cg

changeset 105:6c48f37d0f0c

.
author bshanks@bshanks.dyndns.org
date Wed Apr 22 07:39:32 2009 -0700 (16 years ago)
parents d6ecbc494f0b
children ffa1390e4f39
files grant.doc grant.html grant.odt grant.pdf grant.txt
line diff
1.1 Binary file grant.doc has changed
2.1 --- a/grant.html Wed Apr 22 07:35:14 2009 -0700 2.2 +++ b/grant.html Wed Apr 22 07:39:32 2009 -0700 2.3 @@ -33,9 +33,8 @@ 2.4 ______________ 2.5 The Challenge and Potential impact 2.6 Each of our three aims will be discussed in turn. For each aim, we will develop a conceptual framework for 2.7 -thinking about the task, and we will present our strategy for solving it. Next we will discuss related work. At the 2.8 -conclusion of each section, we will summarize why our strategy is different from what has been done before. At 2.9 -the end of this section, we will describe the potential impact. 2.10 +thinking about the task. Next we will discuss related work, and then summarize why our strategy is different from 2.11 +what has been done before. After we have discussed all three aims, we will describe the potential impact. 2.12 Aim 1: Given a map of regions, find genes that mark the regions 2.13 Machine learning terminology: classifiers The task of looking for marker genes for known anatomical regions 2.14 means that one is looking for a set of genes such that, if the expression level of those genes is known, then the 2.15 @@ -73,8 +72,8 @@ 2.16 Both gene expression data and anatomical atlases have errors, due to a variety of factors. Individual subjects 2.17 have idiosyncratic anatomy. Subjects may be improperly registered to the atlas. The method used to measure 2.18 gene expression may be noisy. The atlas may have errors. It is even possible that some areas in the anatomical 2.19 +atlas are “wrong” in that they do not have the same shape as the natural domains of gene expression to which 2.20 1Strictly speaking, the features are gene expression levels, but we’ll call them genes. 2.21 -atlas are “wrong” in that they do not have the same shape as the natural domains of gene expression to which 2.22 they correspond. These sources of error can affect the displacement and the shape of both the gene expression 2.23 data and the anatomical target areas. Therefore, it is important to use feature selection methods which are 2.24 robust to these kinds of errors.
3.1 Binary file grant.odt has changed
4.1 Binary file grant.pdf has changed
5.1 --- a/grant.txt Wed Apr 22 07:35:14 2009 -0700 5.2 +++ b/grant.txt Wed Apr 22 07:39:32 2009 -0700 5.3 @@ -52,7 +52,7 @@ 5.4 \vspace{0.3cm}\hrule 5.5 == The Challenge and Potential impact == 5.6 5.7 -Each of our three aims will be discussed in turn. For each aim, we will develop a conceptual framework for thinking about the task, and we will present our strategy for solving it. Next we will discuss related work. At the conclusion of each section, we will summarize why our strategy is different from what has been done before. At the end of this section, we will describe the potential impact. 5.8 +Each of our three aims will be discussed in turn. For each aim, we will develop a conceptual framework for thinking about the task. Next we will discuss related work, and then summarize why our strategy is different from what has been done before. After we have discussed all three aims, we will describe the potential impact. 5.9 5.10 === Aim 1: Given a map of regions, find genes that mark the regions === 5.11