1 Specific aims

2 Massivenew datasets obtained with techniques such as in situ hybridization (ISH), immunohistochemistry, in situ transgenic

3 reporter, microarray voxelation, and others, allow the expression levels of many genes at many locations to be compared.

4 Our goal is to develop automated methods to relate spatial variation in gene expression to anatomy. We want to find marker

5 genes for specific anatomical regions, and also to draw new anatomical maps based on gene expression patterns. We have

6 three specific aims:

7 (1) develop an algorithm to screen spatial gene expression data for combinations of marker genes which selectively target

8 anatomical regions

9 (2) develop an algorithm to suggest new ways of carving up a structure into anatomically distinct regions, based on

10 spatial patterns in gene expression

11 (3) create a 2-D “flat map” dataset of the mouse cerebral cortex that contains a flattened version of the Allen Mouse

12 Brain Atlas ISH data, as well as the boundaries of cortical anatomical areas. This will involve extending the functionality of

13 Caret, an existing open-source scientific imaging program. Use this dataset to validate the methods developed in (1) and (2).

14 Although our particular application involves the 3D spatial distribution of gene expression, we anticipate that the methods

15 developed in aims (1) and (2) will generalize to any sort of high-dimensional data over points located in a low-dimensional

16 space.

17 In terms of the application of the methods to cerebral cortex, aim (1) is to go from cortical areas to marker genes,

18 and aim (2) is to let the gene profile define the cortical areas. In addition to validating the usefulness of the algorithms,

19 the application of these methods to cortex will produce immediate benefits, because there are currently no known genetic

20 markers for most cortical areas. The results of the project will support the development of new ways to selectively target

21 cortical areas, and it will support the development of a method for identifying the cortical areal boundaries present in small

22 tissue samples.

23 All algorithms that we develop will be implemented in a GPL open-source software toolkit. The toolkit, as well as the

24 machine-readable datasets developed in aim (3), will be published and freely available for others to use.

25 The challenge topic

26 This proposal addresses challenge topic 06-HG-101. Massive new datasets obtained with techniques such as in situ hybridiza-

27 tion (ISH), immunohistochemistry, in situ transgenic reporter, microarray voxelation, and others, allow the expression levels

28 of many genes at many locations to be compared. Our goal is to develop automated methods to relate spatial variation in

29 gene expression to anatomy. We want to find marker genes for specific anatomical regions, and also to draw new anatomical

30 maps based on gene expression patterns.

31 The Challenge and Potential impact

32 Now we will discuss each of our three aims in turn. For each aim, we will develop a conceptual framework for thinking

33 about the task, and we will present our strategy for solving it. Next we will discuss related work. At the conclusion of each

34 section, we will summarize why our strategy is different from what has been done before. At the end of this section, we will

35 describe the potential impact.

36 Aim 1: Given a map of regions, find genes that mark the regions

37 Machine learning terminology The task of looking for marker genes for known anatomical regions means that one is

38 looking for a set of genes such that, if the expression level of those genes is known, then the locations of the regions can be

39 inferred.

40 If we define the regions so that they cover the entire anatomical structure to be divided, we may say that we are using

41 gene expression to determine to which region each voxel within the structure belongs. We call this a classification task,

42 because each voxel is being assigned to a class (namely, its region). An understanding of the relationship between the

43 combination of their expression levels and the locations of the regions may be expressed as a function. The input to this

44 function is a voxel, along with the gene expression levels within that voxel; the output is the regional identity of the target

45 voxel, that is, the region to which the target voxel belongs. We call this function a classifier. In general, the input to a

46 classifier is called an instance, and the output is called a label (or a class label).

47 The object of aim 1 is not to produce a single classifier, but rather to develop an automated method for determining a

48 classifier for any known anatomical structure. Therefore, we seek a procedure by which a gene expression dataset may be

49 analyzed in concert with an anatomical atlas in order to produce a classifier. The initial gene expression dataset used in

50 the construction of the classifier is called training data. In the machine learning literature, this sort of procedure may be

51 thought of as a supervised learning task, defined as a task in which the goal is to learn a mapping from instances to labels,

52 and the training data consists of a set of instances (voxels) for which the labels (regions) are known.

53 Each gene expression level is called a feature, and the selection of which genes1 to include is called feature selection.

54 Feature selection is one component of the task of learning a classifier. Some methods for learning classifiers start out with

55 a separate feature selection phase, whereas other methods combine feature selection with other aspects of training.

56 One class of feature selection methods assigns some sort of score to each candidate gene. The top-ranked genes are then

57 chosen. Some scoring measures can assign a score to a set of selected genes, not just to a single gene; in this case, a dynamic

58 procedure may be used in which features are added and subtracted from the selected set depending on how much they raise

59 the score. Such procedures are called “stepwise” or “greedy”.

60 Although the classifier itself may only look at the gene expression data within each voxel before classifying that voxel, the

61 algorithm which constructs the classifier may look over the entire dataset. We can categorize score-based feature selection

62 methods depending on how the score of calculated. Often the score calculation consists of assigning a sub-score to each voxel,

63 and then aggregating these sub-scores into a final score (the aggregation is often a sum or a sum of squares or average). If

64 only information from nearby voxels is used to calculate a voxel’s sub-score, then we say it is a local scoring method. If only

65 information from the voxel itself is used to calculate a voxel’s sub-score, then we say it is a pointwise scoring method.

66 Our strategy for Aim 1

67 Key questions when choosing a learning method are: What are the instances? What are the features? How are the features

68 chosen? Here are four principles that outline our answers to these questions.

69 Principle 1: Combinatorial gene expression

70 It is too much to hope that every anatomical region of interest will be identified by a single gene. For example, in the

71 cortex, there are some areas which are not clearly delineated by any gene included in the Allen Brain Atlas (ABA) dataset.

72 However, at least some of these areas can be delineated by looking at combinations of genes (an example of an area for

73 which multiple genes are necessary and sufficient is provided in Preliminary Studies, Figure 4). Therefore, each instance

74 should contain multiple features (genes).

75 _______

76 1Strictly speaking, the features are gene expression levels, but we’ll call them genes.

77 Principle 2: Only look at combinations of small numbers of genes

78 When the classifier classifies a voxel, it is only allowed to look at the expression of the genes which have been selected

79 as features. The more data that are available to a classifier, the better that it can do. For example, perhaps there are weak

80 correlations over many genes that add up to a strong signal. So, why not include every gene as a feature? The reason is that

81 we wish to employ the classifier in situations in which it is not feasible to gather data about every gene. For example, if we

82 want to use the expression of marker genes as a trigger for some regionally-targeted intervention, then our intervention must

83 contain a molecular mechanism to check the expression level of each marker gene before it triggers. It is currently infeasible

84 to design a molecular trigger that checks the level of more than a handful of genes. Similarly, if the goal is to develop a

85 procedure to do ISH on tissue samples in order to label their anatomy, then it is infeasible to label more than a few genes.

86 Therefore, we must select only a few genes as features.

87 The requirement to find combinations of only a small number of genes limits us from straightforwardly applying many

88 of the most simple techniques from the field of supervised machine learning. In the parlance of machine learning, our task

89 combines feature selection with supervised learning.

90 Principle 3: Use geometry in feature selection

91 When doing feature selection with score-based methods, the simplest thing to do would be to score the performance of

92 each voxel by itself and then combine these scores (pointwise scoring). A more powerful approach is to also use information

93 about the geometric relations between each voxel and its neighbors; this requires non-pointwise, local scoring methods. See

94 Preliminary Studies, figure 3 for evidence of the complementary nature of pointwise and local scoring methods.

95 Principle 4: Work in 2-D whenever possible

96 There are many anatomical structures which are commonly characterized in terms of a two-dimensional manifold. When

97 it is known that the structure that one is looking for is two-dimensional, the results may be improved by allowing the analysis

98 algorithm to take advantage of this prior knowledge. In addition, it is easier for humans to visualize and work with 2-D

99 data. Therefore, when possible, the instances should represent pixels, not voxels.

100 Related work

101 There is a substantial body of work on the analysis of gene expression data, most of this concerns gene expression data

102 which are not fundamentally spatial2.

