Advertisement

Automatic characterisation of dye decolourisation in fungal strains using expert, traditional, and deep features

  • Marina Arredondo-Santoyo
  • César Domínguez
  • Jónathan HerasEmail author
  • Eloy Mata
  • Vico Pascual
  • Mª Soledad Vázquez-Garcidueñas
  • Gerardo Vázquez-MarrufoEmail author
Methodologies and Application

Abstract

Fungi have diverse biotechnological applications in, among others, agriculture, bioenergy generation, or remediation of polluted soil and water. In this context, culture media based on colour change in response to degradation of dyes are particularly relevant, but measuring dye decolourisation of fungal strains mainly relies on a visual and semiquantitative classification of colour intensity changes. Such a classification is a subjective, time-consuming, and difficult to reproduce process. In order to deal with these problems, we have performed a systematic evaluation of different image-classification approaches considering ad hoc expert features, traditional computer vision features, and transfer-learning features obtained from deep neural networks. Our results favour the transfer learning approach reaching an accuracy of 96.5% in the evaluated dataset. In this paper, we provide the first, at least up to the best of our knowledge, method to automatically characterise dye decolourisation level of fungal strains from images of inoculated plates.

Keywords

Fungal decolourisation Image classification Computer vision Deep learning Transfer learning 

Notes

Acknowledgements

This work was partially supported by the Ministerio de Economía y Competitividad [MTM2014-54151-P, MTM2017-88804-P], and Agencia de Desarrollo Económico de La Rioja [2017-I-IDD-00018].

Compliance with ethical standards

Conflict of interest

All the authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

References

  1. Abadi M et al (2015) TensorFlow: large-scale machine learning on heterogeneous systems. http://tensorflow.org/
  2. Abdel-Raheem A, Shearer CA (2002) Extracellular enzyme production by freshwater ascomycetes. Fungal Divers 11:1–19Google Scholar
  3. Aguilar-Pontes MW et al (2014) (Post-) genomics approaches in fungal research. Brief Funct Genomics 13(6):424–439Google Scholar
  4. Anastasi A et al (2009) Decolourisation of model and industrial dyes by mitosporic fungi in different culture conditions. World J Microbiol Biotechnol 25(8):1363–1374Google Scholar
  5. Andrews MY et al (2016) Digital image quantification of siderophores on agar plates. Data Brief 6:890–898Google Scholar
  6. Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, OxfordzbMATHGoogle Scholar
  7. Branco P, Torgo L, Ribeiro R (2016) A survey of predictive modeling on imbalanced domains. ACM Comput Surv 49(2):31:1–31:50Google Scholar
  8. Breiman L (2001) Random forests. Mach Learn 45(1):5–32zbMATHGoogle Scholar
  9. Casieri L et al (2010) Survey of ectomycorrhizal, litter-degrading, and wood-degrading basidiomycetes for dye decolorization and ligninolytic enzyme activity. Antonie van Leeuwenhoek 98(4):483–504Google Scholar
  10. Chambergo FS, Valencia EY (2016) Fungal biodiversity to biotechnology. Appl Microbiol Biotechnol 100(6):2567–2577Google Scholar
  11. Chawla NV, Bowyer KW, Hall L, Kegelmeyer W (2002) Smote: synthetic minority over-sampling technique. J Artif Intell Res 16(1):321–357zbMATHGoogle Scholar
  12. Chawla NV, Japkowicz N, Kotcz A (2004) Editorial: special issue on learning from imbalanced datasets. ACM SIGKDD Explor Newsl 6(1):1–6Google Scholar
  13. Chollet F (2016) Xception: deep learning with depthwise separable convolutions. CoRR arXiv:1610.02357
  14. Chollet F et al (2015) Keras. https://github.com/fchollet/keras
  15. Christodoulidis S et al (2017) Multisource transfer learning with convolutional neural networks for lung pattern analysis. IEEE J Biomed Health Inform 21(1):76–84Google Scholar
  16. Codella N et al (2015) Deep learning, sparse coding, and SVM for melanoma recognition in dermoscopy images. In: Proceedings of international workshop on machine learning in medical imaging (MICCAI 2015). Lecture notes in computer science. Springer, pp 118–126Google Scholar
  17. Coelho LP (2013) Mahotas: open source software for scriptable computer vision. J Open Res Softw 1(1):e3Google Scholar
  18. Cohen J (1969) Statistical power analysis for the behavioral sciences. Academic Press, CambridgezbMATHGoogle Scholar
  19. Cohen J (1973) Eta-squared and partial eta-squared in fixed factor anova designs. Educ Psychol Meas 33:107–112Google Scholar
  20. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297zbMATHGoogle Scholar
  21. Cover T, Hart P (2006) Nearest neighbor pattern classification. IEEE Trans Inf Theor 13(1):21–27zbMATHGoogle Scholar
  22. Culibrk L et al (2016) Systems biology approaches for host–fungal interactions: an expanding multi-omics frontier. Omics J Integr Biol 20(3):127–138Google Scholar
  23. Cázares-García SV et al (2016) Typing and selection of wild strains of Trichoderma spp. producers of extracellular laccase. Biotechnol Prog 32(3):787–798Google Scholar
  24. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol 1, CVPR ’05. IEEE Computer Society, San Diego, pp 886–893Google Scholar
  25. Dhouib A et al (2005) Screening for ligninolytic enzyme production by diverse fungi from Tunisia. World J Microbiol Biotechnol 21(8):1415–1423Google Scholar
  26. Gao D et al (2010) A critical review of the application of white rot fungus to environmental pollution control. Crit Rev Biotechnol 30(1):70–77Google Scholar
  27. Garcia S et al (2010) Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining: Experimental analysis of power. Inf Sci 180:2044–2064Google Scholar
  28. Geurts P, Ernst D, Wehenkel L (2006) Extremely randomized trees. Mach Learn 63(1):3–42zbMATHGoogle Scholar
  29. Ghafoorian M et al (2017) Transfer learning for domain adaptation in MRI: application in brain lesion segmentation. CoRR arXiv:1702.07841
  30. Hanking L, Anagnostakis SL (1975) The use of solid media for detection of enzyme production by fungi. Mycology 67(3):597–607Google Scholar
  31. Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern SMC–3(6):610–621Google Scholar
  32. He K et al (2016) Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16), IEEE Computer Society. IEEE, Las Vegas, pp 770–778Google Scholar
  33. Holm OS (1979) A simple sequentially rejective multiple test procedure. Scand J Stat 6:65–70MathSciNetzbMATHGoogle Scholar
  34. Huang G, Liu Z, van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17)Google Scholar
  35. Hunter RS (1948) Photoelectric color-difference meter. J Opt Soc Am 38(7):661Google Scholar
  36. Hyun MW et al (2006) Detection of cellulolytic activity in Ophiostoma and Leptographium species by chromogenic reaction. Mycobiology 34(2):108–110Google Scholar
  37. Jayasiri SC et al (2015) The faces of fungi database: fungal names linked with morphology, phylogeny and human impacts. Fungal Divers 74(1):3–18Google Scholar
  38. Kaehler A, Bradski G (2015) Learning OpenCV 3. O’Reilly Media, SebastopolGoogle Scholar
  39. Kameshwar AKS, Qin W (2017) Qualitative and quantitative methods for isolation and characterization of lignin-modifying enzymes secreted by microorganisms. BioEnergy Res 10(1):248–266Google Scholar
  40. Kasana RC et al (2008) A rapid and easy method for the detection of microbial cellulases on agar plates using Gram’s iodine. Curr Microbiol 57(5):503–507Google Scholar
  41. Kiiskinen LL et al (2004) Screening for novel laccase producing microbes. J Appl Microbiol 97:640–646Google Scholar
  42. Korniłłowicz-Kowalska T, Rybczyńska K (2015) Screening of microscopic fungi and their enzyme activities for decolorization and biotransformation of some aromatic compounds. Int J Environ Sci Technol 12(8):2673–2686Google Scholar
  43. Krizhevsky A et al (2012) ImageNet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ (eds) Advances in neural information processing systems, vol 25. Curran Associates, Inc., Red Hook, pp 1097–1105Google Scholar
