benchmark. A tool can change hands, or lose its original developer entirely, and families still know it meets the bar.

Read the full model on GitHub

Devs: we challenge you to solve these

NPKUA's TruPKU / Voice of the Patient report catalogs the friction of living with PKU beyond the clinic and the lab. Each pain point below is a suggested hack for the PKU Commons community, a concrete place to point AI and devops at the real burden of living with PKU. Themes summarized from the public report; see pain-points.mdfor the source of record.

1 · The daily counting grind

Every food is weighed, calculated, and logged by hand. It becomes a tedious, never-ending accounting chore that families eventually abandon, and the clinic loses the data.

Hack: Cut estimation-to-log to one tap: label parse, scale weight, and auto-log, verified against the benchmark so families can trust it.

2 · Slow blood-phe feedback

Blood phe results come back 5 to 14 days later by mail. There is no timely link between what someone ate, how they feel, and their measured level.

Hack: Build the food, symptom, and level data link: structured logs ready to correlate as soon as faster home testing arrives.

3 · Labels don't speak PKU

USDA protein grams are too coarse. Phe per gram varies by protein source. Families reverse-engineer every label by hand.

Hack: Improve the ingredient-to-phe classifier and grow the living food list so the very-low-protein staples are covered and cited.

4 · Tools that fade away

Apps built by one parent or one small shop go unmaintained and disappear, leaving the families who relied on them without a tool.

Hack: Ship on shared, benchmark-gated infrastructure so an app keeps working and stays trustworthy after its author steps away.

5 · Real-world conditions break tools

Estimation happens in a grocery aisle on weak store Wi-Fi, one-handed, under time pressure, far from a lab.

Hack: Design for the aisle: offline-tolerant, low-bandwidth, and deterministic behavior, with graceful degradation when the network is poor.

6 · New drugs raise the stakes

Powerful new PKU therapies can over-correct into hypophenylalaninemia, which needs a fast dietary response, but the dietary data loop is slow.

Hack: Make dietary phe data fast and shareable enough to support quick, safe adjustments alongside modern treatment.

Solved one of these, or found a seventh? Open a PR or tell us what you think. Every accepted improvement is measured on the benchmark and credited on the leaderboard.