Abstract: A neural network is trained for, and may be used in, the simulation of the fluid flow through a domain around an object geometry. A first training process for the neural network includes training (902) the network on a first set of encodings of pre-computed computational fluid dynamics (CFD) simulations for object geometries and associated boundary conditions. The first training process uses a first loss function that evaluates an error between the network output and the pre-computed CFD simulations. A second training process is then carried out which includes training (905) the network on a second set of encodings of object geometries and associated boundary conditions. The second training process uses a second loss function that evaluates an error between the network output and a set of fluid dynamics conditions.

Abstract: A method for identification of circulating tumor cells (CTCs) in a blood sample uses magnetic enrichment and a nanowell assay. The CTCs are magnetically labeled with cancer cell markers conjugated to magnetic nanoparticles and then separated by passing the blood sample through a magnetic sifter. The enriched CTCs are then loaded into a microfluidic single-cell molecular assay comprising an array of 25,600 or more nanowells, each containing at most a single one of the CTCs. Using multiple fluorescent gene markers, simultaneous multiple-color multiplexed gene expression of the CTCs is performed, preferably using RT-PCR. Images of fluorescence signals from individual nanowells are analyzed to identify CTCs.

Abstract: A method for identification of circulating tumor cells (CTCs) in a blood sample uses magnetic enrichment and a nanowell assay. The CTCs are magnetically labeled with cancer cell markers conjugated to magnetic nanoparticles and then separated by passing the blood sample through a magnetic sifter. The enriched CTCs are then loaded into a microfluidic single-cell molecular assay comprising an array of 25,600 or more nanowells, each containing at most a single one of the CTCs. Using multiple fluorescent gene markers, simultaneous multiple-color multiplexed gene expression of the CTCs is performed, preferably using RT-PCR. Images of fluorescence signals from individual nanowells are analyzed to identify CTCs.