Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Submit feedback
Sign in
Toggle navigation
A
AIIM2023-GNNs
Project overview
Project overview
Details
Activity
Releases
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Boards
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Disnet
GNNs
AIIM2023-GNNs
Commits
512b75a8
Commit
512b75a8
authored
Nov 30, 2022
by
ADRIAN AYUSO MUNOZ
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Add logo
parent
c498b47f
Changes
2
Expand all
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
33 additions
and
0 deletions
+33
-0
README.md
README.md
+32
-0
logo/logo.svg
logo/logo.svg
+1
-0
No files found.
README.md
0 → 100644
View file @
512b75a8
# AIIM2023
<img
src=
"./logo/logo.svg"
>
## Content in each directory:
-
**documentation**
: Instructions to install the needed libraries.
-
**graphData**
: Data of DISNET's graph.
-
**metrics**
: Training, testing and RepoDB verification ROC & PRC, also loss evolution for training and validation.
-
**models**
: Trained models.
-
**results**
: Result files of the RepoDB test and the distribution plots (once these are generated).
-
**Code files:**
-
deepSnapPred (train & test DeepSnap)
-
heterograph_construction (build graph)
-
testRepoDB (validate model using RepoDB)
-
topN (getting top N new predictions of a model)
-
utilities (plotting utilities)
-
visualizeDistribution (Checks the distribution of the predictions for a group of diseases, check TFG for more information).
-
visualizeEmbeddings (visualization of embeddings)
## Summary
Using Graph Neural Networks (GNNs) to predict new drug repurposing hypothesis. The objective is to predict new edges between
drugs and diseases (edge inference) or predict the type of edge (drug) between two diseases (edge classification).
One models is generated using DeepSnap library. The model has an encoder-decoder (GraphSAGE-Dot product) architecture,
the use of different architectures will be studied in the future. This is the generated models and its status:
-
🟢
**DeepSnap:**
Passed verification tests, proved to be functional and works well.
### Symbol legend:
-
🟢 : Ready to use.
-
🟡 : Use is not recommended due to major issues.
-
🟠 : Not usable
logo/logo.svg
0 → 100644
View file @
512b75a8
This diff is collapsed.
Click to expand it.
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment