Denoising Protein–Protein interaction network via variational graph auto-encoder for protein complex detection
Abstract
Identifying protein complexes is an important issue in computational biology, as it benefits the understanding of cellular functions and the design of drugs. In the past decades, many computational methods have been proposed by mining dense subgraphs in Protein–Protein Interaction Networks (PINs). However, the high rate of false positive/negative interactions in PINs prevents accurately detecting complexes directly from the raw PINs. In this paper, we propose a denoising approach for protein complex detection by using variational graph auto-encoder. First, we embed a PIN to vector space by a stacked graph convolutional network (GCN), then decide which interactions in the PIN are credible. If the probability of an interaction being credible is less than a threshold, we delete the interaction. In such a way, we reconstruct a reliable PIN. Following that, we detect protein complexes in the reconstructed PIN by using several typical detection methods, including CPM, Coach, DPClus, GraphEntropy, IPCA and MCODE, and compare the results with those obtained directly from the original PIN. We conduct the empirical evaluation on four yeast PPI datasets (Gavin, Krogan, DIP and Wiphi) and two human PPI datasets (Reactome and Reactomekb), against two yeast complex benchmarks (CYC2008 and MIPS) and three human complex benchmarks (REACT, REACT_uniprotkb and CORE_COMPLEX_human), respectively. Experimental results show that with the reconstructed PINs obtained by our denoising approach, complex detection performance can get obviously boosted, in most cases by over 5%, sometimes even by 200%. Furthermore, we compare our approach with two existing denoising methods (RWS and RedNemo) while varying different matching rates on separate complex distributions. Our results show that in most cases (over 2/3), the proposed approach outperforms the existing methods.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Due to experimental and resource constraints, the most current PPI networks remain limited in the number of protein nodes and physical interaction edges.
“Due to experimental and resource constraints, the most updated PPI networks are still limited in their number of nodes (proteins) and edges (physical interactions) [118].”
From Graph representation learning in biomedicine and healthcare (2022) · cites this paper as [118]
Cites
node2vec: Scalable Feature Learning for Networks
Grover, A., & Leskovec, J. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939754 · Cited by 10,926 · see citing works
DeepWalk: online learning of social representations
Perozzi, B., Al-Rfou, R., & Skiena, S. (2014) · Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2623330.2623732 · Cited by 10,123 · see citing works
Extracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436 · see citing works
An automated method for finding molecular complexes in large protein interaction networks
Bader, G. D., & Hogue, C. W. V. (2003) · BMC Bioinformatics · doi:10.1186/1471-2105-4-2 · Cited by 6,112 · see citing works
LINE: Large-scale Information Network Embedding
Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., & Mei, Q. (2015) · Proceedings of the 24th International Conference on World Wide Web · doi:10.1145/2736277.2741093 · Cited by 5,416 · see citing works
An efficient algorithm for large-scale detection of protein families
Enright, A. J. (2002) · Nucleic Acids Research · doi:10.1093/nar/30.7.1575 · Cited by 3,536 · see citing works
Global landscape of protein complexes in the yeast Saccharomyces cerevisiae
Krogan, N. J., Cagney, G., Yu, H., Zhong, G., Guo, X., Ignatchenko, A., Li, J., Pu, S., Datta, N., Tikuisis, A., et al. (2006) · Nature · doi:10.1038/nature04670 · Cited by 2,915 · see citing works
Structural Deep Network Embedding
Wang, D., Cui, P., & Zhu, W. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939753 · Cited by 2,845 · see citing works
Proteome survey reveals modularity of the yeast cell machinery
