The platform · Disease + Drug + ConductorBuilt on transcriptomic foundations
The platform

Drug discovery asks: does this molecule hit its target?We ask: what does it do to an entire cell?

Three integrated systems — all built on the same transcriptomic foundation. Disease, drugs, and the models that connect them — and every molecule we test feeds back in, so the platform sharpens with each cycle.

Pillar · 01
Disease Signature Atlas

Mapping disease at the resolution of cells

Every disease leaves a transcriptomic signature — a pattern across thousands of genes, in specific cell types. Most platforms measure a handful; we measure them all, in patient-derived tissue at single-cell resolution. Then we build validated signatures — fusing expression, human genetics, and mechanism — so we target what causes a disease, not just what shifts with it.

Patient-derived
Sourced from the cell types where the disease actually unfolds
Full transcriptome
Thousands of genes, not a curated short list
Single-cell + bulk
Cell-type resolution where it matters, breadth where it helps
Longitudinal
Snapshots across disease stages where available
Expression · patient-derived tissuescRNA-seq
64 cells →
LowHigh
Drug signatureProfiled compound · full perturbation profile
Pillar · 02
Drug-Gene Atlas

Measuring everything a drug perturbs

We don't screen blindly. The disease signature tells us which compounds are worth profiling — then DRUG-seq measures the full transcriptomic response of each, at dose, in disease-relevant human cells. A drug doesn't just hit one target: every compound changes the expression of thousands of genes, intended and unintended. We capture the whole profile.

Profiled in context
Every compound, measured in the cell type where the disease lives.

Most drug screens run in immortalized cancer cell lines — convenient, but disconnected from the biology that matters. We profile compounds in human-derived, disease-relevant cells. The response we measure is the response that matters.

iPSC neuronsMotor neuronsFibroblastsMuscle progenitorsCardiomyocytesHepatocytes
Pillar · 03
Conductor AI · Matching

Finding the drugs that reverse disease

Machine-learning models trained on the union of both atlases. The Conductor asks: what compounds, alone or in combination, push a diseased cell back toward health? It surfaces reversal candidates no human could enumerate by hand.

Trained on both
Disease signatures + drug perturbations in one space
Combination-aware
Surfaces single agents and combinations
Cell-type aware
Predictions tied to the cell types that matter
Iterates with the lab
Wet-lab confirmations feed back into the model
Disease signature19q12 · Autism Spectrum Disorder
Candidate · rank #1 of 22Reversal score +0.000
22 candidates · ranked by reversal scoreauto-cycling
Reversal score = how strongly the compound's signature inverts the disease's
03b · Conductor AI · Virtual screening

Beyond matching known drugs — searching for new ones.

Conductor AI predicts which molecules should produce a target transcriptomic profile, then screens billions of on-demand, synthesizable compounds in silico — narrowing a library no chemist could enumerate by hand to a shortlist worth synthesizing.

Predict
Which structures should produce the target signature
Screen
Billions of synthesizable compounds, in silico
Validate
Top candidates synthesized and bench-tested at full transcriptomic resolution
Iterate
Every wet-lab result trains the next round
Predicted reversal
+0.41
Conductor AI · designing the reverser
What the platform produces

A pipeline that doesn't wait for a single moonshot.

Tier 1

FDA-approved compounds

Enter repurposing trials fastest. Validate the matching method against established safety.

Months to clinic
Tier 2

Late-stage clinical assets

Carry existing safety data forward. New indications discovered through the Drug-Gene Atlas.

12–24 months
Tier 3

Novel molecules

Discovered by Conductor AI for a target signature. Deepest therapeutic potential.

Multi-year, highest ceiling

Together, the three tiers generate staggered clinical proof-of-concept — validating the platform while advancing programs. Capital flows to the matches the data supports, and away from the ones it doesn't.

Meet the team →Partner with us