CELL ACTIVITY MACHINE LEARNING

1 . A method for characterizing cellular activity, the method comprising:

making a recording of activity of one or more electrically-active cells;

presenting the recording to a machine learning system trained on training data comprising recordings from cells with a known pathology and cells without the pathology; and

reporting, by the machine learning system, a phenotype of the electrically-active cells.

2 . The method of claim 1 , wherein the recording comprises one or more action potentials exhibited by the electrically-active cells.

3 . The method of claim 1 , wherein the machine learning system reports the phenotype of the electrically-active cells as having, or not having, the pathology.

4 . The method of claim 1 , further comprising exposing the electrically-active cells to a test compound.

5 . The method of claim 1 , wherein the machine learning system reports the phenotype of the electrically active cells as reverting from having the pathology to not having the pathology with exposure to test compound.

6 . The method of claim 1 , wherein the recording is a digital movie made by imaging the electrically-active cells through a microscope with a CMOS images sensor.

7 . The method of claim 1 , wherein the machine learning system is resident in a computer system comprising a processor coupled to memory, and the recording is saved in the memory.

8 . The method of claim 1 , wherein the recording captures action potentials, and the method further comprises measuring, and storing, a plurality of features from the action potentials.

9 . The method of claim 1 , further comprising measuring features from the recording and presenting the features to the machine learning system, optionally wherein the features comprise one or more of spike rate, spike height, spike width, depth of afterhyperpolarization, onset timing, timing of cessation of firing, inter-spike interval, adaptation over a constant stimulation, a first derivative of spike waveform, and a second derivative of spike waveform.

10 . The method of claim 1 , further comprising operating the machine learning system under control of a budget wrapper that limits a number of features that are presented to the machine learning system.

11 . The method of claim 1 , further comprising extracting greater than 100 features from the recording and further wherein a budget wrapper presents fewer than about 20 of the features to the machine learning system.

12 . The method of claim 1 , wherein the machine learning system comprises a neural network.

13 . The method of claim 12 , wherein the neural network is an autoencoder neural network that operates by representation learning.

14 . The method of claim 13 , wherein the autoencoder has been trained using manually selected training data comprising the recordings from cells with the known pathology and the cells without the pathology in samples that have been exposed to known compounds with known efficacy and control samples that have not be exposed to the known compounds.

15 . The method of claim 1 , wherein the machine learning system was trained using a hierarchical bootstrapping algorithm.

16 . The method of claim 15 , wherein the hierarchical bootstrapping algorithm recursively samples from an arbitrary number of levels of nested data.

17 . The method of claim 15 , wherein the hierarchical bootstrapping algorithm creates augmented samples by re-sampling with replacement from features measured from action potentials in the training data, and wherein the machine learning system is trained using the augmented samples.

18 . A method for compressing raw movie data, the method comprising:

obtaining digital video data of electrically active cells;

processing the video data in a block-wise manner by, for each block, calculating a covariance matrix and an eigenvalue decomposition of that block and truncating the eigenvalue decomposition and retaining only a number of principal components, thereby discarding noise from the block, and

writing the video to memory as a compressed video using only the retained principal components.

19 . The method of claim 18 , wherein the blocks are selected by parcellating the data using region-based tiling based on a local intensity maxima of a mean movie frame.

20 . The method of claim 18 , wherein the digital video data is obtained from the electrically active cells expressing optical reporters of cellular electrical activity.

21 . The method of claim 18 , wherein the cells are neurons and the digital video data shows action potentials propagating along axons of the neurons.

22 . The method of claim 21 , wherein the compressed video can be retrieved and played to display the action potentials propagating along the axons of the neurons.

23 . The method of claim 21 , further comprising measuring, by a machine learning system, features from the action potentials, wherein the machine learning system obtains the same values for the measured features whether measuring from the digital video data or the compressed video.

24 . The method of claim 23 , wherein the features comprise one or more of voltage, fluorescence versus time, spike height, spike width, shape change, slope, frequency, and timing.

25 . The method of claim 18 , wherein the compressed video occupies less than about 10% of disc space required for the digital video data.

26 . The method of claim 18 , wherein the obtaining step comprises filming, through a microscope and using a digital image sensor, live neurons firing.

27 . The method of claim 26 , wherein the digital image sensor is connected to a computer that performs the processing step, and further wherein the compressed video is written to a remote computer via an Internet connection.

28 . The method of claim 26 , wherein the digital image sensor produces over 50 terabytes of the digital video data in one day.

29 . The method of claim 28 , wherein the processing step compresses the digital video data by at least about 20×.