MLRDA: A Multi-Task Semi-Supervised Learning Framework for Drug-Drug Interaction Prediction
Authors: Xu Chu, Yang Lin, Yasha Wang, Leye Wang, Jiangtao Wang, Jingyue Gao
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on real-world datasets demonstrate that MLRDA significantly outperforms state-of-the-art DDI prediction methods by up to 10.3% in AUPR. |
| Researcher Affiliation | Academia | 1Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China 2National Engineering Research Center of Software Engineering, Peking University, Beijing, China 3School of Electronics Engineering and Computer Science, Peking University, Beijing, China 4School of Computing and Communications, Lancaster University, Lancashire, UK {chu xu, bdly, wangyasha, leyewang, gaojingyue1997}@pku.edu.cn, jiangtao.wang@lancaster.ac.uk |
| Pseudocode | No | The paper does not contain any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not include any explicit statements about releasing source code or provide links to a code repository for the described methodology. |
| Open Datasets | Yes | The labeled DDI data is from Twosides database6 [Tatonetti et al., 2012]. It contains 645 drugs and 1318 types of DDIs, and in total 63473 drug pairs associated with DDI reports. Drug chemical structure data I: The first chemical structure data are extracted from Pubchem2 substructure fingerprint. Drug chemical structure data II: The second chemical structure features are extended-connectivity fingerprints with diameter 6 (ECFP6) generated by R package rcdk 3. Drug indication data: The drug indication data is from SIDER4. Drug targets data: The drug target data is from Therapeutic Target Database5. Drug side effect data: The drug indication data is also from SIDER. (Footnotes: 2https://pubchem.ncbi.nlm.nih.gov/, 3https://cran.r-project.org/web/packages/rcdk/index.html, 4http://sideeffects.embl.de/download/, 5https://db.idrblab.org/ttd/full-data-download, 6http://tatonettilab.org/resources/tatonetti-stm.html) |
| Dataset Splits | Yes | We randomly select 10% of drugs and mask all DDIs associated with these drugs for testing. DDIs associated with drugs not in the testing set are used for training all models and we use 10-fold cross-validation to tune all hyperparameters of different methods. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU or CPU models used for running the experiments. |
| Software Dependencies | No | The paper mentions using "Adam optimizer" and "R package rcdk" but does not provide specific version numbers for these or other key software components or libraries required for replication. |
| Experiment Setup | Yes | We optimized the hyperparameters for MLRDA and fix them for all MLRDA variants. The hyperparameters are shown in Table 4. The models are trained by Adam optimizer[Kingma and Ba, 2014] with a learning rate of 0.0001 and a dropout rate of 0.1. We consider decaying learning rate after 10 epochs. (Table 4 includes: Number of layers H + 1 5 (2+1+2), Number of neurons in encoders 2048, 1024, Number of neurons in decoders 1024, 2048, Dimension of Zs 256, Activation function t( ) Re LU, (β, γ) of C1IT (125,0.25), (β, γ) of C2IS (50,0.25), Decay rate αs of C1IT (0.2, 0.6, 0.2), Decay rate αs of C2IS (0.3, 0.2, 0.6), Mini-batch size 1024) |