Advertisement

Classification of Crystallization Trial Images

Chapter
  • 589 Downloads
Part of the Computational Biology book series (COBO, volume 25)

Abstract

Large number of features are extracted from protein crystallization trial images to improve the accuracy of classifiers for predicting the presence of crystals or phases of the crystallization process. The excessive number of features and computationally intensive image processing methods to extract these features make utilization of automated classification tools on stand-alone computing systems inconvenient due to the required time to complete the classification tasks. In this chapter, we provide an analysis of combinations of image feature sets, feature reduction, and classification techniques for crystallization images benefiting from trace fluorescent labeling. Features are categorized into intensity, graph, histogram, texture, shape-adaptive, and region features (using binarized images generated by Otsu’s, green percentile, and morphological thresholding). The effects of normalization, feature reduction with principal components analysis (PCA), and feature selection using random forest classifier are also investigated. Moreover, the time required to extract feature categories is computed and an estimated time of extraction is provided for feature category combinations. The analysis in this chapter shows that research groups can select features according to their hardware setups for real-time analysis.

Notes

Acknowledgements

The original version of this chapter appeared as M. Sigdel, I. Dinc, M. S. Sigdel, S. Dinc, M. L. Pusey, and R. S. Aygun, “Feature analysis for classification of trace fluorescent labeled protein crystallization images,” BioData Mining, vol. 10, p. 14, 2017 [41]. Some modifications have been made to fit into this book.

