extraction.core.extractor.Extractor

class Extractor(parameters, store=None, tiler=None)

Bases: StepABC

Apply a metric to cells identified in the tiles.

Using the cell masks, the Extractor applies a metric, such as area or median, to cells identified in the image tiles.

Its methods require both tile images and masks.

Usually the metric is applied to only a tile’s masked area, but some metrics depend on the whole tile.

Extraction follows a three-level tree structure. Channels, such as GFP, are the root level; the reduction algorithm, such as maximum projection, is the second level; the specific metric, or operation, to apply to the masks is the third level.

Parameters

parameters: core.extractor Parameters

Parameters that include the channels, and reduction and extraction functions.

store: str

Path to the h5 file, which must contain the cell masks.

tiler: pipeline-core.core.segmentation tiler

Class that contains or fetches the images used for segmentation.

Attributes

channels

Get a tuple of the available channels.

current_position

group

parameters

Methods

extract_funs(traps, masks, metrics, **kwargs)	Returns dict with metrics as key and metrics applied to data as values for data from one timepoint.
extract_tp(tp[, tree, tile_size, masks, labels])	Extract for an individual time-point.
extract_traps(traps, masks, metric, labels)	Apply a function to a whole position.
from_img(parameters, store, img_meta)	Initiate from images.
from_tiler(parameters, store, tiler)	Initiate from a tiler instance.
get_imgs(channel, traps[, channels])	Return image from a correct source, either raw or bgsub.
get_tiles(tp[, channels, z])	Find tiles for a given time point and given channels and z-stacks.
load_custom_funs()	Define any custom functions to be functions of cell_masks and trap_image only.
load_meta()	Load metadata from h5 file.
reduce_dims(img[, method])	Collapse a z-stack into 2d array using method.
reduce_extract(traps, masks, red_metrics, ...)	Wrapper to apply reduction and then extraction.
run_tp(**kwargs)
save_to_hdf(dict_series[, path])	Save the extracted data to the h5 file.

get_meta
load_funs
run

Initialise Extractor.

Parameters

parameters: ExtractorParameters object

store: str

Name of h5 file

tiler: Tiler object

Attributes

channels

Get a tuple of the available channels.

current_position

group

parameters

Methods

extract_funs(traps, masks, metrics, **kwargs)	Returns dict with metrics as key and metrics applied to data as values for data from one timepoint.
extract_tp(tp[, tree, tile_size, masks, labels])	Extract for an individual time-point.
extract_traps(traps, masks, metric, labels)	Apply a function to a whole position.
from_img(parameters, store, img_meta)	Initiate from images.
from_tiler(parameters, store, tiler)	Initiate from a tiler instance.
get_imgs(channel, traps[, channels])	Return image from a correct source, either raw or bgsub.
get_tiles(tp[, channels, z])	Find tiles for a given time point and given channels and z-stacks.
load_custom_funs()	Define any custom functions to be functions of cell_masks and trap_image only.
load_meta()	Load metadata from h5 file.
reduce_dims(img[, method])	Collapse a z-stack into 2d array using method.
reduce_extract(traps, masks, red_metrics, ...)	Wrapper to apply reduction and then extraction.
run_tp(**kwargs)
save_to_hdf(dict_series[, path])	Save the extracted data to the h5 file.

get_meta
load_funs
run

__init__(parameters, store=None, tiler=None)

Initialise Extractor.

Parameters

parameters: ExtractorParameters object

store: str

Name of h5 file

tiler: Tiler object

Methods

__init__(parameters[, store, tiler])	Initialise Extractor.
extract_funs(traps, masks, metrics, **kwargs)	Returns dict with metrics as key and metrics applied to data as values for data from one timepoint.
extract_tp(tp[, tree, tile_size, masks, labels])	Extract for an individual time-point.
extract_traps(traps, masks, metric, labels)	Apply a function to a whole position.
from_img(parameters, store, img_meta)	Initiate from images.
from_tiler(parameters, store, tiler)	Initiate from a tiler instance.
get_imgs(channel, traps[, channels])	Return image from a correct source, either raw or bgsub.
get_meta(flds)
get_tiles(tp[, channels, z])	Find tiles for a given time point and given channels and z-stacks.
load_custom_funs()	Define any custom functions to be functions of cell_masks and trap_image only.
load_funs()
load_meta()	Load metadata from h5 file.
reduce_dims(img[, method])	Collapse a z-stack into 2d array using method.
reduce_extract(traps, masks, red_metrics, ...)	Wrapper to apply reduction and then extraction.
run()
run_tp(**kwargs)
save_to_hdf(dict_series[, path])	Save the extracted data to the h5 file.

