ttgump / scdeepcluster Goto Github PK
View Code? Open in Web Editor NEWscDeepCluster for Single Cell RNA-seq data
License: Apache License 2.0
scDeepCluster for Single Cell RNA-seq data
License: Apache License 2.0
hello, I have some question about the code.
the first question:
'''
zinb = ZINB(pi, theta=disp, ridge_lambda=self.ridge, debug=self.debug)
self.loss = zinb.loss
'''
the model contains the above loss function but I find that the loss function of ZINB class needs two parameters(y_true and y_pred), you may not pass arguments to it.
the second question:
'''
loss = self.model.train_on_batch(x = [x_counts[index * batch_size:(index + 1) * batch_size],
sf[index * batch_size : (index + 1) * batch_size]],
y = [p[index * batch_size:(index + 1) * batch_size],
raw_counts[index * batch_size:(index + 1) * batch_size]])
'''
what's the action of y? what can it calculate?
the third question:
the preprocessing progress transform the count data to normalized data, but you may pass the normalized data to the neural network, why not the count data based on your model?
thank you!
I have noticed the issue #6, so I have created the same environment as you mentioned in readme.md
After running the tutorial you provided in own machine,
the ARI,NMI is very low and did't achieved perfect result. It seems strange that scDeepCluster is unstable for this simulation data, And I noticed that the tutorial.ipynb you have running is not the version you provided in readme.md, the warning information in the tutorial.ipynb seems you are using python3.7, which is not compatible with the python 3.6.3 you mentioned in main page, can you give me some suggestions? Thank you!
What is the difference between scDeepCluster.py,scDeepCluster_latent.py and scDeepCluster_estimate_k.py?
Hi Tiantain,
Is scDeepCluster available for HPC for example SDSC or TACC?
Thanks.
Shicheng
when I run your code, I find that keras runs on cpu, not my gpu. I search for solution on the internet but get nothing. Thus can you tell me some of your opinion?
Hi,
Could you check and see whether the jupyter noebook is working fine? I tried to open it with different laptops and on none of them could get jupyter notebook loaded.
Thanks a lot.
hi, I 've downloaded and repeated your code successfully, then I got three clustering results called NMI,CA and ARI.but how can I find clustering information of every cell such as Fig. 3: Benchmark results on four real scRNA-seq datasets with true labels-b
fig
Hi Tian Tian:
I read the paper "Clustering single-cell RNA-seq data with a model-based deep learning approach" on nature machine intelligence, I can not repeat a few results in your paper, such as the result of Mouse ES cells dataset on Fig.3 in the paper, the CA, NMI and ARI is 0.98, 0.97, 0.97 in the paper, but I repeat is ACC: 0.7674, NMI: 0.6714, ARI: 0.5398.
In another hand, for the splatter dataset, the CA and ARI are 0.75, 0.55 when setting sigma to 0.2 in Supplementary Figure 3. The results I repeat are 0.4420 and 0.0390. so, maybe I need to set some parameters but I ignored, can you give me some suggestions? Thank you!
best wishes
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.