The ability to phenotype cells is fundamentally important in biological research and medicine. Current methods rely primarily on fluorescence labeling of specific markers. However, there are many situations where this approach is unavailable or undesirable. Machine learning has been used for image cytometry but has been limited by cell agglomeration and it is currently unclear if this approach can reliably phenotype cells that are difficult to distinguish by the human eye. Here, we show disaggregated single cells can be phenotyped with a high degree of accuracy using low-resolution bright-field and non-specific fluorescence images of the nucleus, cytoplasm, and cytoskeleton. Specifically, we trained a convolutional neural network using automatically segmented images of cells from eight standard cancer cell-lines. These cells could be identified with an average F1-score of 95.3%, tested using separately acquired images. Our results demonstrate the potential to develop an “electronic eye” to phenotype cells directly from microscopy images.

Solid-state nanopores are now well established as single-biomolecule sensors that hold great promise as sensing elements in diagnostic and sequencing applications. However, until recently this promise has been limited by the expensive, labor-intensive, and low-yield methods used to fabricate low-noise and precisely sized pores. To address this problem, we pioneered a low-cost and scalable solid-state nanopore fabrication method, termed controlled breakdown (CBD), which is rapidly becoming the method of choice for fabricating solid-state nanopores. Since its initial development, nanopore research groups around the world have applied and adapted the CBD method in a variety of ways, with varying levels of success. In this work, we present our accumulated knowledge of nanopore fabrication by CBD, including a detailed description of the instrumentation, software, and procedures required to reliably fabricate low-noise and precisely sized solid-state nanopores with a yield of >85% in less than 1 h. The assembly instructions for the various custom instruments can be found in the Supplementary Manual, and take approximately a day to complete, depending on the unit that the user is building and their level of skill with mechanical and electrical assembly. Unlike traditional beam-based nanopore fabrication technologies, the methods presented here are accessible to non-experts, lowering the cost of, and technical barriers to, fabricating nanoscale pores in thin solid-state membranes.