Journal of Applied Data Sciences
Vol 6, No 3: September 2025

Modeling Neuroelectrical-Microbiome Crosstalk: AI-Driven Insights into Gut-Brain Bioelectrical Signaling

Fadhil, Shumoos Aziz (Unknown)
Radif, Mustafa (Unknown)
Alrammahi, Atheer Hadi (Unknown)



Article Info

Publish Date
12 Jul 2025

Abstract

The gut-brain axis, traditionally understood as a chemical communication network, is reconceptualized in this study as a bidirectional bioelectrical system. This paper introduces a novel framework for exploring host–microbiome interactions through neuroelectrical signaling, integrating Artificial Intelligence (AI)-based modeling with experimental insights. The objective is to assess how microbial metabolites, especially Short-Chain Fatty Acids (SCFAs) such as butyrate (1.5–3.5 mM), modulate host membrane potentials, and how these bioelectrical changes influence microbial behavior. Using a hybrid simulation platform combining Recurrent Neural Networks (RNNs) and Graph Neural Networks (GNNs), we modeled dynamic interactions within a low-inflammation gut environment. Results demonstrated that increasing butyrate concentration from 1.5 to 3.5 mM led to a depolarization of enteric neurons from –70.0 mV to –63.1 mV over 24 hours. This shift was associated with a 2.5-fold increase in microbial diversity index and a suppression of pathogenic Enterobacteriaceae. SHAP (SHapley Additive exPlanations) analysis identified butyrate concentration (+0.43) and potassium channel expression (+0.27) as top contributors to excitability enhancement. Additionally, the simulation predicted improved gut motility and increased abundance of beneficial taxa such as Bifidobacterium. These findings suggest a previously underappreciated electrical layer of gut-brain communication that complements chemical pathways. The novelty of this work lies in its systems-level approach that quantifies and predicts the reciprocal influence between microbial activity and host electrophysiology. By combining bioelectrical principles with AI-driven simulation, the study contributes a mechanistic understanding and virtual testing environment for neuroelectrical-microbiome dynamics. This research opens new avenues for non-invasive interventions—such as dietary modulation or vagus nerve stimulation—to treat microbiome-related neurological and gastrointestinal disorders.

Copyrights © 2025






Journal Info

Abbrev

JADS

Publisher

Subject

Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management

Description

One of the current hot topics in science is data: how can datasets be used in scientific and scholarly research in a more reliable, citable and accountable way? Data is of paramount importance to scientific progress, yet most research data remains private. Enhancing the transparency of the processes ...