# HG changeset patch # User bshanks@bshanks.dyndns.org # Date 1239505141 25200 # Node ID 075618f574d81f402278963faa1e5bb9e80ce740 # Parent 3c874c1cd8379e10a65459f0634ed81d1fccaaf9 . --- a/grant.html Sat Apr 11 19:53:38 2009 -0700 +++ b/grant.html Sat Apr 11 19:59:01 2009 -0700 @@ -1,6 +1,5 @@ Specific aims - todo2 - Massive new datasets obtained with techniques such as in situ hybridization + Massive new datasets obtained with techniques such as in situ hybridization (ISH) and BAC-transgenics allow the expression levels of many genes at many locations to be compared. Our goal is to develop automated methods to relate spatial variation in gene expression to anatomy. We want to find marker genes @@ -35,10 +34,10 @@ determine to which subregion each voxel within the structure belongs. We call this a classification task, because each voxel is being assigned to a class (namely, its subregion). - 1 - Therefore, an understanding of the relationship between the combination of their expression levels and the locations of the subregions may be expressed as + 1 + a function. The input to this function is a voxel, along with the gene expression levels within that voxel; the output is the subregional identity of the target voxel, that is, the subregion to which the target voxel belongs. We call this @@ -80,11 +79,11 @@ Key questions when choosing a learning method are: What are the instances? What are the features? How are the features chosen? Here are four principles that outline our answers to these questions. - 2 - Principle 1: Combinatorial gene expression Above, we defined an “instance” as the combination of a voxel with the “asso- ciated gene expression data”. In our case this refers to the expression level of + 2 + genes within the voxel, but should we include the expression levels of all genes, or only a few of them? It is too much to hope that every anatomical region of interest will be iden- @@ -122,10 +121,10 @@ the analysis algorithm to take advantage of this prior knowledge. In addition, it is easier for humans to visualize and work with 2-D data. Therefore, when possible, the instances should represent pixels, not voxels. - 3 - Aim 2 todo + 3 + Aim 3 Background The cortex is divided into areas and layers. To a first approximation, the par- @@ -165,11 +164,11 @@ day cortical maps was driven by the application of histological stains. It is conceivable that if a different set of stains had been available which identified a different set of features, then the today’s cortical maps would have come out - 4 - differently. Since the number of classes of stains is small compared to the number of genes, it is likely that there are many repeated, salient spatial patterns in the gene expression which have not yet been captured by any stain. Therefore, + 4 + current ideas about cortical anatomy need to incorporate what we can learn from looking at the patterns of gene expression. While we do not here propose to analyze human gene expression data, it is @@ -200,7 +199,9 @@ expression profiles. We achieved classification accuracy of about 81%3. As noted above, however, a classifier that looks at all the genes at once isn’t practically useful. -_____________________ + The requirement to find combinations of only a small number of genes limits + us from straightforwardly applying many of the most simple techniques from +__________________________ 1“WW, C2 and coiled-coil domain containing 1”; EntrezGene ID 211652 2“mitochondrial translational initiation factor 2”; EntrezGene ID 76784 3Using the Shogun SVM package (todo:cite), with parameters type=GMNPSVM (multi- @@ -221,8 +222,13 @@ expression and blue meaning little. 6 - The requirement to find combinations of only a small number of genes limits - us from straightforwardly applying many of the most simple techniques from + + + Figure 2: The top row shows the three genes which (individually) best predict + area AUD, according to logistic regression. The bottom row shows the three + genes which (individually) best match area AUD, according to gradient similar- + ity. From left to right and top to bottom, the genes are Ssr1, Efcbp1, Aph1a, + Ptk7, Aph1a again, and Lepr the field of supervised machine learning. In the parlance of machine learning, our task combines feature selection with supervised learning. Principle 3: Use geometry @@ -240,6 +246,16 @@ may be particularly good markers. None of these genes are, individually, a perfect marker for AUD; we deliberately chose a “difficult” area in order to better contrast pointwise with geometric methods. +__________________________ + 4For each gene, a logistic regression in which the response variable was whether or not a +surface pixel was within area AUD, and the predictor 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 they predict area AUD. + 5For each gene the gradient similarity (see section ??) between (a) a map of the expression +of each gene on the cortical surface and (b) the shape of area AUD, was calculated, and this +was used to rank the genes. + 7 + Principle 4: Work in 2-D whenever possible In anatomy, the