References

  1. 1.
    Bern, M., Goldberg, D., Stevens, R. C., & Kuhn, P. (2004). Automatic classification of protein crystallization images using a curve-tracking algorithm. Journal of applied crystallography, 37(2), 279–287.Google Scholar
  2. 2.
    Berry, I. M., Dym, O., Esnouf, R., Harlos, K., Meged, R., Perrakis, A., et al. (2006). Spine high-throughput crystallization, crystal imaging and recognition techniques: current state, performance analysis, new technologies and future aspects. Acta Crystallographica Section D: Biological Crystallography, 62(10), 1137–1149.CrossRefGoogle Scholar
  3. 3.
    Calle, M. L., & Urrea, V. (2011). Letter to the editor: stability of random forest importance measures. Briefings in Bioinformatics, 12(1), 86–89.CrossRefGoogle Scholar
  4. 4.
    Clausi, D. A. (2002). An analysis of co-occurrence texture statistics as a function of grey level quantization. Canadian Journal of Remote Sensing, 28(1), 45–62.CrossRefGoogle Scholar
  5. 5.
    Cumbaa, C., & Jurisica, I. (2005). Automatic classification and pattern discovery in high-throughput protein crystallization trials. Journal of Structural and Functional Genomics, 6(2–3), 195–202.CrossRefGoogle Scholar
  6. 6.
    Cumbaa, C. A., & Jurisica, I. (2010). Protein crystallization analysis on the world community grid. Journal of Structural Functional Genomics, 11(1), 61–9.CrossRefGoogle Scholar
  7. 7.
    Cumbaa, C. A., & Jurisica, I. (2010). Protein crystallization analysis on the world community grid. Journal of Structural and Functional Genomics, 11(1), 61–69.CrossRefGoogle Scholar
  8. 8.
    Cumbaa, C. A., Lauricella, A., Fehrman, N., Veatch, C., Collins, R., Luft, J., et al. (2003). Automatic classification of sub-microlitre protein-crystallization trials in 1536-well plates. Acta Crystallographica Section D: Biological Crystallography, 59(9), 1619–1627.CrossRefGoogle Scholar
  9. 9.
    Dinç, I., Dinç, S., Sigdel, M., Sigdel, M. S., Aygün, R. S., Pusey, M. L. (2015). Chapter 12–dt-binarize: A decision tree based binarization for protein crystal images. In Morgan Kaufmann In Emerging Trends in Image Processing, Computer Vision and Pattern Recognition. (pp. 183–199).Google Scholar
  10. 10.
    Dinç, I., Dinç, S., Sigdel, M., Sigdel, M. S., Pusey, M. L., Aygün, R. S. (2014). Dt-binarize: A hybrid binarization method using decision tree for protein crystallization images. In Proceedings of The 2014 International Conference on Image Processing, Computer Vision & Pattern Recognition, ser. IPCV, vol. 14, (pp. 304–311).Google Scholar
  11. 11.
    Dinc, I., Dinc, S., Sigdel, M., Sigdel, M., Pusey, M. L., Aygun, R. S. (2016). Super-thresholding: Supervised thresholding of protein crystal images. In IEEE/ACM transactions on computational biology and bioinformatics.Google Scholar
  12. 12.
    Dinç, I., Pusey, M. L., Aygün, R. S. (2015). Protein crystallization screening using associative experimental design. In International Symposium on Bioinformatics Research and Applications, (pp. 84–95). Berlin: Springer,Google Scholar
  13. 13.
    Dinç, I., Sigdel, M., Dinç, S., Sigdel, M. S., Pusey, M. L., Aygun, R. S. (2014). Evaluation of normalization and pca on the performance of classifiers for protein crystallization images. In South east conference 2014, IEEE (pp. 1–6).Google Scholar
  14. 14.
    Dinç, İ., Pusey, M. L., & Aygün, R. S. (2016). Optimizing associative experimental design for protein crystallization screening. IEEE Transactions on Nanobioscience, 15(2), 101–112.CrossRefGoogle Scholar
  15. 15.
    Hampton research. Accessed 7 June 2016.Google Scholar
  16. 16.
    Haralick, R. M., Shanmugam, K., & Dinstein, I. H. (1973). Textural features for image classification. Systems, Man and Cybernetics, IEEE Transactions on, 6, 610–621.CrossRefGoogle Scholar
  17. 17.
    Harris, C., Stephens, M. (1988). A combined corner and edge detector. In Alvey vision conference vol. 15, Citeseer, p. 50.Google Scholar
  18. 18.
    Hough, P. (1962) Method and means for recognizing complex patterns, US Patent 3,069,654.Google Scholar
  19. 19.
    Hung, J., Collins, J., Weldetsion, M., Newland, O., Chiang, E., Guerrero, S., Okada, K. (2014). Protein crystallization image classification with elastic net. In SPIE Medical Imaging, International Society for Optics and Photonics.Google Scholar
  20. 20.
    Jolliffe, I. (2002). Principal component analysis. Wiley Online Library.Google Scholar
  21. 21.
    Leung, T., & Malik, J. (2001). Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons. International Journal of Computer Vision, 43(1), 29–44.CrossRefzbMATHGoogle Scholar
  22. 22.
    Liu, R., Freund, Y., & Spraggon, G. (2008). Image-based crystal detection: a machine-learning approach. Acta Crystallographica Section D: Biological Crystallography, 64(12), 1187–1195.CrossRefGoogle Scholar
  23. 23.
    MATLAB. (2013).version 7.10.0 (R2013a). The MathWorks Inc., Natick, Massachusetts.Google Scholar
  24. 24.
    McPherson, A., Gavira, J. A. Introduction to protein crystallization. Acta crystallographica. Section F, Structural biology communications 70, Pt 1 (Jan. 2014), 2–20.Google Scholar
  25. 25.
    Mele, K., Lekamge, B. M. T., Fazio, V. J., & Newman, J. (2014). Using Time Courses To Enrich the Information Obtained from Images of Crystallization Trials. Crystal Growth & Design, 14(1), 261–269.CrossRefGoogle Scholar
  26. 26.
    Mitchell, T.M. (1997). et al. Machine learning. wcb.Google Scholar
  27. 27.
    Ng, J. T., Dekker, C., Kroemer, M., Osborne, M., & von Delft, F. (2014). Using textons to rank crystallization droplets by the likely presence of crystals. Acta Crystallographica Section D: Biological Crystallography, 70(10), 2702–2718.CrossRefGoogle Scholar
  28. 28.
