Accurate Prediction of Epigenetic Multi-Targets with Graph Neural Network-Based Feature Extraction
Abstract
:1. Introduction
2. Results
2.1. Experimental Dataset Analysis
2.2. Performance Evaluation and Comparison of Different Graph Neural Networks in Single-Target Performance
2.3. Multi-Target Validation
2.4. Retrospective Identification of Multi-Targets
- Case1: Prediction and analysis of polypharmacology of known drugs.
- Case2: Multi-target prediction of new compounds
2.5. Molecular Docking Verification
3. Discussion
4. Materials and Methods
4.1. Data Set Preparation
4.2. Molecular Graph
4.3. Multi-Target Fishing Model Generation
4.4. Performance Metrics
4.5. Experimental Environment
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Felsenfeld, G.; Groudine, M. Controlling the double helix. Nature 2003, 421, 448–453. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Gilbert, J.; Gore, S.D.; Herman, J.G.; Carducci, M.A. The clinical application of targeting cancer through histone acetylation and hypomethylatio. Clin. Cancer Res. 2004, 10, 4589–4596. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Li, L.C.; Carroll, P.R.; Dahiya, R. Epigenetic changes in prostate cancer: Implication for diagnosis and treatment. J. Natl. Cancer Inst. 2005, 97, 103–115. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Fang, J.; Huang, Y.; Mao, G.; Yang, S.; Rennert, G.; Gu, L.; Li, H.; Li, G.-M. Cancer-driving H3G34V/R/D mutations block H3K36 methylation and H3K36me3–MutSα interaction. Proc. Natl. Acad. Sci. USA 2018, 115, 9598–9603. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Nan, X.; Ng, H.H.; Johnson, C.A.; Laherty, C.D.; Turner, B.M.; Eisenman, R.N.; Bird, A. Transcriptional repression by the methyl-CpG-binding protein MeCP2 involves a histone deacetylase complex. Nature 1998, 393, 386–389. [Google Scholar] [CrossRef]
- Lehnertz, B.; Ueda, Y.; Derijck, A.A.; Braunschweig, U.; Perez-Burgos, L.; Kubicek, S.; Chen, T.; Li, E.; Jenuwein, T.; Peters, A.H. Suv39h-Mediated Histone H3 Lysine 9 Methylation Directs DNA Methylation to Major Satellite Repeats at Pericentric Heterochromatin. Curr. Biol. 2003, 13, 1192–1200. [Google Scholar] [CrossRef] [Green Version]
- Bachman, K.E.; Park, B.H.; Rhee, I.; Rajagopalan, H.; Herman, J.G.; Baylin, S.B.; Kinzler, K.W.; Vogelstein, B. Histone modifications and silencing prior to DNA methylation of a tumor suppressor gene. Cancer Cell 2003, 3, 89–95. [Google Scholar] [CrossRef] [Green Version]
- Mager, J.; Montgomery, N.D.; de Villena, F.P.M.; Magnuson, T. Genome imprinting regulated by the mouse Polycomb group protein Eed. Nat. Genet. 2003, 33, 502–507. [Google Scholar] [CrossRef]
- Martínez-Chantar, M.L.; Vázquez-Chantada, M.; Ariz, U.; Martínez, N.; Varela, M.; Luka, Z.; Capdevila, A.; Rodríguez, J.; Aransay, A.M.; Matthiesen, R.; et al. Loss of the glycine N-methyltransferase gene leads to steatosis and hepatocellular carcinoma in mice. Hepatology 2007, 47, 1191–1199. [Google Scholar] [CrossRef] [Green Version]
- Pannetier, M.; Julien, E.; Schotta, G.; Tardat, M.; Sardet, C.; Jenuwein, T.; Feil, R. PR-SET7 and SUV4-20H regulate H4 lysine-20 methylation at imprinting control regions in the mouse. EMBO Rep. 2008, 9, 998–1005. [Google Scholar] [CrossRef]