Gavin, A., Aloy, P., Grandi, P., Krause, R., Böesche, M., Marzioch, M., Rau, C., Jensen, L. J., Bastuck, S., Dümpelfeld, B., et al. (2006) · Nature · doi:10.1038/nature04532 · Cited by 2,544 · see citing works
Xénarios, I. (2002) · Nucleic Acids Research · doi:10.1093/nar/30.1.303 · Cited by 1,746 · see citing works
Protein complexes and functional modules in molecular networks
Spirin, V., & Mirny, L. A. (2003) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2032324100 · Cited by 1,468 · see citing works
Cui, P., Wang, X., Pei, J., & Zhu, W. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2849727 · Cited by 1,274 · see citing works
CFinder: locating cliques and overlapping modules in biological networks
Adamcsek, B., Palla, G., Farkas, I. J., Derényi, I., & Vicsek, T. (2006) · Bioinformatics · doi:10.1093/bioinformatics/btl039 · Cited by 932 · see citing works
Adversarially Regularized Graph Autoencoder for Graph Embedding
Pan, S., Hu, R., Long, G., Jiang, J., Yao, L., & Zhang, C. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/362 · Cited by 929 · see citing works
MIPS: analysis and annotation of proteins from whole genomes
Mewes, H. (2003) · Nucleic Acids Research · doi:10.1093/nar/gkh092 · Cited by 713 · see citing works
Protein complex prediction via cost-based clustering
King, A. D., Pržulj, N., & Jurišica, I. (2004) · Bioinformatics · doi:10.1093/bioinformatics/bth351 · Cited by 666 · see citing works
Up-to-date catalogues of yeast protein complexes
Pu, S., Wong, J., Turner, B., Cho, E., & Wodak, S. J. (2008) · Nucleic Acids Research · doi:10.1093/nar/gkn1005 · Cited by 606 · see citing works
CORUM: the comprehensive resource of mammalian protein complexes—2019
Giurgiu, M., Reinhard, J., Brauner, B., Dunger-Kaltenbach, I., Fobo, G., Frishman, G., Montrone, C., & Ruepp, A. (2019) · Nucleic Acids Research · doi:10.1093/nar/gky973 · Cited by 595 · see citing works
Altaf‐Ul‐Amin, M., Shinbo, Y., Mihara, K., et al. (2006) · BMC Bioinformatics · doi:10.1186/1471-2105-7-207 · Cited by 495 · see citing works
Wang, C., Pan, S., Long, G., Xingquan Zhu, A., & Jiang, J. B. (2017) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3132847.3132967 · Cited by 419 · see citing works
A core-attachment based method to detect protein complexes in PPI networks
Wu, M., Li, X., Kwoh, C. K., & Ng, S.-K. (2009) · BMC Bioinformatics · doi:10.1186/1471-2105-10-169 · Cited by 378 · see citing works
Modifying the DPClus algorithm for identifying protein complexes based on new topological structures
Li, M., Chen, J., Wang, J., Hu, B., & Chen, G. (2008) · BMC Bioinformatics · doi:10.1186/1471-2105-9-398 · Cited by 246 · see citing works
Predicting Protein Complexes from PPI Data: A Core-Attachment Approach
Leung, H. C. M., Xiang, Q., Yiu, S. M., et al. (2009) · Journal of Computational Biology · doi:10.1089/cmb.2008.01tt · Cited by 222 · see citing works
Lei, C., & Ruan, J. (2012) · Bioinformatics · doi:10.1093/bioinformatics/bts688 · Cited by 196 · see citing works
Geometric De-noising of Protein-Protein Interaction Networks
Kuchaiev, O., Rašajski, M., Higham, D. J., & Pržulj, N. (2009) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1000454 · Cited by 180 · see citing works
Wang, J., Peng, X., Li, M., et al. (2012) · PROTEOMICS · doi:10.1002/pmic.201200277 · Cited by 162 · see citing works
USING INDIRECT PROTEIN–PROTEIN INTERACTIONS FOR PROTEIN COMPLEX PREDICTION
Chua, H. N., Ning, K., Sung, W.-K. K., et al. (2008) · Journal of Bioinformatics and Computational Biology · doi:10.1142/s0219720008003497 · Cited by 149 · see citing works
Maraziotis, I. A., Dimitrakopoulou, K., & Bezerianos, A. (2007) · BMC Bioinformatics · doi:10.1186/1471-2105-8-408 · Cited by 87 · see citing works
Ma, C., Chen, Y. P., Berger, B., et al. (2017) · Bioinformatics · doi:10.1093/bioinformatics/btx043 · Cited by 85 · see citing works
WI‐PHI: A weighted yeast interactome enriched for direct physical interactions
Kiemer, L., Costa, S., Ueffing, M., & Cesareni, G. (2007) · PROTEOMICS · doi:10.1002/pmic.200600448 · Cited by 84 · see citing works