manifold of interest is usually either defined by a combination of two relevant anatomical axes (todo), or by the surface of the structure (as is @@ -257,23 +273,6 @@ the method we develop to include a statistical test that warns the user if the assumption of 2-D structure seems to be wrong. —— -____________________ - 4For each gene, a logistic regression in which the response variable was whether or not a -surface pixel was within area AUD, and the predictor 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 they predict area AUD. - 5For each gene the gradient similarity (see section ??) between (a) a map of the expression -of each gene on the cortical surface and (b) the shape of area AUD, was calculated, and this -was used to rank the genes. - 7 - - - - Figure 2: The top row shows the three genes which (individually) best predict - area AUD, according to logistic regression. The bottom row shows the three - genes which (individually) best match area AUD, according to gradient similar- - ity. From left to right and top to bottom, the genes are Ssr1, Efcbp1, Aph1a, - Ptk7, Aph1a again, and Lepr Massive new datasets obtained with techniques such as in situ hybridization (ISH) and BAC-transgenics allow the expression levels of many genes at many locations to be compared. This can be used to find marker genes for specific @@ -296,10 +295,10 @@ datasets will be made available in both MATLAB and Caret formats. (5) validate the methods developed in (1), (2) and (3) by applying them to the cerebral cortex datasets created in (4) - 8 - All algorithms that we develop will be implemented in an open-source soft- ware toolkit. The toolkit, as well as the machine-readable datasets developed in + 8 + aim (4) and any other intermediate dataset we produce, will be published and freely available for others to use. In addition to developing generally useful methods, the application of these @@ -341,11 +340,11 @@ as a testbed. The Allen Brain Atlas has collected a dataset containing the expression level of about 4000 genes* over a set of over 150000 voxels, with a spatial resolution of approximately 200 microns[?]. + We expect to discover sets of marker genes that pick out specific cortical +areas. This will allow the development of drugs and other interventions that +selectively target individual cortical areas. Therefore our research will lead 9 - We expect to discover sets of marker genes that pick out specific cortical - areas. This will allow the development of drugs and other interventions that - selectively target individual cortical areas. Therefore our research will lead to application in drug discovery, in the development of other targeted clinical interventions, and in the development of new experimental techniques. The best way to divide up rodent cortex into areas has not been completely @@ -389,11 +388,11 @@ in our publications . We also expect to weigh in on the debate about how to best partition rodent cortex - 10 - be useful for drug discovery as well * Another 16000 genes are available, but they do not cover the entire cerebral cortex with high spatial resolution. + 10 + User-definable ROIs Combinatorial gene expression Negative as well as pos- itive signal Use geometry Search for local boundaries if necessary Flatmapped Specific aims @@ -428,10 +427,10 @@ matically find the cortical layer boundaries. 4. Run the procedures that we developed on the cortex: we will present, for each area, a short list of markers to identify that area; and we will also - 11 - present lists of “panels” of genes that can be used to delineate many areas at once. + 11 + Develop algorithms to suggest a division of a structure into anatom- ical parts 1. Explore dimensionality reduction algorithms applied to pixels: including @@ -472,12 +471,12 @@ Finder then looks for genes which can distinguish the ROI from the comparator region. Specifically, it finds genes for which the ratio (expression energy in the ROI) / (expression energy in the comparator region) is high. - 12 - Informally, the Gene Finder first infers an ROI based on clustering the seed voxel with other voxels. Then, the Gene Finder finds genes which overexpress in the ROI as compared to other voxels in the major anatomical region. There are three major differences between our approach and Gene Finder. + 12 + First, Gene Finder focuses on individual genes and individual ROIs in isola- tion. This is great for regions which can be picked out from all other regions by a single gene, but not all of them can (todo). There are at least two ways this can @@ -520,12 +519,12 @@ posal. The goal of AGEA’s hierarchial clustering is to generate a binary tree of clusters, where a cluster is a collection of voxels. AGEA begins by computing the Pearson correlation between each pair of voxels. They then employ a recur- - 13 - sive divisive (top-down) hierarchial clustering procedure on the voxels, which means that they start with all of the voxels, and then they divide them into clus- ters, and then within each cluster, they divide that cluster into smaller clusters, etc***. At each