103 As noted above, there has been much work on both supervised learning and there are many available algorithms for

104 each. However, the algorithms require the scientist to provide a framework for representing the problem domain, and the

105 way that this framework is set up has a large impact on performance. Creating a good framework can require creatively

106 reconceptualizing the problem domain, and is not merely a mechanical “fine-tuning” of numerical parameters. For example,

107 we believe that domain-specific scoring measures (such as gradient similarity, which is discussed in Preliminary Studies) may

108 be necessary in order to achieve the best results in this application.

109 We are aware of six existing efforts to find marker genes using spatial gene expression data using automated methods.

110 [11 ] mentions the possibility of constructing a spatial region for each gene, and then, for each anatomical structure of

111 interest, computing what proportion of this structure is covered by the gene’s spatial region.

112 GeneAtlas[5] and EMAGE [23] allow the user to construct a search query by demarcating regions and then specifing

113 either the strength of expression or the name of another gene or dataset whose expression pattern is to be matched. For the

114 similiarity score (match score) between two images (in this case, the query and the gene expression images), GeneAtlas uses

115 the sum of a weighted L1-norm distance between vectors whose components represent the number of cells within a pixel3

116 whose expression is within four discretization levels. EMAGE uses Jaccard similarity4. Neither GeneAtlas nor EMAGE

117 allow one to search for combinations of genes that define a region in concert but not separately.

118 [13 ] describes AGEA, ”Anatomic Gene Expression Atlas”. AGEA has three components. Gene Finder: The user

119 selects a seed voxel and the system (1) chooses a cluster which includes the seed voxel, (2) yields a list of genes which are

120 overexpressed in that cluster. (note: the ABA website also contains pre-prepared lists of overexpressed genes for selected

121 structures). Correlation: The user selects a seed voxel and the system then shows the user how much correlation there is

122 between the gene expression profile of the seed voxel and every other voxel. Clusters: will be described later

123 Gene Finder is different from our Aim 1 in at least three ways. First, Gene Finder finds only single genes, whereas we

124 will also look for combinations of genes. Second, gene finder can only use overexpression as a marker, whereas we will also

125 search for underexpression. Third, Gene Finder uses a simple pointwise score5, whereas we will also use geometric scores

126 such as gradient similarity (described in Preliminary Studies). Figures 4, 2, and 3 in the Preliminary Studies section contains

127 evidence that each of our three choices is the right one.

128 _________________________________________

129 2By “fundamentally spatial” we mean that there is information from a large number of spatial locations indexed by spatial coordinates; not

130 just data which have only a few different locations or which is indexed by anatomical label.

131 3Actually, many of these projects use quadrilaterals instead of square pixels; but we will refer to them as pixels for simplicity.

132 4the number of true pixels in the intersection of the two images, divided by the number of pixels in their union.

133 5“Expression energy ratio”, which captures overexpression.

134 [6 ] looks at the mean expression level of genes within anatomical regions, and applies a Student’s t-test with Bonferroni

135 correction to determine whether the mean expression level of a gene is significantly higher in the target region. Like AGEA,

136 this is a pointwise measure (only the mean expression level per pixel is being analyzed), it is not being used to look for

137 underexpression, and does not look for combinations of genes.

138 [9 ] describes a technique to find combinations of marker genes to pick out an anatomical region. They use an evolutionary

139 algorithm to evolve logical operators which combine boolean (thresholded) images in order to match a target image. Their

140 match score is Jaccard similarity.

141 In summary, there has been fruitful work on finding marker genes, but only one of the previous projects explores

142 combinations of marker genes, and none of these publications compare the results obtained by using different algorithms or

143 scoring methods.

144 Aim 2: From gene expression data, discover a map of regions

145 Machine learning terminology: clustering

146 If one is given a dataset consisting merely of instances, with no class labels, then analysis of the dataset is referred to as

147 unsupervised learning in the jargon of machine learning. One thing that you can do with such a dataset is to group instances

148 together. A set of similar instances is called a cluster, and the activity of finding grouping the data into clusters is called

149 clustering or cluster analysis.

150 The task of deciding how to carve up a structure into anatomical regions can be put into these terms. The instances

151 are once again voxels (or pixels) along with their associated gene expression profiles. We make the assumption that voxels

152 from the same anatomical region have similar gene expression profiles, at least compared to the other regions. This means

153 that clustering voxels is the same as finding potential regions; we seek a partitioning of the voxels into regions, that is, into

154 clusters of voxels with similar gene expression.

155 It is desirable to determine not just one set of regions, but also how these regions relate to each other. The outcome of

156 clustering may be a hierarchial tree of clusters, rather than a single set of clusters which partition the voxels. This is called

157 hierarchial clustering.

158 Similarity scores A crucial choice when designing a clustering method is how to measure similarity, across either pairs

159 of instances, or clusters, or both. There is much overlap between scoring methods for feature selection (discussed above

160 under Aim 1) and scoring methods for similarity.

161 Spatially contiguous clusters; image segmentation We have shown that aim 2 is a type of clustering task. In fact,

162 it is a special type of clustering task because we have an additional constraint on clusters; voxels grouped together into a

163 cluster must be spatially contiguous. In Preliminary Studies, we show that one can get reasonable results without enforcing

164 this constraint; however, we plan to compare these results against other methods which guarantee contiguous clusters.

165 Image segmentation is the task of partitioning the pixels in a digital image into clusters, usually contiguous clusters. Aim

166 2 is similar to an image segmentation task. There are two main differences; in our task, there are thousands of color channels

167 (one for each gene), rather than just three6. A more crucial difference is that there are various cues which are appropriate

168 for detecting sharp object boundaries in a visual scene but which are not appropriate for segmenting abstract spatial data

169 such as gene expression. Although many image segmentation algorithms can be expected to work well for segmenting other

170 sorts of spatially arranged data, some of these algorithms are specialized for visual images.

171 Dimensionality reduction In this section, we discuss reducing the length of the per-pixel gene expression feature

172 vector. By “dimension”, we mean the dimension of this vector, not the spatial dimension of the underlying data.

173 Unlike aim 1, there is no externally-imposed need to select only a handful of informative genes for inclusion in the

174 instances. However, some clustering algorithms perform better on small numbers of features7. There are techniques which

175 “summarize” a larger number of features using a smaller number of features; these techniques go by the name of feature

176 extraction or dimensionality reduction. The small set of features that such a technique yields is called the reduced feature

177 set. Note that the features in the reduced feature set do not necessarily correspond to genes; each feature in the reduced set

178 may be any function of the set of gene expression levels.

179 Clustering genes rather than voxels Although the ultimate goal is to cluster the instances (voxels or pixels), one

180 strategy to achieve this goal is to first cluster the features (genes). There are two ways that clusters of genes could be used.

181 Gene clusters could be used as part of dimensionality reduction: rather than have one feature for each gene, we could

182 have one reduced feature for each gene cluster.

183 __

184 6There are imaging tasks which use more than three colors, for example multispectral imaging and hyperspectral imaging, which are often

185 used to process satellite imagery.

186 7First, because the number of features in the reduced dataset is less than in the original dataset, the running time of clustering algorithms

187 may be much less. Second, it is thought that some clustering algorithms may give better results on reduced data.

188 Gene clusters could also be used to directly yield a clustering on instances. This is because many genes have an expression

189 patternwhich seems to pick out a single, spatially continguous region. Therefore, it seems likely that an anatomically

190 interesting region will have multiple genes which each individually pick it out8. This suggests the following procedure:

191 cluster together genes which pick out similar regions, and then to use the more popular common regions as the final clusters.

192 In Preliminary Studies, Figure 7, we show that a number of anatomically recognized cortical regions, as well as some

193 “superregions” formed by lumping together a few regions, are associated with gene clusters in this fashion.

194 The task of clustering both the instances and the features is called co-clustering, and there are a number of co-clustering

195 algorithms.

196 Related work

197 Some researchers have attempted to parcellate cortex on the basis of non-gene expression data. For example, [15], [2], [16],

198 and [1 ] associate spots on the cortex with the radial profile9 of response to some stain ([10] uses MRI), extract features from

199 this profile, and then use similarity between surface pixels to cluster. Features used include statistical moments, wavelets,

200 and the excess mass functional. Some of these features are motivated by the presence of tangential lines of stain intensity

201 which correspond to laminar structure. Some methods use standard clustering procedures, whereas others make use of the

202 spatial nature of the data to look for sudden transitions, which are identified as areal borders.

