The Causal Data Layer

9 billion possible variants.
Less than 0.05% are understood.

Codebreaker edits variants into primary human cells and measures what they actually do. Genomics learned to read; our CODEX drives AI that understands.

12345678910111213141516171819202122XYCODEXCAUSAL DATA LAYERFOR GENOMICS AI
3
Atlases
in build
10,000s
Variants edited
in parallel
1 bp
Causal resolution,
measured
10
Indications
named in the pipeline
9.3 billion possible single-nucleotide variants (3.1 Gb reference × 3 alternate bases). ClinVar holds ~3.9M variant records; ~1.9M carry a classification other than “uncertain significance” — 0.02% of the possible space.
The Thesis

Nature varies one base at a time. So must the data.

Human variation is overwhelmingly single-nucleotide, and WGS and GWAS return it that way. A model trained on gene knockouts is one full resolution coarser than the question it is asked.

GENE-LEVELONE GENEON / OFF1 MEASUREMENTOne answer per gene: present, or absent.VARIANT-LEVELMEASURED EFFECT1000+ MEASUREMENTS · SAME GENEOne answer per base: which one, and how much.
The existing paradigm

Gene-level, in cell lines

  • Deletes whole genes — patients carry variants, not knockouts
  • Runs in immortalized lines standing in for patient biology
  • A trillion cells at the wrong resolution is still the wrong resolution
Codebreaker

Variant-level, in primary human cells

  • The same unit a WGS or GWAS hands you, and the same unit the model must predict
  • Tested in the disease-relevant primary cell, not a stand-in line
  • Breaks linkage — variants tested one at a time, at scale
CODEX

Not one dataset. An Atlas at a time.

Each Atlas is a finished, licensable asset the day it completes — measured data and the models trained on it. Every one deepens CODEX.

01

Our AI reads everything

Models trained in-house mine the world's genetic evidence and nominate every variant worth testing. For most of the field, in-silico prediction is the finished product. For us it is step one.

What step 01 reads
GWAS CatalogClinVarBiobank cohorts Published case literaturePartner datasets
02 in parallel

Map the variants

Multiplexed CRISPR in the disease-relevant primary human cell. Runs with or without a partner.

Partner with the KOL

Where a cohort investigator is involved, they bring direction, credibility and clinical reach.

03

Test in parallel

10K variants — every program sharing a cell type runs at once.

04 license either, or both

Ship the Atlas

The reference causal variant-to-function dataset for that indication.

Build / train the AI

Models trained on that Atlas. License the insights in addition to the data, or instead of it.

↻ Every completed Atlas compounds into CODEX
Atlases

Three in build. A designed pipeline behind them.

Every locus resolved to the single base, across the whole genome. Lanes are cell-type platforms — everything inside a validated lane can start immediately.

12345678910111213141516171819202122XYchr158 LOCIchr537 LOCIchr1629 LOCICODEXIBD · 320+ LOCI3 REGIONS · GENOME-WIDERESOLUTIONONE GENE1 TO 1,000s OF VARIANTS TESTED INDIVIDUALLY · 1 bp RESOLUTIONT-cellVALIDATED · RUNNING9 INDICATIONSPediatric ImmunologyIN BUILDLeukemia (Pediatric)IN BUILDLeukemia (Adult)IN BUILDInflammatory bowel diseaseIN DESIGN320+ LOCIRheumatoid arthritisIN DESIGN100+ LOCILupus (SLE)IN DESIGN100+ LOCIAsthmaIN DESIGN100+ LOCIPsoriasisIN DESIGN80+ LOCIAtopic dermatitisIN DESIGN75+ LOCIFibroblastSTANDING UP3 INDICATIONSGastrointestinal diseaseIN DESIGNTBDIN DESIGNTBDIN DESIGNiPSCNOT YET BUILT1 INDICATIONOpen lane — partner-nominatedINVITATIONPOSITIONS ILLUSTRATIVE PENDING ATLAS DATA
Scroll the figure sideways to see every lane

Atlas pipeline, as a table

Cell-type platform lanes and the indications in each
Cell platformIndicationStatusPublished loci
T-cellPediatric ImmunologyIn Build
T-cellLeukemia (Pediatric)In Build
T-cellLeukemia (Adult)In Build
T-cellInflammatory bowel diseaseIn Design320+
T-cellRheumatoid arthritisIn Design100+
T-cellLupus (SLE)In Design100+
T-cellAsthmaIn Design100+
T-cellPsoriasisIn Design80+
T-cellAtopic dermatitisIn Design75+
FibroblastGastrointestinal diseaseIn Design
FibroblastTBDIn Design
FibroblastTBDIn Design
iPSCOpen lane — partner-nominatedInvitation
Throughput
10,000s

Variants edited and read out in parallel, in a single run.

