<p style="TEXT-INDENT: 0cm; MARGIN: 0cm 0cm 0pt; mso-char-indent-count: 0" class="MsoNormal"><span lang="EN-US"><font size="3" face="Times New Roman">Thanks for per and yark.</font></span></p>
<div style="MARGIN: 0cm 0cm 0pt" class="MsoNormal"><span lang="EN-US"><font size="3" face="Times New Roman"></font></span> </div>
<div style="MARGIN: 0cm 0cm 0pt" class="MsoNormal"><span lang="EN-US"><font size="3" face="Times New Roman">We know that Rotman toolbox is a good candidate to do PLS analysis in neuroimaging, but we always hope we can do it in pymvpa framework because it is simple and easy to use.</font></span></div>
<div style="MARGIN: 0cm 0cm 0pt" class="MsoNormal"><span lang="EN-US"><font size="3" face="Times New Roman"></font></span> </div>
<div style="MARGIN: 0cm 0cm 0pt" class="MsoNormal"><span lang="EN-US"><font size="3" face="Times New Roman">In our situations, generally, there are two groups of variables, one group is multi-voxel/vertex/region pattern, and the other group is a set of scores from a group of behavior tests. Our target was to test whether the two group variables are relevant (correlated) with PLS, i.e., whether the neural patterns can predict these behaviors. If they show high relevant, we also want o know what are the contribution of each voxel and behavior score to the correlation. Furthermore, we will do cross-validation for the PLS model.</font></span></div>
<p style="MARGIN: 0cm 0cm 0pt" class="MsoNormal"><span lang="EN-US"><font size="3" face="Times New Roman">The multi-voxel/region pattern may derive from MRI, fMRI, rfMRI or DTI. For example, we can test whether the thickness pattern of brain can predict subjects’ attention abilities which are test by a group attention paradigm such as flanker, alert, top-down and bottom-up test.</font></span></p>
<div style="MARGIN: 0cm 0cm 0pt" class="MsoNormal"><span lang="EN-US"><font size="3" face="Times New Roman"></font></span> </div>
<div style="MARGIN: 0cm 0cm 0pt" class="MsoNormal"><span lang="EN-US"><font size="3" face="Times New Roman">For PLS applications in neuroimaging, there is a good tutorial to start. The link as bellow:</font></span></div>
<p style="MARGIN: 0cm 0cm 0pt" class="MsoNormal"><span lang="EN-US"><font size="3" face="Times New Roman">A Krishnan, et al, 2010. Partial Least Squares (PLS) methods for neuroimaging: A tutorial and review, NeuroImage.</font></span></p>
<p style="TEXT-INDENT: 0cm; MARGIN: 0cm 0cm 0pt; mso-char-indent-count: 0" class="MsoNormal"><span lang="EN-US"><a href="http://linkinghub.elsevier.com/retrieve/pii/S1053811910010074"><span style="mso-ascii-font-family: 'Times New Roman'; mso-hansi-font-family: 'Times New Roman'; mso-bidi-font-family: 'Times New Roman'; mso-bidi-theme-font: minor-bidi"><font size="3">http://linkinghub.elsevier.com/retrieve/pii/S1053811910010074</font></span></a></span></p>
<p style="TEXT-INDENT: 0cm; MARGIN: 0cm 0cm 0pt; mso-char-indent-count: 0" class="MsoNormal"><span lang="EN-US"><font size="3" face="Times New Roman"> </font></span></p>
<p style="TEXT-INDENT: 0cm; MARGIN: 0cm 0cm 0pt; mso-char-indent-count: 0" class="MsoNormal"><span lang="EN-US"><font size="3" face="Times New Roman"> </font></span></p>
<p style="TEXT-INDENT: 0cm; MARGIN: 0cm 0cm 0pt; mso-char-indent-count: 0" class="MsoNormal"><span lang="EN-US"><font size="3" face="Times New Roman">Zonglei</font></span></p><br><br>
<div class="gmail_quote">2011/5/12 Yaroslav Halchenko <span dir="ltr"><<a href="mailto:debian@onerussian.com">debian@onerussian.com</a>></span><br>
<blockquote style="BORDER-LEFT: #ccc 1px solid; MARGIN: 0px 0px 0px 0.8ex; PADDING-LEFT: 1ex" class="gmail_quote">Hi Per, Hi Zhen,<br><br>actually I think things are not that hopeless ;-)<br><br>PLS has been implemented in scikits.learn, so, most probably, there is<br>
no need to reimplement it, unless you see some obvious drawbacks in<br>scikits.learn implementation(s)? on PyMVPA side we have started<br>implementing a basic adapter to make scikits.learn machinery<br>easily pluggable within PyMVPA. So, theoretically, you could already<br>
started playing with something like<br><br>from scikits.learn.pls import PLSRegression as sklPLSRegression<br>pls = SKLLearnerAdapter(sklPLSRegression())<br><br>so pls should look like a regular PyMVPA learner.<br><br>But could you please very briefly describe what kind of a task you are<br>
looking for to tackle with PLS, e.g. what would be your "targets" and where<br>within processing pipeline PLS would need to be used?<br>
<div class="im"><br>On Wed, 11 May 2011, Per B. Sederberg wrote:<br>> Hi Zonglei:<br><br>> I started to implement PLS in PyMVPA now almost 3 years ago, but never<br>> finished. I still think it would be a good addition, but I don't have<br>
> time to finish it up. I'd love to replicate a good bit of the PLS<br>> functionality from the Rotman toolbox:<br><br>> <a href="http://www.rotman-baycrest.on.ca/index.php?section=84" target="_blank">http://www.rotman-baycrest.on.ca/index.php?section=84</a><br>
<br>> So, to my knowledge, there is no way to do it now, but I'd be happy to<br>> chat with someone who would like to take on finishing up this<br>> addition.<br><br>> Best,<br>> Per<br><br><br>> On Wed, May 11, 2011 at 9:48 PM, Zhen Zonglei <<a href="mailto:zonglei.fsl@gmail.com">zonglei.fsl@gmail.com</a>> wrote:<br>
> > Dear all:<br>> > Is there a easy way to do PLS analysis in Pymvpa? I exepect to<br>> > investigate the correlation between neural patterns and a group of behavior<br>> > index, so I restort to PLS.<br>
> > If you have any info on how to do this in pymvpa, please let me know.<br><br></div><font color="#888888">--<br>=------------------------------------------------------------------=<br>Keep in touch <a href="http://www.onerussian.com/" target="_blank">www.onerussian.com</a><br>
Yaroslav Halchenko <a href="http://www.ohloh.net/accounts/yarikoptic" target="_blank">www.ohloh.net/accounts/yarikoptic</a><br></font>
<div>
<div></div>
<div class="h5"><br>_______________________________________________<br>Pkg-ExpPsy-PyMVPA mailing list<br><a href="mailto:Pkg-ExpPsy-PyMVPA@lists.alioth.debian.org">Pkg-ExpPsy-PyMVPA@lists.alioth.debian.org</a><br><a href="http://lists.alioth.debian.org/mailman/listinfo/pkg-exppsy-pymvpa" target="_blank">http://lists.alioth.debian.org/mailman/listinfo/pkg-exppsy-pymvpa</a><br>
</div></div></blockquote></div><br><br clear="all"><br>-- <br>
<div>Zonglei Zhen, PhD</div>
<div>BNU Imaging Center for Brain Research, State Key Laboratory of Cognitive Neuroscience and Learning, P.R. China</div><br>