OPLS-DA Log Out | Topics | Search
Moderators | Register | Edit Profile

NIR Discussion Forum » Bruce Campbell's List » Chemometrics » OPLS-DA « Previous Next »

Author Message
Top of pagePrevious messageNext messageBottom of page Link to this message

kanchan sonkar (kanchi2209)
New member
Username: kanchi2209

Post Number: 4
Registered: 4-2010
Posted on Tuesday, April 06, 2010 - 6:07 am:   

Hello Sir,
Thank you very much for the responce and the references.. as you recommended I have downloaded SIMCA-P+ software and will use this for learning purpose..but I would like to implement OPLS-DA in MATLAB....
I got only Ref 1, it will be very helpful if you provide these two references.
Thank you again..
Kanchan
Top of pagePrevious messageNext messageBottom of page Link to this message

Johan Trygg (trygg)
New member
Username: trygg

Post Number: 2
Registered: 1-2006
Posted on Tuesday, April 06, 2010 - 3:45 am:   

Hi,
I would recommend that you download a fully working demo of SIMCA-P+ software to do your OPLS-DA modelling (www.umetrics.com), a direct link is http://www.umetrics.com/Content/Downloads/SIMCA-P%2B_12.0.1_Demo.ept.

Then, have a look at the following references that contains the workflow (ref 1) and the underlying method theory (ref 2 & 3) of the method. If you want, I can email you the electronic pdfs.

Ref 1.) Wiklund S, Johansson E, Sj�str�m L, Mellerowicz EJ, Edlund U, Shockcor JP, Gottfries J, Moritz T, Trygg J, Visualization of GC/TOF-MS-Based Metabolomics Data for Identification of Biochemically Interesting Compounds Using OPLS Class Models, ANALYTICAL CHEMISTRY 2008 80, 1:115-22

Ref 2.) Bylesj� B, Rantalainen M, Cloarec O, Nicholson JK, Holmes E, Trygg J, OPLS Discriminant Analysis, Combining the strengths of PLS-DA and SIMCA classification, JOURNAL OF CHEMOMETRICS, 20 (8-10), 341-351 2006

Ref 3.) Trygg J, Wold S. Orthogonal projections to latent structures, O-PLS. JOURNAL OF CHEMOMETRICS, 2002; 16: 119-128

If you still want to do it with Matlab code, then you get enough info by reading the original reference (Ref 3) and implement it yourself. There the algorithm is presented in detail for single-Y, which you can use for the two-class discriminant analysis if you construct a binary y-variable (1/0) where 0 defines the control class. See Ref 1, if you want more info on this. Cross-validation and other diagnostic tools, including plotting and prediction capabilities are already at hand in the SIMCA-P+ software so it makes it easier.

Good luck, and let me know if you need those references,

Regards,
Johan Trygg
Ume� University, Sweden
Top of pagePrevious messageNext messageBottom of page Link to this message

venkatarman (venkynir)
Senior Member
Username: venkynir

Post Number: 100
Registered: 3-2004
Posted on Tuesday, April 06, 2010 - 2:56 am:   

There are good number of Publicaiotn in OPLS-DA. use CSIR journal search , you can get very good publicaiton with code. Chemo.Ins, Analyst, Talanta etc.. are good journal to probe.
Top of pagePrevious messageNext messageBottom of page Link to this message

kanchan sonkar (kanchi2209)
New member
Username: kanchi2209

Post Number: 3
Registered: 4-2010
Posted on Tuesday, April 06, 2010 - 2:49 am:   

Hi..
thanx..but the thing is that I want to use OPLS-DA only because my further analysis is dependent on its result.
I am searching but not getting any thing releted to this in Matlab, but people have used OPLS-DA in Matlab. Do you have any idea about this??
Top of pagePrevious messageNext messageBottom of page Link to this message

venkatarman (venkynir)
Senior Member
Username: venkynir

Post Number: 99
Registered: 3-2004
Posted on Tuesday, April 06, 2010 - 2:37 am:   

Good ; In the case of DA latest technique is SVM(support Vector Machine ). There ae tool box in Matalab for SVM.
You may get good result.
Top of pagePrevious messageNext messageBottom of page Link to this message

kanchan sonkar (kanchi2209)
New member
Username: kanchi2209

Post Number: 2
Registered: 4-2010
Posted on Tuesday, April 06, 2010 - 12:52 am:   

The data which I am using is NMR spectroscopic data of infected and control samples. I want to discriminate between infected and control, on the basis of differences which appear in both the cases, as is done using other chemometric tools like PCA.
Instead of using PCA or any other method I would like to use OPLS-DA as I mentioned in my previous post. That is why I am asking for Matlab code for this.
Top of pagePrevious messageNext messageBottom of page Link to this message

venkatarman (venkynir)
Senior Member
Username: venkynir

Post Number: 98
Registered: 3-2004
Posted on Monday, April 05, 2010 - 6:09 am:   

Kindly mention the analysis .Your questions is vague . Better emerging DA analysis are available as a tool.
Nothing is mentioned about your data /analysis
Top of pagePrevious messageNext messageBottom of page Link to this message

kanchan sonkar (kanchi2209)
New member
Username: kanchi2209

Post Number: 1
Registered: 4-2010
Posted on Monday, April 05, 2010 - 5:06 am:   

HI....
I am doing some analysis in which I have to incorporate OPLS-DA method. For the analysis, I am using MATLAB Version 7.8. Can anyone provide me the codes for OPLS-DA.
Thanx in advance

Add Your Message Here
Posting is currently disabled in this topic. Contact your discussion moderator for more information.