Dear All, I have analyzed a dataset for differential gene expression using LIMMA. The requirement was to select probesets with highest value of expression. I notice that there is a change in results for when i filter for probesets before and after performing LIMMA. The logFC and gene list remains the same, only change is in the p-value and B Value, again this is possible because the probesets are not averaged to the gene level but retained on maximum expression there by not having any affect of the filtering on the fold change. I can see that a similar question had been asked before https://stat.ethz.ch/pipermail/bioconductor/2011-June/039936.html Would be grateful if someone can please tell me if its best to filter before any statistical analysis or after? I am leaning towards 'filter before always' but though will gather more views on the same. Many Thanks. Regards, Ekta The information contained in this electronic message and in any attachments to this message is confidential, legally privileged and intended only for use by the person or entity to which this electronic message is addressed. If you are not the intended recipient, and have received this message in error, please notify the sender and system manager by return email and delete the message and its attachments and also you are hereby notified that any distribution, copying, review, retransmission, dissemination or other use of this electronic transmission or the information contained in it is strictly prohibited. Please note that any views or opinions presented in this email are solely those of the author and may not represent those of the Company or bind the Company. Any commitments made over e-mail are not financially binding on the company unless accompanied or followed by a valid purchase order. This message has been scanned for viruses and dangerous content by Mail Scanner, and is believed to be clean. The Company accepts no liability for any damage caused by any virus transmitted by this email. www.jubl.com [[alternative HTML version deleted]]

Dear Ekta, Clearly filtering should be done before topTable(), because there is no point in conducting multiple testing adjustments over probes that are to be filtered. Whether to filter before for after eBayes() is not so clear. I would suggest filtering before, assuming that the probes after filtering are still representative of the whole genome. It makes no difference whether filtering is done before or after lmFit(). Best wishes Gordon > Date: Thu, 1 Mar 2012 09:56:49 +0530 > From: Ekta Jain <ekta_jain at="" jubilantbiosys.com=""> > To: "bioconductor at r-project.org" <bioconductor at="" r-project.org=""> > Cc: "sdavis2 at mail.nih.gov" <sdavis2 at="" mail.nih.gov=""> > Subject: [BioC] Filtering genes on highest expression before or after > LIMMA? > > Dear All, > I have analyzed a dataset for differential gene expression using LIMMA. > The requirement was to select probesets with highest value of > expression. I notice that there is a change in results for when i filter > for probesets before and after performing LIMMA. The logFC and gene list > remains the same, only change is in the p-value and B Value, again this > is possible because the probesets are not averaged to the gene level but > retained on maximum expression there by not having any affect of the > filtering on the fold change. > > I can see that a similar question had been asked before > https://stat.ethz.ch/pipermail/bioconductor/2011-June/039936.html > > Would be grateful if someone can please tell me if its best to filter > before any statistical analysis or after? I am leaning towards 'filter > before always' but though will gather more views on the same. > > Many Thanks. > > Regards, > Ekta ______________________________________________________________________ The information in this email is confidential and intend...{{dropped:4}}