Abstract
This paper presents a novel deep learning-based method for learning a functional representation of mammalian neural images. The method uses a deep convolutional denoising autoencoder (CDAE) for generating an invariant, compact representation of in situ hybridization (ISH) images. While most existing methods for bio-imaging analysis were not developed to handle images with highly complex anatomical structures, the results presented in this paper show that functional representation extracted by CDAE can help learn features of functional gene ontology categories for their classification in a highly accurate manner. Using this CDAE representation, our method outperforms the previous state-of-the-art classification rate, by improving the average AUC from 0.92 to 0.98, i.e., achieving 75% reduction in error. The method operates on input images that were downsampled significantly with respect to the original ones to make it computationally feasible.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The cerebellum is a region of the brain. It plays an important role in motor control, and has some effect on cognitive functions [23].
References
Kordmahalleh, M.M., Homaifar, A., Dukka, B.K.C.: Hierarchical multi-label gene function prediction using adaptive mutation in crowding niching. In: Proceedings of IEEE International Conference on Bioinformatics and Bioengineering, pp. 1–6 (2013)
Krizhevsky, A., Hinton, G.E.: Using very deep autoencoders for content-based image retrieval. In: Proceedings of European Symposium on Artificial Neural Networks (2011)
Henry, A.M., Hohmann, J.G.: High-resolution gene expression atlases for adult and developing mouse brain and spinal cord. Mamm. Genome 23, 539–549 (2012)
Cortes, C., Vapnik, V.: Support vector networks. Mach. Learn. 20(3), 273–297 (1995)
The Gene Ontology Consortium: The gene ontology project in 2008. Nucleic Acids Res. 36, D440–D444 (2008)
Masci, J., Meier, U., Cireşan, D., Schmidhuber, J.: Stacked convolutional auto-encoders for hierarchical feature extraction. In: Honkela, T., Duch, W., Girolami, M., Kaski, S. (eds.) ICANN 2011. LNCS, vol. 6791, pp. 52–59. Springer, Heidelberg (2011). doi:10.1007/978-3-642-21735-7_7
Pinoli, P., Chicco, D., Masseroli, M.: Computational algorithms to predict gene ontology annotations. BMC Bioinform. 16(6), S4 (2015)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Skunca, N., du Plessis, L., Dessimoz, C.: The what, where, how and why of gene ontology-a primer for bioinformaticians. Briefings Bioinform. 12(6), 723–735 (2011)
Hawrylycz, M., Ng, L., Page, D., Morris, J., Lau, C., Faber, S., Faber, V., Sunkin, S., Menon, V., Lein, E., Jones, A.: Multi-scale correlation structure of gene expression in the brain. Neural Netw. 24, 933–942 (2011)
Lein, E.S., et al.: Genome-wide atlas of gene expression in the adult mouse brain. Nature 445, 168–176 (2007)
Ng, L., et al.: An anatomic gene expression atlas of the adult mouse brain. Nat. Neurosci. 12, 356–362 (2009)
Davis, F.P., Eddy, S.R.: A tool for identification of genes expressed in patterns of interest using the allen brain atlas. Bioinformatics 25, 1647–1654 (2009)
Ashburner, M., Ball, C.A., Blake, J.A., Botstein, D., Butler, H., Cherry, J.M.: Gene ontology: tool for the unification of biology. Nat. Genet. 25(1), 25–29 (2000)
King, O.D., Foulger, R.E., Dwight, S.S., White, J.V., Roth, F.P.: Predicting gene function from patterns of annotation. Genome Res. 13(5), 896–904 (2013)
Puniyani, K., Xing, E.P.: GINI: from ISH images to gene interaction networks. PLoS Comput. Biol. 9, 10 (2013)
Shalit, U., Liscovitch, N., Chechik, G.: FuncISH: learning a functional representation of neural ISH images. Bioinformatics 29(13), i36–i43 (2013)
Zitnik, M., Zupan, B.: Matrix factorization-based data fusion for gene function prediction in baker’s yeast and slime mold. In: Proceedings of Pacific Symposium on Biocomputing, pp. 400–411 (2014)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). doi:10.1007/978-3-319-10590-1_53
Bork, P., Thode, G., Perez, A.J., Perez-Iratxeta, C., Andrade, M.A.: Gene annotation from scientific literature using mappings between keyword systems. Bioinformatics 20(13), 2084–2091 (2004)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Vembu, S., Morris, Q.: An efficient algorithm to integrate network and attribute data for gene function prediction. In: Proceedings of Pacific Symposium on Biocomputing, pp. 388–399 (2014)
Rapoport, M.J., Wolf, U., Schweizer, T.A.: Evaluating the affective component of the cerebellar cognitive affective syndrome. J. Neuropsychol. Clin. Neurosci. 21(3), 245–253 (2009)
Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine learning, pp. 1096–1103 (2008)
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371–3408 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix: Network Architecture Description
Appendix: Network Architecture Description
We provide a brief explanation as to the choice of the main parameters of the CDAE architecture. Our objective was to obtain a more compact feature representation than the 2,004-dimensional vector used in FuncISH. Since a CNN is used, the representation along the grid should capture the two-dimensional structure of the input, i.e., the image dimensions should be determined according to the intended representation vector, while maintaining the aspect ratio of the original input image. Thus, we picked an 1,800-dimensional feature vector, corresponding to an (output) image of size \(60 \times 30\). Taking into account the characteristic of max-pooling (i.e., that at each stage the dimension is reduced by 2), the desire to keep the number of layers as small as possible, and the fact that the encoding and decoding phases each contains the same number of layers (resulting in twice the number of layers in the network), we settled for two max-pooling layers, namely an input image of size \(240 \times 120\). Between each two max-pooling layers, which eliminate feature redundancy, there is an “array” of 16 convolution layers, each with the purpose of detecting locally connected features from its previous layer. The number of convolution layers (i.e., different filters used) was determined after experimenting with several different layers, all of which gave similar results. Choosing 16 layers (as shown in Fig. 4) provided the best result. We experimented also with various filter sizes for each layer, ranging from \(3 \times 3\) to \(11 \times 11\); while increasing the filter size significantly increased the amount of network parameters learned, it did not contribute much to the feature extraction or the improvement of the results. Using a learning rate decay in the training of large networks (where there is a large number of randomly generated parameters) has proven helpful in the network’s convergence. Specifically, the combination of a 0.05 learning rate parameter with a 0.9 learning rate decay resulted in an optimal change of the parameter value. In this case, too, small changes in the parameters did not result in significant changes in the results.
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Cohen, I., David, E.(., Netanyahu, N.S., Liscovitch, N., Chechik, G. (2017). DeepBrain: Functional Representation of Neural In-Situ Hybridization Images for Gene Ontology Classification Using Deep Convolutional Autoencoders. In: Lintas, A., Rovetta, S., Verschure, P., Villa, A. (eds) Artificial Neural Networks and Machine Learning – ICANN 2017. ICANN 2017. Lecture Notes in Computer Science(), vol 10614. Springer, Cham. https://doi.org/10.1007/978-3-319-68612-7_33
Download citation
DOI: https://doi.org/10.1007/978-3-319-68612-7_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68611-0
Online ISBN: 978-3-319-68612-7
eBook Packages: Computer ScienceComputer Science (R0)