    Otsu, N. (1975). A threshold selection method from gray-level histograms. Automatica, 11(285–296), 23–27.Google Scholar
  29. 29.
    Pan, S., Shavit, G., Penas-Centeno, M., Xu, D.-H., Shapiro, L., Ladner, R., et al. (2006). Automated classification of protein crystallization images using support vector machines with scale-invariant texture and gabor features. Acta Crystallographica Section D: Biological Crystallography, 62(3), 271–279.CrossRefGoogle Scholar
  30. 30.
    Po, M. J., Laine, A. F. (2008). Leveraging genetic algorithm and neural network in automated protein crystal recognition. In Proceedings of the 30th Annual International Conference of the IEEE(2008), Engineering in Medicine and Biology Society, EMBS 2008, (pp. 1926–1929).Google Scholar
  31. 31.
    Pusey, M. L., Liu, Z.-J., Tempel, W., Praissman, J., Lin, D., Wang, B.-C., et al. (2005). Life in the fast lane for protein crystallization and x-ray crystallography. Progress in Biophysics and Molecular Biology, 88(3), 359–386.CrossRefGoogle Scholar
  32. 32.
    Pusey, M., Barcena, J., Morris, M., Singhal, A., Yuan, Q., & Ng, J. (2015). Trace fluorescent labeling for protein crystallization. Acta Crystallographica Section F, 71(7), 806–814.Google Scholar
  33. 33.
    Randomforest-matlab. Accessed 7 June 2016.Google Scholar
  34. 34.
    Saitoh, K., Kawabata, K., Asama, H. (2006). Design of classifier to automate the evaluation of protein crystallization states. In Proceedings 2006 IEEE International Conference on Robotics and Automation, ICRA 2006 (pp. 1800–1805).Google Scholar
  35. 35.
    Saitoh, K., Kawabata, K., Kunimitsu, S., Asama, H., Mishima, T. (2004). Evaluation of protein crystallization states based on texture information. In Proceedings of the International Conference on 2004 IEEE/RSJ, Intelligent Robots and Systems, 2004.(IROS 2004) vol. 3, IEEE, (pp. 2725–2730).Google Scholar
  36. 36.
    Shapiro, L., Stockman, G. C. (2001). Computer vision. 2001. ed: Prentice Hall.Google Scholar
  37. 37.
    Sigdel, M., Aygün, R. S. (2013) Pacc-a discriminative and accuracy correlated measure for assessment of classification results. In Machine Learning and Data Mining in Pattern Recognition. (pp. 281–295). Springer.Google Scholar
  38. 38.
    Sigdel, M., Dinc, I., Dinc, S., Sigdel, M. S., Pusey, M. L., Aygiun, R. S. (2014). Evaluation of semi- supervised learning for classification of protein crystallization imagery. In Proceedings of South East Conference, IEEE, (pp. XX).Google Scholar
  39. 39.
    Sigdel, M., Sigdel, M. S., Dinç, I., Dinç, S., Aygün, R. S., Pusey, M. L. (2015). Chapter 27 - automatic classification of protein crystal images. In Morgan Kaufmann, In Emerging Trends in Image Processing, Computer Vision and Pattern Recognition. (pp. 421–432).Google Scholar
  40. 40.
    Sigdel, M., Pusey, M. L., & Aygun, R. S. (2013). Real-time protein crystallization image acquisition and classification system. Crystal Growth & Design, 13(7), 2728–2736.CrossRefGoogle Scholar
  41. 41.
    Sigdel, M., Dinc, I., Sigdel, M. S., Dinc, S., Pusey, M. L., & Aygun, R. S. (2017). Feature analysis for classification of trace fluorescent labeled protein crystallization images. BioData Mining, 10, 14.CrossRefGoogle Scholar
  42. 42.
    Soh, L.-K., & Tsatsoulis, C. (1999). Texture analysis of sar sea ice imagery using gray level co-occurrence matrices. Geoscience and Remote Sensing, IEEE Transactions on, 37(2), 780–795.CrossRefGoogle Scholar
  43. 43.
    Spraggon, G., Lesley, S. A., Kreusch, A., & Priestle, J. P. (2002). Computational analysis of crystallization trials. Acta Crystallographica Section D: Biological Crystallography, 58(11), 1915–1923.CrossRefGoogle Scholar
  44. 44.
    Tan, P.-N., Steinbach, M., & Kumar, V. (2005). Introduction to Data Mining (1st ed.). Inc, Boston, MA, USA: Addison-Wesley Longman Publishing Co.Google Scholar
  45. 45.
    Walker, C. G., Foadi, J., & Wilson, J. (2007). Classification of protein crystallization images using fourier descriptors. Journal of Applied Crystallography, 40(3), 418–426.CrossRefGoogle Scholar
  46. 46.
    Wilson, J. (2002). Towards the automated evaluation of crystallization trials. Acta Crystallographica Section D: Biological Crystallography, 58(11), 1907–1914.CrossRefGoogle Scholar
  47. 47.
    Xu, G., Chiu, C., Angelini, E. D., Laine, A. F. (2006). An incremental and optimized learning method for the automatic classification of protein crystal images. In 2006 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2006 (pp. 6526–6529). New York.Google Scholar
  48. 48.
    Yang, X., Chen, W., Zheng, Y. F., Jiang, T. (2006). Image-based classification for automating protein crystal identification. In Intelligent Computing in Signal Processing and Pattern Recognition, (pp. 932–937). Berlin: Springer.Google Scholar
  49. 49.
    Yann, M. L.-J., Tang, Y. (2016). Learning deep convolutional neural networks for x-ray protein crystallization image analysis. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16).Google Scholar
  50. 50.
    Zheng, Y., Wang, X., & Wang, C. (2014). Shape-adaptive dct and its application in region-based image coding. International Journal of Signal Processing, Image Processing and Pattern Recognition, 7(1), 99–108.CrossRefGoogle Scholar
  51. 51.
    Zhu, X., Sun, S., Bern, M. Classification of protein crystallization imagery. (2004). In Engineering in Medicine and Biology Society, 2004. IEMBS 04. 26th Annual International Conference of the IEEE vol. 1, IEEE, (pp. 1628–1631).Google Scholar
  52. 52.
    Zuk, W. M., & Ward, K. B. (1991). Methods of analysis of protein crystal images. Journal of Crystal Growth, 110(1), 148–155.CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.iXpressGenes, Inc.HuntsvilleUSA
  2. 2.University of Alabama in HuntsvilleHuntsvilleUSA

Personalised recommendations