step, the collection of voxels is partitioned into two smaller + 13 + clusters in a way that maximizes the following quantity: average correlation between all possible pairs of voxels containing one voxel from each cluster. There are three major differences between our approach and AGEA’s hier- @@ -568,12 +567,12 @@ the performance of our techniques against AGEA’s. Another difference between our techniques and AGEA’s is that AGEA allows the user to enter only a voxel location, and then to either explore the rest of - 14 - the brain’s relationship to that particular voxel, or explore a partitioning of the brain based on pairwise voxel correlation. If the user is interested not in a single voxel, but rather an entire anatomical structure, AGEA will only succeed to the extent that the selected voxel is a typical representative of the structure. + 14 + As discussed in the previous paragraph, this poses problems for structures like cortical areas, which (because of their division into cortical layers) do not have a single “typical representative”. @@ -616,12 +615,12 @@ Despite the distinct roles of different cortical areas in both normal function- ing and disease processes, there are no known marker genes for many cortical areas. This project will be immediately useful for both drug discovery and clini- - 15 - cal research because once the markers are known, interventions can be designed which selectively target specific cortical areas. This techniques we develop will be useful because they will be applicable to the analysis of other anatomical areas, both in terms of finding marker genes + 15 + for known areas, and in terms of suggesting new anatomical subdivisions that are based upon the gene expression data. _______________________________ @@ -659,12 +658,12 @@ able to import and export data to standard formats so that users can use our software in tandem with other software tools created by other teams. We will support the following formats: NIFTI (Neuroimaging Informatics Technology +Initiative), SEV (Allen Brain Institute Smoothed Energy Volume), and MAT- +LAB. This ensures that our users will not have to exclusively rely on our tools +when analyzing data. For example, users will be able to use the data visualiza- +tion and analysis capabilities of MATLAB and Caret alongside our software. 16 - Initiative), SEV (Allen Brain Institute Smoothed Energy Volume), and MAT- - LAB. This ensures that our users will not have to exclusively rely on our tools - when analyzing data. For example, users will be able to use the data visualiza- - tion and analysis capabilities of MATLAB and Caret alongside our software. To our knowledge, there is no currently available software to convert between these formats, so we will also provide a format conversion tool. This may be useful even for groups that don’t use any of our other software. @@ -706,13 +705,13 @@ combination of genes are expressed, the local tissue is probably part of a certain subregion. This means that we can then confidentally develop an intervention which is triggered only when that combination of genes are expressed; and to - 17 - the extent that the result procedure is reliable, we know that the intervention will only be triggered in the target subregion. We said that the result procedure provides “a way to use the gene expression profiles of voxels in a tissue sample” in order to “determine where the subregions are”. + 17 + Does the result procedure get as input all of the gene expression profiles of each voxel in the entire tissue sample, and produce as output all of the subregional boundaries all at once? @@ -752,12 +751,12 @@ if multiple subregions are present, where they each are. Or it can be used indirectly; imagine that the result procedure tells us that whenever a certain combination of genes are expressed, the local tissue is probably part of a certain - 18 - subregion. This means that we can then confidentally develop an intervention which is triggered only when that combination of genes are expressed; and to the extent that the result procedure is reliable, we know that the intervention will only be triggered in the target subregion. + 18 + We said that the result procedure provides “a way to use the gene expression profiles of voxels in a tissue sample” in order to “determine where the subregions are”. Binary file grant.odt has changed --- a/grant.txt Sat Apr 11 19:53:38 2009 -0700 +++ b/grant.txt Sat Apr 11 19:59:01 2009 -0700 @@ -1,7 +1,5 @@ == Specific aims == -todo2 - Massive new datasets obtained with techniques such as in situ hybridization (ISH) and BAC-transgenics allow the expression levels of many genes at many locations to be compared. Our goal is to develop automated methods to relate spatial variation in gene expression to anatomy. We want to find marker genes for specific anatomical regions, and also to draw new anatomical maps based on gene expression patterns. We have three specific aims: (1) develop an algorithm to screen spatial gene expression data for combinations of marker genes which selectively target anatomical regions