More about configuration file

1. Full single cell image dataset

No changes need to be made in the configuration file if you downloaded the full single cell image dataset.

2. Full single cell segmentation image dataset

These are the changes that need to be made in case you skipped downloading the raw images and only have the segmentations available:

data:
    cell:
        alias: MEM
        channel: membrane_segmentation
        color: '#F200FF'
    nucleus:
        alias: NUC
        channel: dna_segmentation
        color: '#3AADA7'
    structure:
        alias: STR
        channel: struct_segmentation_roof
        color: '#000000'

and

features:
    aliases: ["NUC", "MEM", "STR"]
    # Intensity features: specify aliases for raw image and
    # corresponding segmentation mask.
    intensity:
    # 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

3. non-edges, edges, i1 and i2 datasets

Change the default configuration file in the corresponding staging folder to

preprocessing:
    remove_mitotics: off
    remove_outliers: off
    filtering:
        filter: off
        csv:
        specs:

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: 0.0
    # Number of principal components to be calculated
    number_of_shape_modes: 1
    # Map points
    map_points: [0.0]
    plot:
        frame: on
        swapxy_on_zproj: off
        # limits of x and y axies in the animated GIFs
        limits: [-150, 150, -80, 80]

3. m1 and m2 datasets

Change the default configuration file in the corresponding staging folder to

data:
    cell:
        alias: MEM
        channel: MEMSEG
        color: '#F200FF'
    cell-roof:
        alias: MEMROOF
        channel: MEMSEG-ROOF
        color: '#F200FF'
    nucleus:
        alias: NUC
        channel: NUCSEG-SOLID
        color: '#3AADA7'
    structure:
        alias: STR
        channel: STRSEG-ROOF
        color: '#000000'
    raw-structure-str:
        alias: RAWSTR_MASKEDBY_STR
        channel: STR
        color: '#000000'
    raw-structure-nuc:
        alias: RAWSTR_MASKEDBY_NUC
        channel: STR
        color: '#000000'
    raw-structure-mem:
        alias: RAWSTR_MASKEDBY_MEM
        channel: STR
        color: '#000000'

and

preprocessing:
    remove_mitotics: off
    remove_outliers: off
    filtering:
        filter: off
        csv:
        specs:

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: 0.0
    # Number of principal components to be calculated
    number_of_shape_modes: 1
    # Map points
    map_points: [0.0]
    plot:
        frame: on
        swapxy_on_zproj: off
        # limits of x and y axies in the animated GIFs
        limits: [-150, 150, -80, 80]

5. Custom dataset of cell and nuclear segmentation

If your dataset contains single cell images representing cell and nuclear segmentation, you can use cvapipe_analysis to generate a shape space by adjusting the configuration file as

data:
    cell:
        alias: MEM
        channel: membrane
        color: '#F200FF'
    nucleus:
        alias: NUC
        channel: nucleus
        color: '#3AADA7'

features:
    aliases: ["NUC", "MEM"]
    # Intensity features: specify aliases for raw image and
    # corresponding segmentation mask.
    intensity:
    # 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