research-article

KG-MTL: Knowledge Graph Enhanced Multi-Task Learning for Molecular Interaction

Authors:

Xiangxiang ZengAuthors Info & Claims

IEEE Transactions on Knowledge and Data Engineering, Volume 35, Issue 7

Pages 7068 - 7081

https://doi.org/10.1109/TKDE.2022.3188154

Published: 01 July 2023 Publication History

Abstract

Molecular interaction prediction is essential in various applications including drug discovery and material science. The problem becomes quite challenging when the interaction is represented by unmapped relationships in molecular networks, namely molecular interaction, because it easily suffers from (i) insufficient labeled data with many false-positive samples, and (ii) ignoring a large number of biological entities with rich information in the knowledge graph. Most of the existing methods cannot properly exploit the information of knowledge graph and molecule graph simultaneously. In this paper, we propose a large-scale <bold>K</bold>nowledge <bold>G</bold>raph enhanced <bold>M</bold>ulti-<bold>T</bold>ask <bold>L</bold>earning model, namely KG-MTL, which extracts the features from both knowledge graph and molecular graph in a synergistic way. Moreover, we design an effective <italic>Shared Unit</italic> that helps the model to jointly preserve the semantic relations of drug entity and the neighbor structures of the compound in both knowledge graph and molecular graph. Extensive experiments on four real-world datasets demonstrate that our proposed KG-MTL outperforms the state-of-the-art methods on two representative molecular interaction prediction tasks: drug-target interaction prediction and compound-protein interaction prediction. The source code of KG-MTL is available at <uri>https://github.com/xzenglab/KG-MTL</uri>.

References

[1]

M. Lukačišin and T. Bollenbach, “Emergent gene expression responses to drug combinations predict higher-order drug interactions,” Cell Syst., vol. 9, no. 5, pp. 423–433, 2019.

[2]

M. Bredel and E. Jacoby, “Chemogenomics: An emerging strategy for rapid target and drug discovery,” Nature Rev. Genet., vol. 5, no. 4, pp. 262–275, 2004.

[3]

Y.-S. Lee, A. Krishnan, R. Oughtred, J. Rust, C. S. Chang, J. Ryu, V. N. Kristensen, K. Dolinski, C. L. Theesfeld, and O. G. Troyanskaya, “A computational framework for genome-wide characterization of the human disease landscape,” Cell Syst., vol. 8, no. 2, pp. 152–162, 2019.

[4]

C. Zang and F. Wang, “MoFlow: An invertible flow model for generating molecular graphs,” in Proc. 26th ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, 2020, pp. 617–626.

[5]

Z. Hao et al., “ASGN: An active semi-supervised graph neural network for molecular property prediction,” in Proc. 26th ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, 2020, pp. 731–752.

[6]

M. Sun, F. Wang, O. Elemento, and J. Zhou, “Structure-based drug-drug interaction detection via expressive graph convolutional networks and deep sets (student abstract),” in Proc. AAAI Conf. Artif. Intell., 2020, pp. 13927–13928.

[7]

T. Fu, C. Xiao, L. Glass, and J. Sun, “MOLER: Incorporate molecule-level reward to enhance deep generative model for molecule optimization,” IEEE Trans. Knowl. Data Eng., early access, Jan. 21, 2021.

[8]

C. Xiao, P. Zhang, W. A. Chaowalitwongse, J. Hu, and F. Wang, “Adverse drug reaction prediction with symbolic latent Dirichlet allocation,” in Proc. AAAI Conf. Artif. Intell., 2017, pp. 1590–1596.

[9]

S. Dey, P. Zhang, D. Sow, and K. Ng, “PerDREP: Personalized drug effectiveness prediction from longitudinal observational data,” in Proc. 25th ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, 2019, pp. 1258–1268.

[10]

I. Shaked, M. A. Oberhardt, N. Atias, R. Sharan, and E. Ruppin, “Metabolic network prediction of drug side effects,” Cell Syst., vol. 2, no. 3, pp. 209–213, 2016.

[11]

F. Ma et al., “Unsupervised discovery of drug side-effects from heterogeneous data sources,” in Proc. 23rd ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, 2017, pp. 967–976.

[12]

K. Bleakley and Y. Yamanishi, “Supervised prediction of drug-target interactions using bipartite local models,” Bioinformatics, vol. 25, no. 18, pp. 2397–2403, 2009.

Digital Library

[13]

T. van Laarhoven, S. B. Nabuurs, and E. Marchiori, “Gaussian interaction profile kernels for predicting drug-target interaction,” Bioinformatics, vol. 27, no. 21, pp. 3036–3043, 2011.

Digital Library

[14]

K. Y. Gao, A. Fokoue, H. Luo, A. Iyengar, S. Dey, and P. Zhang, “Interpretable drug target prediction using deep neural representation,” in Proc. Int. Joint Conf. Artif. Intell., 2018, pp. 3371–3377.

[15]

M. Tsubaki, K. Tomii, and J. Sese, “Compound-protein interaction prediction with end-to-end learning of neural networks for graphs and sequences,” Bioinformatics, vol. 35, no. 2, pp. 309–318, 2019.