- Fraga, M.F.; Ballestar, E.; Villar-Garea, A.; Boix-Chornet, M.; Espada, J.; Schotta, G.; Bonaldi, T.; Haydon, C.; Ropero, S.; Petrie, K.; et al. Loss of acetylation at Lys16 and trimethylation at Lys20 of histone H4 is a common hallmark of human cancer. Nat. Genet. 2005, 37, 391–400. [Google Scholar] [CrossRef]
- Schübeler, D.; MacAlpine, D.M.; Scalzo, D.; Wirbelauer, C.; Kooperberg, C.; Van Leeuwen, F.; Gottschling, D.E.; O’Neill, L.P.; Turner, B.M.; Delrow, J.; et al. The histone modification pattern of active genes revealed through genome-wide chromatin analysis of a higher eukaryote. Genes Dev. 2004, 18, 1263–1271. [Google Scholar] [CrossRef] [Green Version]
- Okitsu, C.Y.; Hsieh, C.-L. DNA Methylation Dictates Histone H3K4 Methylation. Mol. Cell. Biol. 2007, 27, 2746–2757. [Google Scholar] [CrossRef] [Green Version]
- Xu, W.; Li, J.; Rong, B.; Zhao, B.; Wang, M.; Dai, R.; Chen, Q.; Liu, H.; Gu, Z.; Liu, S.; et al. Correction to: DNMT3A reads and connects histone H3K36me2 to DNA methylation. Protein Cell 2020, 11, 230. [Google Scholar] [CrossRef] [Green Version]
- Kalin, J.H.; Wu, M.; Gomez, A.V.; Song, Y.; Das, J.; Hayward, D.; Adejola, N.; Wu, M.; Panova, I.; Chung, H.J.; et al. Targeting the CoREST complex with dual histone deacetylase and demethylase inhibitors. Nat. Commun. 2018, 9, 53. [Google Scholar] [CrossRef] [Green Version]
- Mendez, D.; Gaulton, A.; Bento, A.P.; Chambers, J.; De Veij, M.; Félix, E.; Magariños, M.P.; Mosquera, J.F.; Mutowo, P.; Nowotka, M.; et al. ChEMBL: Towards directdeposition of bioassay data. Nucleic Acids Res. 2019, 47, D930–D940. [Google Scholar] [CrossRef]
- Wang, Y.; Zhang, S.; Li, F.; Zhou, Y.; Zhang, Y.; Wang, Z.; Zhang, R.; Zhu, J.; Ren, Y.; Tan, Y.; et al. Therapeutic target database 2020: Enriched resource for facilitating research and early development of targeted therapeutics. Nucleic Acids Res. 2020, 48, D1031–D1041. [Google Scholar] [CrossRef] [Green Version]
- Keiser, M.; Roth, B.L.; Armbruster, B.N.; Ernsberger, P.; Irwin, J.; Shoichet, B.K. Relating protein pharmacology by ligand chemistry. Nat. Biotechnol. 2007, 25, 197–206. [Google Scholar] [CrossRef] [Green Version]
- Awale, M.; Reymond, J.-L. The Polypharmacology Browser: A web-based multi-fingerprint target prediction tool using ChEMBL bioactivity data. J. Cheminform. 2017, 9, 11. [Google Scholar] [CrossRef] [Green Version]
- Gfeller, D.; Grosdidier, A.; Wirth, M.; Daina, A.; Michielin, O.; Zoete, V. SwissTargetPrediction: A web server for target prediction of bioactive small molecules. Nucleic Acids Res. 2014, 42, W32–W38. [Google Scholar] [CrossRef]
- Cherkasov, A.; Muratov, E.N.; Fourches, D.; Varnek, A.; Baskin, I.I.; Cronin, M.; Dearden, J.; Gramatica, P.; Martin, Y.C.; Todeschini, R.; et al. QSAR modeling: Where have you been? Where are you going to? J. Med. Chem. 2014, 57, 4977–5010. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Yao, X.J.; Panaye, A.; Doucet, J.P.; Zhang, R.S.; Chen, H.F.; Liu, M.C.; Hu, Z.D.; Fan, B.T. Comparative Study of QSAR/QSPR Correlations Using Support Vector Machines, Radial Basis Function Neural Networks, and Multiple Linear Regression. J. Chem. Inf. Comput. Sci. 2004, 44, 1257–1266. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Svetnik, V.; Liaw, A.; Tong, C.; Culberson, J.C.; Sheridan, R.P.; Feuston, B.P. Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling. J. Chem. Inf. Comput. Sci. 2003, 43, 1947–1958. [Google Scholar] [CrossRef] [PubMed]
