STL-based Optimization of Biomolecular Neural Networks for Regression and Control

2025-09-05

AI Summary

Biological molecular neural networks (BNNs) face significant challenges in training regression and closed-loop control tasks when labeled target data are unavailable. Method: This paper introduces signal temporal logic (STL) into the BNN training framework for the first time, leveraging its quantitative semantics to define differentiable temporal specification objectives, thereby enabling gradient-based weight optimization without reliance on ground-truth labels. Contribution/Results: The proposed approach supports unsupervised regression inference and safety-guaranteed closed-loop control. Experiments demonstrate accurate identification of dysregulated biological states and precise anti-inflammatory regulation in a chronic inflammation model, while avoiding excessive responses to external pathogenic stimuli. This work establishes a novel paradigm for verifiable, interpretable, and safety-assured molecular intelligent systems tailored to biomedical applications.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Reasoning under Uncertainty: Stochastic Optimization
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Biomolecular Neural Networks (BNNs), artificial neural networks with biologically synthesizable architectures, achieve universal function approximation capabilities beyond simple biological circuits. However, training BNNs remains challenging due to the lack of target data. To address this, we propose leveraging Signal Temporal Logic (STL) specifications to define training objectives for BNNs. We build on the quantitative semantics of STL, enabling gradient-based optimization of the BNN weights, and introduce a learning algorithm that enables BNNs to perform regression and control tasks in biological systems. Specifically, we investigate two regression problems in which we train BNNs to act as reporters of dysregulated states, and a feedback control problem in which we train the BNN in closed-loop with a chronic disease model, learning to reduce inflammation while avoiding adverse responses to external infections. Our numerical experiments demonstrate that STL-based learning can solve the investigated regression and control tasks efficiently.

Problem

• Training biomolecular neural networks without target data
• Leveraging Signal Temporal Logic for training objectives
• Enabling regression and control tasks in biological systems

Innovation

• STL specifications define BNN training objectives
• Gradient-based optimization of BNN weights
• Learning algorithm enables regression and control tasks