Skip to main content
SpringerLink
Log in

Exploring fragment-based target-specific ranking protocol with machine learning on cathepsin S

  • Published:
Journal of Computer-Aided Molecular Design Aims and scope Submit manuscript

Abstract

Cathepsin S (CatS), a member of cysteine cathepsin proteases, has been well studied due to its significant role in many pathological processes, including arthritis, cancer and cardiovascular diseases. CatS inhibitors have been included in D3R-GC3 for both docking pose prediction and affinity ranking, and in D3R-GC4 for binding affinity ranking. The difficulties posed by CatS inhibitors in D3R mainly come from three aspects: large size, high flexibility and similar chemical structures. We have participated in GC4; our best submitted model, which employs a similarity-based alignment docking and Vina scoring protocol, yielded Kendall’s τ of 0.23 for 459 binders in GC4. In our further explorations with machine learning, by curating a CatS specific training set, adopting a similarity-based constrained docking method as well as an arm-based fragmentation strategy which can describe large inhibitors in a locality-sensitive fashion, our best structure-based ranking protocol can achieve Kendall’s τ of 0.52 for all binders in GC4. In this exploration process, we have demonstrated the importance of training data, docking approaches and fragmentation strategies in inhibitor-ranking protocol development with machine learning.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Lavecchia A, Di Giovanni C (2013) Virtual screening strategies in drug discovery: a critical review. Curr Med Chem 20(23):2839–2860

    CAS  PubMed  Google Scholar 

  2. Schneider G (2010) Virtual screening: an endless staircase? Nat Rev Drug Discov 9(4):273–276

    CAS  PubMed  Google Scholar 

  3. Ashtawy HM, Mahapatra NR (2012) A comparative assessment of ranking accuracies of conventional and machine-learning-based scoring functions for protein-ligand binding affinity prediction. IEEE/ACM Trans Comput Biol Bioinform 9(5):1301–1313

    PubMed  Google Scholar 

  4. Kim R, Skolnick J (2008) Assessment of programs for ligand binding affinity prediction. J Comput Chem 29(8):1316–1331

    CAS  PubMed  PubMed Central  Google Scholar 

  5. Stjernschantz E, Oostenbrink C (2010) Improved ligand-protein binding affinity predictions using multiple binding modes. Biophys J 98(11):2682–2691

    CAS  PubMed  PubMed Central  Google Scholar 

  6. Su MY, Yang QF, Du Y, Feng GQ, Liu ZH, Li Y, Wang RX (2019) Comparative assessment of scoring functions: the CASF-2016 update. J Chem Inf Model 59(2):895–913

    CAS  PubMed  Google Scholar 

  7. Li Y, Liu ZH, Li J, Han L, Liu J, Zhao ZX, Wang RX (2014) Comparative assessment of scoring functions on an updated benchmark: 1. Compilation of the test set. J Chem Inf Model 54(6):1700–1716

    CAS  PubMed  Google Scholar 

  8. Li Y, Han L, Liu ZH, Wang RX (2014) Comparative assessment of scoring functions on an updated benchmark: 2. Evaluation methods and general results. J Chem Inf Model 54(6):1717–1736

    CAS  PubMed  Google Scholar 

  9. Cheng TJ, Li QL, Zhou ZG, Wang YL, Bryant SH (2012) Structure-based virtual screening for drug discovery: a problem-centric review. AAPS J 14(1):133–141

    CAS  PubMed  PubMed Central  Google Scholar 

  10. Cheng TJ, Li X, Li Y, Liu ZH, Wang RX (2009) Comparative assessment of scoring functions on a diverse test set. J Chem Inf Model 49(4):1079–1093

    CAS  PubMed  Google Scholar 

  11. Bauer MR, Ibrahim TM, Vogel SM, Boeckler FM (2013) Evaluation and optimization of virtual screening workflows with DEKOIS 2.0-a public library of challenging docking benchmark sets. J Chem Inf Model 53(6):1447–1462

    CAS  PubMed  Google Scholar 

  12. Mysinger MM, Carchia M, Irwin JJ, Shoichet BK (2012) Directory of useful decoys, enhanced (DUD-E): better ligands and decoys for better benchmarking. J Med Chem 55(14):6582–6594

    CAS  PubMed  PubMed Central  Google Scholar 

  13. Rohrer SG, Baumann K (2009) Maximum unbiased validation (MUV) data sets for virtual screening based on PubChem bioactivity data. J Chem Inf Model 49(2):169–184

    CAS  PubMed  Google Scholar 

  14. Amini A, Shrimpton PJ, Muggleton SH, Sternberg MJE (2007) A general approach for developing system-specific functions to score protein-ligand docked complexes using support vector inductive logic programming. Proteins 69(4):823–831