[16]

H. Chen and J. Li, “Learning data-driven drug-target-disease interaction via neural tensor network,” in Proc. Int. Joint Conf. Artif. Intell., 2020, pp. 3452–3458.

[17]

W. Zhao, J. Zhu, M. Yang, D. Xiao, G. P. C. Fung, and X. Chen, “A semi-supervised network embedding model for protein complexes detection,” in Proc. AAAI Conf. Artif. Intell., 2018, pp. 8185–8186.

[18]

Y. Luo et al., “A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information,” Nature Commun., vol. 8, no. 1, pp. 1–13, 2017.

[19]

F. Wan, L. Hong, A. Xiao, T. Jiang, and J. Zeng, “NeoDTI: Neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions,” Bioinformatics, vol. 35, no. 1, pp. 104–111, 2019.

[20]

M. Tognetti et al., “Deciphering the signaling network of breast cancer improves drug sensitivity prediction,” Cell Syst., vol. 12, no. 5, pp. 401–418, 2021.

[21]

H. Liu, J. Sun, J. Guan, J. Zheng, and S. Zhou, “Improving compound-protein interaction prediction by building up highly credible negative samples,” Bioinformatics, vol. 31, no. 12, pp. i221–i229, 2015.

[22]

K. Huang, C. Xiao, T. Hoang, L. Glass, and J. Sun, “CASTER: Predicting drug interactions with chemical substructure representation,” in Proc. AAAI Conf. Artif. Intell., 2020, pp. 702–709.

[23]

X. Lin, Z. Quan, Z.-J. Wang, T. Ma, and X. Zeng, “KGNN: Knowledge graph neural network for drug-drug interaction prediction,” in Proc. Int. Joint Conf. Artif. Intell., 2020, pp. 2739–2745.

[24]

J. Shang, C. Xiao, T. Ma, H. Li, and J. Sun, “GAMENet: Graph augmented memory networks for recommending medication combination,” in Proc. Artif. Intell., 2019, pp. 1126–1133.

[25]

S. K. Mohamed, V. Nováček, and A. Nounu, “Discovering protein drug targets using knowledge graph embeddings,” Bioinformatics, vol. 36, no. 2, pp. 603–610, 2020.

[26]

I. Misra, A. Shrivastava, A. Gupta, and M. Hebert, “Cross-stitch networks for multi-task learning,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 3994–4003.

[27]

J. Xu, J. Zhou, P.-N. Tan, X. Liu, and L. Luo, “Spatio-temporal multi-task learning via tensor decomposition,” IEEE Trans. Knowl. Data Eng., vol. 33, no. 6, pp. 2764–2775, Jun. 2021.

[28]

H. Xiao, Y. Chen, and X. Shi, “Knowledge graph embedding based on multi-view clustering framework,” IEEE Trans. Knowl. Data Eng., vol. 33, no. 2, pp. 585–596, Feb. 2021.

Digital Library

[29]

S. Li, F. Wan, H. Shu, T. Jiang, D. Zhao, and J. Zeng, “MONN: A multi-objective neural network for predicting compound-protein interactions and affinities,” Cell Syst., vol. 10, no. 4, pp. 308–322, 2020.

[30]

G. Landrum, “RDKit: Open-source cheminformatics,” 2006. [Online]. Available: https://rdkit.org/

[31]

V. N. Ioannidis et al., “DRKG - Drug repurposing knowledge graph for COVID-19,” 2020. [Online]. Available: https://github.com/gnn4dr/DRKG/

[32]

J. Chen, T. Ma, and C. Xiao, “FastGCN: Fast learning with graph convolutional networks via importance sampling,” in Proc. Int. Conf. Learn. Representations, 2018, pp. 1–15.

[33]

M. Schlichtkrull et al., “Modeling relational data with graph convolutional networks,” in Proc. Eur. Semantic Web Conf., 2018, pp. 593–607.

[34]

T. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” 2017,.

[35]

Z. Quan, Y. Guo, X. Lin, Z.-J. Wang, and X. Zeng, “GraphCPI: Graph neural representation learning for compound-protein interaction,” in Proc. IEEE Int. Conf. Bioinf. Biomed., 2019, pp. 717–722.

[36]

B. Dzmitry, C. Kyunghyun, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,” in Proc. Int. Conf. Learn. Representations, 2014, pp. 1–15.

[37]

R. Wang, B. Fu, G. Fu, and M. Wang, “Deep & cross network for ad click predictions,” in Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, 2017, pp. 1–7.

[38]

A. Kendall, Y. Gal, and R. Cipolla, “Multi-task learning using uncertainty to weigh losses for scene geometry and semantics,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2018, pp. 7482–7491.

[39]

H. Li, Y. Wang, Z. Lyu, and J. Shi, “Multi-task learning for recommendation over heterogeneous information network,” IEEE Trans. Knowl. Data Eng., vol. 34, no. 2, pp. 789–802, Feb. 2022.

