Skip to main content
SpringerLink
Log in

De-MISTED: Image-based classification of erroneous multiple sequence alignments using convolutional neural networks

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

The widespread use of high throughput genome sequencing technologies has resulted in a significant increase in the number of available sequences, creating new challenges for genome annotation and prediction of protein-coding genes in terms of error detection and quality control. Multiple Sequence Alignments (MSAs) of the predicted protein sequences provide important contextual information that can be used to distinguish errors (caused by artifacts in the raw genome data, badly predicted gene sequences, or the alignment methods themselves) from true biological events. This can be achieved either by human expertise or by statistical analysis of the sequence data. Here, we propose a new approach that uses visual representations of MSAs as inputs for Convolutional Neural Networks (CNN) to classify MSAs into erroneous and non-erroneous categories. The MSAs are extracted from a unique in-house dataset, in which errors are carefully identified. Our model, called De-MISTED (Deep learning for MultIple Sequence alignmenTs Error Detection) identifies MSAs containing erroneous sequences with high accuracy (87%) and sensitivity (92%). Visual explanation techniques show that our model correctly identifies the position of multiple errors of different types (insertions, deletions and mismatches). Close examination of the data showed that our model can also identify errors that were not previously annotated in the data. The De-MISTED method thus contributes to a more robust exploitation of the genome data.

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
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Data Availability

The dataset generated for the current study is available in the Zenodo repository: https://doi.org/10.5281/zenodo.6637475.

Notes

  1. The filtering protocol is a simple in-house program that takes as input an erroneous MSA in XML format and filters out erroneous sequences which are defined by specific start and end tags

References

  1. Aoki G, Sakakibara Y (2018) Convolutional neural networks for classification of alignments of non-coding RNA sequences. Bioinformatics 34:i237–i244

    Article  Google Scholar 

  2. Carroll H, Beckstead W, O’Connor T et al (2007) Dna reference alignment benchmarks based on tertiary structure of encoded proteins. Bioinform (Oxford England) 23:2648–9. https://doi.org/10.1093/bioinformatics/btm389

    Article  Google Scholar 

  3. Chatzou M, Magis C, Chang JM et al (2015) Multiple sequence alignment modeling: methods and applications. Brief Bioinform 2015. https://doi.org/10.1093/bib/bbv099

  4. Chiner-Oms A, González-Candelas F (2016) Evalmsa: A program to evaluate multiple sequence alignments and detect outliers. Evol Bioinform 12:EBO.S40,583. https://doi.org/10.4137/EBO.S40583

    Article  Google Scholar 

  5. Consortium TU (2018) UniProt: a worldwide hub of protein knowledge. Nucleic Acids Res 47 (D1):D506–D515. https://doi.org/10.1093/nar/gky1049

    Article  Google Scholar 

  6. Corpet F, Servant F, Gouzy J et al (2000) ProDom and ProDom-CG: tools for protein domain analysis and whole genome comparisons. Nucleic Acids Res 28:267–9. https://doi.org/10.1093/nar/28.1.267

    Article  Google Scholar 

  7. DeBlasio DF, Kececioglu J (2018) Adaptive local realignment of protein sequences. J Comput Biol J Comput Mol Cell Biol 25(7):780–793

    Article  MathSciNet  Google Scholar 

  8. Dragan MA, Moghul I, Priyam A et al (2016) Genevalidator: Identify problems with protein-coding gene predictions. Bioinform 32. https://doi.org/10.1093/bioinformatics/btw015

  9. Edgar RC, Batzoglou S (2006) Multiple sequence alignment. Curr Opin Struct Biol 16 (3):368–73

    Article  Google Scholar 

  10. Finn RD, Bateman A, Clements J et al (2014) Pfam: the protein families database. Nucleic Acids Res 42(D1):D222–D230. https://doi.org/10.1093/nar/gkt1223, https://arxiv.org/abs/https://academic.oup.com/nar/article-pdf/42/D1/D222/3643441/gkt1223.pdf

    Article  Google Scholar 

  11. Gibbs R, Rogers J, Katze M et al (2007) Evolutionary and biomedical insights from the rhesus macaque genome. Science 316:222–34

    Article  Google Scholar 

  12. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). https://doi.org/10.1109/CVPR.2016.90, pp 770–778

  13. Jafari R, Javidi M, Kuchaki Rafsanjani M (2019) Using deep reinforcement learning approach for solving the multiple sequence alignment problem. SN Appl Sci 1. https://doi.org/10.1007/s42452-019-0611-4

  14. Jehl P, Sievers F, Higgins D (2015) OD-seq: Outlier detection in multiple sequence alignments. BMC Bioinforma 16:269. https://doi.org/10.1186/s12859-015-0702-1

    Article  Google Scholar 

  15. Kanz C, Aldebert P, Althorpe N et al (2005) The embl nucleotide sequence database. Nucleic Acids Res 33:D29–33. https://doi.org/10.1093/nar/gki098

    Article  Google Scholar 

  16. Katoh K, Standley D, Katoh K, Standley DM (2013) MAFFT multiple sequence alignment software version 7: Improvements in performance and usability. Mol Biol Evol 30:772–780. Molecular biology and evolution 30. https://doi.org/10.1093/molbev/mst010

    Article  Google Scholar 

  17. Katoh K, Misawa K, Ki Kuma et al (2002) MAFFT: A novel method for rapid multiple sequence alignment based on fast fourier transform. Nucleic Acids Res 30:3059–66

    Article  Google Scholar 

  18. Khenoussi W, Vanhoutreve R, Poch O et al (2014) SIBIS: A Bayesian model for inconsistent protein sequence estimation. Bioinform (Oxford England) 30. https://doi.org/10.1093/bioinformatics/btu329

  19. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Commun ACM 60:84–90

    Article  Google Scholar 

  20. Larkin M, Blackshields G, Brown N et al (2007) Clustal W and clustal X version 2.0. Bioinformatics 23:2947–2948

    Article  Google Scholar 

  21. Meyer C, Scalzitti N, Jeannin-Girardon A et al (2020) Understanding the causes of errors in eukaryotic protein-coding gene prediction: a case study of primate proteomes. BMC Bioinforma 21

  22. Mircea IG, Bocicor I, Czibula G (2018a) A reinforcement learning based approach to based approach multiple sequence alignment. In: Balas VE, Jain LC, Balas MM (eds) Soft computing applications. Springer International Publishing, Cham, pp 54– 70

    Chapter  Google Scholar 

  23. Mircea I-G, Bocicor M-I (2014) On reinforcement learning based multiple sequence alignment

  24. Nagy A, Patthy L (2013) MisPred: A resource for identification of erroneous protein sequences in public databases. Database J Biol Databases Curation 2013:bat053. https://doi.org/10.1093/database/bat053

    Article  Google Scholar 

  25. Nagy A, Patthy L (2014) Fixpred: a resource for correction of erroneous protein sequences. Database: The Journal of Biological Databases and Curation

  26. Nagy A, Hegyi H, Farkas K et al (2008) Identification and correction of abnormal, incomplete and mispredicted proteins in public databases. BMC Bioinforma 9:353. https://doi.org/10.1186/1471-2105-9-353

    Article  Google Scholar 

  27. Notredame C, Higgins DG, Heringa J (2000) T-Coffee: A novel method for fast and accurate multiple sequence alignment. J Mol Biol 302(1):205–17

    Article  Google Scholar 

  28. O’Leary NA, Wright MW, Brister JR et al (2015) Reference sequence (RefSeq) database at NCBI: current status, taxonomic expansion, and functional annotation. Nucleic Acids Res 44(D1):D733–D745. https://doi.org/10.1093/nar/gkv1189. https://arxiv.org/abs/https://academic.oup.com/nar/article-pdf/44/D1/D733/9482930/gkv1189.pdf

    Article  Google Scholar 

  29. Pearson W (2004) Finding protein and nucleotide similarities with fasta. Current protocols in bioinformatics / editoral board. Andreas D Baxevanis [others] Chapter 3. https://doi.org/10.1002/0471250953.bi0309s04

  30. Prosdocimi F, Linard B, Pontarotti P et al (2011) Controversies in modern evolutionary biology: the imperative for error detection and quality control. BMC Genomics 13:5–5

    Article  Google Scholar 

  31. Rajpurkar P, Irvin J, Zhu K et al (2017) Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv:http://arxiv.org/abs/1711.05225

  32. Russakovsky O, Deng J, Su H et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115:211–252

    Article  MathSciNet  Google Scholar 

  33. Scalzitti N, Jeannin-Girardon A, Collet P et al (2020) A benchmark study of ab initio gene prediction methods in diverse eukaryotic organisms. BMC Genomics 21:293. https://doi.org/10.1186/s12864-020-6707-9

    Article  Google Scholar 

  34. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. arXiv:http://arxiv.org/abs/1409.1556

  35. Srivastava N, Hinton GE, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958

    MathSciNet  MATH  Google Scholar 

  36. Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 1–9. https://doi.org/10.1109/CVPR.2015.7298594

    Google Scholar 

  37. Szegedy C, Vanhoucke V, Ioffe S et al (2016) Rethinking the inception architecture for computer vision. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 2818–2826

    Chapter  Google Scholar 

  38. Tamura K, Stecher G, Peterson D et al (2013) MEGA6: Molecular evolutionary genetics analysis version 6.0. Mol Biol Evol 30 https://doi.org/10.1093/molbev/mst197

  39. Thompson J, Higgins D, Gibson T (1994) Clustal W: improving the sensitivity of progressive multiple sequence alignment through sequence weighting, position-specific gap penalties and weight matrix choice. Nucleic Acids Res 22(22):4673–80

    Article  Google Scholar 

  40. Thompson J, Plewniak F, Poch O (1999) Balibase: A benchmark alignment database for the evaluation of multiple alignment programs. Bioinforma (Oxford England) 15:87–8. https://doi.org/10.1093/bioinformatics/15.1.87

    Article  Google Scholar 

  41. Thompson J, Plewniak F, Ripp R et al (2001) Towards a reliable objective function for multiple sequence alignments. J Mol Biol 314:937–951. https://doi.org/10.1006/jmbi.2001.5187

    Article  Google Scholar 

  42. Thompson J, Thierry JC, Poch O (2003) Rascal: Rapid scanning and correction of multiple sequence alignments. Bioinforma (Oxford England) 19:1155–61. https://doi.org/10.1093/bioinformatics/btg133

    Article  Google Scholar 

  43. Thompson JD (2016) Statistics for bioinformatics : methods for multiple sequence alignment. iSTE Press

  44. Thompson JD, Linard B, Lecompte O et al (2011) A comprehensive benchmark study of multiple sequence alignment methods: Current challenges and future perspectives. PLoS ONE 6

  45. Tong J, Pei J, Otwinowski Z et al (2014) Refinement by shifting secondary structure elements improves sequence alignments. Proteins Struct Funct Bioinform 83. https://doi.org/10.1002/prot.24746

  46. Vanhoutreve R, Kress A, Legrand B et al (2016) LEON-BIS: Multiple alignment evaluation of sequence neighbours using a bayesian inference system. BMC Bioinforma 17. https://doi.org/10.1186/s12859-016-1146-y

  47. Wang H, Wang Z, Du M et al (2020) Score-CAM: Score-weighted visual explanations for convolutional neural networks. In: 2020 IEEE/CVF conference on computer vision and pattern recognition workshops (CVPRW), pp 111–119

    Chapter  Google Scholar 

  48. Wang Y, Wu H, Cai Y (2018) A benchmark study of sequence alignment methods for protein clustering. BMC Bioinformatics 19. https://doi.org/10.1186/s12859-018-2524-4

  49. Warnow T (2021) Revisiting evaluation of multiple sequence alignment methods. Humana Press Inc., pp 299–317. Methods in Molecular Biology, https://doi.org/10.1007/978-1-0716-1036-7_17

  50. Xuyu X, Dafan Z, Qin J et al (2010) Ant colony with genetic algorithm based on planar graph for multiple sequence alignment. Inf Technol J 9. https://doi.org/10.3923/itj.2010.274.281

  51. Yosinski J, Clune J, Bengio Y et al et al (2014) How transferable are features in deep neural networks?. In: Ghahramani Z, Welling M, Cortes C (eds) Advances in neural information processing systems. https://proceedings.neurips.cc/paper/2014/file/375c71349b295fbe2dcdca9206f20a06-Paper.pdf, vol 27. Curran Associates Inc

  52. Zaal D, Nota B (2015) Adoma: A command line tool to modify clustalw multiple alignment output. Mol Inform 35. https://doi.org/10.1002/minf.201500083

  53. Zhang C, Zheng W, Mortuza S et al (2019) DeepMSA: Constructing deep multiple sequence alignment to improve contact prediction and fold-recognition for distant-homology proteins. Bioinform (Oxford England) 36. https://doi.org/10.1093/bioinformatics/btz863

Download references

Acknowledgements

The authors would like to thank the BiGEst bioinformatics platform for technical support. This work was supported by the French Infrastructure Institut Français de Bioinformatique (IFB) ANR-11-INBS-0013, ANR ArtIC ANR-20-THIA-0006 and Institute funds from the French Centre National de la Recherche Scientifique and the University of Strasbourg.

Author information

Author notes

    Authors and Affiliations

    1. University of Strasbourg, ICube Laboratory UMR7357, 1 Rue Eugène Boeckel, 67000, Strasbourg, France

      Hiba Khodji, Pierre Collet, Julie D. Thompson & Anne Jeannin-Girardon

    Authors
    1. Hiba Khodji
      View author publications

      You can also search for this author in PubMed Google Scholar

    2. Pierre Collet
      View author publications

      You can also search for this author in PubMed Google Scholar

    3. Julie D. Thompson
      View author publications

      You can also search for this author in PubMed Google Scholar

    4. Anne Jeannin-Girardon
      View author publications

      You can also search for this author in PubMed Google Scholar

    Corresponding author

    Correspondence to Hiba Khodji.

    Ethics declarations

    Competing interests

    The authors declare no competing interests.

    Additional information

    Publisher’s note

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

    Supplementary Information

    We include supplementary material providing additional Score-CAM [47] results obtained by our proposed models (A) and (B).

    Pierre Collet, Julie D. Thompson and Anne Jeannin-Girardon contributed equally to this work.

    Electronic supplementary material

    Below is the link to the electronic supplementary material.

    (3.70 MB)

    (8.15 MB)

    Rights and permissions

    Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

    Reprints and permissions

    About this article

    Check for updates. Verify currency and authenticity via CrossMark

    Cite this article

    Khodji, H., Collet, P., Thompson, J.D. et al. De-MISTED: Image-based classification of erroneous multiple sequence alignments using convolutional neural networks. Appl Intell 53, 18806–18820 (2023). https://doi.org/10.1007/s10489-022-04390-7

    Download citation

    • Accepted:

    • Published:

    • Issue Date:

    • DOI: https://doi.org/10.1007/s10489-022-04390-7

    Keywords

    Search

    Navigation