NeuronDiscover separates causes of brain fluid transport in neurons
NeuronDiscover: Agent-in-Twin for Mechanistic Discovery in Neuronal Microenvironments with World Action Models
Machine Learning
Summary
Understanding how fluids and signals move around neurons is tricky because errors in models can look like real changes in the brain. The authors designed a system called NeuronDiscover that acts like a digital twin to suggest smart experiments. This system helps figure out whether observations come from true brain mechanisms or just model errors, improving confidence in findings. They tested it with simulated brain data and real neuron recordings, showing it identifies correct explanations better than existing methods.
What this means in practice
- •For neurotechnology developers: Design targeted experiments distinguishing real brain transport mechanisms from modeling errors to improve neuro-device function.
- •For pharmaceutical researchers: Guide mechanistic experiments in neuron environments to better understand drug effects on fluid transport and neuronal response.
Authors
Haowei Xu, Wanyi Fu, Hongbin Han, Zhaoheng Xie
Abstract
Mechanistic discovery in neuronal microenvironments requires interventions and measurements that separate competing explanations of solute transport and neuronal response. Predictive accuracy cannot settle the question: a real mechanistic change and an error in the computational twin leave the same signature in sparse observations. We formalize this twin confounding and reason over a joint mechanism--discrepancy belief, designing experiments that separate the two. NeuronDiscover is an Agent-in-Twin framework whose shared, mechanism-grounded World Action Model (WAM) couples prediction, intervention proposals, and observation design; independently adjudicated outcomes revise a scoped Mechanism--Intervention--Observation--Outcome (MIOY) graph, whose supported relations compile into executable programs carrying discrepancy-adjusted acceptance bounds. We evaluate on simulated brain-fluid tracer-transport worlds adjudicated by an independently frozen finer-mesh reference solver, and on donor-disjoint public current-clamp recordings of cortical neurons. Counting only relations that reach a certified terminal status, and scoring abstentions as unresolved for every method, at a matched budget of 16 experiments over 32 source units NeuronDiscover resolves 4.0 relations per assigned world against 3.4 for the strongest baseline and 3.2 without graph revision, at 5% false support and 82% scope accuracy. Joint mechanism--discrepancy acquisition resolves 3.8 relations versus 2.9 for plug-in expected information gain; discrepancy-adjusted verification lowers accepted-program failure from 15% to 9% at 60% acceptance coverage; and transfer to the recordings yields 1.94 versus 1.53 relations per assigned world. Correctness is adjudicated within declared model worlds and archival recordings.