Commit 5ce42fee authored by Ngan Thi Dong's avatar Ngan Thi Dong
Browse files

update README.md

parent 6f888834
......@@ -56,5 +56,24 @@ To calculate disease semantic similarity from MESH ontology, disease GIP or miRN
### Results
1. Effect of the data leakage problem on different models on HMDD2 dataset.
![erroneous_vs_correct.png](images/erroneous_vs_correct.png)
2. Average AP scores for our studied models on HMDD2 and HMDD3 datasets. Simpler variances in many cases, out-perform the originally proposed models.
![hmdd2_hmdd3_ap_scores.png](images/hmdd2_hmdd3.png)
3. Effect of balance training data and imbalanced training data on different models on HMDD2 and HMDD3 datasets.
![balance_vs_imbalance.png](images/balance_vs_imbalance.png)
If you use the code in your work, please cite the following paper:
Dong, Thi Ngan, and Megha Khosla. "A consistent evaluation of miRNA-disease association prediction models." bioRxiv (2020).
_Dong, Thi Ngan, and Megha Khosla. "A consistent evaluation of miRNA-disease association prediction models." bioRxiv (2020)._
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment