Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Leveraging implicit knowledge in neural networks for functional dissection and engineering of proteins

A Publisher Correction to this article was published on 21 May 2019

This article has been updated


Proteins are nature’s most versatile molecular machines. Deep neural networks trained on large protein datasets have recently been used to tackle the unmet complexity of protein sequence–function relationships. The implicit knowledge contained in these networks represents a powerful, but thus far inaccessible, resource for understanding protein biology. Here, we show that occlusion-based sensitivity analysis can leverage the knowledge present in deep-neural-network-based protein sequence classifiers to identify functionally relevant parts of proteins. We first validated our approach by successfully predicting positions that mediate small molecule binding or catalytic activity across different protein classes. Next, we inferred the impact of point mutations on the activity of ERK and HRas, signalling factors frequently deregulated in cancer. Finally, we used our approach to identify engineering hotspots in CRISPR–Cas9 and anti-CRISPR protein AcrIIA4. Our work demonstrates how implicit knowledge in neural networks can be harnessed for protein functional dissection and protein engineering.

This is a preview of subscription content, access via your institution

Access options

Buy this article

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Sensitivity analysis pipeline for functional annotation and engineering of proteins.
Fig. 2: DeeProtein architecture and performance evaluation.
Fig. 3: Sensitivity analysis highlights ligand binding regions and active sites.
Fig. 4: Sensitivity analysis infers catalytic residues in kinases.
Fig. 5: ERK2 sensitivity analysis dissects functional regions and identifies mutation-intolerant residues.
Fig. 6: CRISPR–Cas9 nuclease sensitivity can infer the biological activity of CRISPR–Cas9 domain insertion mutants.
Fig. 7: Sensitivity analysis can infer an engineering hotspot in anti-CRISPR protein AcrIIA4.

Similar content being viewed by others

Data availability

Sensitivity analysis data for all presented proteins, including the ~800 proteins used to calculate spatial homogeneity of sphere variances, as well as weights for DeeProtein classifier, are available on Zenodo ( and AcrIIA4–LOV2 expression vectors can be obtained from the corresponding authors on reasonable request.

Code availability

The code for DeeProtein, including scripts employed for sensitivity analysis, and code for mapping sensitivities to protein 3D structures in PyMol, is available on GitHub under MIT License (, A stand-alone compute capsule covering central functions of DeeProtein is available on Code Ocean (

Change history

  • 21 May 2019

    An amendment to this paper has been published and can be accessed via a link at the top of the paper


  1. Kulmanov, M., Khan, M. A., Hoehndorf, R. & Wren, J. DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier. Bioinformatics 34, 660–668 (2018).

    Article  Google Scholar 

  2. Jensen, L. J., Gupta, R., Staerfeldt, H. H. & Brunak, S. Prediction of human protein function according to Gene Ontology categories. Bioinformatics 19, 635–642 (2003).

    Article  Google Scholar 

  3. You, R. et al. GOLabeler: improving sequence-based large-scale protein function prediction by learning to rank. Bioinformatics 34, 2465–2473 (2018).

    Article  Google Scholar 

  4. Frasca, M. & Cesa Bianchi, N. Combining cost-sensitive classification with negative selection for protein function prediction. Preprint at (2018).

  5. Szalkai, B. & Grolmusz, V. Near perfect protein multi-label classification with deep neural networks. Methods 132, 50–56 (2018).

    Article  Google Scholar 

  6. Sinai, S., Kelsic, E., Church, G. M. & Nowak, M. A. Variational auto-encoding of protein sequences. Preprint at (2017).

  7. Riesselman, A. J., Ingraham, J. B. & Marks, D. S. Deep generative models of genetic variation capture the effects of mutations. Nat. Methods 15, 816–822 (2018).

    Article  Google Scholar 

  8. Fowler, D. M. et al. High-resolution mapping of protein sequence–function relationships. Nat. Methods 7, 741–746 (2010).