    CAS  PubMed  Google Scholar 

  15. Ballester PJ, Mitchell JBO (2010) A machine learning approach to predicting protein-ligand binding affinity with applications to molecular docking. Bioinformatics 26(9):1169–1175

    CAS  PubMed  Google Scholar 

  16. Durrant JD, McCammon JA (2011) NNScore 2.0: a neural-network receptor-ligand scoring function. J Chem Inf Model 51(11):2897–2903

    CAS  PubMed  PubMed Central  Google Scholar 

  17. Kinnings SL, Liu NN, Tonge PJ, Jackson RM, Xie L, Bourne PE (2011) A machine learning-based method to improve docking scoring functions and its application to drug repurposing. J Chem Inf Model 51(2):408–419

    CAS  PubMed  PubMed Central  Google Scholar 

  18. Li LW, Khanna M, Jo IH, Wang F, Ashpole NM, Hudmon A, Meroueh SO (2011) Target-specific support vector machine scoring in structure-based virtual screening: computational validation, on vitro testing in kinases, and effects on lung cancer cell proliferation. J Chem Inf Model 51(4):755–759

    CAS  PubMed  PubMed Central  Google Scholar 

  19. Zilian D, Sotriffer CA (2013) SFCscore(RF): a random forest-based scoring function for improved affinity prediction of protein-ligand complexes. J Chem Inf Model 53(8):1923–1933

    CAS  PubMed  Google Scholar 

  20. Ragoza M, Hochuli J, Idrobo E, Sunseri J, Koes DR (2017) Protein-ligand scoring with convolutional neural networks. J Chem Inf Model 57(4):942–957

    CAS  PubMed  PubMed Central  Google Scholar 

  21. Wang C, Zhang YK (2017) Improving scoring-docking-screening powers of protein-ligand scoring functions using random forest. J Comput Chem 38(3):169–177

    PubMed  Google Scholar 

  22. Jimenez J, Skalic M, Martinez-Rosell G, De Fabritiis G (2018) K-DEEP: protein-ligand absolute binding affinity prediction via 3D-convolutional neural networks. J Chem Inf Model 58(2):287–296

    CAS  PubMed  Google Scholar 

  23. Gathiaka S, Liu S, Chiu M, Yang HW, Stuckey JA, Kang YN, Delproposto J, Kubish G, Dunbar JB, Carlson HA, Burley SK, Walters WP, Amaro RE, Feher VA, Gilson MK (2016) D3R Grand Challenge 2015: evaluation of protein-ligand pose and affinity predictions. J Comput Aided Mol Des 30(9):651–668

    CAS  PubMed  PubMed Central  Google Scholar 

  24. Gaieb Z, Parks CD, Chiu M, Yang HW, Shao CH, Walters WP, Lambert MH, Nevins N, Bembenek SD, Ameriks MK, Mirzadegan T, Burley SK, Amaro RE, Gilson MK (2019) D3R Grand Challenge 3: blind prediction of protein-ligand poses and affinity rankings. J Comput Aided Mol Des 33(1):1–18

    CAS  PubMed  PubMed Central  Google Scholar 

  25. Gaieb Z, Liu S, Gathiaka S, Chiu M, Yang HW, Shao CH, Feher VA, Walters WP, Kuhn B, Rudolph MG, Burley SK, Gilson MK, Amaro RE (2018) D3R Grand Challenge 2: blind prediction of protein-ligand poses, affinity rankings, and relative binding free energies. J Comput Aided Mol Des 32(1):1–20

    CAS  PubMed  Google Scholar 

  26. Turk V, Stoka V, Vasiljeva O, Renko M, Sun T, Turk B, Turk D (2012) Cysteine cathepsins: from structure, function and regulation to new frontiers. Biochim Biophys Acta 1824(1):68–88

    CAS  PubMed  Google Scholar 

  27. Wilkinson RDA, Williams R, Scott CJ, Burden RE (2015) Cathepsin S: therapeutic, diagnostic, and prognostic potential. Biol Chem 396(8):867–882

    CAS  PubMed  Google Scholar 

  28. Trott O, Olson AJ (2010) Software news and update AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. J Comput Chem 31(2):455–461

    CAS  PubMed  PubMed Central  Google Scholar 

  29. Ameriks MK, Axe FU, Bembenek SD, Edwards JP, Gu Y, Karlsson L, Randal M, Sun SQ, Thurmond RL, Zhu J (2009) Pyrazole-based cathepsin S inhibitors with arylalkynes as P1 binding elements. Bioorg Med Chem Lett 19(21):6131–6134