- Maleki, A.; Daraei, H.; Alaei, L.; Faraji, A. Comparison of QSAR models based on combinations of genetic algorithm, stepwise multiple linear regression, and artificial neural network methods to predict Kd of some derivatives of aromatic sulfonamides as carbonic anhydrase II inhibitors. Russ. J. Bioorg. Chem. 2014, 40, 61–75. [Google Scholar] [CrossRef]
- Eberhardt, J.; Santos-Martins, D.; Tillack, A.F.; Forli, S. AutoDock Vina 1.2.0: New Docking Methods, Expanded Force Field, and Python Bindings. J. Chem. Inf. Model. 2021, 61, 3891–3898. [Google Scholar] [CrossRef]
- Gong, P.; Zhang, C.; Chen, M. Editorial: Deep Learning for Toxicity and Disease Prediction. Front. Genet. 2020, 11, 175. [Google Scholar] [CrossRef] [Green Version]
- Lavecchia, A. Deep learning in drug discovery: Opportunities, challenges and future prospects. Drug Discov. Today 2019, 24, 2017–2032. [Google Scholar] [CrossRef]
- Friedman, J.; Hastie, T.; Tibshirani, R. Additive logistic regression: A statistical view of boosting (with discussion and a rejoinder by the authors). Ann. Stat. 2000, 28, 337–407. [Google Scholar] [CrossRef]
- Friedman, J.H. Greedy function approximation: A gradientboosting machine. Ann. Stat. 2001, 29, 1189–1232. [Google Scholar] [CrossRef]
- Li, B.; Wang, W.; Sun, Y.; Zhang, L.; Ali, M.A.; Wang, Y. GraphER: Token-Centric Entity Resolution with Graph Convolutional Neural Networks. Proc. Conf. AAAI Artif. Intell. 2020, 34, 8172–8179. [Google Scholar] [CrossRef]
- Dey, R.; Salemt, F.M. Gate-variants of Gated Recurrent Unit (GRU) neural networks. In Proceedings of the 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS), Boston, MA, USA, 6–9 August 2017; pp. 1597–1600. [Google Scholar]
- Yang, K.; Swanson, K.; Jin, W.; Coley, C.; Eiden, P.; Gao, H.; Guzman-Perez, A.; Hopper, T.; Kelley, B.; Mathea, M. Analyzinglearned molecular representations for property prediction. J. Chem. Inf. Model. 2019, 59, 3370. [Google Scholar] [CrossRef] [Green Version]
- Harada, T.; Ohguchi, H.; Grondin, Y.; Kikuchi, S.; Sagawa, M.; Tai, Y.-T.; Mazitschek, R.; Hideshima, T.; Anderson, K.C. HDAC3 regulates DNMT1 expression in multiple myeloma: Therapeutic implications. Leukemia 2017, 31, 2670–2677. [Google Scholar] [CrossRef] [Green Version]
- Pathania, R.; Ramachandran, S.; Mariappan, G.; Thakur, P.; Shi, H.; Choi, J.-H.; Manicassamy, S.; Kolhe, R.; Prasad, P.D.; Sharma, S.; et al. Combined Inhibition of DNMT and HDAC Blocks the Tumorigenicity of Cancer Stem-like Cells and Attenuates Mammary Tumor Growth. Cancer Res. 2016, 76, 3224–3235. [Google Scholar] [CrossRef] [Green Version]
- Rose, N.R.; Ng, S.S.; Mecinovic, J.; Liénard, B.M.; Bello, S.H.; Sun, Z.; McDonough, M.A.; Oppermann, U.; Schofield, C.J. Inhibitor scaffolds for 2-oxoglutarate-dependent histone lysine demethylases. J. Med. Chem. 2008, 51, 7053–7056. [Google Scholar] [CrossRef]
- Available online: https://github.com/rdkit/rdkit/tree/master/Contrib/IFG (accessed on 1 May 2022).
