Comments (6)
Some GO terms might NOT have directly annotated genes. They exist in the hierarchy because the number of propagated genes from their children is bigger than the number of genes annotated by their children and the difference exceeds our threshold.
from drugcell.
Hi @jisoopark,
Thank you for your reply. I appreciated it. I am not sure if I understand the difference between propagated genes from their children
and genes annotated by their children
? If possible, could you please elaborate on that? If you could use one example GO term, that would be perfect. Thank you.
from drugcell.
For example, GO:0002757 has two children in our hierarchy: GO:0002429 and GO:0002758.
121 and 102 genes are annotated by GO:0002429 and GO:0002758, respectively.
Gene propagation means that the parent, GO:0002757, will contain the union of the annotated genes of its children, GO:0002429 and GO:0002758. In this example, GO:0002757 annotates 168 genes which is union of 121 genes from GO:0002429 and 102 genes from GO:0002758.
Note: some of 121 and 102 genes in GO:0002429 and GO:0002758 might have been propagated from their children.
Does this make sense?
from drugcell.
Hi @jisoopark,
Thanks again for the explanation. Yes, it makes perfect sense to me. Just to confirm I understand it correctly, since GO:0002757's genes all come from its two children GO:0002429 and GO:0002758 (i.e., GO:0002757 does not have any gene other than those from its two children), therefore no gene was annotated for GO:0002757 in the drugcell_ont.txt
file, correct? Thanks.
from drugcell.
Yes, that is correct. GO:0002757 has no directly annotated genes. All came from GO:0002429 and GO:0002758. You can conclude in a similar way for other 17 GO terms that you found. Thanks!
from drugcell.
Thank you for your help, @jisoopark! I appreciate it.
from drugcell.
Related Issues (20)
- Try to run it on google colab/ jupyter notebook, report error in "final_input = torch.cat((term_NN_out_map[self.root], drug_out), 1)" (line 177 of drugcell_NN.py)) HOT 1
- Output Format Not Explained HOT 2
- Resource Guide Missing HOT 3
- Installation Instructions Require Anaconda HOT 1
- Mistakes in User Guide HOT 1
- Interpretable Pathway Models not Documented
- how to hash the morgen fingerprint into binary drug feature HOT 1
- Mistake on commandline_train.sh HOT 1
- RLIPP Calulcation
- Question about the network uncertainty
- Release of full training data HOT 1
- Reproducibility of the ontology hierarchy (VNN) HOT 1
- Question about Evaluation Metric
- new cell feature
- pretrained_model avaliable? HOT 2
- about Figure 3
- will provide train data preprocessing code
- Where can I get RLIPP program? HOT 2
- failed to download pretrained model at https://drugcell.ucsd.edu/downloads/ HOT 2
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 drugcell.