    CAS  PubMed  Google Scholar 

  30. Thurmond RL, Sun SQ, Sehon CA, Baker SM, Cai H, Gu Y, Jiang W, Riley JP, Williams KN, Edwards JP, Karlsson L (2004) Identification of a potent and selective noncovalent cathepsin S inhibitor. J Pharmacol Exp Ther 308(1):268–276

    CAS  PubMed  Google Scholar 

  31. Wiener DK, Lee-Dutra A, Bembenek S, Nguyen S, Thurmond RL, Sun S, Karlsson L, Grice CA, Jones TK, Edwards JP (2010) Thioether acetamides as P3 binding elements for tetrahydropyrido-pyrazole cathepsin S inhibitors. Bioorg Med Chem Lett 20(7):2379–2382

    CAS  PubMed  Google Scholar 

  32. Liu ZH, Su MY, Han L, Liu J, Yang QF, Li Y, Wang RX (2017) Forging the basis for developing protein-ligand interaction scoring functions. Acc Chem Res 50(2):302–309

    CAS  PubMed  Google Scholar 

  33. Dunbar JB, Smith RD, Yang CY, Ung PMU, Lexa KW, Khazanov NA, Stuckey JA, Wang SM, Carlson HA (2011) CSAR benchmark exercise of 2010: selection of the protein-ligand complexes (vol 51, pg 2036, 2011). J Chem Inf Model 51(9):2146

    CAS  PubMed Central  Google Scholar 

  34. Huang SY, Zou XQ (2011) Scoring and lessons learned with the CSAR benchmark using an improved iterative knowledge-based scoring function. J Chem Inf Model 51(9):2097–2106

    CAS  PubMed  PubMed Central  Google Scholar 

  35. Gaulton A, Hersey A, Nowotka M, Bento AP, Chambers J, Mendez D, Mutowo P, Atkinson F, Bellis LJ, Cibrian-Uhalte E, Davies M, Dedman N, Karlsson A, Magarinos MP, Overington JP, Papadatos G, Smit I, Leach AR (2017) The ChEMBL database in 2017. Nucleic Acids Res 45(D1):D945–D954

    CAS  PubMed  Google Scholar 

  36. Rogers D, Hahn M (2010) Extended-connectivity fingerprints. J Chem Inf Model 50(5):742–754

    CAS  PubMed  Google Scholar 

  37. RDKit: Open-source cheminformatics; http://www.rdkit.org

  38. Koukos PI, Xue LC, Bonvin A (2019) Protein-ligand pose and affinity prediction: lessons from D3R Grand Challenge 3. J Comput Aided Mol Des 33(1):83–91

    CAS  PubMed  Google Scholar 

  39. Kumar A, Zhang KYJ (2019) Shape similarity guided pose prediction: lessons from D3R Grand Challenge 3. J Comput Aided Mol Des 33(1):47–59

    CAS  PubMed  Google Scholar 

  40. Lam PCH, Abagyan R, Totrov M (2019) Hybrid receptor structure/ligand-based docking and activity prediction in ICM: development and evaluation in D3R Grand Challenge 3. J Comput Aided Mol Des 33(1):35–46

    CAS  PubMed  Google Scholar 

  41. Nguyen DD, Cang ZX, Wu KD, Wang ML, Cao Y, Wei GW (2019) Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges. J Comput Aided Mol Des 33(1):71–82

    CAS  PubMed  Google Scholar 

  42. Ignatov M, Liu C, Alekseenko A, Sun ZYZ, Padhorny D, Kotelnikov S, Kazennov A, Grebenkin I, Kholodov Y, Kolosvari I, Perez A, Dill K, Kozakov D (2019) Monte Carlo on the manifold and MD refinement for binding pose prediction of protein-ligand complexes: 2017 D3R Grand Challenge. J Comput Aided Mol Des 33(1):119–127

    CAS  PubMed  Google Scholar 

  43. Dolinsky TJ, Czodrowski P, Li H, Nielsen JE, Jensen JH, Klebe G, Baker NA (2007) PDB2PQR: expanding and upgrading automated preparation of biomolecular structures for molecular simulations. Nucleic Acids Res 35:W522–W525

    PubMed  PubMed Central  Google Scholar 

  44. SciFinder; https://scifinder.cas.org/scifinder/

  45. Riniker S, Landrum GA (2015) Better informed distance geometry: using what we know to improve conformation generation. J Chem Inf Model 55(12):2562–2574

    CAS  PubMed  Google Scholar 

  46. Halgren TA (1996) Merck molecular force field. 1. Basis, form, scope, parameterization, and performance of MMFF94. J Comput Chem 17(5–6):490–519

