A PBN-RL-XAI Framework for Discovering a "Hit-and-Run" Therapeutic Strategy in Melanoma

TL;DR

This paper introduces a computational framework combining probabilistic Boolean networks, reinforcement learning, and explainable AI to identify a novel, time-dependent therapeutic strategy to overcome immunotherapy resistance in melanoma.

Contribution

It develops an integrated PBN-RL-XAI framework that uncovers a specific, multi-step intervention to reverse resistance mechanisms in melanoma.

Findings

A 4-step LOXL2 inhibition effectively erases resistance signatures

The intervention allows the network to self-correct without continuous treatment

The framework provides a new approach for discovering complex therapeutic protocols

Abstract

Innate resistance to anti-PD-1 immunotherapy remains a major clinical challenge in metastatic melanoma, with the underlying molecular networks being poorly understood. To address this, we constructed a dynamic Probabilistic Boolean Network model using transcriptomic data from patient tumor biopsies to elucidate the regulatory logic governing therapy response. We then employed a reinforcement learning agent to systematically discover optimal, multi-step therapeutic interventions and used explainable artificial intelligence to mechanistically interpret the agent's control policy. The analysis revealed that a precisely timed, 4-step temporary inhibition of the lysyl oxidase like 2 protein (LOXL2) was the most effective strategy. Our explainable analysis showed that this ''hit-and-run" intervention is sufficient to erase the molecular signature driving resistance, allowing the network to self-correct without requiring sustained intervention. This study presents a novel, time-dependent therapeutic hypothesis for overcoming immunotherapy resistance and provides a powerful computational framework for identifying non-obvious intervention protocols in complex biological systems.