Comments (4)
Hi Kathrin, thanks for the question.
It sounds like you are giving the PCA coordinates of cells as input to Harmony. Is that right? If so, please see the documentation for your PCA function to get the variance explained for your PCs.
For example, you might be using the PCA function from the sklearn Python package:
https://scikit-learn.org/stable/modules/generated/sklearn.decomposition.PCA.html
Here is a detailed tutorial that shows how to use that function and find the variance explained:
https://jakevdp.github.io/PythonDataScienceHandbook/05.09-principal-component-analysis.html
In the issue you linked to, Ilya mentions that he added standard deviations of Harmony output to the Seurat V3 object. Here's the code for that:
harmonydata <- Seurat::CreateDimReducObject(
embeddings = harmonyEmbed,
stdev = as.numeric(apply(harmonyEmbed, 2, stats::sd)),
assay = assay.use,
key = reduction.save
)
You can see that it's applying the sd()
function to each column of the Harmony output matrix.
Maybe that's what you're looking for?
In Python, you can use numpy to get the standard deviation of each column of a matrix:
https://numpy.org/doc/1.18/reference/generated/numpy.std.html
from harmonypy.
Thanks for the quick and detailed answer! I will calculate it using some of your suggestions.
May I ask your opinion on something related to this? Would you usually select the number of PCAs to use before running harmony (e.g. do an elbow plot) or is it acceptable to do a component selection post running harmony?
from harmonypy.
I like to run multiple analyses with different parameters to get some sense of how they can affect the final results. The methods section of published papers can occasionally be helpful to see what strategies people use to choose parameters.
For general questions, you might consider asking for analysis advice on Biostars.
from harmonypy.
Thanks for the answer, sorry if I hadn't phrase the question very clearly: it was specifically about harmony component selection. No worries though, you've answered my original question. I'll close this now, thanks again for the great tool & your help!
from harmonypy.
Related Issues (20)
- Try filprofiler HOT 1
- How to cite this work? HOT 2
- ValueError: operands could not be broadcast together with shapes HOT 9
- Feature request: plot convergence HOT 1
- ValueError: operands could not be broadcast together HOT 1
- How to get the result after running harmony? HOT 2
- feature request: HOT 2
- run harmonypy true_divide error HOT 3
- Running multiple instances of the same variable in vars_use. HOT 5
- Runharmony with R and run_harmony with Python produced different results HOT 1
- Harmony with two or more covariates HOT 3
- Build changes have broken Conda install HOT 1
- Unique key is not in pandas describe HOT 3
- Add converged status to harmony object HOT 1
- Results not reproducible HOT 18
- sklearn.cluster.KMeans issue with kmeans_single() and threadpool_limits() HOT 4
- Reference mapping option HOT 2
- AttributeError: 'NoneType' object has no attribute 'split' HOT 5
- Error in running large dataset HOT 2
- Will the latest R harmony updates be propagated to the harmonypy HOT 1
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 harmonypy.