Skip to main content

AICS Features Extraction

from aicsfeatures.extractor import *

/feature_calc

Functions related to feature extraction. Feature extraction should be done like this:

from aicsfeatures.extractor import *

features_result = xxx.get_features(args=None, seg=image_xxx)

where xxx can be

  • mem, for cell membrane-related features
  • dna, for nucleus-related features
  • structure, for structure-specific features.
  • stack, for stack-related features.

Assumptions of each function about the input image should be detailed inside the function like this

    Assumptions:
        - Input is a ZYX 16-bit numpy array (2D images can be passed in as a 1YX)
        - There is a single object of interest
        - Background has value 0
        - Object of interest have pixel value > 0

The result features_result should always be a single row Pandas dataframe.

exutils.py: Main routine for feature calculation. We try to re-use functions from skimage (shape analysis) and Mahotas (texture analysis). Here is also the place to implement new features that are not found in those packages. We try to be general and do not say anything specific about the type of biological structure that the input image should represent.

mem.py: Wrappers for feature extraction of cell membrane images.

dna.py: Wrappers for feature extraction of dna images.

structure.py: Wrappers for feature extraction of structures images. Things to be defined: which type of feature we should extract for each given structure. Or do we do all to all?

stack.py: Wrappers for feature extraction of whole stack images.

How to Build

The default project layout and build steps are discussed in BUILD.md. Some of the information is related to the AICS build process.

  • License (Before you release the project publicly please check with your manager to ensure the license is appropriate and has been run through legal review as necessary.)
  • Contribution Agreement (Additionally update the contribution agreement to reflect the level of contribution you are expecting, and the level of support you intend to provide.)

Metadata

Release files for aicsfeature 0.2.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for aicsfeature 0.2.1
File Interpreter ABI Platform
aicsfeature-0.2.1-py2.py3-none-any.whl Python 2, Python 3 none any Details

Release files / aicsfeature-0.2.1-py2.py3-none-any.whl

Download URL aicsfeature-0.2.1-py2.py3-none-any.whl
Size 15.3 kB
Tags Python 2 Python 3
SHA-256 checksum
How to use checksums
80552b09842f11f46b78f6e5415fa4508b56d42567b11d07de1d231acb41d597
BLAKE2b-256 checksum
How to use checksums
8b9eca5da1cf84340ebdf5f1fb6811691c3f9db8459ce1b78ee766c44cfb2a50
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.1 CPython/3.6.7

Release history Release notifications | RSS feed

This release

0.2.1 This release

1 release file

0.2.0

1 release file

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page