Gene expression controls how the brain develops and functions. Understanding control processes in the brain is particularly hard since they involve numerous types of neurons and glia, and very little is known about which genes are expressed in which cells and brain layers. Here we describe an approach to detect genes whose expression is primarily localized to a specific brain layer and apply it to the mouse cerebellum. We learn typical spatial patterns of expression from a few markers that are known to be localized to specific layers, and use these patterns to predict localization for new genes. We analyze images of in-situ hybridization (ISH) experiments, which we represent using histograms of local binary patterns (LBP) and train image classifiers and gene classifiers for four layers of the cerebellum: the Purkinje, granular, molecular and white matter layer. On held-out data, the layer classifiers achieve accuracy above 94% (AUC) by representing each image at multiple scales and by combining multiple image scores into a single gene-level decision. When applied to the full mouse genome, the classifiers predict specific layer localization for hundreds of new genes in the Purkinje and granular layers. Many genes localized to the Purkinje layer are likely to be expressed in astrocytes, and many others are involved in lipid metabolism, possibly due to the unusual size of Purkinje cells.
References
[1]
Kang H, Kawasawa Y, Cheng F, Zhu Y, Xu X, et al. (2011) Spatio-temporal transcriptome of the human brain. Nature 478: 483–489. doi: 10.1038/nature10523
[2]
Colantuoni C, Lipska B, Ye T, Hyde T, Tao R, et al. (2011) Temporal dynamics and genetic control of transcription in the human prefrontal cortex. Nature 478: 519–523. doi: 10.1038/nature10524
Belgard T, Marques A, Oliver P, Abaan H, Sirey T, et al. (2011) A transcriptomic atlas of mouse neocortical layers. Neuron 71: 605–616. doi: 10.1016/j.neuron.2011.06.039
[5]
Bernard A, Lubbers L, Tanis K, Luo R, Podtelezhnikov A, et al. (2012) Transcriptional architecture of the primate neocortex. Neuron 73: 1083–1099. doi: 10.1016/j.neuron.2012.03.002
[6]
Lobo MK, Karsten SL, Gray M, Geschwind DH, Yang XW (2006) Facs-array profiling of striatal projection neuron subtypes in juvenile and adult mouse brains. Nature Neuroscience 9: 443–452. doi: 10.1038/nn1654
[7]
Cahoy JD, Emery B, Kaushal A, Foo LC, Zamanian JL, et al. (2008) A transcriptome database for astrocytes, neurons, and oligodendrocytes: A new resource for understanding brain development and function. The Journal of Neuroscience 28: 264–278. doi: 10.1523/jneurosci.4178-07.2008
[8]
Koirala S, Corfas G (2010) Identification of novel glial genes by single-cell transcriptional profiling of bergmann glial cells from mouse cerebellum. PloS one 5: e9198. doi: 10.1371/journal.pone.0009198
[9]
Rong Y, Wang T, Morgan J (2004) Identification of candidate purkinje cell-specific markers by gene expression profiling in wild-type and pcd3j mice. Molecular brain research 132: 128–145. doi: 10.1016/j.molbrainres.2004.10.015
[10]
Schilling K, Oberdick J, Rossi F, Baader SL (2008) Besides purkinje cells and granule neurons: an appraisal of the cell biology of the interneurons of the cerebellar cortex. Histochemistry and Cell Biology 130: 601–615. doi: 10.1007/s00418-008-0483-y
[11]
Lein E, Hawrylycz M, Ao N, Ayres M, Bensinger A, et al. (2006) Genome-wide atlas of gene expression in the adult mouse brain. Nature 445: 168–176.
[12]
Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence 24: 971–987. doi: 10.1109/tpami.2002.1017623
[13]
Lowe D (1999) Object recognition from local scale-invariant features. In: The Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999. 2: : 1150–1157.
[14]
Bay H, Ess A, Tuytelaars T, Van Gool LV (2006) Surf: Speeded up robust features. In: Computer Vision and Image Understanding (CVIU). ECCV 2006. Graz, Austria. 110: : 404–417.
[15]
Mikolajczyk K, Schmid C (2005) A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence 27: 1615–1630. doi: 10.1109/tpami.2005.188
[16]
Szeliski R (2010) Computer vision: Algorithms and applications. New York: Springer-Verlag.