Kenley, E. C., & Cho, Y. (2011) · PROTEOMICS · doi:10.1002/pmic.201100193 · Cited by 56 · see citing works
Theofilatos, K., Pavlopoulou, N., Papasavvas, C., Likothanassis, S. D., Dimitrakopoulos, C. M., Georgopoulos, E. F., Moschopoulos, C. N., & Mavroudi, S. P. (2015) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2014.12.012 · Cited by 37 · see citing works
Protein complexes predictions within protein interaction networks using genetic algorithms
Ramadan, E., Naef, A., & Ahmed, M. (2016) · BMC Bioinformatics · doi:10.1186/s12859-016-1096-4 · Cited by 32 · see citing works
From the static interactome to dynamic protein complexes: Three challenges
Yong, C. H., & Wong, L. (2015) · Journal of Bioinformatics and Computational Biology · doi:10.1142/s0219720015710018 · Cited by 31 · see citing works
Predicting protein complex in protein interaction network - a supervised learning based method
Yu, F. Y., Yang, Z., Tang, N., Lin, H. F., Wang, J., & Yang, Z. W. (2014) · BMC Systems Biology · doi:10.1186/1752-0509-8-s3-s4 · Cited by 28 · see citing works
Xu, B., Wang, Y., Wang, Z., et al. (2017) · BMC Bioinformatics · doi:10.1186/s12859-017-1820-8 · Cited by 27 · see citing works
Ou-Yang, L., Yan, H., & Zhang, X.-F. (2017) · BMC Bioinformatics · doi:10.1186/s12859-017-1877-4 · Cited by 27 · see citing works
Xu, B., & Guan, J. (2014) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2014.2306825 · Cited by 25 · see citing works
Self-citationXu, Y., Zhou, J., Zhou, S., et al. (2017) · BMC Systems Biology · doi:10.1186/s12918-017-0504-3 · Cited by 23 · see citing works
Survey: Enhancing protein complex prediction in PPI networks with GO similarity weighting
Price, T., Peña, F. I., & Cho, Y. (2013) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-013-0174-9 · Cited by 18 · see citing works
Protein complex detection in PPI networks based on data integration and supervised learning method
Yu, F. Y., Yang, Z., Hu, X. H., et al. (2015) · BMC Bioinformatics · doi:10.1186/1471-2105-16-s12-s3 · Cited by 17 · see citing works
Alkan, F., & Erten, C. (2016) · Bioinformatics · doi:10.1093/bioinformatics/btw655 · Cited by 11 · see citing works
CPredictor 4.0: effectively detecting protein complexes in weighted dynamic PPI networks
Shi, Y., Yao, H., Guan, J., et al. (2018) · International Journal of Data Mining and Bioinformatics · doi:10.1504/ijdmb.2018.094888 · Cited by 9 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Graph representation learning in biomedicine and healthcare
Li, M. M., Huang, K., & Zitnik, M. (2022) · Nature Biomedical Engineering · doi:10.1038/s41551-022-00942-x · Cited by 294 · see citing works
“Similar graph convolution methods can also be used to remove less credible interactions, thereby constructing a more reliable protein–protein interaction network 118 .”
- Authors
- Yao, H., Guan, J., & Liu, T.
- Affiliations
- Tongji University (CN)
- Corresponding author
- Guan, Jihong
- Venue
- Journal of Bioinformatics and Computational Biology
- Publisher
- World Scientific Pub Co Pte Ltd
- Published
- 2020-06
- Volume
- 18
- Issue
- 03
- Pages
- 2040010
- ISSN
- 0219-7200 (ISSN-L)
- 1757-6334
- OpenAlex
- W3033143713
- Cited by
- 23
- References
- 43
- Citations by year
- 2025: 4 · 2024: 1 · 2023: 4 · 2022: 7 · 2021: 5 · 2020: 2
- FWCI
- 1.46
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Bioinformatics and Computational Biology (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (61772367)
- Shanghai Municipal Commission of Economy and Informatization (18XI-05)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Complex Network Analysis Techniques
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene Regulatory Network Analysis
- Keywords
- protein-protein interaction network, protein complex detection, false positive interactions, network inference, dense subgraph mining, yeast interactome, human interactome
- MeSH terms
- Computer Graphics, Humans, Probability, Saccharomyces cerevisiae, Databases, Factual, Computational Biology, Protein Interaction Mapping, Protein Interaction Maps
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
