Optimizing Gene-Based Testing for Antibiotic Resistance Prediction

TL;DR

This paper presents GenoARM, a novel framework combining reinforcement learning and transformer models to optimize gene test selection for antibiotic resistance prediction, enhancing diagnostic accuracy and efficiency.

Contribution

GenoARM introduces an innovative RL and transformer-based approach to optimize PCR gene test selection for antibiotic resistance diagnostics, outperforming existing methods.

Findings

GenoARM outperforms baseline models in predictive accuracy.

Incorporating metadata improves test selection and prediction.

The framework is effective across multiple bacterial pathogens.

Abstract

Antibiotic Resistance (AR) is a critical global health challenge that necessitates the development of cost-effective, efficient, and accurate diagnostic tools. Given the genetic basis of AR, techniques such as Polymerase Chain Reaction (PCR) that target specific resistance genes offer a promising approach for predictive diagnostics using a limited set of key genes. This study introduces GenoARM, a novel framework that integrates reinforcement learning (RL) with transformer-based models to optimize the selection of PCR gene tests and improve AR predictions, leveraging observed metadata for improved accuracy. In our evaluation, we developed several high-performing baselines and compared them using publicly available datasets derived from real-world bacterial samples representing multiple clinically relevant pathogens. The results show that all evaluated methods achieve strong and reliable performance when metadata is not utilized. When metadata is introduced and the number of selected genes increases, GenoARM demonstrates superior performance due to its capacity to approximate rewards for unseen and sparse combinations. Overall, our framework represents a major advancement in optimizing diagnostic tools for AR in clinical settings.