TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions

Abstract

Although deep learning approaches have had tremendous success in image, video and audio processing, computer vision, and speech recognition, their applications to three-dimensional (3D) biomolecular structural data sets have been hindered by the geometric and biological complexity. To address this problem we introduce the element-specific persistent homology (ESPH) method. ESPH represents 3D complex geometry by one-dimensional (1D) topological invariants and retains important biological information via a multichannel image-like representation. This representation reveals hidden structure-function relationships in biomolecules. We further integrate ESPH and deep convolutional neural networks to construct a multichannel topological neural network (TopologyNet) for the predictions of protein-ligand binding affinities and protein stability changes upon mutation. To overcome the deep learning limitations from small and noisy training sets, we propose a multi-task multichannel topological convolutional neural network (MM-TCNN). We demonstrate that TopologyNet outperforms the latest methods in the prediction of protein-ligand binding affinities, mutation induced globular protein folding free energy changes, and mutation induced membrane protein folding free energy changes. AVAILABILITY: weilab.math.msu.edu/TDL/.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 107

1. 1.

   Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems; 2012. p. 1097–1105.

   Not in our library

2. 2.

   Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556. 2014;.

   Not in our library

3. 3.
   Deep learning · 2015

   No notice
4. 4.

   Ngiam J, Khosla A, Kim M, Nam J, Lee H, Ng AY. Multimodal deep learning. In: Proceedings of the 28th international conference on machine learning (ICML-11); 2011. p. 689–696.

   Not in our library

5. 5.

   Caruana R. Multitask learning In: Learning to learn. Springer; 1998 p. 95–133.

   Not in our library

6. 6.

   Evgeniou T, Pontil M. Regularized multi–task learning. In: Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM; 2004. p. 109–117.

   Not in our library

7. 7.

   Evgeniou A, Pontil M. Multi-task feature learning. Advances in neural information processing systems. 2007;19:41.

   Not in our library

8. 8.

   Liu J, Ji S, Ye J. Multi-task feature learning via efficient l 2, 1-norm minimization. In: Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence. AUAI Press; 2009. p. 339–348.

   Not in our library

9. 9.

   Zhou J, Chen J, Ye J. Clustered multi-task learning via alternating structure optimization. In: Advances in neural information processing systems; 2011. p. 702–710.

   Not in our library

10. 10.

    Unterthiner T, Mayr A, Klambauer G, Hochreiter S. Toxicity prediction using deep learning. arXiv preprint arXiv:150301445. 2015;.

    Not in our library

11. 11.

    Lusci A, Pollastri G, Baldi P. Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules. Journal of chemical information and modeling. 2013;53(7):1563–1575.

    Not in our library10.1021/ci400187y

12. 12.

    Wallach I, Dzamba M, Heifets A. AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery. arXiv preprint arXiv:151002855. 2015;.

    Not in our library

13. 13.

    Dahl GE, Jaitly N, Salakhutdinov R. Multi-task neural networks for QSAR predictions. arXiv preprint arXiv:14061231. 2014;.

    Not in our library

14. 14.

    Wang B, Zhao Z, Wei GW. Automatic parametrization of non-polar implicit solvent models for the blind prediction of solvation free energies. Journal of Chemical Physics. 2016;145:124110

    Not in our library10.1063/1.4963193

15. 15.

    Nguyen DD, Wei GW. The impact of surface area, volume, curvature and Lennard-Jones potential to solvation modeling. Journal of Computational Chemistry. 2017; 38:24–36.

    Not in our library10.1002/jcc.24512

16. 16.

    Feng X, Xia K, Tong Y, Wei GW. Geometric modeling of subcellular structures, organelles and large multiprotein complexes. International Journal for Numerical Methods in Biomedical Engineering. 2012;28:1198–1223.

    Not in our library10.1002/cnm.2532

17. 17.

    Schlick T, Olson WK. Trefoil knotting revealed by molecular dynamics simulations of supercoiled DNA. Science. 1992;257(5073):1110–1115.

    Not in our library10.1126/science.257.5073.1110

18. 18.

    Zomorodian A, Carlsson G. Computing persistent homology. Discrete Comput Geom. 2005;33:249–274.

    Not in our library10.1007/s00454-004-1146-y

19. 19.

    Sumners DW. Knot theory and DNA. In: Proceedings of Symposia in Applied Mathematics. vol. 45; 1992. p. 39–72.

    Not in our library

20. 20.

    Darcy IK, Vazquez M. Determining the topology of stable protein-DNA complexes. Biochemical Society Transactions. 2013;41:601–605.

    Not in our library10.1042/bst20130004

21. 21.

    Heitsch C, Poznanovic S. Combinatorial insights into RNA secondary structure, in Jonoska N. and Saito M., editors. Discrete and Topological Models in Molecular Biology. 2014;Chapter 7:145–166.