203 [20 ] describes an analysis of the anatomy of the hippocampus using the ABA dataset. In addition to manual analysis,

204 two clustering methods were employed, a modified Non-negative Matrix Factorization (NNMF), and a hierarchial recursive

205 bifurcation clustering scheme based on correlation as the similarity score. The paper yielded impressive results, proving

206 the usefulness of computational genomic anatomy. We have run NNMF on the cortical dataset10 and while the results are

207 promising, they also demonstrate that NNMF is not necessarily the best dimensionality reduction method for this application

208 (see Preliminary Studies, Figure 6).

209 AGEA[13] includes a preset hierarchial clustering of voxels based on a recursive bifurcation algorithm with correlation

210 as the similarity metric. EMAGE[23] allows the user to select a dataset from among a large number of alternatives, or by

211 running a search query, and then to cluster the genes within that dataset. EMAGE clusters via hierarchial complete linkage

212 clustering with un-centred correlation as the similarity score.

213 [6 ] clustered genes, starting out by selecting 135 genes out of 20,000 which had high variance over voxels and which were

214 highly correlated with many other genes. They computed the matrix of (rank) correlations between pairs of these genes, and

215 ordered the rows of this matrix as follows: “the first row of the matrix was chosen to show the strongest contrast between

216 the highest and lowest correlation coefficient for that row. The remaining rows were then arranged in order of decreasing

217 similarity using a least squares metric”. The resulting matrix showed four clusters. For each cluster, prototypical spatial

218 expression patterns were created by averaging the genes in the cluster. The prototypes were analyzed manually, without

219 clustering voxels.

220 [9 ] applies their technique for finding combinations of marker genes for the purpose of clustering genes around a “seed

221 gene”. They do this by using the pattern of expression of the seed gene as the target image, and then searching for other

222 genes which can be combined to reproduce this pattern. Other genes which are found are considered to be related to the

223 seed. The same team also describes a method[22] for finding “association rules” such as, “if this voxel is expressed in by

224 any gene, then that voxel is probably also expressed in by the same gene”. This could be useful as part of a procedure for

225 clustering voxels.

226 In summary, although these projects obtained clusterings, there has not been much comparison between different algo-

227 rithms or scoring methods, so it is likely that the best clustering method for this application has not yet been found. The

228 projects using gene expression on cortex did not attempt to make use of the radial profile of gene expression. Also, none of

229 these projects did a separate dimensionality reduction step before clustering pixels, none tried to cluster genes first in order

230 to guide automated clustering of pixels into spatial regions, and none used co-clustering algorithms.

231 Aim 3: apply the methods developed to the cerebral cortex

232 Background

233 The cortex is divided into areas and layers. Because of the cortical columnar organization, the parcellation of the cortex

234 into areas can be drawn as a 2-D map on the surface of the cortex. In the third dimension, the boundaries between the

235 _________________________________________

236 8This would seem to contradict our finding in aim 1 that some cortical areas are combinatorially coded by multiple genes. However, it is

237 possible that the currently accepted cortical maps divide the cortex into regions which are unnatural from the point of view of gene expression;

238 perhaps there is some other way to map the cortex for which each region can be identified by single genes. Another possibility is that, although

239 the cluster prototype fits an anatomical region, the individual genes are each somewhat different from the prototype.

240 9A radial profile is a profile along a line perpendicular to the cortical surface.

241 10We ran “vanilla” NNMF, whereas the paper under discussion used a modified method. Their main modification consisted of adding a soft

242 spatial contiguity constraint. However, on our dataset, NNMF naturally produced spatially contiguous clusters, so no additional constraint was

243 needed. The paper under discussion also mentions that they tried a hierarchial variant of NNMF, which we have not yet tried.

244 areas continue downwards into the cortical depth, perpendicular to the surface. The layer boundaries run parallel to the

245 surface.One can picture an area of the cortex as a slice of a six-layered cake11.

246 It is known that different cortical areas have distinct roles in both normal functioning and in disease processes, yet there

247 are no known marker genes for most cortical areas. When it is necessary to divide a tissue sample into cortical areas, this is

248 a manual process that requires a skilled human to combine multiple visual cues and interpret them in the context of their

249 approximate location upon the cortical surface.

250 Even the questions of how many areas should be recognized in cortex, and what their arrangement is, are still not

251 completely settled. A proposed division of the cortex into areas is called a cortical map. In the rodent, the lack of a single

252 agreed-upon map can be seen by contrasting the recent maps given by Swanson[19] on the one hand, and Paxinos and

253 Franklin[14] on the other. While the maps are certainly very similar in their general arrangement, significant differences

254 remain.

255 The Allen Mouse Brain Atlas dataset

256 The Allen Mouse Brain Atlas (ABA) data were produced by doing in-situ hybridization on slices of male, 56-day-old

257 C57BL/6J mouse brains. Pictures were taken of the processed slice, and these pictures were semi-automatically analyzed

258 to create a digital measurement of gene expression levels at each location in each slice. Per slice, cellular spatial resolution

259 is achieved. Using this method, a single physical slice can only be used to measure one single gene; many different mouse

260 brains were needed in order to measure the expression of many genes.

261 An automated nonlinear alignment procedure located the 2D data from the various slices in a single 3D coordinate

262 system. In the final 3D coordinate system, voxels are cubes with 200 microns on a side. There are 67x41x58 = 159,326

263 voxels in the 3D coordinate system, of which 51,533 are in the brain[13].

264 Mus musculus is thought to contain about 22,000 protein-coding genes[25]. The ABA contains data on about 20,000

265 genes in sagittal sections, out of which over 4,000 genes are also measured in coronal sections. Our dataset is derived from

266 only the coronal subset of the ABA12.

267 The ABA is not the only large public spatial gene expression dataset13. With the exception of the ABA, GenePaint, and

268 EMAGE, most of the other resources have not (yet) extracted the expression intensity from the ISH images and registered

269 the results into a single 3-D space, and to our knowledge only ABA and EMAGE make this form of data available for public

270 download from the website14. Many of these resources focus on developmental gene expression.

271 Related work

272 [13 ] describes the application of AGEA to the cortex. The paper describes interesting results on the structure of correlations

273 between voxel gene expression profiles within a handful of cortical areas. However, this sort of analysis is not related to either

274 of our aims, as it neither finds marker genes, nor does it suggest a cortical map based on gene expression data. Neither of

275 the other components of AGEA can be applied to cortical areas; AGEA’s Gene Finder cannot be used to find marker genes

276 for the cortical areas; and AGEA’s hierarchial clustering does not produce clusters corresponding to the cortical areas15.

277 In summary, for all three aims, (a) only one of the previous projects explores combinations of marker genes, (b) there has

278 been almost no comparison of different algorithms or scoring methods, and (c) there has been no work on computationally

279 finding marker genes for cortical areas, or on finding a hierarchial clustering that will yield a map of cortical areas de novo

280 from gene expression data.

281 Our project is guided by a concrete application with a well-specified criterion of success (how well we can find marker

282 genes for / reproduce the layout of cortical areas), which will provide a solid basis for comparing different methods.

283 _________________________________________

284 11Outside of isocortex, the number of layers varies.

285 12The sagittal data do not cover the entire cortex, and also have greater registration error[13]. Genes were selected by the Allen Institute for

286 coronal sectioning based on, “classes of known neuroscientific interest... or through post hoc identification of a marked non-ubiquitous expression

287 pattern”[13].

288 13Other such resources include GENSAT[8], GenePaint[24], its sister project GeneAtlas[5], BGEM[12], EMAGE[23], EurExpress (http://www.

289 eurexpress.org/ee/; EurExpress data are also entered into EMAGE), EADHB (http://www.ncl.ac.uk/ihg/EADHB/database/EADHB_database.

290 html), MAMEP (http://mamep.molgen.mpg.de/index.php), Xenbase (http://xenbase.org/), ZFIN[18], Aniseed (http://aniseed-ibdm.

291 univ-mrs.fr/), VisiGene (http://genome.ucsc.edu/cgi-bin/hgVisiGene ; includes data from some of the other listed data sources), GEISHA[4],

292 Fruitfly.org[21], COMPARE (http://compare.ibdml.univ-mrs.fr/), GXD[17], GEO[3] (GXD and GEO contain spatial data but also non-spatial

293 data. All GXD spatial data are also in EMAGE.)

