Comments (1)
In the PBMC walkthrough it actually specifies several non-default options with which to run suggestK
, whereas this figure looks like it was produced with only the default options. I would recommend one change from the current walkthrough command, which is to run multiple iterations of NMF at each value of k by setting nrep
; this might allow you to more easily identify an inflection point in the curve. For example, here is the result from running with the following options:
k.suggest <- suggestK(a.pbmc, num.cores = 5, gen.new = T, return.data = T, plot.log2 = F,
nrep = 5)
While this variation does take longer to run, I think it's more clear the inflection point is somewhere between k=15 and k=25. As the walkthrough states, we selected k=22 (after some inspection of downstream results), but you can try other values of k for similar results. For the supplementary figure in the paper, we set nrep=20 (though I would not recommend this for most analyses as it takes over an hour to run). We'll update the walkthrough with this recommended change; feel free to look at the paper supplement and methods for a more detailed explanation of this heuristic.
from liger.
Related Issues (20)
- "shared factor neighborhood" not used anymore as described in the paper? HOT 3
- log transform data first? HOT 1
- Another request for help regarding SCTransform HOT 1
- Generate gene and promoter bed files
- Problems with scaleNotCenter() HOT 2
- Prepare for upcoming Seurat v5 release HOT 1
- Bug in Seurat's wrapper function HOT 1
- cran package archived HOT 6
- NaNs during `SelectGenes()` HOT 1
- Error on makeFeatureMatrix HOT 1
- How to improving similarity between snRNA-seq and snATAC-seq nuclei, by tuning parameters like 'k', 'lambda'? HOT 4
- Dataset specificity plot
- Issue with loading old liger object via convertOldLiger function HOT 3
- Error in `signal_stage()` HOT 4
- invalid type "list" in R_matrix_as_sparse error HOT 3
- no slot name "defaultCluster" for this object of class "liger" HOT 1
- Query on building shared factor neighborhood graph HOT 2
- Error when performing the Wilcoxon test on the peak counts HOT 1
- Error in ImputeKNN
- How can I determine the similarity scores between clusters using Liger's UINMF? HOT 5
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 liger.