Moderator: Gordon Smyth

gravatar for Gordon Smyth
Gordon Smyth30k
Reputation:
29,860
Status:
Trusted
Location:
Walter and Eliza Hall Institute of Medical Research, Melbourne, Australia
Website:
http://www.statsci.org...
Scholar ID:
Google Scholar Page
Last seen:
4 hours ago
Joined:
14 years, 1 month ago
Email:
s****@wehi.edu.au

Head of Bioinformatics Division at the Walter and Eliza Hall Institute of Medical Research

Posts by Gordon Smyth

<prev • 2,867 results • page 1 of 287 • next >
0
votes
1
answers
88
views
1
answers
Comment: C: How did the edgeR authors compute Figure 2 (genewise deviance statistics?)
... You've forgotten to apply Holm multiple-testing adjustment to the p-values (as mentioned in the figure caption). See the code in my comment to Davis' answer. The plot is analogous to the classic qq plot of normal residuals. The idea is identify outlier residuals rather than to check for correlation ...
written 17 hours ago by Gordon Smyth30k
0
votes
1
answers
88
views
1
answers
Comment: C: How did the edgeR authors compute Figure 2 (genewise deviance statistics?)
... You can make these plots very simply in edgeR using the function gof() provided for this purpose. Here is the code to make the common plot: d <- estimateDisp(d, design) fit <- glmFit(d, design, dispersion=d$common.dispersion) gof(fit, p=0.05, plot=TRUE) If you want to program all the gory d ...
written 17 hours ago by Gordon Smyth30k
0
votes
1
answers
63
views
1
answers
Answer: A: Calculating probability of getting xx genes past FDR10%
... You are confusing FDR with p-values. You would expect 10% of the miRNAs to have p < 0.1 if actually there were none significant, but FDRs are different. You will notice that limma gives you both p-value and FDR columns in the output and the FDR values are higher than the p-values. The question s ...
written 1 day ago by Gordon Smyth30k
0
votes
1
answers
56
views
1
answers
Answer: A: linear model " limma "
... Well, the problem is that you have 9 arrays but you have created the design matrix as if there are 8 arrays -- the error is telling you to check your design matrix. I am guessing that you meant to write: design <- model.matrix(~ 0+factor(c(1,1,1,2,2,2,3,3,3))) i.e., you meant to have 3 arrays ...
written 1 day ago by Gordon Smyth30k
0
votes
1
answers
72
views
1
answers
Comment: C: how to use log2 transformation and limma
... Kindly follow my answer and read Section 17.2. There is no mention of "RG" in that section. If you read the limma User's Guide a little more carefully, you will see that RG objects are only used for two color microarrays. BTW, when I wrote my original answer, you hadn't mentioned anything about tr ...
written 2 days ago by Gordon Smyth30k
0
votes
1
answers
72
views
1
answers
Answer: A: log2 transformation and limma
... You give limma the normalized data, for example: fit <- lmfit(rma, design) and so on. Have a look at the case study in Section 17.2 of the limma User's Guide for an example analysis. ...
written 2 days ago by Gordon Smyth30k
0
votes
2
answers
107
views
2
answers
Answer: A: plotMDS Input Feature Filtering
... Yes, it would make sense to filter out the sex-linked genes to see more clearly what the batch effect looks like with the sex inbalance removed. In our practice, we frequently filter out sex-linked genes when (i) the experimental conditions are not themselves sex-linked in their effects but (ii) bo ...
written 3 days ago by Gordon Smyth30k
0
votes
1
answers
108
views
1
answers
Comment: C: threshold to filter lowly expressed genes
... The form of the quoted sentence is "if A then B", but you are reading it to mean "if B then A". You're not the first person to make the same interpretation, so I guess that making the reasoning longer and even more explicit may have been worthwhile. I'm always surprised by how much confusion the is ...
written 6 days ago by Gordon Smyth30k
0
votes
1
answers
108
views
1
answers
Answer: A: threshold to filter lowly expressed genes
... The section called "Filtering to remove low counts" in the workflow article    https://f1000research.com/articles/5-1438/v2 gives a clear rule of thumb for filtering that you could apply in your situation. ...
written 6 days ago by Gordon Smyth30k
0
votes
2
answers
176
views
2
answers
Comment: C: Differential binding of ATAC-seq data with no replicates
... No, you would still be over-stating the differences between conditions. To follow the advice in our NAR article, you would pool all 32 libraries together for peak calling. ...
written 9 days ago by Gordon Smyth30k

Latest awards to Gordon Smyth

Commentator 14 hours ago, created a comment with at least 3 up-votes. For C: How did the edgeR authors compute Figure 2 (genewise deviance statistics?)
Commentator 14 hours ago, created a comment with at least 3 up-votes. For C: How did the edgeR authors compute Figure 2 (genewise deviance statistics?)
Teacher 10 days ago, created an answer with at least 3 up-votes. For A: limma; Only fit list of certain genes/ filter eSet
Scholar 16 days ago, created an answer that has been accepted. For A: limma; Only fit list of certain genes/ filter eSet
Teacher 16 days ago, created an answer with at least 3 up-votes. For A: limma; Only fit list of certain genes/ filter eSet
Teacher 16 days ago, created an answer with at least 3 up-votes. For A: seeking a paper or journal review about repeated multiple testing for Biological
Teacher 25 days ago, created an answer with at least 3 up-votes. For A: limma; Only fit list of certain genes/ filter eSet
Scholar 25 days ago, created an answer that has been accepted. For A: limma; Only fit list of certain genes/ filter eSet
Scholar 28 days ago, created an answer that has been accepted. For A: limma; Only fit list of certain genes/ filter eSet
Popular Question 4 weeks ago, created a question with more than 1,000 views. For File format for single channel analysis of Agilent microarray data with Limma?
Scholar 5 weeks ago, created an answer that has been accepted. For A: limma; Only fit list of certain genes/ filter eSet
Teacher 5 weeks ago, created an answer with at least 3 up-votes. For A: limma; Only fit list of certain genes/ filter eSet
Great Question 6 weeks ago, created a question with more than 5,000 views. For EdgeR LogCpm and LogFC values calculation
Scholar 7 weeks ago, created an answer that has been accepted. For A: limma; Only fit list of certain genes/ filter eSet
Scholar 7 weeks ago, created an answer that has been accepted. For A: limma; Only fit list of certain genes/ filter eSet
Teacher 7 weeks ago, created an answer with at least 3 up-votes. For A: limma; Only fit list of certain genes/ filter eSet
Popular Question 7 weeks ago, created a question with more than 1,000 views. For LIMMA - summarization of Illumina probes for same gene
Popular Question 7 weeks ago, created a question with more than 1,000 views. For LIMMA - summarization of Illumina probes for same gene
Scholar 9 weeks ago, created an answer that has been accepted. For A: Question about genas function in the limma package
Teacher 11 months ago, created an answer with at least 3 up-votes. For A: Calculating a p value by permutation analysis
Teacher 11 months ago, created an answer with at least 3 up-votes. For A: limma-voom for miRNA seq
Teacher 11 months ago, created an answer with at least 3 up-votes. For A: limma-voom when testing differential expression of a subset of genes.
Teacher 11 months ago, created an answer with at least 3 up-votes. For A: Error when fitting linear model with technical replicates and blocking variable
Teacher 11 months ago, created an answer with at least 3 up-votes. For A: Effects of continuous variable with adjustment for gender

Help
Access

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.
Powered by Biostar version 2.2.0
Traffic: 229 users visited in the last hour