294 14without prior offline registration

295 15In both cases, the cause is that pairwise correlations between the gene expression of voxels in different areas but the same layer are often stronger

296 than pairwise correlations between the gene expression of voxels in different layers but the same area. Therefore, a pairwise voxel correlation

297 clustering algorithm will tend to create clusters representing cortical layers, not areas (there may be clusters which presumably correspond to the

298 intersection of a layer and an area, but since one area will have many layer-area intersection clusters, further work is needed to make sense of

299 these). The reason that Gene Finder cannot the find marker genes for cortical areas is that, although the user chooses a seed voxel, Gene Finder

300 chooses the ROI for which genes will be found, and it creates that ROI by (pairwise voxel correlation) clustering around the seed.

301 Significance

302 The method developed in aim (1) will be applied to each cortical area to find a set of marker genes such that the combinatorial

303 expression pattern of those genes uniquely picks out the target area. Finding marker genes will be useful for drug discovery

304 as well as for experimentation because marker genes can be used to design interventions which selectively target individual

305 cortical areas.

306 The application of the marker gene finding algorithm to the cortex will also support the development of new neuroanatom-

307 ical methods. In addition to finding markers for each individual cortical areas, we will find a small panel of genes that can

308 find many of the areal boundaries at once. This panel of marker genes will allow the development of an ISH protocol that

309 will allow experimenters to more easily identify which anatomical areas are present in small samples of cortex.

310 The method developed in aim (2) will provide a genoarchitectonic viewpoint that will contribute to the creation of a

311 better map. The development of present-day cortical maps was driven by the application of histological stains. If a different

312 set of stains had been available which identified a different set of features, then today’s cortical maps may have come out

313 differently. It is likely that there are many repeated, salient spatial patterns in the gene expression which have not yet been

314 captured by any stain. Therefore, cortical anatomy needs to incorporate what we can learn from looking at the patterns of

315 gene expression.

316 While we do not here propose to analyze human gene expression data, it is conceivable that the methods we propose

317 to develop could be used to suggest modifications to the human cortical map as well. In fact, the methods we will develop

318 will be applicable to other datasets beyond the brain. We will provide an open-source toolbox to allow other researchers

319 to easily use our methods. With these methods, researchers with gene expression for any area of the body will be able to

320 efficiently find marker genes for anatomical regions, or to use gene expression to discover new anatomical patterning. As

321 described above, marker genes have a variety of uses in the development of drugs and experimental manipulations, and in

322 the anatomical characterization of tissue samples. The discovery of new ways to carve up anatomical structures into regions

323 may lead to the discovery of new anatomical subregions in various structures, which will widely impact all areas of biology.

324 Although our particular application involves the 3D spatial distribution of gene expression, we anticipate that the

325 methods developed in aims (1) and (2) will not be limited to gene expression data, but rather will generalize to any sort of

326 high-dimensional data over points located in a low-dimensional space.

327 The approach: Preliminary Studies

328 Format conversion between SEV, MATLAB, NIFTI

329 We have created software to (politely) download all of the SEV files16 from the Allen Institute website. We have also created

330 software to convert between the SEV, MATLAB, and NIFTI file formats, as well as some of Caret’s file formats.

331 Flatmap of cortex

332 We downloaded the ABA data and applied a mask to select only those voxels which belong to cerebral cortex. We divided

333 the cortex into hemispheres.

334 Using Caret[7], we created a mesh representation of the surface of the selected voxels. For each gene, for each node of

335 the mesh, we calculated an average of the gene expression of the voxels “underneath” that mesh node. We then flattened

336 the cortex, creating a two-dimensional mesh.

337 We sampled the nodes of the irregular, flat mesh in order to create a regular grid of pixel values. We converted this grid

338 into a MATLAB matrix.

339 We manually traced the boundaries of each of 49 cortical areas from the ABA coronal reference atlas slides. We then

340 converted these manual traces into Caret-format regional boundary data on the mesh surface. We projected the regions

341 onto the 2-d mesh, and then onto the grid, and then we converted the region data into MATLAB format.

342 At this point, the data are in the form of a number of 2-D matrices, all in registration, with the matrix entries representing

343 a grid of points (pixels) over the cortical surface:

344 _

345 16SEV is a sparse format for spatial data. It is the format in which the ABA data is made available.

346

347

348

349 Figure 1: Top row: Genes Nfic and

350 A930001M12Rik are the most correlated

351 with area SS (somatosensory cortex). Bot-

352 tom row: Genes C130038G02Rik and

353 Cacna1i are those with the best fit using

354 logistic regression. Within each picture, the

355 vertical axis roughly corresponds to anterior

356 at the top and posterior at the bottom, and

357 the horizontal axis roughly corresponds to

358 medial at the left and lateral at the right.

359 The red outline is the boundary of region

360 SS. Pixels are colored according to correla-

361 tion, with red meaning high correlation and

362 blue meaning low.

363 ∙A 2-D matrix whose entries represent the regional label associated with each surface pixel

364 ∙For each gene, a 2-D matrix whose entries represent the average expression level underneath each surface pixel

365

366 Figure 2: Gene Pitx2

367 is selectively underex-

368 pressed in area SS. We created a normalized version of the gene expression data by subtracting each gene’s mean

369 expression level (over all surface pixels) and dividing the expression level of each gene by its

370 standard deviation.

371 The features and the target area are both functions on the surface pixels. They can be referred

372 to as scalar fields over the space of surface pixels; alternately, they can be thought of as images

373 which can be displayed on the flatmapped surface.

374 To move beyond a single average expression level for each surface pixel, we plan to create a

375 separate matrix for each cortical layer to represent the average expression level within that layer.

376 Cortical layers are found at different depths in different parts of the cortex. In preparation for

377 extracting the layer-specific datasets, we have extended Caret with routines that allow the depth

378 of the ROI for volume-to-surface projection to vary.

379 In the Research Plan, we describe how we will automatically locate the layer depths. For

380 validation, we have manually demarcated the depth of the outer boundary of cortical layer 5 throughout the cortex.

381 Feature selection and scoring methods

382 Underexpression of a gene can serve as a marker Underexpression of a gene can sometimes serve as a marker. See,

383 for example, Figure 2.

384 Correlation Recall that the instances are surface pixels, and consider the problem of attempting to classify each instance

385 as either a member of a particular anatomical area, or not. The target area can be represented as a boolean mask over the

386 surface pixels.

387 One class of feature selection scoring methods contains methods which calculate some sort of “match” between each gene

388 image and the target image. Those genes which match the best are good candidates for features.

389 One of the simplest methods in this class is to use correlation as the match score. We calculated the correlation between

390 each gene and each cortical area. The top row of Figure 1 shows the three genes most correlated with area SS.

391

392

393

394 Figure 3: The top row shows the two genes

395 which (individually) best predict area AUD,

396 according to logistic regression. The bot-

397 tom row shows the two genes which (indi-

398 vidually) best match area AUD, according

399 to gradient similarity. From left to right and

400 top to bottom, the genes are Ssr1, Efcbp1,

401 Ptk7, and Aph1a. Conditional entropy An information-theoretic scoring method is to find

402 features such that, if the features (gene expression levels) are known, uncer-

403 tainty about the target (the regional identity) is reduced. Entropy measures

404 uncertainty, so what we want is to find features such that the conditional dis-

405 tribution of the target has minimal entropy. The distribution to which we are

406 referring is the probability distribution over the population of surface pixels.

407 The simplest way to use information theory is on discrete data, so we

408 discretized our gene expression data by creating, for each gene, five thresholded

409 boolean masks of the gene data. For each gene, we created a boolean mask of

410 its expression levels using each of these thresholds: the mean of that gene, the

411 mean minus one standard deviation, the mean minus two standard deviations,

412 the mean plus one standard deviation, the mean plus two standard deviations.

413 Now, for each region, we created and ran a forward stepwise procedure

414 which attempted to find pairs of gene expression boolean masks such that the

415 conditional entropy of the target area’s boolean mask, conditioned upon the

416 pair of gene expression boolean masks, is minimized.

