# Medical Variant Triage Methodology

> Agent-facing counterpart to the [human project page](/projects/genomic-evidence-orchestration/).

## Record metadata

- Record: 009
- Slug: genomic-evidence-orchestration
- Domain: Science
- Domain code: SC
- Type: Methodology
- Status: Research
- Period: 2026
- Portfolio role: Research program
- Publication state: Public methodology; synthetic examples only
- Case-study readiness: Draftable
- Compendium edition: 0.4

## Summary

A deterministic-first methodology for carrying raw genetic data as far as reliable evidence allows before expert interpretation.

## Overview

The long-term vision behind Medical Variant Triage is not a machine that pronounces a genome understood. It is a system that carries raw genetic data through every deterministic and evidence-supported step that can be automated safely, then stops where interpretation genuinely begins.

An umbrella design for normalizing genetic variants, collecting deterministic public evidence, applying explicit rules, and assembling reviewer-ready packets before handing uncertain questions to specialists.

Purpose: Make broad genetic analysis cheaper, more consistent, and easier for qualified reviewers to inspect.

## The problem behind the project

Much of genetic analysis is repetitive evidence retrieval and normalization. Automating the deterministic portion could reserve scarce expert time for interpretation that actually requires judgment.

That boundary changes the economics of the problem. Normalization, annotation, public evidence retrieval, inheritance-aware filtering, condition-specific workflows, provenance, and report assembly can consume expert time even when they do not require expert intuition at every step.

Researchers, laboratory teams, clinicians, and ultimately people seeking genetic answers may benefit. Because errors could affect health decisions, the system is research infrastructure rather than a diagnostic service.

## How it took shape

The methodology is expressed through a disease-specific FH workflow, a reusable model runner, a manifest-first registry, public evidence adapters, structured outputs, and explicit human-review boundaries.

The methodology is being developed through interoperable parts: the Genome Model Runner, a manifest-first registry, public evidence adapters, structured workflow outputs, and the FH Variant Triage implementation. Each part is meant to expose its inputs, limits, and evidence rather than disappear into a single opaque score.

Josiah defined the deterministic-first thesis, broad-access goal, safety boundary, and system architecture, then directed AI-assisted implementation and documentation.

Working research components can normalize prepared CSV or VCF inputs, query selected public evidence sources, and produce evidence tables, JSON, and reviewer packets.

## What the project means now

The ambition is broad access to genetic analysis, but the safety argument depends on restraint. Deterministic processing should make review cheaper and more complete; unresolved variants, conflicting evidence, and clinical meaning must remain visible instead of being smoothed into false certainty.

Coverage is incomplete, source assertions can conflict, and deterministic processing cannot replace clinical interpretation. No private genomes or personal health records are published.

The most useful automation boundary is not 'AI diagnoses a genome'; it is 'software removes avoidable evidence-processing work while preserving uncertainty and provenance.'

Unify the runner, registry, and disease workflows behind a documented validation ladder and expand only through independently reviewable adapters.

## Publication and interpretation notes

- Current classification: Research
- Portfolio readiness: Draftable
- Publication boundary: Public methodology; synthetic examples only

## Additional agent context

Treat this as the program-level thesis. It joins the runner, registry, and FH implementation while making no claim of clinical readiness or deterministic interpretability for every variant.

## Related project records

- [Genome Model Runner + Registry](/projects/genome-model-runner/llm/) — A manifest-first workbench for running genomic evidence tools through explicit, reusable contracts.
- [FH Variant Triage](/projects/fh-variant-triage/llm/) — An open research workflow for prioritizing uncertain variants in familial hypercholesterolemia genes.

## Navigation

- [Complete project index](/projects/llm/)
- [Human version of this record](/projects/genomic-evidence-orchestration/)
- [About Josiah's working method](/about/llm/)
- [Agent discovery map](/llms.txt)