3D bioprinting has transformed tissue engineering and cancer studies by enabling the precise creation of biomimetic structures with controlled properties. Despite its progress, the technique faces challenges due to numerous variables affecting printing quality and cell behavior. Traditional optimization methods are time-consuming and costly, relying heavily on trial and error. This talk introduces a novel approach using Bayesian optimization on neural networks to enhance cell viability and functionality during bioprinting. We developed and validated neural network models for gelatine and alginate-based bioinks and extrusion-based bioprinting, demonstrating superior predictive performance. Additionally, a cellular automata model is presented to predict post-printing cell behavior within 3D constructs, accurately simulating in-vitro observations. These computational frameworks offer significant advancements and reduce experimental repetitions.