Digital Library

[40]

D. S. Wishart et al., “DrugBank 5.0: A major update to the drugbank database for 2018,” Nucleic Acids Res., vol. 46, pp. D1074–D1082, 2018.

[41]

O. Ursu et al., “DrugCentral: Online drug compendium,” Nucleic Acids Res., vol. 45, no. D1, pp. D932–D939, 2016.

[42]

K. Huang, C. Xiao, L. Glass, and J. Sun, “MolTrans: Molecular interaction transformer for drug target interaction prediction,” Bioinformatics, vol. 37, pp. 830–836, 2021.

[43]

M. Wen et al., “Deep learning-based drug-target interaction prediction,” J. Proteome Res., vol. 16, no. 4, pp. 1401–1409, 2017.

[44]

I. Lee, J. Keum, and H. Nam, “DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences,” PLoS Comput. Biol., vol. 15, no. 6, 2019, Art. no.

[45]

A. Bordes, N. Usunier, A. Garcia-Duran, J. Weston, and O. Yakhnenko, “Translating embeddings for modeling multi-relational data,” in Proc. Int. Conf. Neural Inf. Process. Syst., 2013, pp. 2787–2795.

[46]

B. Yang, W.-T. Yih, X. He, J. Gao, and L. Deng, “Embedding entities and relations for learning and inference in knowledge bases,” 2014,.

[47]

F. Costa and K. De Grave, “Fast neighborhood subgraph pairwise distance kernel,” in Proc. Int. Conf. Mach. Learn., 2010, pp. 255–262.

[48]

Y. Zhao, A. Zhang, R. Xie, K. Liu, and X. Wang, “Connecting embeddings for knowledge graph entity typing,” in Proc. 58th Annu. Meeting Assoc. Comput. Linguistics, 2020, pp. 6419–6428.

[49]

D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” 2014,.

[50]

T. Liu, Y. Lin, X. Wen, R. N. Jorissen, and M. K. Gilson, “BindingDB: A web-accessible database of experimentally determined protein–ligand binding affinities,” Nucleic Acids Res., vol. 35, no. suppl_1, pp. D198–D201, 2007.

[51]

J. Davis and M. Goadrich, “The relationship between precision-recall and ROC curves,” in Proc. Int. Conf. Mach. Learn., 2006, pp. 233–240.

[52]

G. Bocci et al., “A machine learning platform to estimate anti-SARS-CoV-2 activities,” Nature Mach. Intell., vol. 3, pp. 527–535, 2021.

Cited By

Li XLiang SLei YLi CHou YZheng DMa TSerra ESpezzano F(2024)CausalMed: Causality-Based Personalized Medication Recommendation Centered on Patient Health StateProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3679542(1276-1285)Online publication date: 21-Oct-2024
https://dl.acm.org/doi/10.1145/3627673.3679542
Li XLiang SHou YMa T(2024)StratMedKnowledge-Based Systems10.1016/j.knosys.2023.111239284:COnline publication date: 25-Jan-2024
https://dl.acm.org/doi/10.1016/j.knosys.2023.111239

Recommendations

Novel insight into the molecular interaction of catalase and sucrose: A combination of in silico and in planta assays study
Highlights
- In silico 3D structure modelling of rice catalase-A (CatA) protein and its molecular interaction with sucrose was studied.
Abstract
Osmolytes are known to be an important factor for the stabilization and proficient functioning of proteins. However, the stabilization mechanism of proteins by the interaction of osmolytes is still not well explored. Here, we performed ...
Multi-target protein-chemical interaction prediction using task-regularized and boosted multi-task learning
BCB '12: Proceedings of the ACM Conference on Bioinformatics, Computational Biology and Biomedicine

Interactions between proteins and small-molecule chemicals modulate many protein functions and biological processes, and identifying these interactions is a crucial step in modern drug discovery. Supervised learning methods for predicting protein-...
Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction
WWW '21: Proceedings of the Web Conference 2021

Potential Drug-Drug Interactions (DDI) occur while treating complex or co-existing diseases with drug combinations, which may cause changes in drugs’ pharmacological activity. Therefore, DDI prediction has been an important task in the medical health ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image IEEE Transactions on Knowledge and Data Engineering

IEEE Transactions on Knowledge and Data Engineering Volume 35, Issue 7

July 2023

1090 pages

ISSN:1041-4347

Issue’s Table of Contents

1041-4347 © 2022 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.

Publisher

IEEE Educational Activities Department

United States

Publication History

Published: 01 July 2023

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 21 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Li XLiang SLei YLi CHou YZheng DMa TSerra ESpezzano F(2024)CausalMed: Causality-Based Personalized Medication Recommendation Centered on Patient Health StateProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3679542(1276-1285)Online publication date: 21-Oct-2024
https://dl.acm.org/doi/10.1145/3627673.3679542
Li XLiang SHou YMa T(2024)StratMedKnowledge-Based Systems10.1016/j.knosys.2023.111239284:COnline publication date: 25-Jan-2024
https://dl.acm.org/doi/10.1016/j.knosys.2023.111239

View Options

View options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents