Presentation:
Canary Circuit Slides
:contentReference[oaicite:0]{index=0} (HD) is a fatal inherited neurodegenerative disorder caused by a CAG trinucleotide repeat expansion in the HTT gene.
Although individuals are born with this mutation, neurons remain functionally stable for most of life. Rapid degeneration occurs only after the repeat crosses a somatic threshold of approximately 150 CAGs. This process is described by the ELongATE model.
This project proposes Canary Circuit: a two-part computational and conceptual framework that:
Like a canary in a coal mine, the circuit is intended to signal danger before the critical threshold is crossed.
Huntington’s disease is an autosomal dominant disorder. Global prevalence has increased from 2.71 to 4.88 per 100,000 individuals, with founder-effect populations reaching dramatically higher frequencies.
Although the mutation is inherited at birth, symptoms emerge only after decades, followed by rapid neurological decline. This prolonged pre-symptomatic phase historically lacked a mechanistic explanation.
Handsaker et al. (Cell, 2025) demonstrated that the delay arises from somatic repeat expansion. Using single-cell measurements of CAG repeat length and genome-wide gene expression in human striatal neurons, the study showed:
This progression is formalized as the ELongATE model, which divides disease progression into five sequential phases (A–E).
The study established that somatic expansion itself — rather than inherited repeat length alone — is the proximal driver of neuronal degeneration.
Independent studies further support this framework.
The ELongATE model remains descriptive rather than mechanistic.
It identifies:
but does not resolve the minimal regulatory system connecting:
Without this mechanistic layer, predicting individual disease trajectories or designing targeted interventions remains difficult.
Neurons spend more than 95% of their lifespan in a pre-symptomatic but unstable state — creating a potentially large therapeutic intervention window.
The Canary Circuit specifically targets this silent transition period.
The first aim validates whether the PINN can recover the biology observed experimentally by Handsaker et al.
Using:
the network is trained by minimizing both:
This aim establishes the computational foundation for subsequent aims.
This aim moves from validation into mechanistic inference.
The objective is to determine why expansion accelerates during the Phase A → B transition.
Modifier genes identified through GWAS are incorporated as PINN covariates:
Additional analyses include:
A minimal regulatory graph identifying the components most predictive of transition timing.
This is the primary novel contribution of the project.
The third aim translates the inferred regulatory graph into the Canary Circuit.
The circuit detects signatures of Phase B acceleration before the ~150 CAG toxicity threshold is crossed.
The circuit is simulated using ordinary differential equations (ODEs).
The hypothesis is that the circuit can discriminate:
using inferred regulatory dynamics.
| Dataset | Source | Role in Project |
|---|---|---|
| Single-cell CAG + expression data | Handsaker et al. (2025), NeMO | PINN observational constraint |
| GWAS modifier genotypes | GeM-HD Consortium | Covariate selection |
| Multi-region transcriptomics | Mätlik et al. (2024) | Cross-regional comparison |
Only open-access components of the datasets are used.
Controlled-access sequencing data requiring dbGaP approval is not included in this project.
The biological dynamics are modeled using the Handsaker CTMC master equation.
Per-cell repeat lengths are binned into donor-level probability distributions.
The PINN is trained on distributions rather than individual cells.
A feedforward neural network learns the expansion-rate functions:
where ( n ) is repeat length.
Leave-one-out cross-validation across six deeply sampled donors.
Primary metric:
The discrete CTMC is expressed in its continuous Fokker–Planck limit:
:contentReference[oaicite:1]{index=1}
where:
The model tracks the full population distribution of neurons.
Initially, neurons cluster near inherited repeat lengths (~42 CAGs). Over time, the distribution:
The drift component:
:contentReference[oaicite:2]{index=2}
controls directional expansion.
Within the Canary Circuit framework:
High MSH3 activity increases drift magnitude, while FAN1-associated stabilization reduces it.
The diffusion component:
:contentReference[oaicite:3]{index=3}
captures stochastic variability between neurons.
Even identical starting repeat lengths diverge over time due to:
Without diffusion, the model predicts a narrow deterministic wave rather than the experimentally observed broad distribution.
The original CTMC is discrete and difficult to differentiate directly within neural-network optimization.
The Fokker–Planck approximation is continuous and differentiable, enabling automatic differentiation during PINN training.
Rather than repeatedly solving simulations numerically, the PINN learns a continuous approximation:
:contentReference[oaicite:4]{index=4}
Once trained, the model can estimate distributions for arbitrary modifier combinations using a single forward pass.
GWAS modifiers identify which DNA repair genes alter HD onset timing.
Selected modifiers include:
Expression values from the Handsaker dataset are incorporated as continuous covariates affecting expansion-rate parameters.
Published knockout measurements initialize directional effects before fitting to human single-cell data.
The minimal regulatory graph is inferred by:
Cross-regional transcriptomic datasets are analyzed to determine whether transition dynamics are striatum-specific.
The Canary Circuit is simulated as a two-node ODE system.
Represents:
Represents a threshold-activated reporter.
The output crosses a detection threshold during the Phase B acceleration window.
SciPy odeint in Python.
The ~150 CAG threshold used during PINN training originates from the same Handsaker dataset.
This creates unavoidable circularity within a single-cohort cross-sectional dataset.
The PINN therefore does not independently discover the threshold; it incorporates it as prior biological knowledge.
The PINN recovers dynamics by embedding the CTMC master equation directly into the optimization process.
Recovered parameters therefore depend strongly on the assumptions built into the governing equations.
The model is trained on six deeply sampled donors with inherited repeat lengths between 40–43 CAGs.
Generalization to:
remains uncertain.
The ~150 CAG threshold is treated as invariant.
If thresholds differ across:
then recovered parameters may become biased.
All datasets are:
No new patient data is collected.
The project is entirely computational.
If implemented experimentally in the future:
Additionally, because HD disproportionately affects founder-effect populations such as the Lake Maracaibo community, equitable access and community engagement must remain central to any future translational development.