    Article  Google Scholar 

  9. Biswas, S. et al. Toward machine-guided design of proteins. Preprint at (2018).

  10. Fong, R. & Vedaldi, A. Interpretable explanations of black boxes by meaningful perturbation. Preprint at

  11. Kindermans, P.-J. et al. Learning how to explain neural networks: PatternNet and PatternAttribution. Preprint at (2017).

  12. Grégoire, M., Samek, W. & Müller, K.-R. Methods for interpreting and understanding deep neural networks. Dig. Sig. Process. 73, 1–15 (2018)..

  13. Radivojac, P. et al. A large-scale evaluation of computational protein function prediction. Nat. Methods 10, 221–227 (2013).

    Article  Google Scholar 

  14. Arras, L., Horn, F., Montavon, G., Müller, K.-R. & Wojciech, S. “What is relevant in a text document?”: an interpretable machine learning approach. PLoS ONE 12, e0181142 (2017).

  15. He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern Recognition 770–778 (IEEE, 2016).

  16. Boutet, E., Lieberherr, D., Tognolli, M., Schneider, M. & Bairoch, A. UniProtKB/Swiss-Prot. Methods Mol. Biol. 406, 89–112 (2007).

    Google Scholar 

  17. Ashburner, M. et al. Gene ontology: tool for the unification of biology. Nat. Genet. 25, 25–29 (2000).

    Article  Google Scholar 

  18. The Gene Ontology Consortium Expansion of the Gene Ontology knowledgebase and resources. Nucleic Acids Res. 45, D331–D338 (2017).

    Article  Google Scholar 

  19. Cozzetto, D., Minneci, F., Currant, H. & Jones, D. T. FFPred 3: feature-based function prediction for all Gene Ontology domains. Sci. Rep. 6, 31865 (2016).

    Article  Google Scholar 

  20. Gong, Q., Ning, W. & Tian, W. GoFDR: a sequence alignment based method for predicting protein functions. Methods 93, 3–14 (2016).

    Article  Google Scholar 

  21. Zeiler, M. D. & Fergus, R. Visualizing and understanding convolutional networks. In European Conference on Computer Vision (eds Fleet, D., Pajdla, T., Schiele, B. & Tuytelaars, T.) 818–833 (Springer, 2014).

  22. Berman, H. M. et al. The Protein Data Bank. Nucleic Acids Res. 28, 235–242 (2000).

    Article  Google Scholar 

  23. Zhang, L. et al. Functional role of histidine in the conserved His–x–Asp motif in the catalytic core of protein kinases. Sci. Rep. 5, 10115 (2015).

    Article  Google Scholar 

  24. Samatar, A. A. & Poulikakos, P. I. Targeting RAS-ERK signalling in cancer: promises and challenges. Nat. Rev. Drug Discov. 13, 928–942 (2014).

    Article  Google Scholar 

  25. Roskoski, R. Jr. ERK1/2 MAP kinases: structure, function, and regulation. Pharmacol. Res. 66, 105–143 (2012).

    Article  Google Scholar 

  26. Kornev, A. P., Taylor, S. S. & Ten Eyck, L. F. A helix scaffold for the assembly of active protein kinases. Proc. Natl Acad. Sci. USA 105, 14377–14382 (2008).

    Article  Google Scholar 

  27. Brenan, L. et al. Phenotypic characterization of a comprehensive set of MAPK1/ERK2 missense mutants. Cell Rep. 17, 1171–1183 (2016).

    Article  Google Scholar 

  28. Bandaru, P. et al. Deconstruction of the Ras switching cycle through saturation mutagenesis. eLife (2017).

  29. Richter, F. et al. Switchable Cas9. Curr. Opin. Biotechnol. 48, 119–126 (2017).

    Article  Google Scholar 

  30. Ha, J. H. & Loh, S. N. Protein conformational switches: from nature to design. Chemistry 18, 7984–7999 (2012).

    Article  Google Scholar 

  31. Stein, V. & Alexandrov, K. Synthetic protein switches: design principles and applications. Trends Biotechnol. 33, 101–110 (2015).

