jmuhlich / auto-minerva Goto Github PK

View Code? Open in Web Editor NEW

4.0 4.0 2.0 26 KB

Python 96.34% HTML 3.66%

auto-minerva's People

Contributors

Stargazers

Watchers

Forkers

adamjtaylor thejohnhoffer

auto-minerva's Issues

set proper colors for H&E legend

copy scale from metadata to story.json

Slice step cannot be zero

Example HTAN dataset syn24829436, an mIHC dataset, fails with the error slice step cannot be zero

python story.py ~/miniature/data/HTA9_1_BA_M_ROI03.ome.tif

opening image: /home/ubuntu/miniature/data/HTA9_1_BA_M_ROI03.ome.tif
reading metadata
analyzing channel 1/12
Traceback (most recent call last):
  File "/home/ubuntu/auto-minerva/story.py", line 109, in <module>
    main()
  File "/home/ubuntu/auto-minerva/story.py", line 90, in main
    vmin, vmax = auto_threshold(img)
  File "/home/ubuntu/auto-minerva/story.py", line 16, in auto_threshold
    img = img[::ss, ::ss]
ValueError: slice step cannot be zero

Home button access denied

Generated stories show access denied when clicking the home button (for s3 hosted stories served through cloudfront.

Can we remove or point this back to the story "start"

Add option for intro markdown file

Elegantly set thresholds for empty channels

Auto-minerva story.py fails on blank channels as follows (where channel 15 is all zero)
[note there is also a Warning for channel 1]

This is likely to occur for techniques such as MIBI where there is very low contrast, particularly for normal tissues with no/few cells exhibiting a particular marker and for included control channels.

Could we add a try/except into the mixture fitting that perhaps just sets [0,1] threshold when fitting fails

nxf-scratch-dir ip-172-22-12-59.ec2.internal:/tmp/nxf.MWYxHayB6P
opening image: Point3301_31717.ome.tif
reading metadata
WARNING: Could not read OME metadata. Story will use generic channel names and
    the scale bar will be omitted.
analyzing channel 1/45
/venv/lib/python3.9/site-packages/sklearn/mixture/_base.py:143: ConvergenceWarning: Number of distinct clusters (2) found smaller than n_clusters (3). Possibly due to duplicate points in X.
  cluster.KMeans(
analyzing channel 2/45
analyzing channel 3/45
analyzing channel 4/45
analyzing channel 5/45
analyzing channel 6/45
analyzing channel 7/45
analyzing channel 8/45
analyzing channel 9/45
analyzing channel 10/45
analyzing channel 11/45
analyzing channel 12/45
analyzing channel 13/45
analyzing channel 14/45
analyzing channel 15/45
Traceback (most recent call last):
  File "/auto-minerva/story.py", line 139, in
    main()
  File "/auto-minerva/story.py", line 120, in main
    vmin, vmax = auto_threshold(img)
  File "/auto-minerva/story.py", line 22, in auto_threshold
    gmm.fit(img_log.reshape((-1,1)))
  File "/venv/lib/python3.9/site-packages/sklearn/mixture/_base.py", line 198, in fit
    self.fit_predict(X, y)
  File "/venv/lib/python3.9/site-packages/sklearn/mixture/_base.py", line 228, in fit_predict
    X = self._validate_data(X, dtype=[np.float64, np.float32], ensure_min_samples=2)
  File "/venv/lib/python3.9/site-packages/sklearn/base.py", line 561, in _validate_data
    X = check_array(X, **check_params)
  File "/venv/lib/python3.9/site-packages/sklearn/utils/validation.py", line 797, in check_array
    raise ValueError(
ValueError: Found array with 0 sample(s) (shape=(0, 1)) while a minimum of 2 is required.

Can't handle float32 pixel type

story.py fails for an example HTAN dataset (syn25701060, an IMC image)

python story.py ~/miniature/data/HT060P1_REMAIN_ROI_04.ome.tiff  > HT060P1_REMAIN_ROI04.story.json

opening image: /home/ubuntu/miniature/data/HT060P1_REMAIN_ROI_04.ome.tiff
Traceback (most recent call last):
  File "/home/ubuntu/auto-minerva/story.py", line 109, in <module>
    main()
  File "/home/ubuntu/auto-minerva/story.py", line 58, in main
    raise Exception(f"Can't handle {zarray.dtype} pixel type")
Exception: Can't handle float32 pixel type

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.