User: Gordon Smyth

gravatar for Gordon Smyth
Gordon Smyth1.9k
Reputation:
1,900
Status:
Trusted
Location:
Australia
Website:
http://www.statsci.org...
Scholar ID:
Google Scholar Page
Last seen:
1 day, 1 hour ago
Joined:
6 years ago
Email:
s****@wehi.edu.au

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

My research group created the limma, edgeR, goseq, Rsubread, csaw and diffHic packages, all part of the Bioconductor project.

Posts by Gordon Smyth

<prev • 139 results • page 1 of 14 • next >
2
votes
1
answer
2.2k
views
1
answers
Answer: A: Random Variance T-Test In R?
... The random variance model of BRB Tools is essentially the same idea as the empirical Bayes model of limma. BRB Tools calls it a random model whereas limma calls it a prior distribution, but mathematically they are the same. limma would be a logical R equivalent of BRB Tools, although limma estimates ...
written 15 days ago by Gordon Smyth1.9k
1
vote
1
answer
2.2k
views
1
answers
Comment: C: Random Variance T-Test In R?
... I think you might have misinterpreted the BRB Tools variance model. The random variance model that BRBtools uses is between genes, not between samples, and it is closely analogous to what limma does. Both tools allow variances to be different between genes but the same for samples within each gene. ...
written 15 days ago by Gordon Smyth1.9k
1
vote
3
answers
209
views
3
answers
Comment: C: RNAseq Variance calculation
... Where have you read that you need to get rid of low variance genes? Filtering by variance is incompatible with all the empirical Bayes algorithms including limma, edgeR and DESeq2 because it introduces bias into the dispersion estimation step. Use instead the filtering recommended by those packages. ...
written 5 weeks ago by Gordon Smyth1.9k
2
votes
1
answer
99
views
1
answers
Answer: A: How to deal with Hi-C replicates from different patients' tissue sample?
... The Bioconductor package diffHic is specifically designed for this purpose, leveraging the capabilites of the edgeR package. I don't know of other Hi-C methods or tools that can account for batch effects and which properly evaluate variation between biological replicates. For an example of use see: ...
written 5 weeks ago by Gordon Smyth1.9k
1
vote
1
answer
235
views
1
answers
Comment: C: Limma:Coefficients not estimable, please help
... You can't use your current design matrix because it contains redundancies. Any contrast you form from it will be meaningless. Just form the design matrix in the standard way, e.g., as suggested by Devon. ...
written 8 weeks ago by Gordon Smyth1.9k
0
votes
1
answer
161
views
1
answers
Answer: A: How to Normalize and log tranform the miRNA Seq data using DeSeQ2 / EdgeR?
... Your script already does what you say you want. Negative values on the log-scale are not a problem, although you could reduce the number of negative values by leaving prior.count at the default value instead of setting it so small. ...
written 8 weeks ago by Gordon Smyth1.9k
0
votes
2
answers
307
views
2
answers
Comment: C: DEG Analysis in R
... That error could only occur if the data object (the first argument of `lmFit`) was NULL, which could not be the case if you have run the code you claim to have run. ...
written 9 weeks ago by Gordon Smyth1.9k
0
votes
1
answer
666
views
1
answers
Comment: C: What this error means?Error in getEAWP(object) : data object isn't of a recogniz
... I suspect you missed out `gset <- gset[[1]]` the first time, meaning that `gset` would be a list rather than an ExpressionSet. That would produce the error message from limma. ...
written 9 weeks ago by Gordon Smyth1.9k
2
votes
2
answers
307
views
2
answers
Answer: A: DEG Analysis in R
... `getGEO` returns a list of ExpressionSets rather than a simpleExpressionSet, so to pass the data to limma you need to access the relevant component by ``` fit <- lmFit(gset$GSE75693, design) ``` However your design matrix is difficult to understand. The GEO dataset you've read is not a cancer d ...
written 9 weeks ago by Gordon Smyth1.9k
0
votes
0
answers
108
views
0
answers
Comment: C: How to correctly assign the matrix row for DGE analysis?
... Cross-posted to Bioconductor https://support.bioconductor.org/p/132599/ ...
written 10 weeks ago by Gordon Smyth1.9k

Latest awards to Gordon Smyth

Teacher 20 days ago, created an answer with at least 3 up-votes. For A: published array data not replicable with limma analysis
Good Answer 21 days ago, created an answer that was upvoted at least 5 times. For A: Differential expression: replicates in one condition, no replicates in the other
Scholar 4 weeks ago, created an answer that has been accepted. For A: DESeq and Limma+Voom Normalization for Rna-Seq Data Using Ercc Spike-In
Teacher 4 weeks ago, created an answer with at least 3 up-votes. For A: published array data not replicable with limma analysis
Scholar 5 weeks ago, created an answer that has been accepted. For A: DESeq and Limma+Voom Normalization for Rna-Seq Data Using Ercc Spike-In
Teacher 8 weeks ago, created an answer with at least 3 up-votes. For A: published array data not replicable with limma analysis
Scholar 3 months ago, created an answer that has been accepted. For A: DESeq and Limma+Voom Normalization for Rna-Seq Data Using Ercc Spike-In
Teacher 4 months ago, created an answer with at least 3 up-votes. For A: published array data not replicable with limma analysis
Scholar 4 months ago, created an answer that has been accepted. For A: DESeq and Limma+Voom Normalization for Rna-Seq Data Using Ercc Spike-In
Supporter 4 months ago, voted at least 25 times.
Commentator 4 months ago, created a comment with at least 3 up-votes. For C: Trying to understand the maths behind one Limma function
Good Answer 7 months ago, created an answer that was upvoted at least 5 times. For A: Differential expression: replicates in one condition, no replicates in the other
Teacher 7 months ago, created an answer with at least 3 up-votes. For A: published array data not replicable with limma analysis
Centurion 7 months ago, created 100 posts.
Scholar 7 months ago, created an answer that has been accepted. For A: DESeq and Limma+Voom Normalization for Rna-Seq Data Using Ercc Spike-In
Teacher 7 months ago, created an answer with at least 3 up-votes. For A: published array data not replicable with limma analysis
Scholar 9 months ago, created an answer that has been accepted. For A: DESeq and Limma+Voom Normalization for Rna-Seq Data Using Ercc Spike-In
Teacher 10 months ago, created an answer with at least 3 up-votes. For A: published array data not replicable with limma analysis
Teacher 10 months ago, created an answer with at least 3 up-votes. For A: published array data not replicable with limma analysis
Teacher 10 months ago, created an answer with at least 3 up-votes. For A: published array data not replicable with limma analysis
Scholar 10 months ago, created an answer that has been accepted. For A: DESeq and Limma+Voom Normalization for Rna-Seq Data Using Ercc Spike-In
Teacher 11 months ago, created an answer with at least 3 up-votes. For A: published array data not replicable with limma analysis

Help
Access

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.
Powered by Biostar version 2.3.0
Traffic: 1783 users visited in the last hour