Disclosing incoherent sparse and low-rank patterns inside homologous GPCR tasks for better modelling of ligand bioactivities

Abstract

There are many new and potential drug targets in G protein-coupled receptors (GPCRs) without sufficient ligand associations, and accurately predicting and interpreting ligand bioactivities is vital for screening and optimizing hit compounds targeting these GPCRs. To efficiently address the lack of labeled training samples, we proposed a multi-task regression learning with incoherent sparse and low-rank patterns (MTR-ISLR) to model ligand bioactivities and identify their key substructures associated with these GPCRs targets. That is, MTR-ISLR intends to enhance the performance and interpretability of models under a small size of available training data by introducing homologous GPCR tasks. Meanwhile, the low-rank constraint term encourages to catch the underlying relationship among homologous GPCR tasks for greater model generalization, and the entry-wise sparse regularization term ensures to recognize essential discriminative substructures from each task for explanative modeling. We examined MTR-ISLR on a set of 31 important human GPCRs datasets from 9 subfamilies, each with less than 400 ligand associations. The results show that MTR-ISLR reaches better performance when compared with traditional single-task learning, deep multi-task learning and multi-task learning with joint feature learning-based models on most cases, where MTR-ISLR obtains an average improvement of 7% in correlation coefficient (r²) and 12% in root mean square error (RMSE) against the runner-up predictors. The MTR-ISLR web server appends freely all source codes and data for academic usages. ^①

Graphical abstract

Keywords

G protein-coupled receptors (GPCRs) / ligand bioactivities / multi-task learning / incoherent sparse and low-rank patterns

References

[1] Sriram K , Insel P A . G protein-coupled receptors as targets for spproved drugs: how many targets and how many drugs?. Molecular Pharmacology, 2018, 93( 4): 251– 258

[2] Hauser A S , Attwood M M , Raskandersen M , Schioth H B , Gloriam D E . Trends in GPCR drug discovery : new agents, targets and indications. Nature Reviews Drug Discovery, 2017, 16( 12): 829– 842

[3] Berman H M , Westbrook J , Feng Z , Gilliland G , Bhat T , Weissig H , Shindyalov I N , Bourne P E . The protein data bank. Nucleic Acids Research, 2010, 28 : 235– 242

[4] Chan W K B , Zhang H , Yang J , Brender J R , Hur J , Ozgur A , Zhang Y . GLASS: a comprehensive database for experimentally validated GPCR-ligand associations. Bioinformatics, 2015, 31( 18): 3035– 3042

[5] Blum L C , Reymond J . 970 million druglike small molecules for virtual screening in the chemical universe database GDB-13. Journal of the American Chemical Society, 2009, 131( 25): 8732– 8733

[6] Wang C-C , Zhao Y , Chen X . Drug-pathway association prediction: from experimental results to computational models. Briefings in Bioinformatics, 2020,

[7] Lee D . CONET: a virtual human system-centered platform for drug discovery. Frontiers of Computer Science, 2018, 12( 1): 1– 3

[8] Cherkasov A , Muratov E N , Fourches D , Varnek A , Baskin I I , Cronin M T D , Dearden J C , Gramatica P , Martin Y C , Todeschini R . QSAR modeling: Where have you been? Where are you going to?. Journal of Medicinal Chemistry, 2014, 57( 12): 4977– 5010

[9] Ceretomassague A , Ojeda M J , Valls C , Mulero M , Garciavallve S , Pujadas G . Molecular fingerprint similarity search in virtual screening. Methods, 2015, 71 : 58– 63

[10] Melville J L , Burke E K , Hirst J D . Machine learning in virtual screening. Combinatorial Chemistry High Throughput Screening, 2009, 12( 4): 332– 343

[11] Wallach I , Dzamba M , Heifets A . AtomNet: A deep convolutional neural network for bioactivity prediction in structure-based drug discovery. Mathematische Zeitschrift, 2015, 47( 1): 34– 46

[12] Winkler D A, Le T C. Performance of deep and shallow neural networks, the universal approximation theorem, activity cliffs, and QSAR. Molecular Informatics, 2016, 36(1−2)

[13] Lavecchia A . Deep learning in drug discovery: opportunities, challenges and future prospects. Drug Discovery Today, 2019, 24( 10): 2017– 2032

[14] Ramsundar B , Liu B , Wu Z , Verras A , Tudor M , Sheridan R P , Pande V . Is multitask deep learning practical for pharma?. Journal of Chemical Information and Modeling, 2017, 57( 8): 2068– 2076