  44. LeCun Y et al (2002) Neural networks: tricks of the trade. Lecture notes in computer science, vol 1524, chap. Efficient BackProp. Springer, Berlin, pp 9–50Google Scholar
  45. Lee H et al (2014) Biotechnological procedures to select white rot fungi for the degradation of PAHs. J Microbiol Methods 97:56–62Google Scholar
  46. Levene H (1960) Contributions to probability and statistics: essays in honor of Harold Hotelling, chap. Robust tests for equality of variances. Stanford University Press, Stanford, pp 278–292Google Scholar
  47. McCullagh P, Nelder JA (1989) Generalized linear models. Chapman & Hall, LondonzbMATHGoogle Scholar
  48. Menegola A et al (2017) Knowledge transfer for melanoma screening with deep learning. CoRR arXiv:1703.07479
  49. Mouhamadou B et al (2017) Molecular screening of xerophilic Aspergillus strains producing mycophenolic acid. Fungal Biol 121(2):103–111Google Scholar
  50. Nyanhongo GS et al (2002) Decolorization of textile dyes by laccases from a newly isolated strain of Trametes modesta. Water Res 36:1449–1456Google Scholar
  51. Oses R et al (2006) Evaluation of fungal endophytes for lignocellulolytic enzyme production and wood biodegradation. Int Biodeterior Biodegrad 57(2):129–135Google Scholar
  52. Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359Google Scholar
  53. Peay KG et al (2016) Dimensions of biodiversity in the Earth mycobiome. Nat Rev Microbiol 14(7):434–447Google Scholar
  54. Pedregosa F et al (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830MathSciNetzbMATHGoogle Scholar
  55. Pedrini N et al (2009) Control of pyrethroid-resistant chagas disease vectors with entomopathogenic fungi. PLOS Negl Trop Dis 3:1–11Google Scholar
  56. Pointing SB (1999) Qualitative methods for the determination of lignocellulolytic enzyme production by tropical fungi. Fungal Divers 2:17–33Google Scholar
  57. Pointing SB et al (2000) Dye decolorization by sub-tropical basidiomycetous fungi and the effect of metals on decolorizing ability. World J Microbiol Biotechnol 16(2):199–205Google Scholar
  58. Pointing SB et al (2003) Production of wood-decay enzymes, mass loss and lignin solubilization in wood by tropical xylariaceae. Mycol Res 107(2):231–235Google Scholar
  59. Razavian AS et al (2014) CNN features off-the-shelf: an astounding baseline for recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW’14), IEEE Computer Society. IEEE, Columbus, pp 512–519Google Scholar
  60. Rhoads DD et al (2015) A review of the current state of digital plate reading of cultures in clinical microbiology. J Pathol Inform 6(23):1–8Google Scholar
  61. Rodríguez-Fdez I et al (2015) STAC: a web platform for the comparison of algorithms using statistical tests. In: Proceedings of the 2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)Google Scholar
  62. Rovati JI et al (2013) Polyphenolic substrates and dyes degradation by yeasts from 25 de Mayo/King George Island (Antarctica). Yeast 30(11):459–470Google Scholar
  63. Russakovsky O et al (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252MathSciNetGoogle Scholar
  64. Schoch CL et al (2014) Finding needles in haystacks: linking scientific names, reference specimens and molecular data for fungi. Database.  https://doi.org/10.1093/database/bau061 Google Scholar
  65. Sermanet P et al (2013) OverFeat: integrated recognition, localization and detection using convolutional networks. CoRR arXiv:1312.6229
  66. Shapiron SS, Wilk MB (1965) An analysis for variance test for normality (complete samples). Inf Sci 180:2044–2064Google Scholar
  67. Sheskin D (2011) Handbook of parametric and nonparametric statistical procedures. CRC Press, LondonzbMATHGoogle Scholar
  68. Simard P, Steinkraus D, Platt JC (2003) Best practices for convolutional neural networks applied to visual document analysis. In: I.C. Society (ed) Proceedings of the 12th International Conference on Document Analysis and Recognition (ICDAR’03), vol. 2, pp 958–964Google Scholar
  69. Simonis JL et al (2008) Extracellular enzymes and soft rot decay: are ascomycetes important degraders in fresh water? Fungal Divers 31(1):135–146Google Scholar
  70. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. CoRR arXiv:1409.1556
  71. Sørensen A et al (2011) Onsite enzyme production during bioethanol production from biomass: screening for suitable fungal strains. Appl Biochem Biotechnol 164(7):1058–1070Google Scholar
  72. Szegedy C et al (2014) DeepFace: closing the gap to human-level performance in face verification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR’14), IEEE Computer Society. IEEE, pp 1701–1708Google Scholar
  73. Szegedy C et al (2015a) Going deeper with convolutions. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15), IEEE Computer Society. IEEE, Boston, pp 1–9Google Scholar
  74. Szegedy C et al (2015b) Rethinking the inception architecture for computer vision. CoRR arXiv:1512.00567
  75. Szekeres A et al (2006) A novel, image analysis-based method for the evaluation of in vitro antagonism. J Microbiol Methods 65(3):619–622Google Scholar
  76. Szeliski R (2010) Computer vision: algorithms and applications. Springer, LondonzbMATHGoogle Scholar
  77. Tortella GR et al (2008) Enzymatic characterization of Chilean native wood-rotting fungi for potential use in the bioremediation of polluted environments with chlorophenols. World J Microbiol Biotechnol 24(12):2805Google Scholar
  78. Wolpert DH (1996) The lack of a priori distinction between learning algorithms. Neural Comput 8(7):1341–1390Google Scholar
  79. Xu C et al (2015) Screening of ligninolytic fungi for biological pretreatment of lignocellulosic biomass. Can J Microbiol 61(10):745–752Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Multidisciplinary Center of Biotechnology Studies (CMEB), Faculty of Veterinary MedicineUniversidad Michoacana de San Nicolás de HidalgoMoreliaMexico
  2. 2.Department of Mathematics and Computer ScienceUniversity of La RiojaLogroñoSpain
  3. 3.Division of Postgraduate Studies, Faculty of Medical and Biological Sciences “Dr. Ignacio Chávez”Universidad Michoacana de San Nicolás de HidalgoMoreliaMexico

Personalised recommendations