Comments (4)
There are two categories of images - cell painting images (that make the cp_sat_df) and barcoding images (that make the bc_sat_df). Each has a different threshold for triggering a saturated warning - CP if an image is > 1% saturated, BC if an image > .2% saturated (which is determined by the ImageQuality_PercentMaximal_
column in the Image.csv).
My goal was to output a list of sites that fail as saturated_sites.csv but to NOT save an empty .csv so that a user will know that if a .csv is created it means there is a problem.
I had also intended for no site to be listed twice (i.e. if it fails in saturation in both CP and BC then it should only be listed once), but now that I'm thinking about it, an even more helpful solution would be to have any site only ever listed once, but for there to be additional columns added of "Fails_Sat_BC" and "Fails_Sat_CP" and have those populated with True/False accordingly.
from pooled-cell-painting-profiling-recipe.
ok cool - I think I got it.
#39 is already getting kinda bloated though - Let's address this issue in the next PR. After we merge #39, do you want to give this enhancement a shot? I'm going to shift my focus early next week to organizing the template, migrating working config files, and actually performing our first weld.
from pooled-cell-painting-profiling-recipe.
Happy to give it a shot.
we may need to slightly tinker the code to make sure we extract all saturated sites
I'm not sure I understand what you were initially concerned about? Does my suggested enhancement of
to have any site only ever listed once, but for there to be additional columns added of "Fails_Sat_BC" and "Fails_Sat_CP" and have those populated with True/False accordingly.
fix your initial concern?
from pooled-cell-painting-profiling-recipe.
yeah, I think reworking the full code block to add this enhancement will address my "tinker comment".
More specifically, the two lines of code of this form: cp_sat_df = image_df[image_df[col] > 1]
inside the for loop will be overwritten each time through the loop. Therefore, unless I am missing something, sat_df = cp_sat_df.append(bc_sat_df).drop_duplicates(subset="site")
will not contain the intended outcome.
from pooled-cell-painting-profiling-recipe.
Related Issues (20)
- Add multi-plate option HOT 1
- Remove example_site requirement in prefilter feature config HOT 2
- Add logger to capture weld parameters, warnings, and errors
- Include summary step for guide + guide abundances (cell count per perturbation) HOT 12
- Single cell normalization enhancement option HOT 1
- Maintaining different versions of recipe HOT 2
- Barcode controls missing from guide abundance summary (cell count per perturbation)
- Add load_features import
- Convert quality_col to list
- Cell count file is outputting NaN for plate, well, and site_location columns
- Aggregate fails when output_single_file_only option set to False HOT 1
- Error in 4.image-and-segmentation-qc.py HOT 2
- 4.image-and-segmentation-qc.py should produce figures on a per-plate basis HOT 3
- Hardcoding Cells and Nuclei for threshold QC
- Add output file specifically for comparison to NGS data. HOT 1
- Skip corrupted site files HOT 1
- Make folders only when necessary
- Codify new contribution protocol HOT 8
- Config mismatch between recipe and template HOT 1
- Change Skip Site/Overwrite Behavior in 0.preprocess-sites
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.
from pooled-cell-painting-profiling-recipe.