    Article  Google Scholar 

  32. Hoffmann, M. D., Bubeck, F., Eils, R. & Niopek, D. Controlling cells with light and LOV. Adv. Biosyst. (2018).

    Article  Google Scholar 

  33. Mali, P. et al. RNA-guided human genome engineering via Cas9. Science 339, 823–826 (2013).

    Article  Google Scholar 

  34. Jinek, M. et al. A programmable dual-RNA-guided DNA endonuclease in adaptive bacterial immunity. Science 337, 816–821 (2012).

    Article  Google Scholar 

  35. Cong, L. et al. Multiplex genome engineering using CRISPR/Cas systems. Science 339, 819–823 (2013).

    Article  Google Scholar 

  36. Liu, J. J. et al. CasX enzymes comprise a distinct family of RNA-guided genome editors. Nature 566, 218–223 (2019).

    Article  Google Scholar 

  37. Oakes, B. L. et al. Profiling of engineering hotspots identifies an allosteric CRISPR–Cas9 switch. Nat. Biotechnol. 34, 646–651 (2016).

    Article  Google Scholar 

  38. Rauch, B. J. et al. Inhibition of CRISPR-Cas9 with bacteriophage proteins. Cell 168, 150–158 (2017).

    Article  Google Scholar 

  39. Bubeck, F. et al. Engineered anti-CRISPR proteins for optogenetic control of CRISPR–Cas9. Nat. Methods 15, 924–927 (2018).

    Article  Google Scholar 

  40. Basgall, E. M. et al. Gene drive inhibition by the anti-CRISPR proteins AcrIIA2 and AcrIIA4 in Saccharomyces cerevisiae. Microbiology 164, 464–474 (2018).

    Article  Google Scholar 

  41. Dong, D. et al. Structural basis of CRISPR-SpyCas9 inhibition by an anti-CRISPR protein. Nature 546, 436–439 (2017).

    Article  Google Scholar 

  42. Yang, H. & Patel, D. J. Inhibition mechanism of an anti-CRISPR suppressor AcrIIA4 targeting SpyCas9. Mol. Cell 67, 117–127 e115 (2017).

    Article  Google Scholar 

  43. Shin, J. et al. Disabling Cas9 by an anti-CRISPR DNA mimic. Sci. Adv. 3, e1701620 (2017).

    Article  Google Scholar 

  44. McReynolds, A. C. et al. Phosphorylation or mutation of the ERK2 activation loop alters oligonucleotide binding. Biochemistry 55, 1909–1917 (2016).

    Article  Google Scholar 

  45. Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. Preprint at (2017).

  46. Bach, S. et al. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10, e0130140 (2015).

    Article  Google Scholar 

  47. Shrikumar, A., Greenside, P. & Kundaje, A. Learning important features through propagating activation differences. In Proceedings of the 34th International Conference on Machine Learning 3145–3153 (PMLR, 2017).

  48. Martín Abadi, A. A., et al. TensorFlow: large-scale machine learning on heterogeneous systems. Preprint at (2015).

  49. Dong, H. et al. TensorLayer: a versatile library for efficient deep learning development. In Proceedings of the 25th ACM international conference on Multimedia 1201–1204 (ACM, 2017).

  50. Glorot, X., Bordes, A. & Bengio, Y. Deep sparse rectifier neural networks. Proc. 14th International Conference on Artificial Intelligence and Statistics. Vol. 15, 35–323 (2011).

  51. He, K., Zhang, X., Ren, S. & Sun, J. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. Preprint at (2015).

  52. Ioffe, S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift. ICML (2015).

  53. Finn, R. D. et al. The Pfam protein families database: towards a more sustainable future. Nucleic Acids Res. 44, D279–D285 (2016).