Attributes

channels	Get a tuple of the available channels.
current_position
default_meta
group
parameters

property channels

Get a tuple of the available channels.

extract_funs(traps, masks, metrics, **kwargs)

Returns dict with metrics as key and metrics applied to data as values for data from one timepoint.

Return type

Dict[str, Series]

extract_tp(tp, tree=None, tile_size=117, masks=None, labels=None, **kwargs)

Extract for an individual time-point.

Parameters

tpint

Time point being analysed.

treedict

Nested dictionary indicating channels, reduction functions and metrics to be used. For example: {‘general’: {‘None’: [‘area’, ‘volume’, ‘eccentricity’]}}

tile_sizeint

Size of the tile to be extracted.

maskslist of arrays

A list of masks per trap with each mask having dimensions (ncells, tile_size, tile_size).

labelsdict

A dictionary with trap_ids as keys and cell_labels as values.

**kwargskeyword arguments

Passed to extractor.reduce_extract.

Returns

d: dict

Dictionary of the results with three levels of dictionaries. The first level has channels as keys. The second level has reduction metrics as keys. The third level has cell or background metrics as keys and a two-tuple as values. The first tuple is the result of applying the metrics to a particular cell or trap; the second tuple is either (trap_id, cell_label) for a metric applied to a cell or a trap_id for a metric applied to a trap.

An example is d[“GFP”][“np_max”][“mean”][0], which gives a tuple of the calculated mean GFP fluorescence for all cells.

rtype

Dict[str, Dict[str, Dict[str, tuple]]] ..

extract_traps(traps, masks, metric, labels)

Apply a function to a whole position.

Parameters

traps: list of arrays

List of images.

masks: list of arrays

List of masks.

metric: str

Metric to extract.

labels: dict

A dict of cell labels with trap_ids as keys and a list of cell labels as values.

pos_info: bool

Whether to add the position as an index or not.

Returns

res_idx: a tuple of tuples

A two-tuple of a tuple of results and a tuple with the corresponding trap_id and cell labels

rtype

Tuple[Union[Tuple[float], Tuple[Tuple[int]]]] ..

classmethod from_img(parameters, store, img_meta)

Initiate from images.

classmethod from_tiler(parameters, store, tiler)

Initiate from a tiler instance.

get_imgs(channel, traps, channels=None)

Return image from a correct source, either raw or bgsub.

Parameters

channel: str

Name of channel to get.

traps: ndarray

An array of the image data having dimensions of (trap_id, channel, tp, tile_size, tile_size, n_zstacks).

channels: list of str (optional)

List of available channels.

Returns

img: ndarray

An array of image data with dimensions (no traps, X, Y, no Z channels)

get_tiles(tp, channels=None, z=None, **kwargs)

Find tiles for a given time point and given channels and z-stacks.

Returns None if no tiles are found.

Any additional keyword arguments are passed to tiler.get_tiles_timepoint

Parameters

tp: int

Time point of interest

channels: list of strings (optional)

Channels of interest

z: list of integers (optional)

Indices for the z-stacks of interest

:rtype: :py:data:`~typing.Optional`[:py:class:`~numpy.ndarray`]

load_custom_funs()

Define any custom functions to be functions of cell_masks and trap_image only.

Any other parameters are taken from the experiment’s metadata and automatically applied. These parameters therefore must be loaded within an Extractor instance.

load_meta()

Load metadata from h5 file.

reduce_dims(img, method=None)

Collapse a z-stack into 2d array using method.

If method is None, return the original data.

Parameters

img: array

An array of the image data arranged as (X, Y, Z)

method: function

The reduction function

:rtype: :py:class:`~numpy.ndarray`

reduce_extract(traps, masks, red_metrics, **kwargs)

Wrapper to apply reduction and then extraction.

Parameters

traps: array

An array of image data arranged as (traps, X, Y, Z)

masks: list of arrays

An array of masks for each trap: one per cell at the trap

red_metrics: dict

dict for which keys are reduction functions and values are either a list or a set of strings giving the metric functions. For example: {‘np_max’: {‘max5px’, ‘mean’, ‘median’}}

**kwargs: dict

All other arguments passed to Extractor.extract_funs.

Returns

——

Dictionary of dataframes with the corresponding reductions and metrics nested.

:rtype: :py:class:`~typing.Dict`[:py:class:`str`, :py:class:`~typing.Dict`[:py:data:`~typing.Union`[:py:data:`~typing.Callable`, :py:class:`str`, :py:obj:`None`], :py:class:`~typing.Dict`[:py:class:`str`, :py:class:`~pandas.core.series.Series`]]]

save_to_hdf(dict_series, path=None)

Save the extracted data to the h5 file.

Parameters

dict_series: dict

A dictionary of the extracted data, created by run.

path: Path (optional)

To the h5 file.