https://gcat.davidson.edu/GcatWiki/index.php?action=history&feed=atom&title=Notes_2%2F9%2F16 2026-05-18T13:03:03Z Revision history for this page on the wiki MediaWiki 1.28.2 https://gcat.davidson.edu/GcatWiki/index.php?title=Notes_2/9/16&diff=18054&oldid=prev 2016-02-09T19:41:05Z

<p>Created page with &quot;&#039;&#039;&#039;Clustering&#039;&#039;&#039;: grouping like items together &#039;&#039;&#039;Why cluster?&#039;&#039;&#039; Allows us to analyze representative data points, not the whole data set Just graphing expression levels m...&quot;</p> <p><b>New page</b></p><div>'''Clustering''': grouping like items together<br /> <br /> '''Why cluster?'''<br /> <br /> Allows us to analyze representative data points, not the whole data set <br /> <br /> Just graphing expression levels makes it easy to see induction but harder to see repression....if you use the log are able to see both induction and repression of genes...allows you to see some sort of coregulation <br /> <br /> for clustering do we want to cluster opposites too or only similar (probably want opposites too because shows coregulation <br /> <br /> '''Proximity Measures'''<br /> <br /> many ways of measuring relationship between things <br /> <br /> '''Linkage Methods'''<br /> <br /> find average or central part of cluster and compare that &quot;fake point&quot; with the other point <br /> <br /> only going to let in if close to everyone (max)<br /> <br /> only going to let in if close to someone (min)<br /> <br /> '''Hierarchical Clustering'''<br /> <br /> What we are seeing with our results from DeSeq<br /> <br /> How we do it: find the most similar genes, join net two most similar objects, repeat until all genes have been joined starting at 1 correlation and stopping at -1 (can't ever be pulled apart no matter what you find in the rest of the data<br /> <br /> Cutting the Tree: group together all the things that are still joined when you draw a line through the tree, big question: WHERE DO YOU CUT THE TREE?!?!<br /> <br /> '''K-means Clustering'''<br /> <br /> Specify how many clusters to form <br /> <br /> randomly assign each gene to one of k different clusters (how do you know what number of clusters to make) then group so similar to each other <br /> <br /> '''Supervised Clustering'''<br /> <br /> Find genes in expression file whose patterns are highly similar to a desired gene or pattern <br /> <br /> could define a pattern and then use data to pull in all those genes that are like that pattern <br /> <br /> '''Quality Clustering'''<br /> <br /> Each gene builds a supervised cluster (how big is the group going to be and how similar does it have to be to join) <br /> have some rule about what makes the best cluster, decided to take the one with the biggest number</div>

Ktsmith