- Kingma, D.; Ba, J. Adam: A Method for Stochastic Optimization. arXiv 2014, arXiv:1412.6980. [Google Scholar]
Object | Target | GCN | GGNN | DMPNN | ||||||
---|---|---|---|---|---|---|---|---|---|---|
MCC | F1 | BA | MCC | F1 | BA | MCC | F1 | BA | ||
HDAC | SIRT3 | 0.516 | 0.556 | 1 | 0.411 | 0.526 | 0.833 | 0.516 | 0.556 | 1 |
SIRT1 | 0.667 | 0.78 | 0.75 | 0.624 | 0.75 | 0.732 | 0.602 | 0.734 | 0.725 | |
HDAC9 | 0.391 | 0.725 | 0.735 | 0.282 | 0.725 | 0.644 | 0.482 | 0.784 | 0.75 | |
HDAC8 | 0.669 | 0.896 | 0.862 | 0.69 | 0.901 | 0.867 | 0.721 | 0.913 | 0.863 | |
HDAC7 | 0.283 | 0.55 | 0.55 | 0.33 | 0.613 | 0.543 | 0.436 | 0.655 | 0.667 | |
HDAC6 | 0.637 | 0.941 | 0.93 | 0.625 | 0.938 | 0.93 | 0.689 | 0.948 | 0.94 | |
HDAC4 | 0.482 | 0.714 | 0.727 | 0.43 | 0.64 | 0.775 | 0.6 | 0.767 | 0.82 | |
HDAC3 | 0.55 | 0.919 | 0.89 | 0.56 | 0.92 | 0.9 | 0.6 | 0.93 | 0.91 | |
HDAC2 | 0.44 | 0.91 | 0.86 | 0.314 | 0.9 | 0.84 | 0.48 | 0.92 | 0.88 | |
HDAC1 | 0.46 | 0.92 | 0.89 | 0.46 | 0.922 | 0.91 | 0.57 | 0.94 | 0.92 | |
HMT | PRMT3 | 0.315 | 0.643 | 0.75 | 0.167 | 0.571 | 0.667 | 0.667 | 0.87 | 0.762 |
PRKCB | 0.553 | 0.935 | 0.906 | 0.51 | 0.925 | 0.901 | 0.615 | 0.937 | 0.934 | |
EHMT2 | 0.04 | 0.61 | 0.82 | 0.05 | 0.88 | 0.81 | 0.25 | 0.9 | 0.83 | |
DOT1L | 0.27 | 0.42 | 0.8 | 0.285 | 0.643 | 0.64 | 0.247 | 0.66 | 0.571 | |
EZH2 | 0.403 | 0.942 | 0.892 | 0.323 | 0.92 | 0.90 | 0.32 | 0.931 | 0.875 | |
CARM1 | 0.12 | 0.667 | 0.63 | 0.34 | 0.77 | 0.68 | 0.13 | 0.667 | 0.63 | |
HDM | KDM6B | 0.201 | 0.133 | 1 | 0.276 | 0.522 | 0.667 | 0.189 | 0.6 | 0.526 |
KDM5A | 0.341 | 0.375 | 0.75 | 0.434 | 0.526 | 0.71 | 0.167 | 0.25 | 0.5 | |
KDM4E | 0.176 | 0.4 | 0.6 | 0.186 | 0 | 0 | 0.28 | 0.556 | 0.625 | |
KDM4C | 0.173 | 0.6 | 0.437 | 0.309 | 0.59 | 0.59 | 0.45 | 0.68 | 0.64 | |
KDM1A | 0.42 | 0.89 | 0.84 | 0.55 | 0.9 | 0.89 | 0.537 | 0.891 | 0.91 | |
HAT | KAT2B | 0.19 | 0.65 | 0.52 | 0.24 | 0.67 | 0.5 | 0.267 | 0.647 | 0.58 |
CREBBP | 0.36 | 0.86 | 0.77 | 0.245 | 0.83 | 0.77 | 0.368 | 0.82 | 0.83 | |
DNMT | DNMT1 | 0.316 | 0.83 | 0.8 | 0.438 | 0.76 | 0.86 | 0.55 | 0.83 | 0.88 |
Model | Object | PRECISION | RECALL |
---|---|---|---|
GCN | HDAC | 0.819 ± 0.091 | 0.796 ± 0.013 |
HMT | 0.782 ± 0.11 | 0.94 ± 0.081 | |