[17]
Ji S, Sun L, Jin R, Kumar S, Ye J (2008) Automated annotation of drosophila gene expression patterns using a controlled vocabulary. Bioinformatics 24: 1881–1888. doi: 10.1093/bioinformatics/btn347
[18]
Li Y, Ji S, Kumar S, Ye J, Zhou Z (2012) Drosophila gene expression pattern annotation through multi-instance multi-label learning. IEEE/ACMTransactions on Computational Biology and Bioinformatics (TCBB) 9: 98–112. doi: 10.1109/tcbb.2011.73
[19]
Mace D, Varnado N, Zhang W, Frise E, Ohler U (2010) Extraction and comparison of gene expression patterns from 2d rna in situ hybridization images. Bioinformatics 26: 761–769. doi: 10.1093/bioinformatics/btp658
[20]
Puniyani K, Faloutsos C, Xing EP (2010) Spex2: automated concise extraction of spatial gene expression patterns from fly embryo ish images. Bioinformatics 26: i47–i56. doi: 10.1093/bioinformatics/btq172
[21]
Meng T, Shyu M (2011) Automatic annotation of drosophila developmental stages using association classification and information integration. In: 2011 IEEE International Conference onInformation Reuse and Integration (IRI). IEEE, pp. 142–147.
[22]
Hawrylycz M, Ng L, Page D, Morris J, Lau C, et al. (2011) Multi-scale correlation structure of gene expression in the brain. Neural Networks 24: 933–42. doi: 10.1016/j.neunet.2011.06.012
[23]
？ajn L, Kononenko I (2008) Multiresolution image parametrization for improving texture classification. EURASIP Journal on Advances in Signal Processing 2008: 137:1–137:12. doi: 10.1155/2008/617457
[24]
Boureau Y, Ponce J, LeCun Y (2010) A theoretical analysis of feature pooling in visual recognition. In: 27th International Conference on Machine Learning. Haifa, Israel.
[25]
Zhang L, Goldman JE (1996) Generation of cerebellar interneurons from dividing progenitors in white matter. Neuron 16: 47–54. doi: 10.1016/s0896-6273(00)80022-7
[26]
Ghandour MS, Vincendon G, Gombos G (1980) Astrocyte and oligodendrocyte distribution in adult rat cerebellum: an immunohistological study. Journal of Neurocytology 9: 637–646. doi: 10.1007/bf01205030
[27]
Mao Z, Bonni A, Xia F, Nadal-Vicens M, Greenberg ME (1999) Neuronal activity-dependent cell survival mediated by transcription factor mef2. Science 286: 785–790. doi: 10.1126/science.286.5440.785
[28]
Groffen A, Martens S, Arazola R, Cornelisse L, Lozovaya N, et al. (2010) Doc2b is a high-affinity ca2+ sensor for spontaneous neurotransmitter release. Science's STKE 327: 1614. doi: 10.1126/science.1183765
[29]
Korteweg N, Denekamp F, Verhage M, Burbach J (2000) Different spatiotemporal expression of doc2 genes in the developing rat brain argues for an additional, nonsynaptic role of doc2b in early development. European Journal of Neuroscience 12: 165–171. doi: 10.1046/j.1460-9568.2000.00898.x
[30]
Lee CK, Sunkin SM, Kuan C, Thompson CL, Pathak S, et al. (2008) Quantitative methods for genome-scale analysis of in situ hybridization and correlation with microarray data. Genome Biology 9: R23. doi: 10.1186/gb-2008-9-1-r23
[31]
Chang CC, Lin CJ (2011) LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2: 27:1–27:27. doi: 10.1145/1961189.1961199
[32]
Alexa A, Rahnenführer J, Lengauer T (2006) Improved scoring of functional groups from gene expression data by decorrelating go graph structure. Bioinformatics 22: 1600–1607. doi: 10.1093/bioinformatics/btl140
[33]
Benjamini Y, Hochberg Y (1995) Controlling the false discovery rate: a practical and powerful approach to multiple testing. Journal of the Royal Statistical Society Series B (Methodological) 57: 289–300.
