Dry Lab
Overview
Our dry lab encompasses two pivotal domains: computational biology and machine learning.
Computational Biology
Within the realm of computational biology, we undertook the molecular docking of the ZAP1 protein with its internal transcribed spacer (ITS) rDNA. This critical analysis allowed us to explore and characterize the various conformations in which these two entities interact and bind. The insights gained from these simulations are invaluable, as they illuminate the binding mechanisms and affinities of the ZAP1 protein, providing a deeper understanding of its functional role as a biomarker in our project. By elucidating these molecular interactions, we can better inform the design and operational efficacy of our detection kit.
Machine Learning
On the machine learning front, we developed a sophisticated model capable of detecting Red Rot disease from images of sugarcane stems and leaves. When implemented on a larger scale, this model has the potential to significantly reduce operational costs while simultaneously promoting the health and productivity of sugarcane crops. By harnessing advanced algorithms, our model can identify the early signs of Red Rot disease, enabling timely intervention and management strategies that are critical for sustaining agricultural yields.
The integration of these two components—molecular docking simulations and machine learning detection models—creates a robust framework that not only advances our scientific understanding but also fosters practical applications in agriculture. The molecular insights derived from the docking studies, coupled with the predictive power of our machine learning model, enhance our capacity to tackle the challenges posed by plant diseases effectively.