HDM | 0.762 ± 0.19 | 0.64 ± 0.13 | |
HAT | 0.65 ± 0.15 | 0.98 ± 0.03 | |
DNMT | 0.88 | 1 | |
GGNN | HDAC | 0.79 ± 0.02 | 0.766 ± 0.06 |
HMT | 0.74 ± 0.21 | 0.91 ± 0.11 | |
HDM | 0.611 ± 0.32 | 0.58 ± 0.06 | |
HAT | 0.602 ± 0.21 | 0.975 ± 0.04 | |
DNMT | 0.86 | 1 | |
DMPNN | HDAC | 0.85 ± 0.02 | 0.95 ± 0.13 |
HMT | 0.85 ± 0.17 | 0.945 ± 0.02 | |
HDM | 0.66 ± 0.11 | 0.71 ± 0.3 | |
HAT | 0.705 ± 0.19 | 0.99 ± 0.01 | |
DNMT | 0.89 | 1 |
Drug Name | HDAC | HMT | HDM | HAT | DNMT |
---|---|---|---|---|---|
AZACITIDINE | Sig | No | No | No | Sig |
DECITABINE | Sig | No | No | No | Sig |
TRYPTOPHAN | No | Sig | Sig | Sig | Sig |
HYDRALAZINE | Sig | No | Sig | Sig | Sig |
PROCAINE | No | No | No | No | Sig |
CEPHALOTHIN | No | No | No | No | Sig |
PROCAINAMIDE | No | No | No | No | Sig |
CURCUMIN | No | No | Sig | Sig | No |
FLUCONAZOLE | Sig | No | No | Sig | Sig |
TACRINE | Sig | Sig | No | Sig | Sig |
TAZEMETOSTAT | Sig | Sig | No | No | Sig |
VORINOSTAT | Sig | Sig | No | No | Sig |
DIPHENHYDRAMINE | No | Sig | Sig | Sig | Sig |
BENZTHIAZIDE | No | No | Sig | No | Sig |
PANOBINOSTAT | Sig | Sig | Sig | Sig | No |
BELINOSTAT | Sig | No | Sig | Sig | No |
ROMIDEPSIN | Sig | Sig | No | No | Sig |
VORINOSTAT | Sig | No | No | No | Sig |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wang, Y.; Qi, J.; Chen, X. Accurate Prediction of Epigenetic Multi-Targets with Graph Neural Network-Based Feature Extraction. Int. J. Mol. Sci. 2022, 23, 13347. https://doi.org/10.3390/ijms232113347
Wang Y, Qi J, Chen X. Accurate Prediction of Epigenetic Multi-Targets with Graph Neural Network-Based Feature Extraction. International Journal of Molecular Sciences. 2022; 23(21):13347. https://doi.org/10.3390/ijms232113347
Chicago/Turabian StyleWang, Yishu, Juan Qi, and Xiaomin Chen. 2022. "Accurate Prediction of Epigenetic Multi-Targets with Graph Neural Network-Based Feature Extraction" International Journal of Molecular Sciences 23, no. 21: 13347. https://doi.org/10.3390/ijms232113347
APA StyleWang, Y., Qi, J., & Chen, X. (2022). Accurate Prediction of Epigenetic Multi-Targets with Graph Neural Network-Based Feature Extraction. International Journal of Molecular Sciences, 23(21), 13347. https://doi.org/10.3390/ijms232113347