Find the Likely Responders Your Biomarkers Miss
Use tissue features as a lens: MiraTyper measures the biology that drives response, so patients outside the standard biomarker cut stop being invisible.
- Measure feature prevalence across archived cohorts before committing to a trial design
- Identify subpopulations outside the standard biomarker cut that share the responder phenotype
- Same measurements across H&E, spatial, and single-cell data, so cohorts are comparable
Three Steps, Agreed Up Front
Define the responder phenotype
Start from the patients who responded, and the features that separate them — immune infiltration, lymphoid structures, stromal organization, tumor architecture.
Screen the wider population
Run those measurements across archived slides and existing cohorts, including patients excluded by the current biomarker definition.
Size the opportunity
Report how many patients carry the phenotype, how they are distributed, and which features drive the grouping.
Measurements, Not a Verdict
Every number traces back to the region of the slide it came from, so the pathology team can check the work.
Feature prevalence by cohort
How common each measured feature is in every cohort screened, with distributions rather than a single cut-off.
Candidate subpopulations
Groups that share the responder phenotype but sit outside the current biomarker definition.
Comparable cross-platform measurements
One label space across H&E, spatial, and single-cell data, so cohorts from different sources can be pooled.
Evidence pack
Overlays and per-patient values behind every group, for review before a design decision.
What Has Actually Been Measured
MSI-high status accounts for roughly 15% of colorectal cancers, leaving a large microsatellite-stable majority that single-agent immunotherapy does not reach. Measuring immune phenotype directly is a way to look inside that majority rather than around it.
See what MiraTyper finds in your data
Add your details, pick a time and we will run two datasets for free. Quick and easy.
- 1. Your details
- 2. Choose a time
Choose a time to get started
Your request is saved. If none of these times work, we can follow up by email.
Loading available times…
Calendar not loading? Open scheduling in a new tab.
Before You Book
Can this run on old trial slides?
Yes, that is the usual starting point. Archived H&E is already collected and already consented for analysis in most trials; measuring it does not require new sample collection.
How do you avoid finding patterns that are not real?
Features are defined up front with the pathology team, not mined after the fact, and each detector is validated on orthogonal data. Prevalence is reported with distributions, and the pathologists review the overlays.
Can you combine our spatial data with H&E?
Yes. Cell type is the join key: the same ontology is applied to single-cell, spatial, protein, and H&E data, so measurements from different platforms sit in one label space.
What does a first engagement look like?
A focused pilot on one asset and one decision, scoped to three months, with success metrics agreed before any analysis runs.
Run two datasets for free
Bring one asset and one decision. We will tell you on the call whether the tissue can answer it.
P.S. The fastest version of this starts with slides that already exist and a phenotype that has already been observed.