    Not in our library10.1007/978-3-642-40193-0_7

22. 22.

    Demerdash ONA, Daily MD, Mitchell JC. Structure-Based Predictive Models for Allosteric Hot Spots. PLOS Computational Biology. 2009;5:e1000531

    Not in our library10.1371/journal.pcbi.1000531

23. 23.

    DasGupta B, Liang J. Models and Algorithms for Biomolecules and Molecular Networks. John Wiley & Sons; 2016.

    Not in our library

24. 24.

    Shi X, Koehl P. Geometry and topology for modeling biomolecular surfaces. Far East J Applied Math. 2011;50:1–34.

    Not in our library

25. 25.

    Kaczynski T, Mischaikow K, Mrozek M. Computational Homology vol. 157 of Applied Mathematical Sciences. New York: Springer-Verlag; 2004.

    Not in our library

26. 26.

    Frosini P. A distance for similarity classes of submanifolds of a Euclidean space. BUllentin of Australian Mathematical Society. 1990;42(3):407–416.

    Not in our library10.1017/s0004972700028574

27. 27.

    Robins V. Towards computing homology from finite approximations. In: Topology Proceedings. vol. 24; 1999. p. 503–532.

    Not in our library

28. 28.

    Edelsbrunner H, Letscher D, Zomorodian A. Topological persistence and simplification. Discrete Comput Geom. 2002;28:511–533.

    Not in our library10.1007/s00454-002-2885-2

29. 29.

    Bendich P, Harer J. Persistent Intersection Homology. Foundations of Computational Mathematics (FOCM). 2011;11(3):305–336.

    Not in our library10.1007/s10208-010-9081-1

30. 30.

    Cohen-Steiner D, Edelsbrunner H, Harer J. Stability of Persistence Diagrams. Discrete & Computational Geometry. 2007;37(1):103–120.

    Not in our library10.1007/s00454-006-1276-5

31. 31.

    Cohen-Steiner D, Edelsbrunner H, Harer J. Extending Persistence Using Poincaré and Lefschetz Duality. Foundations of Computational Mathematics. 2009;9(1):79–103.

    Not in our library10.1007/s10208-008-9038-9

32. 32.

    Cohen-Steiner D, Edelsbrunner H, Harer J, Morozov D. Persistent Homology for Kernels, Images, and Cokernels. In: Proceedings of the Twentieth Annual ACM-SIAM Symposium on Discrete Algorithms. SODA 09; 2009. p. 1011–1020.

    Not in our library

33. 33.

    Chazal F, Cohen-Steiner D, Glisse M, Guibas LJ, Oudot S. Proximity of persistence modules and their diagrams. In: Proc. 25th ACM Sympos. on Comput. Geom.; 2009. p. 237–246.

    Not in our library

34. 34.

    Chazal F, Guibas LJ, Oudot SY, Skraba P. Persistence-based clustering in riemannian manifolds. In: Proceedings of the 27th annual ACM symposium on Computational geometry. SoCG’11; 2011. p. 97–106.

    Not in our library

35. 35.

    Carlsson G, Zomorodian A. The theory of multidimensional persistence. Discrete Computational Geometry. 2009;42(1):71–93.

    Not in our library10.1007/s00454-009-9176-0

36. 36.

    Carlsson G, de Silva V, Morozov D. Zigzag persistent homology and real-valued functions. In: Proc. 25th Annu. ACM Sympos. Comput. Geom.; 2009. p. 247–256.

    Not in our library

37. 37.

    de Silva V, Morozov D, Vejdemo-Johansson M. Persistent cohomology and circular coordinates. Discrete and Comput Geom. 2011;45:737–759.

    Not in our library10.1007/s00454-011-9344-x

38. 38.

    Oudot SY, Sheehy DR. Zigzag Zoology: Rips Zigzags for Homology Inference. In: Proc. 29th Annual Symposium on Computational Geometry; 2013. p. 387–396.

    Not in our library

39. 39.

    Dey TK, Fan F, Wang Y. Computing topological persistence for simplicial maps. In: Proc. 30th Annu. Sympos. Comput. Geom. (SoCG); 2014. p. 345–354.

    Not in our library

40. 40.

    Mischaikow K, Nanda V. Morse Theory for Filtrations and Efficient Computation of Persistent Homology. Discrete and Computational Geometry. 2013;50(2):330–353.

    Not in our library10.1007/s00454-013-9529-6

Cited by papers we hold 4

• Algebraic graph-assisted bidirectional transformers for molecular property prediction · 2021
  No notice
• Artificial intelligence and machine learning‐aided drug discovery in central nervous system diseases: State‐of‐the‐arts and future directions · 2020
  No notice
• Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening · 2018
  No notice
• Opportunities and obstacles for deep learning in biology and medicine · 2018
  No notice

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.