    Article  Google Scholar 

  54. Li, W. & Godzik, A. Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences. Bioinformatics 22, 1658–1659 (2006).

    Article  Google Scholar 

  55. The UniProt consortium. UniProt: a worldwide hub of protein knowledge. Nucleic Acids Res. 47, D506–D515 (2019).

  56. Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. In International Conference on Learning Representations (ICLR, 2015).

  57. Oliphant, E., Peterson, P. et al. SciPy: Open source scientific tools for Python, 2001–2019. SciPy (2019).

  58. Altschul, S. F., Gish, W., Miller, W., Myers, E. W. & Lipman, D. J. Basic local alignment search tool. J . Mol. Biol. 215, 403–410 (1990).

    Article  Google Scholar 

  59. Kabsch, W. & Sander, C. Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features. Biopolymers 22, 2577–2637 (1983).

    Article  Google Scholar 

  60. Hamelryck, T. & Manderick, B. PDB file parser and structure class implemented in Python. Bioinformatics 19, 2308–2310 (2003).

  61. Cock, P. J. A. et al. Biopython: freely available Python tools for computational molecular biology and bioinformatics. Bioinformatics 25, 1422–1423 (2009).

    Article  Google Scholar 

  62. Chojnacki, S., Cowley, A., Lee, J., Foix, A. & Lopez, R. Programmatic access to bioinformatics tools from EMBL-EBI update: 2017. Nucleic Acids Res. 45, W550–W553 (2017).

    Article  Google Scholar 

  63. Touw, W. G. et al. A series of PDB-related databanks for everyday needs. Nucleic Acids Res. 43, D364–D368 (2015).

    Article  Google Scholar 

  64. The PyMOL Molecular Graphics System Version 2.0 (Schrödinger, 2019).

  65. Upmeier zu Belzen, J. et al. Leveraging implicit knowledge in neural networks for functional dissection and engineering of proteins. Code Ocean (2019).

Download references


This work was funded by the Klaus Tschira foundation, the German Research Foundation (DFG) and the Federal Ministry of Education and Research. We thank J. Quittek and M. Niepert (both at NEC), T. Wollmann (IPMB, BioQuant and the German Cancer Research Center (DKFZ)) for helpful discussions and M. Hemberger (BioQuant) for support with IT and GPU cluster use. J.U.z.B., T.B., S.H., L.A., C.G., M.K., J.M., P.P., L.P., M.P., M.S., D.H., M.D.H., M.J., C.S., M.W., I.L., D.N. and R.E. represent the iGEM Team Heidelberg 2017.

Author information

Authors and Affiliations



All members of the iGEM Team Heidelberg 2017 conceived the initial idea and J.U.z.B, T.B., S.H., I.L., D.N. and R.E. refined it. T.B., J.U.z.B. and S.H. implemented DeeProtein. J.U.z.B. performed sensitivity analysis. F.B. cloned AcrIIA4–LOV2 fusions and performed luciferase assays. J.U.z.B., T.B., S.H., F.B., D.N. and R.E. interpreted data. D.N. and R.E. jointly supervised the work. J.U.z.B., D.N. and R.E. wrote the paper with support from T.B. and S.H. All authors approved the manuscript.

Corresponding authors

Correspondence to Dominik Niopek or Roland Eils.

Ethics declarations

Competing interests

F.B., M.D.H., D.N. and R.E. have filed a European Patent application (17196813.4) for the AcrIIA4–LOV2 constructs.

Additional information

Publisher’s note: Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Supplementary Figs. 1–10, Supplementary Tables 3–6, Supplementary Notes 1–4, Supplementary references,

Reporting Summary

Supplementary Table 1

Ligand binding sensitivity

Supplementary Table 2

Sensitivity for catalytic activity

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Upmeier zu Belzen, J., Bürgel, T., Holderbach, S. et al. Leveraging implicit knowledge in neural networks for functional dissection and engineering of proteins. Nat Mach Intell 1, 225–235 (2019).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:

This article is cited by


Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing