Prediction of Synthetic Lethal Interactions in Human Cancers Using Multi-View Graph Auto-Encoder

Synthetic lethality (SL) is a very important concept for the development of targeted anticancer drugs. However, experimental methods for SL detection often suffer from various issues like high cost and low consistency across cell lines. Hence, computational methods for predicting novel SLs have recently emerged as complements for wet-lab experiments. In addition, SL data can be represented as a graph where nodes are genes and edges are the SL interactions. It is thus motivated to design advanced graph-based machine learning algorithms for SL prediction. In this paper, we propose a novel SL prediction method using Multi-view Graph Auto-Encoder (SLMGAE). We consider the SL graph as the main view and the graphs from other data sources (e.g., PPI, GO, etc.) as support views. Multiple Graph Auto-Encoders (GAEs) are implemented to reconstruct the graphs for different views. We further design an attention mechanism, which assigns different weights for support views, to combine all the reconstructed graphs for SL prediction. The overall SLMGAE model is then trained by minimizing both the reconstruction error and prediction error. Experimental results on the SynLethDB dataset show that SLMGAE outperforms state-of-the-arts. The case studies on novel predicted SLs also illustrate the effectiveness of our SLMGAE method.

[1]  Roland Arnold,et al.  A negative genetic interaction map in isogenic cancer cell lines reveals cancer cell vulnerabilities , 2013, Molecular systems biology.

[2]  A. Giaccia,et al.  Harnessing synthetic lethal interactions in anticancer drug discovery , 2011, Nature Reviews Drug Discovery.

[3]  P Manimaran,et al.  Identification of synthetic lethal pairs in biological systems through network information centrality. , 2013, Molecular bioSystems.

[4]  Bing Liu,et al.  Learning with Positive and Unlabeled Examples Using Weighted Logistic Regression , 2003, ICML.

[5]  Min Wu,et al.  Predicting synthetic lethal interactions in human cancers using graph regularized self-representative matrix factorization , 2019, BMC Bioinformatics.

[6]  P. Hieter,et al.  Synthetic lethality and cancer , 2017, Nature Reviews Genetics.

[7]  Aaron N. Chang,et al.  Combinatorial CRISPR-Cas9 screens for de novo mapping of genetic interactions , 2017, Nature Methods.

[8]  K. White,et al.  Widespread genetic epistasis among cancer genes , 2014, Nature Communications.

[9]  D. Silver,et al.  Synthetic lethality--a new direction in cancer-drug development. , 2009, The New England journal of medicine.

[10]  Max Welling,et al.  Variational Graph Auto-Encoders , 2016, ArXiv.

[11]  Min Wu,et al.  Dual-dropout graph convolutional network for predicting synthetic lethality in human cancers , 2020, Bioinform..

[12]  Nicholas P. Tatonetti,et al.  Connectivity Homology Enables Inter-Species Network Models of Synthetic Lethality , 2015, PLoS Comput. Biol..

[13]  Neal K. Bennett,et al.  Mapping the Genetic Landscape of Human Cells , 2018, Cell.

[14]  Yong Liu,et al.  SL2MF: Predicting Synthetic Lethality in Human Cancers via Logistic Matrix Factorization , 2018, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[15]  Richard Simon,et al.  Identification of potential synthetic lethal genes to p53 using a computational biology approach , 2013, BMC Medical Genomics.

[16]  Chee Keong Kwoh,et al.  Drug-target interaction prediction by learning from local information and neighbors , 2013, Bioinform..

[17]  Fei Wang,et al.  Multi-View Graph Convolutional Network and Its Applications on Neuroimage Analysis for Parkinson's Disease , 2018, AMIA.

[18]  Fei Wang,et al.  Heterogeneous Hyper-Network Embedding , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

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

[20]  Chee Keong Kwoh,et al.  Predicting Human Microbe-Drug Associations via Graph Convolutional Network with Conditional Random Field , 2020, Bioinform..

[21]  Kara Dolinski,et al.  The BioGRID interaction database: 2017 update , 2016, Nucleic Acids Res..

[22]  G. Mufti,et al.  Applying synthetic lethality for the selective targeting of cancer. , 2014, The New England journal of medicine.

[23]  Martin H. Schaefer,et al.  HIPPIE v2.0: enhancing meaningfulness and reliability of protein–protein interaction networks , 2016, Nucleic Acids Res..

[24]  Michael J. Emanuele,et al.  A Genome-wide RNAi Screen Identifies Multiple Synthetic Lethal Interactions with the Ras Oncogene , 2009, Cell.

[25]  Limsoon Wong,et al.  Inferring synthetic lethal interactions from mutual exclusivity of genetic events in cancer , 2015, Biology Direct.

[26]  Ping Zhang,et al.  Computational Drug Discovery with Dyadic Positive-Unlabeled Learning , 2017, SDM.

[27]  P. Canoll,et al.  Combined HDAC and Bromodomain Protein Inhibition Reprograms Tumor Cell Metabolism and Elicits Synthetic Lethality in Glioblastoma , 2018, Clinical Cancer Research.

[28]  Jure Leskovec,et al.  Representation Learning on Graphs: Methods and Applications , 2017, IEEE Data Eng. Bull..

[29]  Xiangxue Wang.  An Integrative Multi-Network and Multi-Classifier Approach to Predict Genetic Interactions , 2015 .

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

[31]  Xiang Deng,et al.  DiscoverSL: an R package for multi‐omic data driven prediction of synthetic lethality in cancers , 2018, Bioinform..

[32]  Eytan Ruppin,et al.  Predicting Cancer-Specific Vulnerability via Data-Driven Detection of Synthetic Lethality , 2014, Cell.

[33]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[34]  Subarna Sinha,et al.  Systematic discovery of mutation-specific synthetic lethals by mining pan-cancer human primary tumor data , 2017, Nature Communications.

[35]  Hui Liu,et al.  SynLethDB: synthetic lethality database toward discovery of selective and sensitive anticancer drug targets , 2015, Nucleic Acids Res..

[36]  Chee Keong Kwoh,et al.  Multi-View Collaborative Network Embedding , 2020, ACM Trans. Knowl. Discov. Data.

[37]  Hongzhi Yin,et al.  Disease Prediction via Graph Neural Networks , 2020, IEEE Journal of Biomedical and Health Informatics.

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

[39]  Xiangrong Chen,et al.  Predicting synthetic lethal interactions using conserved patterns in protein interaction networks , 2019, PLoS Comput. Biol..

[40]  S. Elledge,et al.  A Role for Mitochondrial Translation in Promotion of Viability in K-Ras Mutant Cells. , 2017, Cell reports.

[41]  Jesse Davis,et al.  Learning from positive and unlabeled data: a survey , 2018, Machine Learning.

[42]  Gaelen T. Hess,et al.  Synergistic drug combinations for cancer identified in a CRISPR screen for pairwise genetic interactions , 2017, Nature Biotechnology.

[43]  Fan Zhang,et al.  In Silico Prediction of Synthetic Lethality by Meta-Analysis of Genetic Interactions, Functions, and Pathways in Yeast and Human Cancer , 2014, Cancer informatics.

[44]  Eytan Ruppin,et al.  Harnessing synthetic lethality to predict the response to cancer treatment , 2018, Nature Communications.

[45]  Philip S. Yu,et al.  A new method to measure the semantic similarity of GO terms , 2007, Bioinform..