417 This finds pairs of genes which are most informative (at least at these dis-

418 cretization thresholds) relative to the question, “Is this surface pixel a member

419 of the target area?”. Its advantage over linear methods such as logistic regres-

420 sion is that it takes account of arbitrarily nonlinear relationships; for example,

421 if the XOR of two variables predicts the target, conditional entropy would

422 notice, whereas linear methods would not.

423

424

425 Figure 4: Upper left: wwc1. Upper right:

426 mtif2. Lower left: wwc1 + mtif2 (each

427 pixel’s value on the lower left is the sum of

428 the corresponding pixels in the upper row). Gradient similarity We noticed that the previous two scoring methods,

429 which are pointwise, often found genes whose pattern of expression did not

430 look similar in shape to the target region. For this reason we designed a

431 non-pointwise local scoring method to detect when a gene had a pattern of

432 expression which looked like it had a boundary whose shape is similar to the

433 shape of the target region. We call this scoring method “gradient similarity”.

434 One might say that gradient similarity attempts to measure how much the

435 border of the area of gene expression and the border of the target region over-

436 lap. However, since gene expression falls off continuously rather than jumping

437 from its maximum value to zero, the spatial pattern of a gene’s expression often

438 does not have a discrete border. Therefore, instead of looking for a discrete

439 border, we look for large gradients. Gradient similarity is a symmetric function

440 over two images (i.e. two scalar fields). It is is high to the extent that matching

441 pixels which have large values and large gradients also have gradients which

442 are oriented in a similar direction. The formula is:

443 ∑

444 pixel<img src="cmsy7-32.png" alt="&#x2208;" />pixels cos(abs(&#x2220;&#x2207;1 -&#x2220;&#x2207;2)) &#x22C5;|&#x2207;1| + |&#x2207;2|

445 2 &#x22C5; pixel_value1 + pixel_value2

446 2

447 where &#x2207;1 and &#x2207;2 are the gradient vectors of the two images at the current

448 pixel; &#x2220;&#x2207;i is the angle of the gradient of image i at the current pixel; |&#x2207;i| is the magnitude of the gradient of image i at

449 the current pixel; and pixel_valuei is the value of the current pixel in image i.

450 The intuition is that we want to see if the borders of the pattern in the two images are similar; if the borders are similar,

451 then both images will have corresponding pixels with large gradients (because this is a border) which are oriented in a

452 similar direction (because the borders are similar).

453 Most of the genes in Figure 5 were identified via gradient similarity.

454 Gradient similarity provides information complementary to correlation

455 To show that gradient similarity can provide useful information that cannot be detected via pointwise analyses, consider

456 Fig. 3. The top row of Fig. 3 displays the 3 genes which most match area AUD, according to a pointwise method17. The

457 bottom row displays the 3 genes which most match AUD according to a method which considers local geometry18 The

458 pointwise method in the top row identifies genes which express more strongly in AUD than outside of it; its weakness is

459 that this includes many areas which don&#8217;t have a salient border matching the areal border. The geometric method identifies

460 _________________________________________

461 17For each gene, a logistic regression in which the response variable was whether or not a surface pixel was within area AUD, and the predictor

462 variable was the value of the expression of the gene underneath that pixel. The resulting scores were used to rank the genes in terms of how well

463 they predict area AUD.

464 18For each gene the gradient similarity between (a) a map of the expression of each gene on the cortical surface and (b) the shape of area AUD,

465 was calculated, and this was used to rank the genes.

466 genes whose salient expression border seems to partially line up with the border of AUD; its weakness is that this includes

467 genes which don&#8217;t express over the entire area. Genes which have high rankings using both pointwise and border criteria,

468 such as Aph1a in the example, may be particularly good markers. None of these genes are, individually, a perfect marker

469 for AUD; we deliberately chose a &#8220;difficult&#8221; area in order to better contrast pointwise with geometric methods.

470

471

472

473

474 Figure 5: From left to right and top

475 to bottom, single genes which roughly

476 identify areas SS (somatosensory primary

477 + supplemental), SSs (supplemental so-

478 matosensory), PIR (piriform), FRP (frontal

479 pole), RSP (retrosplenial), COApm (Corti-

480 cal amygdalar, posterior part, medial zone).

481 Grouping some areas together, we have

482 also found genes to identify the groups

483 ACA+PL+ILA+DP+ORB+MO (anterior

484 cingulate, prelimbic, infralimbic, dorsal pe-

485 duncular, orbital, motor), posterior and lat-

486 eral visual (VISpm, VISpl, VISI, VISp; pos-

487 teromedial, posterolateral, lateral, and pri-

488 mary visual; the posterior and lateral vi-

489 sual area is distinguished from its neigh-

490 bors, but not from the entire rest of the

491 cortex). The genes are Pitx2, Aldh1a2,

492 Ppfibp1, Slco1a5, Tshz2, Trhr, Col12a1,

493 Ets1. Areas which can be identified by single genes Using gradient simi-

494 larity, we have already found single genes which roughly identify some areas

495 and groupings of areas. For each of these areas, an example of a gene which

496 roughly identifies it is shown in Figure 5. We have not yet cross-verified these

497 genes in other atlases.

498 In addition, there are a number of areas which are almost identified by single

499 genes: COAa+NLOT (anterior part of cortical amygdalar area, nucleus of the

500 lateral olfactory tract), ENT (entorhinal), ACAv (ventral anterior cingulate),

501 VIS (visual), AUD (auditory).

502 These results validate our expectation that the ABA dataset can be ex-

503 ploited to find marker genes for many cortical areas, while also validating the

504 relevancy of our new scoring method, gradient similarity.

505 Combinations of multiple genes are useful and necessary for some

506 areas

507 In Figure 4, we give an example of a cortical area which is not marked by

508 any single gene, but which can be identified combinatorially. Acccording to

509 logistic regression, gene wwc1 is the best fit single gene for predicting whether

510 or not a pixel on the cortical surface belongs to the motor area (area MO).

511 The upper-left picture in Figure 4 shows wwc1&#8217;s spatial expression pattern over

512 the cortex. The lower-right boundary of MO is represented reasonably well by

513 this gene, but the gene overshoots the upper-left boundary. This flattened 2-D

514 representation does not show it, but the area corresponding to the overshoot is

515 the medial surface of the cortex. MO is only found on the dorsal surface. Gene

516 mtif2 is shown in the upper-right. Mtif2 captures MO&#8217;s upper-left boundary,

517 but not its lower-right boundary. Mtif2 does not express very much on the

518 medial surface. By adding together the values at each pixel in these two figures,

519 we get the lower-left image. This combination captures area MO much better

520 than any single gene.

521 This shows that our proposal to develop a method to find combinations of

522 marker genes is both possible and necessary.

523 Feature selection integrated with prediction As noted earlier, in gen-

524 eral, any predictive method can be used for feature selection by running it

525 inside a stepwise wrapper. Also, some predictive methods integrate soft con-

526 straints on number of features used. Examples of both of these will be seen in

527 the section &#8220;Multivariate Predictive methods&#8221;.

528 Multivariate Predictive methods

529 Forward stepwise logistic regression Logistic regression is a popular

530 method for predictive modeling of categorial data. As a pilot run, for five

531 cortical areas (SS, AUD, RSP, VIS, and MO), we performed forward stepwise

532 logistic regression to find single genes, pairs of genes, and triplets of genes

533 which predict areal identify. This is an example of feature selection integrated

534 with prediction using a stepwise wrapper. Some of the single genes found

535 were shown in various figures throughout this document, and Figure 4 shows

536 a combination of genes which was found.

537 We felt that, for single genes, gradient similarity did a better job than

538 logistic regression at capturing our subjective impression of a &#8220;good gene&#8221;.

539 SVM on all genes at once

540 In order to see how well one can do when looking at all genes at once, we ran a support vector machine to classify cortical

541 surface pixels based on their gene expression profiles. We achieved classification accuracy of about 81%19. This shows that

542 _________________________________________

543 195-fold cross-validation.

544 the genes included in the ABA dataset are sufficient to define much of cortical anatomy. However, as noted above, a classifier

545 that looks at all the genes at once isn&#8217;t as practically useful as a classifier that uses only a few genes.

