MLRDA: A Multi-Task Semi-Supervised Learning Framework for Drug-Drug Interaction Prediction

Drug-drug interactions (DDIs) are a major cause of preventable hospitalizations and deaths. Recently, researchers in the AI community try to improve DDI prediction in two directions, incorporating multiple drug features to better model the pharmacodynamics and adopting multi-task learning to exploit associations among DDI types. However, these two directions are challenging to reconcile due to the sparse nature of the DDI labels which inflates the risk of overfitting of multi-task learning models when incorporating multiple drug features. In this paper, we propose a multi-task semi-supervised learning framework MLRDA for DDI prediction. MLRDA effectively exploits information that is beneficial for DDI prediction in unlabeled drug data by leveraging a novel unsupervised disentangling loss CuXCov. The CuXCov loss cooperates with the classification loss to disentangle the DDI prediction relevant part from the irrelevant part in a representation learnt by an autoencoder, which helps to ease the difficulty in mining useful information for DDI prediction in both labeled and unlabeled drug data. Moreover, MLRDA adopts a multi-task learning framework to exploit associations among DDI types. 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.

[1]  R. Altman,et al.  Informatics confronts drug-drug interactions. , 2013, Trends in pharmacological sciences.

[2]  Tao Xiang,et al.  Scalable and Effective Deep CCA via Soft Decorrelation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  김삼묘,et al.  “Bioinformatics” 특집을 내면서 , 2000 .

[4]  George Hripcsak,et al.  Detection of drug‐drug interactions through data mining studies using clinical sources, scientific literature and social media , 2018, Briefings Bioinform..

[5]  Carol Friedman,et al.  Drug-drug interaction through molecular structure similarity analysis , 2012, J. Am. Medical Informatics Assoc..

[6]  Andrej Kastrin,et al.  Predicting potential drug-drug interactions on topological and semantic similarity features using statistical learning , 2018, PloS one.

[7]  Yanli Wang,et al.  Predicting drug–drug interactions through drug structural similarities and interaction networks incorporating pharmacokinetics and pharmacodynamics knowledge , 2017, Journal of Cheminformatics.

[8]  Zhongming Zhao,et al.  Machine learning-based prediction of drug-drug interactions by integrating drug phenotypic, therapeutic, chemical, and genomic properties. , 2014, Journal of the American Medical Informatics Association : JAMIA.

[9]  R. Altman,et al.  Data-Driven Prediction of Drug Effects and Interactions , 2012, Science Translational Medicine.

[10]  Fei Wang,et al.  Drug Similarity Integration Through Attentive Multi-view Graph Auto-Encoders , 2018, IJCAI.

[11]  Feng Liu,et al.  Predicting potential drug-drug interactions by integrating chemical, biological, phenotypic and network data , 2017, BMC Bioinformatics.

[12]  Bruno A. Olshausen,et al.  Discovering Hidden Factors of Variation in Deep Networks , 2014, ICLR.

[13]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[14]  Tapani Raiko,et al.  Semi-supervised Learning with Ladder Networks , 2015, NIPS.

[15]  Ping Zhang,et al.  Multitask Dyadic Prediction and Its Application in Prediction of Adverse Drug-Drug Interaction , 2017, AAAI.

[16]  L. Schumm,et al.  Changes in Prescription and Over-the-Counter Medication and Dietary Supplement Use Among Older Adults in the United States, 2005 vs 2011. , 2016, JAMA internal medicine.

[17]  Shin Ishii,et al.  Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[19]  Jianying Hu,et al.  Label Propagation Prediction of Drug-Drug Interactions Based on Clinical Side Effects , 2015, Scientific Reports.

[20]  Xing Xie,et al.  Explainable Recommendation through Attentive Multi-View Learning , 2019, AAAI.

[21]  Jae Yong Ryu,et al.  Deep learning improves prediction of drug–drug and drug–food interactions , 2018, Proceedings of the National Academy of Sciences.

[22]  Harri Valpola,et al.  Weight-averaged consistency targets improve semi-supervised deep learning results , 2017, ArXiv.

[23]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[24]  Thomas G. Dietterich What is machine learning? , 2020, Archives of Disease in Childhood.

[25]  Jorge Nocedal,et al.  On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima , 2016, ICLR.