Abstract: Systems and methods that receive as input microscopy images, extract features, and apply layers of processing units to compute one or more sets of cellular phenotype features, particularly antibodies, corresponding to cellular densities and/or fluorescence measured under different conditions. The system is a machine learning architecture having, in one aspect, a deep neural network, typically a convolutional neural network. The deep neural network can be trained and tested directly on raw microscopy images. The system computes class specific feature maps for every phenotype variable using a deep neural network. The system produces predictions for one or more reference antibody variables based on microscopy images within populations of cells.

Abstract: A multi-layer filter combination having a macrofilter layer with a predetermined thickness and two major sides including porous material impregnable with bacteria-destroying medication and having pore sizes in the range from about 1 micron to about 120 microns. There is also a microfilter layer having a prearranged thickness smaller than the thickness of the macrofilter and including a porous membrane having pore sizes from about 0.1 micron to about 10 microns. The microfilter layer is mechanically bonded to at least a major side of the macrofilter layer, whereby inhibiting transfer of any remaining live bacteria which may have survived exposure to the bacteria-destroying medication, and which may attempt to pass outwardly beyond the microfilter layer. The medication is either an antibiotic and an iodophore.