Question

Questions about limma

0

Entering edit mode

He, Yiwen NIH/CIT ▴ 360

@he-yiwen-nihcit-1177

Last seen 10.3 years ago

Hi, I have some questions about the data that the limma package can work on. If I have some preprocessed/normalized data of log2 ratios from 2-color arrays, but not the raw signal data, can I still use lmFit? A related question is, can limma work on a subset of the data from an array? For example, after normalization, I filter out some probes/spots. If I can retrieve the M and A values of that subset, can I still use limma? Bottom line, do I always have to start with raw data while using limma? Also, are there any test data available in the package? Thank you, Yiwen \\||// (o o) .-. .-. oOOo~(_)~oOOo. .-. .-. /| | | x | | |\ /| | | x | | |\ /| | | x | | |\ /| | | | | |/ \| | | x | | |/ \| | | x | | |/ \| | | x | | |/ `-' `-' `-' `-' `-' `-' `-' -------- Yiwen He, Ph.D., M.P.H. Analyst/Web Developer Contractor, SRA International Inc. Bioinformatics and Molecular Analysis Section Center for Information Technology National Institute of Health -------- Bldg. 12A, Rm. 1018 12 South Dr., Bethesda, MD 20892 Email: heyiwen@mail.nih.gov Phone: 301-402-4636 Fax: 301-402-2867 [[alternative HTML version deleted]]

Normalization limma Normalization limma • 936 views

ADD COMMENT • link updated 19.7 years ago by Sean Davis 21k • written 19.7 years ago by He, Yiwen NIH/CIT ▴ 360

score 0 · Answer 1 · 2005-04-06

0

Entering edit mode

He, Yiwen NIH/CIT ▴ 360

@he-yiwen-nihcit-1177

Last seen 10.3 years ago

Hi, I have some questions about the data that the limma package can work on. If I have some preprocessed/normalized data of log2 ratios from 2-color arrays, but not the raw signal data, can I still use lmFit? A related question is, can limma work on a subset of the data from an array? For example, after normalization, I filter out some probes/spots. If I can retrieve the M and A values of that subset, can I still use limma? Bottom line, do I always have to start with raw data while using limma? Also, are there any test data available in the package? Thank you, Yiwen \\||// (o o) .-. .-. oOOo~(_)~oOOo. .-. .-. /| | | x | | |\ /| | | x | | |\ /| | | x | | |\ /| | | | | |/ \| | | x | | |/ \| | | x | | |/ \| | | x | | |/ `-' `-' `-' `-' `-' `-' `-' -------- Yiwen He, Ph.D., M.P.H. Analyst/Web Developer Contractor, SRA International Inc. Bioinformatics and Molecular Analysis Section Center for Information Technology National Institute of Health -------- Bldg. 12A, Rm. 1018 12 South Dr., Bethesda, MD 20892 Email: heyiwen@mail.nih.gov Phone: 301-402-4636 Fax: 301-402-2867 [[alternative HTML version deleted]]

ADD COMMENT • link 19.7 years ago He, Yiwen NIH/CIT ▴ 360

0

Entering edit mode

On Apr 5, 2005, at 12:10 PM, He, Yiwen (NIH/CIT) wrote: > Hi, I have some questions about the data that the limma package can > work on. > If I have some preprocessed/normalized data of log2 ratios from 2-color > arrays, but not the raw signal data, can I still use lmFit? From the help for lmFit: ------------------------------------ Usage: lmFit(object,design=NULL,ndups=1,spacing=1,block=NULL,correlation=0.75 ,w eights=NULL,method="ls",...) Arguments: object: object of class 'numeric', 'matrix', 'MAList', 'marrayNorm', 'exprSet' or 'PLMset' containing log-ratios or log-values of expression for a series of microarrays ---------------------------------------- So you can use a matrix of log2 ratios, yes. > A related > question is, can limma work on a subset of the data from an array? For > example, after normalization, I filter out some probes/spots. If I can > retrieve the M and A values of that subset, can I still use limma? > You can use any matrix as input to lmFit that you like, doing whatever subsetting you like prior to its use. > Bottom line, do I always have to start with raw data while using limma? > Nope, but limma offers a huge variety of normalization and diagnostic routines that can be very helpful if you start with raw data. > Also, are there any test data available in the package? > Gordon has put a HUGE amount of time and energy into making a VERY comprehensive user guide. I would start by reading it. It will walk you through a number of examples; the data for all of these examples are included with the package. The user guide can be found in multiple places, including the /doc directory of the limma package directory and: http://bioinf.wehi.edu.au/limma/usersguide.pdf Hope this helps. Sean

ADD REPLY • link 19.7 years ago Sean Davis 21k

score 0 · Answer 2 · 2005-04-06

On Apr 6, 2005, at 1:44 PM, He, Yiwen (NIH/CIT) wrote: > Hi Sean, > > Thanks for your help! > > lmFit didn't work on my log ratio data because the data was not > numeric, so I got all NAs for the result. It's now working after I > converted it to numeric. > Glad to hear it. > I did read the User's guide and saw those case studies. However, I was > not able to find any test data that I can load into R to run the test. > Can you point me to the right place? > You are right. I spoke too quickly--it doesn't look like the example files are included--sorry about that! It looks like they are available here: http://bioinf.wehi.edu.au/limmaGUI/DataSets.html > I have a general question: How is limma compared with other > statistical analysis like SAM? I ran both procedures on the same > dataset (one class) and got similar results (28 out of the 30 top > genes overlap, orders differ slightly). But the significant levels > (p/B for limma and q for SAM) differ. For small sample size, SAM's q > is bigger than limma's p values, on the other hand, when sample size > is large, q is much smaller. I understand limma uses empirical bayes > mothods so that it works on small number of replicates. What are the > other advantages of limma? > As for p/q values, they will be different--are you using fdr multiple comparisons correction? I don't generally use siggenes much, though, so I don't know how they compare in practice. As for other advantages of limma, it does linear modeling of experiments, so many complex experimental designs can be handled in the same framework. Sean