    CAS  Google Scholar 

  47. Halgren TA (1996) Merck molecular force field. 2. MMFF94 van der Waals and electrostatic parameters for intermolecular interactions. J Comput Chem 17(5–6):520–552

    CAS  Google Scholar 

  48. Halgren TA (1996) Merck molecular force field. 3. Molecular geometries and vibrational frequencies for MMFF94. J Comput Chem 17(5–6):553–586

    CAS  Google Scholar 

  49. Halgren TA (1996) Merck molecular force field. 5. Extension of MMFF94 using experimental data, additional computational data, and empirical rules. J Comput Chem 17(5–6):616–641

    CAS  Google Scholar 

  50. Halgren TA, Nachbar RB (1996) Merck molecular force field. 4. Conformational energies and geometries for MMFF94. J Comput Chem 17(5–6):587–615

    CAS  Google Scholar 

  51. Tosco P, Stiefl N, Landrum G (2014) Bringing the MMFF force field to the RDKit: implementation and validation. J Cheminform 6:37

    PubMed Central  Google Scholar 

  52. Morris GM, Huey R, Lindstrom W, Sanner MF, Belew RK, Goodsell DS, Olson AJ (2009) AutoDock4 and AutoDockTools4: automated docking with selective receptor flexibility. J Comput Chem 30(16):2785–2791

    CAS  PubMed  PubMed Central  Google Scholar 

  53. Koes DR, Baumgartner MP, Camacho CJ (2013) Lessons learned in empirical scoring with smina from the CSAR 2011 benchmarking exercise. J Chem Inf Model 53(8):1893–1904

    CAS  PubMed  PubMed Central  Google Scholar 

  54. Temelso B, Mabey JM, Kubota T, Appiah-Padi N, Shields GC (2017) ArbAlign: a tool for optimal alignment of arbitrarily ordered isomers using the Kuhn-Munkres algorithm. J Chem Inf Model 57(5):1045–1054

    CAS  PubMed  Google Scholar 

  55. Rooklin D, Wang C, Katigbak J, Arora PS, Zhang YK (2015) Alpha space: fragment-centric topographical mapping to target protein-protein interaction interfaces. J Chem Inf Model 55(8):1585–1599

    CAS  PubMed  PubMed Central  Google Scholar 

  56. Liu TR, Naderi M, Alvin C, Mukhopadhyay S, Brylinski M (2017) Break down in order to build up: decomposing small molecules for fragment-based drug design with eMolFrag. J Chem Inf Model 57(4):627–631

    CAS  PubMed  PubMed Central  Google Scholar 

  57. Murray CW, Rees DC (2009) The rise of fragment-based drug discovery. Nat Chem 1(3):187–192

    CAS  PubMed  Google Scholar 

  58. Lewell XQ, Judd DB, Watson SP, Hann MM (1998) RECAP—retrosynthetic combinatorial analysis procedure: a powerful new technique for identifying privileged molecular fragments with useful applications in combinatorial chemistry. J Chem Inf Comput Sci 38(3):511–522

    CAS  PubMed  Google Scholar 

  59. Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794

  60. XGBoost: A Scalable Tree Boosting System arXiv:1603.02754

  61. Dunbar JB, Smith RD, Damm-Ganamet KL, Ahmed A, Esposito EX, Delproposto J, Chinnaswamy K, Kang YN, Kubish G, Gestwicki JE, Stuckey JA, Carlson HA (2013) CSAR data set release 2012: ligands, affinities, complexes, and docking decoys. J Chem Inf Model 53(8):1842–1852

    CAS  PubMed  PubMed Central  Google Scholar 

  62. Huey R, Morris GM, Olson AJ, Goodsell DS (2007) A semiempirical free energy force field with charge-based desolvation. J Comput Chem 28(6):1145–1152

    CAS  PubMed  Google Scholar 

Download references

Acknowledgements

We would like to acknowledge the support by NIH (Grant Nos. R35-GM127040, R01GM073943 and R01GM120736) and computing resources provided by NYU-ITS.

Author information

Authors and Affiliations

  1. Department of Chemistry, New York University, New York, NY, 10003, USA

    Yuwei Yang, Jianing Lu, Chao Yang & Yingkai Zhang

  2. NYU-ECNU Center for Computational Chemistry at NYU Shanghai, Shanghai, 200062, China

    Yingkai Zhang

Authors
  1. Yuwei Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jianing Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chao Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yingkai Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yingkai Zhang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, Y., Lu, J., Yang, C. et al. Exploring fragment-based target-specific ranking protocol with machine learning on cathepsin S. J Comput Aided Mol Des 33, 1095–1105 (2019). https://doi.org/10.1007/s10822-019-00247-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10822-019-00247-3

Keywords

Search

Navigation