546

547

548

549

550 Figure 6: First row: the first 6 reduced dimensions, using PCA. Second

551 row: the first 6 reduced dimensions, using NNMF. Third row: the first

552 six reduced dimensions, using landmark Isomap. Bottom row: examples

553 of kmeans clustering applied to reduced datasets to find 7 clusters. Left:

554 19 of the major subdivisions of the cortex. Second from left: PCA. Third

555 from left: NNMF. Right: Landmark Isomap. Additional details: In the

556 third and fourth rows, 7 dimensions were found, but only 6 displayed. In

557 the last row: for PCA, 50 dimensions were used; for NNMF, 6 dimensions

558 were used; for landmark Isomap, 7 dimensions were used. Data-driven redrawing of the cor-

559 tical map

560 We have applied the following dimensionality

561 reduction algorithms to reduce the dimension-

562 ality of the gene expression profile associated

563 with each voxel: Principal Components Anal-

564 ysis (PCA), Simple PCA (SPCA), Multi-Dimensional

565 Scaling (MDS), Isomap, Landmark Isomap, Lapla-

566 cian eigenmaps, Local Tangent Space Alignment

567 (LTSA), Hessian locally linear embedding, Dif-

568 fusion maps, Stochastic Neighbor Embedding

569 (SNE), Stochastic Proximity Embedding (SPE),

570 Fast Maximum Variance Unfolding (FastMVU),

571 Non-negative Matrix Factorization (NNMF). Space

572 constraints prevent us from showing many of

573 the results, but as a sample, PCA, NNMF, and

574 landmark Isomap are shown in the first, second,

575 and third rows of Figure 6.

576 After applying the dimensionality reduction,

577 we ran clustering algorithms on the reduced data.

578 To date we have tried k-means and spectral

579 clustering. The results of k-means after PCA,

580 NNMF, and landmark Isomap are shown in the

581 last row of Figure 6. To compare, the left-

582 most picture on the bottom row of Figure 6

583 shows some of the major subdivisions of cor-

584 tex. These results clearly show that different di-

585 mensionality reduction techniques capture dif-

586 ferent aspects of the data and lead to differ-

587 ent clusterings, indicating the utility of our pro-

588 posal to produce a detailed comparion of these

589 techniques as applied to the domain of genomic

590 anatomy.

591

592 Figure 7: Prototypes corresponding to sample gene clusters,

593 clustered by gradient similarity. Region boundaries for the

594 region that most matches each prototype are overlayed. Many areas are captured by clusters of genes We

595 also clustered the genes using gradient similarity to see if

596 the spatial regions defined by any clusters matched known

597 anatomical regions. Figure 7 shows, for ten sample gene

598 clusters, each cluster&#8217;s average expression pattern, compared

599 to a known anatomical boundary. This suggests that it is

600 worth attempting to cluster genes, and then to use the re-

601 sults to cluster voxels.

602 The approach: what we plan to do

603 Flatmap cortex and segment cortical layers

604 There are multiple ways to flatten 3-D data into 2-D. We

605 will compare mappings from manifolds to planes which at-

606 tempt to preserve size (such as the one used by Caret[7])

607 with mappings which preserve angle (conformal maps). Our

608 method will include a statistical test that warns the user if

609 the assumption of 2-D structure seems to be wrong.

610 We have not yet made use of radial profiles. While the radial profiles may be used &#8220;raw&#8221;, for laminar structures like the

611 cortex another strategy is to group together voxels in the same cortical layer; each surface pixel would then be associated

612 with one expression level per gene per layer. We will develop a segmentation algorithm to automatically identify the layer

613 boundaries.

614 Develop algorithms that find genetic markers for anatomical regions

615 We will develop scoring methods for evaluating how good individual genes are at marking areas. We will compare pointwise,

616 geometric, and information-theoretic measures. We already developed one entirely new scoring method (gradient similarity),

617 but we may develop more. Scoring measures that we will explore will include the L1 norm, correlation, expression energy

618 ratio, conditional entropy, gradient similarity, Jaccard similarity, Dice similarity, Hough transform, and statistical tests such

619 as Student&#8217;s t-test, and the Mann-Whitney U test (a non-parametric test). In addition, any predictive procedure induces a

620 scoring measure on genes by taking the prediction error when using that gene to predict the target.

621 Using some combination of these measures, we will develop a procedure to find single marker genes for anatomical regions:

622 for each cortical area, we will rank the genes by their ability to delineate each area.

623 Some cortical areas have no single marker genes but can be identified by combinatorial coding. This requires multivariate

624 scoring measures and feature selection procedures. Many of the measures, such as expression energy, gradient similarity,

625 Jaccard, Dice, Hough, Student&#8217;s t, and Mann-Whitney U are univariate. We will extend these scoring measures for use

626 in multivariate feature selection, that is, for scoring how well combinations of genes, rather than individual genes, can

627 distinguish a target area. There are existing multivariate forms of some of the univariate scoring measures, for example,

628 Hotelling&#8217;s T-square is a multivariate analog of Student&#8217;s t.

629 We will develop a feature selection procedure for choosing the best small set of marker genes for a given anatomical

630 area. In addition to using the scoring measures that we develop, we will also explore (a) feature selection using a stepwise

631 wrapper over &#8220;vanilla&#8221; predictive methods such as logistic regression, (b) predictive methods such as decision trees which

632 incrementally/greedily combine single gene markers into sets, and (c) predictive methods which use soft constraints to

633 minimize number of features used, such as sparse support vector machines.

634 todo

635 Some of these methods, such as the Hough transform, are designed to be resistant to registration error and error in the

636 anatomical map.

637 We will also consider extensions to scoring measures that may improve their robustness to registration error and to

638 error in the anatomical map; for example, a wrapper that runs a scoring method on small displacements and distortions

639 of the data adds robustness to registration error at the expense of computation time. It is possible that some areas in the

640 anatomical map do not correspond to natural domains of gene expression.

641 # Extend the procedure to handle difficult areas by combining or redrawing the boundaries: An area may be difficult to

642 identify because the boundaries are misdrawn, or because it does not &#8220;really&#8221; exist as a single area, at least on the genetic

643 level. We will develop extensions to our procedure which (a) detect when a difficult area could be fit if its boundary were

644 redrawn slightly, and (b) detect when a difficult area could be combined with adjacent areas to create a larger area which

645 can be fit.

646 A future publication on the method that we develop in Aim 1 will review the scoring measures and quantitatively compare

647 their performance in order to provide a foundation for future research of methods of marker gene finding. We will measure

648 the robustness of the scoring measures as well as their absolute performance on our dataset.

649 Decision trees todo

650 20.

651 # confirm with EMAGE, GeneAtlas, GENSAT, etc, to fight overfitting, two hemis

652 # mixture models, etc

653 Develop algorithms to suggest a division of a structure into anatomical parts

654 1.Explore dimensionality reduction algorithms applied to pixels: including TODO

655 2.Explore dimensionality reduction algorithms applied to genes: including TODO

656 3.Explore clustering algorithms applied to pixels: including TODO

657 4.Explore clustering algorithms applied to genes: including gene shaving, TODO

658 5.Develop an algorithm to use dimensionality reduction and/or hierarchial clustering to create anatomical maps

659 6.Run this algorithm on the cortex: present a hierarchial, genoarchitectonic map of the cortex

660 _________________________________________

661 20Already, for each cortical area, we have used the C4.5 algorithm to find a decision tree for that area. We achieved good classification accuracy

662 on our training set, but the number of genes that appeared in each tree was too large. We plan to implement a pruning procedure to generate

663 trees that use fewer genes

664 # Linear discriminant analysis

665 # jbt, coclustering

666 # self-organizing map

667 # Linear discriminant analysis

668 # compare using clustering scores

669 # multivariate gradient similarity

670 # deep belief nets

671 Apply these algorithms to the cortex

672 Using the methods developed in Aim 1, we will present, for each cortical area, a short list of markers to identify that

673 area; and we will also present lists of &#8220;panels&#8221; of genes that can be used to delineate many areas at once. Using the methods

674 developed in Aim 2, we will present one or more hierarchial cortical maps. We will identify and explain how the statistical

675 structure in the gene expression data led to any unexpected or interesting features of these maps, and we will provide

676 biological hypotheses to interpret any new cortical areas, or groupings of areas, which are discovered.

