Binary Pattern Dictionary Learning for Gene Expression Representation in Drosophila Imaginal Discs
We present an image processing pipeline which accepts a large number of images, containing spatial expression information for thousands of genes in Drosophila imaginal discs. We assume that the gene activations are binary and can be expressed as a union of a small set of non-overlapping spatial patterns, yielding a compact representation of the spatial activation of each gene. This lends itself well to further automatic analysis, with the hope of discovering new biological relationships. Traditionally, the images were labeled manually, which was very time consuming. The key part of our work is a binary pattern dictionary learning algorithm, that takes a set of binary images and determines a set of patterns, which can be used to represent the input images with a small error. We also describe the preprocessing phase, where input images are segmented to recover the activation images and spatially aligned to a common reference. We compare binary pattern dictionary learning to existing alternative methods on synthetic data and also show results of the algorithm on real microscopy images of the Drosophila imaginal discs.
This work was supported by the Czech Science Foundation project 14-21421S and by the Grant Agency of the Czech Technical University in Prague under the grant SGS15/154/OHK3/2T/13.
- 4.Brower, D.L.: Engrailed gene expression in Drosophila imaginal discs. EMBO J. 5, 2649–2656 (1986)Google Scholar
- 5.Ahammad, P., Harmon, C.L., Hammonds, A., Sastry, S.S., Rubin, G.M.: Joint nonparametric alignment for analizing spatial gene expression patterns in Drosophila imaginal discs. In: Proceedings of CVPR (2005)Google Scholar
- 7.Kim, J., Kim, K., Kim, J.H.: Semantic signature: comparative interpretation of gene expression on a semantic space. Comput. Math. Methods Med. 2016, 1–10 (2016)Google Scholar
- 8.Klema, J., Malinka, F., Zelezny, F.: Semantic biclustering: a new way to analyze and interpret gene expression data. In: Bourgeois, A., Skums, P., Wan, X., Zelikovsky, A. (eds.) Bioinformatics Research and Applications, pp. 332–333. Springer, Heidelberg (2016)Google Scholar
- 10.Tomancak, P., Beaton, A., Weiszmann, R., Kwan, E., Shu, S., Lewis, S.E., Richards, S., Ashburner, M., Hartenstein, V., Celniker, S.E., Rubin, G.M.: Systematic determination of patterns of gene expression during Drosophila embryogenesis. Genome Biol. 3 (2002). RESEARCH0088, https://genomebiology.biomedcentral.com/articles/10.1186/gb-2002-3-12-research0088
- 12.Wu, S., Joseph, A., Hammonds, A.S., Celniker, S.E., Yu, B., Frise, E.: Stability-driven nonnegative matrix factorization to interpret spatial gene expression and build local gene networks. Proc. Natl. Acad. Sci. 113, 201521171 (2016)Google Scholar
- 15.Mairal, J., Bach, F., Ponce, J., Sapiro, G.: Online dictionary learning for sparse coding. In: Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009, pp. 1–8 (2009)Google Scholar
- 20.Borovec, J.: Fully automatic segmentation of stained histological cuts. In: Husník, L. (ed.) 17th International Student Conference on Electrical Engineering, pp. 1–7. CTU in Prague, Prague (2013)Google Scholar
- 23.Kybic, J., Dolejsi, M., Borovec, J.: Fast registration of segmented images by normal sampling. In: Bio Image Computing (BIC) Workshop at CVPR, pp. 11–19 (2015)Google Scholar