The science

From scattered blood draws to a trajectory.

Serial ctDNA carries a signal that any single test throws away. Span reads the pattern of detections over time, and flags resistance while it's still below the limit of detection.

The core idea

A non-detect is not a zero.

When a liquid biopsy comes back negative, it doesn't mean the resistant clone is gone. It means the clone is below the assay's limit of detection (LoD). At low variant allele frequency, detection flickers, detect, non-detect, detect, because each draw samples a finite number of molecules (Poisson sampling).

A single value is blind during this sub-LoD dwell. So is its slope. But the rising rate of detections is not, and that is what Span models.

A synthetic HR+/HER2− breast-cancer case: Span flags resistance from the sub-LoD detection pattern roughly six months before imaging progression.
From the methods paper. Span alarms on the sub-LoD detection pattern (~6 months of lead in this synthetic demonstration) while a commodity snapshot raises no alarm before imaging progression.
The method

The Span detector: a censored-Poisson Bayesian latent-growth change-point test.

It models the biology of the assay directly, rather than fitting a curve to noisy numbers.

01

Model the detection process

Each draw's detect / non-detect is a Bernoulli outcome under Poisson sampling with LoD left-censoring, so non-detects inform the model instead of being discarded as zeros.

02

Test for a change-point

A sequential generalised-likelihood-ratio (GLR) test watches for an upward shift in each variant's detection rate, the earliest statistical sign a resistant clone is expanding.

03

Aggregate across mechanisms

Evidence is combined across competing resistance pathways (ESR1, PIK3CA, RB1, HER2), so the alarm reflects the whole resistance landscape, not one marker.

04

Fire at a calibrated threshold

The alarm is tuned to a matched false-alarm rate, so lead time is reported honestly against a controlled rate of false positives.

No trainable parameters. The advantage is structural, not learned.

Span is a transparent decision rule, there is nothing to overfit, and every alarm traces back to the detection pattern that produced it. That interpretability is a feature, not a limitation: it's what makes the method defensible to clinicians and regulators.

What it produces

A decision, ahead of time.

Span turns serial ctDNA, EHR context, and standard-of-care imaging into a patient trajectory, and reads three things off it.

  • 1Estimated time-to-resistance. How long the current line is likely to keep working.
  • 2The likely mechanism. Which resistance pathway is most probably emerging.
  • 3Ranked next-line options. The most promising subsequent therapies, including eligible trials.
See the evidence Read the paper (PDF)