677 Timeline and milestones

678 Finding marker genes

679 &#x2219;September-November 2009: Develop an automated mechanism for segmenting the cortical voxels into layers

680 &#x2219;November 2009 (milestone): Have completed construction of a flatmapped, cortical dataset with information for each

681 layer

682 &#x2219;October 2009-April 2010: Develop scoring methods and to test them in various supervised learning frameworks. Also

683 test out various dimensionality reduction schemes in combination with supervised learning. create or extend supervised

684 learning frameworks which use multivariate versions of the best scoring methods.

685 &#x2219;January 2010 (milestone): Submit a publication on single marker genes for cortical areas

686 &#x2219;February-July 2010: Continue to develop scoring methods and supervised learning frameworks. Explore the best way

687 to integrate radial profiles with supervised learning. Explore the best way to make supervised learning techniques

688 robust against incorrect labels (i.e. when the areas drawn on the input cortical map are slightly off). Quantitatively

689 compare the performance of different supervised learning techniques. Validate marker genes found in the ABA dataset

690 by checking against other gene expression datasets. Create documentation and unit tests for software toolbox for Aim

691 1. Respond to user bug reports for Aim 1 software toolbox.

692 &#x2219;June 2010 (milestone): Submit a paper describing a method fulfilling Aim 1. Release toolbox.

693 &#x2219;July 2010 (milestone): Submit a paper describing combinations of marker genes for each cortical area, and a small

694 number of marker genes that can, in combination, define most of the areas at once

695 Revealing new ways to parcellate a structure into regions

696 &#x2219;June 2010-March 2011: Explore dimensionality reduction algorithms for Aim 2. Explore standard hierarchial clus-

697 tering algorithms, used in combination with dimensionality reduction, for Aim 2. Explore co-clustering algorithms.

698 Think about how radial profile information can be used for Aim 2. Adapt clustering algorithms to use radial profile

699 information. Quantitatively compare the performance of different dimensionality reduction and clustering techniques.

700 Quantitatively compare the value of different flatmapping methods and ways of representing radial profiles.

701 &#x2219;March 2011 (milestone): Submit a paper describing a method fulfilling Aim 2. Release toolbox.

702 &#x2219;February-May 2011: Using the methods developed for Aim 2, explore the genomic anatomy of the cortex. If new ways

703 of organizing the cortex into areas are discovered, read the literature and talk to people to learn about research related

704 to interpreting our results. Create documentation and unit tests for software toolbox for Aim 2. Respond to user bug

705 reports for Aim 2 software toolbox.

706 &#x2219;May 2011 (milestone): Submit a paper on the genomic anatomy of the cortex, using the methods developed in Aim 2

707 &#x2219;May-August 2011: Revisit Aim 1 to see if what was learned during Aim 2 can improve the methods for Aim 1. Follow

708 up on responses to our papers. Possibly submit another paper.

709 Bibliography &amp; References Cited

710 [1]Chris Adamson, Leigh Johnston, Terrie Inder, Sandra Rees, Iven Mareels, and Gary Egan. A Tracking Approach to

711 Parcellation of the Cerebral Cortex, volume Volume 3749/2005 of Lecture Notes in Computer Science, pages 294&#8211;301.

712 Springer Berlin / Heidelberg, 2005.

713 [2]J. Annese, A. Pitiot, I. D. Dinov, and A. W. Toga. A myelo-architectonic method for the structural classification of

714 cortical areas. NeuroImage, 21(1):15&#8211;26, 2004.

715 [3]Tanya Barrett, Dennis B. Troup, Stephen E. Wilhite, Pierre Ledoux, Dmitry Rudnev, Carlos Evangelista, Irene F.

716 Kim, Alexandra Soboleva, Maxim Tomashevsky, and Ron Edgar. NCBI GEO: mining tens of millions of expression

717 profiles&#8211;database and tools update. Nucl. Acids Res., 35(suppl_1):D760&#8211;765, 2007.

718 [4]George W. Bell, Tatiana A. Yatskievych, and Parker B. Antin. GEISHA, a whole-mount in situ hybridization gene

719 expression screen in chicken embryos. Developmental Dynamics, 229(3):677&#8211;687, 2004.

720 [5]James P Carson, Tao Ju, Hui-Chen Lu, Christina Thaller, Mei Xu, Sarah L Pallas, Michael C Crair, Joe Warren, Wah

721 Chiu, and Gregor Eichele. A digital atlas to characterize the mouse brain transcriptome. PLoS Comput Biol, 1(4):e41,

722 2005.

723 [6]Mark H. Chin, Alex B. Geng, Arshad H. Khan, Wei-Jun Qian, Vladislav A. Petyuk, Jyl Boline, Shawn Levy, Arthur W.

724 Toga, Richard D. Smith, Richard M. Leahy, and Desmond J. Smith. A genome-scale map of expression for a mouse

725 brain section obtained using voxelation. Physiol. Genomics, 30(3):313&#8211;321, August 2007.

726 [7]D C Van Essen, H A Drury, J Dickson, J Harwell, D Hanlon, and C H Anderson. An integrated software suite for surface-

727 based analyses of cerebral cortex. Journal of the American Medical Informatics Association: JAMIA, 8(5):443&#8211;59, 2001.

728 PMID: 11522765.

729 [8]Shiaoching Gong, Chen Zheng, Martin L. Doughty, Kasia Losos, Nicholas Didkovsky, Uta B. Schambra, Norma J.

730 Nowak, Alexandra Joyner, Gabrielle Leblanc, Mary E. Hatten, and Nathaniel Heintz. A gene expression atlas of the

731 central nervous system based on bacterial artificial chromosomes. Nature, 425(6961):917&#8211;925, October 2003.

732 [9]Jano Hemert and Richard Baldock. Matching Spatial Regions with Combinations of Interacting Gene Expression Pat-

733 terns, volume 13 of Communications in Computer and Information Science, pages 347&#8211;361. Springer Berlin Heidelberg,

734 2008.

735 [10]F. Kruggel, M. K. Brckner, Th. Arendt, C. J. Wiggins, and D. Y. von Cramon. Analyzing the neocortical fine-structure.

736 Medical Image Analysis, 7(3):251&#8211;264, September 2003.

737 [11]Erh-Fang Lee, Jyl Boline, and Arthur W. Toga. A High-Resolution anatomical framework of the neonatal mouse brain

738 for managing gene expression data. Frontiers in Neuroinformatics, 1:6, 2007. PMC2525996.

739 [12]Susan Magdaleno, Patricia Jensen, Craig L. Brumwell, Anna Seal, Karen Lehman, Andrew Asbury, Tony Cheung,

740 Tommie Cornelius, Diana M. Batten, Christopher Eden, Shannon M. Norland, Dennis S. Rice, Nilesh Dosooye, Sundeep

741 Shakya, Perdeep Mehta, and Tom Curran. BGEM: an in situ hybridization database of gene expression in the embryonic

742 and adult mouse nervous system. PLoS Biology, 4(4):e86 EP &#8211;, April 2006.

743 [13]Lydia Ng, Amy Bernard, Chris Lau, Caroline C Overly, Hong-Wei Dong, Chihchau Kuan, Sayan Pathak, Susan M

744 Sunkin, Chinh Dang, Jason W Bohland, Hemant Bokil, Partha P Mitra, Luis Puelles, John Hohmann, David J Anderson,

745 Ed S Lein, Allan R Jones, and Michael Hawrylycz. An anatomic gene expression atlas of the adult mouse brain. Nat

746 Neurosci, 12(3):356&#8211;362, March 2009.

747 [14]George Paxinos and Keith B.J. Franklin. The Mouse Brain in Stereotaxic Coordinates. Academic Press, 2 edition, July

748 2001.

749 [15]A. Schleicher, N. Palomero-Gallagher, P. Morosan, S. Eickhoff, T. Kowalski, K. Vos, K. Amunts, and K. Zilles. Quanti-

750 tative architectural analysis: a new approach to cortical mapping. Anatomy and Embryology, 210(5):373&#8211;386, December

751 2005.

752 [16]Oliver Schmitt, Lars Hmke, and Lutz Dmbgen. Detection of cortical transition regions utilizing statistical analyses of

753 excess masses. NeuroImage, 19(1):42&#8211;63, May 2003.

