Configuration file

The staging folder contains a YAML file named config.yaml where we specify all parameters used by cvapipe_analysis. This file is divided into sections that more or less has a one-to-one mapping to existing workflow steps. Notice that results in the paper are generated using default parameters shown here.

1. Data specification

data:
    cell:
        alias: MEM
        channel: membrane_segmentation
        color: '#F200FF'
    cell-roof:
        alias: MEMROOF
        channel: membrane_segmentation_roof
        color: '#F200FF'
    nucleus:
        alias: NUC
        channel: dna_segmentation
        color: '#3AADA7'
    structure:
        alias: STR
        channel: struct_segmentation_roof
        color: '#000000'
    raw-structure-str:
        alias: RAWSTR_MASKEDBY_STR
        channel: structure
        color: '#000000'
    raw-structure-nuc:
        alias: RAWSTR_MASKEDBY_NUC
        channel: structure
        color: '#000000'
    raw-structure-mem:
        alias: RAWSTR_MASKEDBY_MEM
        channel: structure
        color: '#000000'

Here we assign an alias to each channel of the input dataset. The values specified in the field channel should match the names specified in the manifest used in the loaddata step.

2. Feature extraction

features:
    aliases: ["NUC", "MEM", "STR", "RAWSTR_MASKEDBY_STR", "RAWSTR_MASKEDBY_NUC", "RAWSTR_MASKEDBY_MEM"]
    # Intensity features: specify aliases for raw image and
    # corresponding segmentation mask.
    intensity:
        RAWSTR_MASKEDBY_STR: STR
        RAWSTR_MASKEDBY_NUC: NUC
        RAWSTR_MASKEDBY_MEM: MEMROOF
    # SHE - Spherical harmonics expansion
    SHE:
        alignment:
            align: on
            unique: off
            reference: "cell"
        aliases: ["NUC", "MEM"]
        # Size of Gaussian kernal used to smooth the
        # images before SHE coefficients calculation
        sigma:
            NUC: 2
            MEM: 2
        # Number of SHE coefficients used to describe cell
        # and nuclear shape
        lmax: 16

Here we start specifying all aliases that will be used for feature extraction. NEED TO FINISH THIS

3. Preprocessing

Here we can turn on or off outlier detection and removal of mitotic cells.

preprocessing:
    remove_mitotics: on
    remove_outliers: on
    filtering:
        filter: off
        csv: ""
        specs: {}

4. Shape space

Start by specifying which aliases should be used to generate the shape space. Here we use both NUC and MEM for creating a joint shape space of nucleus and cell. For shape space of nucleus alone you can use aliases: ["NUC"]. We should also specify one alias to sort the values of shape modes. We specify that i) 1% of cells should be remove at extremities of each shape mode, ii) 8 shape modes should be computed and iii) the corresponding map points along each shape mode in units of std.

shapespace:
    # Specify the a set of aliases here
    aliases: ["NUC", "MEM"]
    # Sort shape modes by volume of
    sorter: "MEM"
    # Percentage of exteme points to be removed
    removal_pct: 1.0
    # Number of principal components to be calculated
    number_of_shape_modes: 8
    # Map points
    map_points: [-2.0, -1.5, -1.0, -0.5, 0.0, 0.5, 1.0, 1.5, 2.0]
    plot:
        frame: on
        swapxy_on_zproj: off
        # limits of x and y axies in the animated GIFs
        limits: [-150, 150, -80, 80]