1.1 --- a/grant.html Tue Apr 21 05:34:25 2009 -0700 1.2 +++ b/grant.html Tue Apr 21 05:38:52 2009 -0700 1.3 @@ -660,36 +660,33 @@ 1.4 structure in the gene expression data led to any unexpected or interesting features of these maps. 1.5 Timeline and milestones 1.6 Aim 1 1.7 -∙Oct-Nov 2009: develop an automated mechanism for segmenting the cortical voxels into layers 1.8 -∙Nov 2009 (milestone): a preliminary automated mechanism for segmenting the cortical voxels into layers 1.9 -∙Oct 2009-Feb 2010: develop scoring methods and to test them in various supervised learning frameworks. Also test 1.10 -out various dimensionality reduction schemes in combination with supervised learning. 1.11 -∙Dec 2009-April 2010: create or extend supervised learning frameworks which use multivariate versions of the best 1.12 -scoring methods 1.13 +∙October-November 2009: develop an automated mechanism for segmenting the cortical voxels into layers 1.14 +∙November 2009 (milestone): a preliminary automated mechanism for segmenting the cortical voxels into layers 1.15 +∙October 2009-April 2010: develop scoring methods and to test them in various supervised learning frameworks. Also 1.16 +test out various dimensionality reduction schemes in combination with supervised learning. create or extend supervised 1.17 +learning frameworks which use multivariate versions of the best scoring methods. 1.18 ∙January 2010 (milestone): submit a publication on single marker genes for cortical areas 1.19 -∙February-June 2010: explore the best way to integrate radial profiles with supervised learning. Explore the best way 1.20 -to make supervised learning techniques robust against incorrect labels (i.e. when the areas drawn on the input cortical 1.21 -map are slightly off). Quantitatively compare the performance of different supervised learning techniques. 1.22 -∙May-July 2010: Validate marker genes found in the ABA dataset by checking against other gene expression datasets 1.23 -∙June 2010: submit a paper describing a method fulfilling Aim 1 1.24 -∙July 2010: submit a paper describing combinations of marker genes for each cortical area, and a small number of 1.25 -marker genes that can, in combination, define most of the areas at once 1.26 -∙April-July 2010: create documentation and unit tests for software toolbox for Aim 1. 1.27 -∙August 2010-: respond to user bug reports for Aim 1 software toolbox. 1.28 +∙February-July 2010: Continue to develop scoring methods and supervised learning frameworks. Explore the best way 1.29 +to integrate radial profiles with supervised learning. Explore the best way to make supervised learning techniques 1.30 +robust against incorrect labels (i.e. when the areas drawn on the input cortical map are slightly off). Quantitatively 1.31 +compare the performance of different supervised learning techniques. Validate marker genes found in the ABA dataset 1.32 +by checking against other gene expression datasets. Create documentation and unit tests for software toolbox for Aim 1.33 +1. Respond to user bug reports for Aim 1 software toolbox. 1.34 +∙June 2010 (milestone): submit a paper describing a method fulfilling Aim 1. Release toolbox. 1.35 +∙July 2010 (milestone): submit a paper describing combinations of marker genes for each cortical area, and a small 1.36 +number of marker genes that can, in combination, define most of the areas at once 1.37 Aim 2 1.38 -∙April-September 2010: explore dimensionality reduction algorithms for Aim 2 1.39 -∙June-November 2010: explore standard hierarchial clustering algorithms, used in combination with dimensionality 1.40 -reduction, for Aim 2 1.41 -∙July-December 2010: explore co-clustering algorithms. Think about how radial profile information can be used for 1.42 -Aim 2. Adapt clustering algorithms to use radial profile information. 1.43 +∙April-September 2010: Explore dimensionality reduction algorithms for Aim 2. Explore standard hierarchial clus- 1.44 +tering algorithms, used in combination with dimensionality reduction, for Aim 2. Explore co-clustering algorithms. 1.45 +Think about how radial profile information can be used for Aim 2. Adapt clustering algorithms to use radial profile 1.46 +information. 1.47 ∙January-March 2011: Quantitatively compare the performance of different dimensionality reduction and clustering 1.48 techniques. Quantitatively compare the value of different flatmapping methods and ways of representing radial profiles. 1.49 -∙January-June 2011: using the methods developed for Aim 2, explore the genomic anatomy of the cortex. Read the 1.50 -literature and talk to people to learn about research related to unexpected and interesting discoveries. 1.51 -∙February-May 2011: create documentation and unit tests for software toolbox for Aim 2. 1.52 -∙June 2011-: respond to user bug reports for Aim 1 software toolbox. 1.53 -∙March 2011: submit a paper describing a method fulfilling Aim 2 1.54 -∙May 2011: submit a paper on the genomic anatomy of the cortex, using the methods developed in Aim 2 1.55 +∙March 2011 (milestone): submit a paper describing a method fulfilling Aim 2. Release toolbox. 1.56 +∙February-May 2011: Using the methods developed for Aim 2, explore the genomic anatomy of the cortex. Read 1.57 +the literature and talk to people to learn about research related to unexpected and interesting discoveries. Create 1.58 +documentation and unit tests for software toolbox for Aim 2. Respond to user bug reports for Aim 1 software toolbox. 1.59 +∙May 2011 (milestone): submit a paper on the genomic anatomy of the cortex, using the methods developed in Aim 2 1.60 ∙May-August 2011: revisit Aim 1 to see if what was learned during Aim 2 can improve the methods for Aim 1. 1.61 Bibliography & References Cited 1.62 [1]Chris Adamson, Leigh Johnston, Terrie Inder, Sandra Rees, Iven Mareels, and Gary Egan. A Tracking Approach to