754 [17]Constance M. Smith, Jacqueline H. Finger, Terry F. Hayamizu, Ingeborg J. McCright, Janan T. Eppig, James A.

755 Kadin, Joel E. Richardson, and Martin Ringwald. The mouse gene expression database (GXD): 2007 update. Nucl.

756 Acids Res., 35(suppl_1):D618&#8211;623, 2007.

757 [18]Judy Sprague, Leyla Bayraktaroglu, Dave Clements, Tom Conlin, David Fashena, Ken Frazer, Melissa Haendel, Dou-

758 glas G Howe, Prita Mani, Sridhar Ramachandran, Kevin Schaper, Erik Segerdell, Peiran Song, Brock Sprunger, Sierra

759 Taylor, Ceri E Van Slyke, and Monte Westerfield. The zebrafish information network: the zebrafish model organism

760 database. Nucleic Acids Research, 34(Database issue):D581&#8211;5, 2006. PMID: 16381936.

761 [19]Larry Swanson. Brain Maps: Structure of the Rat Brain. Academic Press, 3 edition, November 2003.

762 [20]Carol L. Thompson, Sayan D. Pathak, Andreas Jeromin, Lydia L. Ng, Cameron R. MacPherson, Marty T. Mortrud,

763 Allison Cusick, Zackery L. Riley, Susan M. Sunkin, Amy Bernard, Ralph B. Puchalski, Fred H. Gage, Allan R. Jones,

764 Vladimir B. Bajic, Michael J. Hawrylycz, and Ed S. Lein. Genomic anatomy of the hippocampus. Neuron, 60(6):1010&#8211;

765 1021, December 2008.

766 [21]Pavel Tomancak, Amy Beaton, Richard Weiszmann, Elaine Kwan, ShengQiang Shu, Suzanna E Lewis, Stephen

767 Richards, Michael Ashburner, Volker Hartenstein, Susan E Celniker, and Gerald M Rubin. Systematic determina-

768 tion of patterns of gene expression during drosophila embryogenesis. Genome Biology, 3(12):research008818814, 2002.

769 PMC151190.

770 [22]Jano van Hemert and Richard Baldock. Mining Spatial Gene Expression Data for Association Rules, volume 4414/2007

771 of Lecture Notes in Computer Science, pages 66&#8211;76. Springer Berlin / Heidelberg, 2007.

772 [23]Shanmugasundaram Venkataraman, Peter Stevenson, Yiya Yang, Lorna Richardson, Nicholas Burton, Thomas P. Perry,

773 Paul Smith, Richard A. Baldock, Duncan R. Davidson, and Jeffrey H. Christiansen. EMAGE edinburgh mouse atlas

774 of gene expression: 2008 update. Nucl. Acids Res., 36(suppl_1):D860&#8211;865, 2008.

775 [24]Axel Visel, Christina Thaller, and Gregor Eichele. GenePaint.org: an atlas of gene expression patterns in the mouse

776 embryo. Nucl. Acids Res., 32(suppl_1):D552&#8211;556, 2004.

777 [25]Robert H Waterston, Kerstin Lindblad-Toh, Ewan Birney, Jane Rogers, Josep F Abril, Pankaj Agarwal, Richa Agar-

778 wala, Rachel Ainscough, Marina Alexandersson, Peter An, Stylianos E Antonarakis, John Attwood, Robert Baertsch,

779 Jonathon Bailey, Karen Barlow, Stephan Beck, Eric Berry, Bruce Birren, Toby Bloom, Peer Bork, Marc Botcherby,

780 Nicolas Bray, Michael R Brent, Daniel G Brown, Stephen D Brown, Carol Bult, John Burton, Jonathan Butler,

781 Robert D Campbell, Piero Carninci, Simon Cawley, Francesca Chiaromonte, Asif T Chinwalla, Deanna M Church,

782 Michele Clamp, Christopher Clee, Francis S Collins, Lisa L Cook, Richard R Copley, Alan Coulson, Olivier Couronne,

783 James Cuff, Val Curwen, Tim Cutts, Mark Daly, Robert David, Joy Davies, Kimberly D Delehaunty, Justin Deri,

784 Emmanouil T Dermitzakis, Colin Dewey, Nicholas J Dickens, Mark Diekhans, Sheila Dodge, Inna Dubchak, Diane M

785 Dunn, Sean R Eddy, Laura Elnitski, Richard D Emes, Pallavi Eswara, Eduardo Eyras, Adam Felsenfeld, Ginger A

786 Fewell, Paul Flicek, Karen Foley, Wayne N Frankel, Lucinda A Fulton, Robert S Fulton, Terrence S Furey, Diane Gage,

787 Richard A Gibbs, Gustavo Glusman, Sante Gnerre, Nick Goldman, Leo Goodstadt, Darren Grafham, Tina A Graves,

788 Eric D Green, Simon Gregory, Roderic Guig, Mark Guyer, Ross C Hardison, David Haussler, Yoshihide Hayashizaki,

789 LaDeana W Hillier, Angela Hinrichs, Wratko Hlavina, Timothy Holzer, Fan Hsu, Axin Hua, Tim Hubbard, Adrienne

790 Hunt, Ian Jackson, David B Jaffe, L Steven Johnson, Matthew Jones, Thomas A Jones, Ann Joy, Michael Kamal,

791 Elinor K Karlsson, Donna Karolchik, Arkadiusz Kasprzyk, Jun Kawai, Evan Keibler, Cristyn Kells, W James Kent,

792 Andrew Kirby, Diana L Kolbe, Ian Korf, Raju S Kucherlapati, Edward J Kulbokas, David Kulp, Tom Landers, J P

793 Leger, Steven Leonard, Ivica Letunic, Rosie Levine, Jia Li, Ming Li, Christine Lloyd, Susan Lucas, Bin Ma, Donna R

794 Maglott, Elaine R Mardis, Lucy Matthews, Evan Mauceli, John H Mayer, Megan McCarthy, W Richard McCombie,

795 Stuart McLaren, Kirsten McLay, John D McPherson, Jim Meldrim, Beverley Meredith, Jill P Mesirov, Webb Miller,

796 Tracie L Miner, Emmanuel Mongin, Kate T Montgomery, Michael Morgan, Richard Mott, James C Mullikin, Donna M

797 Muzny, William E Nash, Joanne O Nelson, Michael N Nhan, Robert Nicol, Zemin Ning, Chad Nusbaum, Michael J

798 O&#8217;Connor, Yasushi Okazaki, Karen Oliver, Emma Overton-Larty, Lior Pachter, Gens Parra, Kymberlie H Pepin, Jane

799 Peterson, Pavel Pevzner, Robert Plumb, Craig S Pohl, Alex Poliakov, Tracy C Ponce, Chris P Ponting, Simon Potter,

800 Michael Quail, Alexandre Reymond, Bruce A Roe, Krishna M Roskin, Edward M Rubin, Alistair G Rust, Ralph San-

801 tos, Victor Sapojnikov, Brian Schultz, Jrg Schultz, Matthias S Schwartz, Scott Schwartz, Carol Scott, Steven Seaman,

802 Steve Searle, Ted Sharpe, Andrew Sheridan, Ratna Shownkeen, Sarah Sims, Jonathan B Singer, Guy Slater, Arian

803 Smit, Douglas R Smith, Brian Spencer, Arne Stabenau, Nicole Stange-Thomann, Charles Sugnet, Mikita Suyama,

804 Glenn Tesler, Johanna Thompson, David Torrents, Evanne Trevaskis, John Tromp, Catherine Ucla, Abel Ureta-Vidal,

805 Jade P Vinson, Andrew C Von Niederhausern, Claire M Wade, Melanie Wall, Ryan J Weber, Robert B Weiss, Michael C

806 Wendl, Anthony P West, Kris Wetterstrand, Raymond Wheeler, Simon Whelan, Jamey Wierzbowski, David Willey,

807 Sophie Williams, Richard K Wilson, Eitan Winter, Kim C Worley, Dudley Wyman, Shan Yang, Shiaw-Pyng Yang,

808 Evgeny M Zdobnov, Michael C Zody, and Eric S Lander. Initial sequencing and comparative analysis of the mouse

809 genome. Nature, 420(6915):520&#8211;62, December 2002. PMID: 12466850.

810

811