Quantum machine learning driven optimization of nutrient-hormone interactions for enhanced in vitro regeneration of...

Common bean (Phaseoulus vulgarsis) is an important edible legume crop, but its improvement through modern biotechnological tools has been limited due to the lack of efficient and reproducible in vitro regeneration protocols. This bottleneck restricts the application of biotechnological applications like genetic transformation, genome editing, and crop improvement. To address the challenges, an experiment was designed to investigate the combined effect of KNO₃ with Indole Butyric acid (IBA) and naphthalene acetic acid (NAA) on shoot proliferation using two different explants, followed by optimizing the results with quantum machine learning (QML) analysis. Results demonstrated enhanced shoot proliferation with increased KNO₃ levels (5700 mg/L), with a shoot count of 6.44 from the shoot meristem explant in the presence of NAA. Whereas lower KNO₃ concentration enlarged the shoot length. Results also revealed the impact of auxin-explant interaction, highlighting the significance of a tailored medium for in vitro regeneration. To strengthen prediction and optimization, classical and quantum machine learning (ML) algorithms were also used. A custom quantum circuit, utilizing RX, RZ, and Hadamard gates, was introduced to enhance classification accuracy using quantum superposition and entanglement principles. Results demonstrated the superior performance of a custom quantum circuit with an accuracy and F1 score of 83% and 84% respectively, for shoot counts. Whereas comparable performance was observed for shoot length classification. This hybrid computational approach not only reduced experimental uncertainty but also increased the nutrient-hormone optimization. These findings demonstrate the potential of hybrid quantum-classical approaches in plant biotechnology. The optimized in vitro system can facilitate downstream applications in plant biotechnology for breeding of legumes and other crops.