Design → AI insights
1 quarter

The pipeline is built to go from variant library to queryable Atlas within a quarter.

Resolution
1 bp

Single-nucleotide causal effect, not regional association.

Cell platforms
2

1 live · 1 standing up. T-cell validated and running; fibroblast in stand-up.

Counts reflect published literature screened during pipeline design. Indications marked In Design are not committed programs.
Partner With Us

Bring what you have. We map causation.

Five ways in. Every one of them starts with something you already own.

Research & Academia

Bring your GWAS

Loci you could never test functionally become measured causal answers. Direction stays with you.

Talk to us about your GWAS →
Hospitals & Health Systems

Bring your WGS / WES

Measured functional evidence for the variants your panels can't interpret.

  • Decision support for uncertain variants in Atlas indications
  • Immunology and autoimmune program support
  • Clinical trial matching and enrollment
Talk to us about your data →
BioPharma

Bring your drug

Causal genetics across the asset lifecycle, from target through label.

  • Target validation
  • Trial WGS / WES — responder vs. non-responder
  • Safety signal attribution
  • Indication expansion

Sponsor programs run ring-fenced. Your data enters CODEX only on your license terms.

Talk to us about your program →
Telehealth

Bring your indication

License an Atlas as the interpretation layer inside the patient funnel you already own.

Talk to us about your indication →
Genomics Platforms

Bring your interpretation AI

Ground-truth your models on measured causal data, not statistical association.

Talk to us about licensing →
Company

Built by the people who made editing industrial.

Twenty-five years of genome engineering — the technologies that made programmable editing a process you can run at scale and on a schedule.

Ryan T. Gill
Ryan T. Gill
Co-Founder, CEO & Director
Inscripta · Artisan · SynBio pioneer
LinkedIn
Tanya Warnecke-Gill
Tanya Warnecke-Gill
Co-Founder, CTO & Director
Inscripta CTO · Artisan CTO · 35+ patents
LinkedIn
Ryan Layer
Ryan Layer
Co-Founder & CSO
CU Boulder · BioFrontiers · Variant AI
LinkedIn

Board of Directors

Sandy Zweifach
Sandy Zweifach
Chairman
LinkedIn
Dalton Wright
Dalton Wright
Director
Kickstart Ventures
LinkedIn
Mark Lupa
Mark Lupa
Director
Buff Gold Ventures
LinkedIn
Ryan T. Gill
Director
Co-Founder & CEO
Tanya Warnecke-Gill
Director
Co-Founder & CTO

Scientific & Industry Advisors

Chris Voigt
Chris Voigt
Chairman, SAB
MIT
Alisa Gaskell
Alisa Gaskell
Chief Genomics Officer
Children's Hospital Colorado
Matt Childs
Matt Childs
Professor, Genomics
Imperial College London
George Church
George Church
Professor, Genetics
Harvard
Greg Findlay
Greg Findlay
Professor, Genomics
The Francis Crick Institute
Aaron Quinlan
Aaron Quinlan
Professor, Genetics
University of Utah
Dieter Weinand
Dieter Weinand
CEO (former)
Bayer HealthCare
Stefan Wildt
Stefan Wildt
CTO (former)
Takeda

Backed by

Kickstart Ventures
Buff Gold Ventures
Denver Ventures
Service Provider Capital
Collaborate

Which variants would you test if you could?

A GWAS never functionally resolved. A platform that needs a causal layer. A model that needs ground truth.

Bring your GWAS

You published the loci. We return causal, variant-level answers.

Bring your platform

Embed causal interpretation where you already own the customer.

Bring your model

Measured causal labels at single-nucleotide causal resolution.

Bring your patients

Clinical decision support built on the Atlas for your population.

Your privacy choices

We would like your consent before any analytics or marketing technology is loaded on this site. Nothing in those categories loads unless you allow it. Strictly necessary storage — used only to remember this choice — is always on. See our Privacy Policy.