[15] Xu Y , Ma J , Liaw A , Sheridan R P , Svetnik V . Demystifying multitask deep neural networks for quantitative structure–activity relationships. Journal of Chemical Information and Modeling, 2017, 57( 10): 2490– 2504

[16] Unterthiner T, Mayr A, Klambauer G, Steijaert M, Wegner J K, Ceulemans H, Hochreiter S. Deep learning as an opportunity in virtual screening. In: Proceedings of the Deep Learning Workshop at NIPS. 2014, 1– 9

[17] Ma J , Sheridan R , Liaw A , Dahl G , Svetnik V . Deep neural nets as a method for quantitative structure–activity relationships. Journal of Chemical Information and Modeling, 2015, 55( 2): 263– 274

[18] Duvenaud D , Maclaurin D , Aguilera-Iparraguirre J , Gómez-Bombarelli R , Hirzel T , Aspuru-Guzik A , Adams R . Convolutional networks on graphs for learning molecular fingerprints. Advances in Neural Information Processing Systems (NIPS), 2015,

[19] Wu J , Zhang Q , Wu W , Pang T , Hu H , Chan W K B , Ke X , Zhang Y . WDL-RF: predicting bioactivities of ligand molecules acting with G protein-coupled receptors by combining weighted deep learning and random forest. Bioinformatics, 2018, 34 : 2271– 2282

[20] Wu J , Liu B , Chan W K B , Wu W , Pang T , Hu H , Yan S , Ke X , Zhang Y . Precise modelling and interpretation of bioactivities of ligands targeting G protein-coupled receptors. Bioinformatics, 2019, 35 : i324– i332

[21] Dahl G E , Jaitly N , Salakhutdinov R . Multi-task neural networks for QSAR predictions. Computer Science, 2014,

[22] Chen L , Shao K , Long X , Wang L . Multi-task regression learning for survival analysis via prior information guided transductive matrix completion. Frontiers of Computer Science, 2020, 14( 5): 97– 110

[23] Wu J , Sun Y , Chan W K B , Zhu Y , Zhu W , Huang W , Hu H , Yan S , Pang T , Ke X . Homologous G protein-coupled receptors boost the modeling and interpretation of bioactivities of ligand molecules. Journal of Chemical Information and Modeling, 2020, 60( 3): 1865– 1875

[24] Simoes R S , Maltarollo V G , Oliveira P R , Honorio K M . Transfer and multi-task learning in QSAR modeling: advances and challenges. Frontiers in Pharmacology, 2018, 9 : 74–

[25] Chen J, Liu J, Ye J. Learning incoherent sparse and low-rank patterns from multiple tasks. In: Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2010, 1179−1187

[26] Bairoch A M , Apweiler R , Wu C H , Barker W C , Boeckmann B , Ferro S , Gasteiger E , Huang H , Lopez R , Magrane M . The universal protein resource (UniProt). Nucleic Acids Research, 2004, 33 : 154– 159

[27] Wang Y , Xiao J , Suzek TO , Zhang J , Wang J , Bryant S H . PubChem: a public information system for analyzing bioactivities of small molecules. Nucleic Acids Research, 2009, 37 : 623– 633

[28] Nesterov Y . Introductory lectures on convex optimization: a basic course. 1st ed. Boston: Springer Publishing Company, 2014,

[29] Zhou J , Chen J , Ye J . MALSAR: multi-task learning via structural regularization. Arizona State University, 2011, 21 :

[30] Zhou J, Liu J, Narayan V A, Ye J. Modeling disease progression via fused sparse group lasso. In: Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2012, 1095−1103

[31] Fang Y , Kenakin T P , Liu C . Editorial: orphan GPCRs as emerging drug targets. Frontiers in Pharmacology, 2015, 6 : 295–

[32] Zhang L , Nothacker H-P , Bohn L , Civelli O . Pharmacological characterization of a selective agonist for Bombesin Receptor Subtype-3. Biochemical and Biophysical Research Communications, 2009, 387( 2): 283– 288

Acknowledgements

This work was supported in part by the National Natural Science Foundation of China (Grant Nos. 61872198, 61971216, 81771478, 81973512), the Basic Research Program of Science and Technology Department of Jiangsu Province (BK20201378), the Natural Science Foundation of the Higher Education Institutions of Jiangsu Province (18KJB416005), and the Natural Science Foundation of Nanjing University of Posts and Telecommunications (NY218092). We thank all the people who have contributed to the system in a variety of ways.

Supporting Information

The supporting information is available online at journal.hep.com.cn and link.springer.com.

RIGHTS & PERMISSIONS

2022 Higher Education Press