Abstract: A computer-implemented method is proposed in a computer-assisted design (CAD) system. In one embodiment, the method obtains gradients of an objective with respect to CAD parameters of a shape in a coordinate space, where the shape is obtained from the CAD parameters. The obtained gradients may then be used to modify the CAD parameters by applying a gradient descent algorithm aimed to maximise or minimise the objective. The present invention thus proposes a differentiable parametric CAD system comprising an artificial neural network, and which can be applied on top of any CAD software tool.

Abstract: A bioprinter for fabricating three-dimensional (3D) cell constructs, the bioprinter comprising one or more holding reservoirs for holding a fluid sample; a printstage for holding a sample container and supporting a substrate on which a 3D cell construct is to be printed; a sample loading system in fluid communication with the one or more holding reservoirs, the sample loading system configured to load a sample from a sample container into the one or more holding reservoirs; a pump in fluid communication with the sample loading system, the pump configured to draw the sample out of a sample container and pump the sample into the one or more holding reservoirs; and a droplet dispensing system in fluid communication with the one or more reservoirs, the droplet dispensing system configured to print sample droplets from the one or more reservoirs onto a substrate supported by the printstage.