User: Raheleh
Raheleh • 90
- Reputation:
- 90
- Status:
- Trusted
- Location:
- Last seen:
- 3 days, 17 hours ago
- Joined:
- 2 years, 10 months ago
- Email:
- r**************@yahoo.com
Posts by Raheleh
<prev
• 51 results •
page 1 of 6 •
next >
0
votes
1
answer
838
views
1
answers
... I saw your comprehensive post [here][1] about how to build a lasso-penalised model. I did based on your instruction and I got this coefficient for each gene:
$`non-Relapse`
46 x 1 sparse Matrix of class "dgCMatrix"
1
(Intercept) 9.97551314
ASPH ...
0
votes
1
answer
838
views
1
answers
... Thank you Kevin. I'll go through that. Could you please what is the reason that I got this warning and how lasso penalty will solve it? ...
written 4 days ago by
Raheleh • 90
0
votes
1
answer
838
views
1
answers
... Many thanks @Kevin for taking the time to address my questions. No, I've never used it before. I really appreciate if you help me with that. ...
written 5 days ago by
Raheleh • 90
0
votes
1
answer
838
views
1
answers
... Thank you @Kevin! Yes I want to reduce the predictors via stepwise regression as you said.
I have 66 samples (46 non-relapse and 20 relapse). These 45 genes are the genes that I got from differential gene expression analysis. I reduced the number of genes to 24 genes, but still get the same warning ...
written 5 days ago by
Raheleh • 90
0
votes
1
answer
838
views
1
answers
... Hi @Kevin. Thank you very much for all your helpful answers.
I built a combined model for my data
null <- glm(Group ~ 1, data = df, family = binomial(link = 'logit'))
full <- glm(Group ~ ASPH + ATP5A1 + ATP5G3 + COL24A1 + DCAF10 + DES + DNMT1 +
EIF2B2 + ETS2 + FLJ38 ...
written 6 days ago by
Raheleh • 90
0
votes
1
answer
130
views
1
answers
... Thank you for your reply. I subtracted off the rowMeans from each row and now it is more meaningful.
why we should do this?
![enter image description here][1]
[1]: https://i.ibb.co/8XL84FM/Park7-Probes-exp-scaled.png
...
written 11 days ago by
Raheleh • 90
0
votes
1
answer
130
views
1
answers
... Thanks! I followed the instruction but didn't work ...
written 11 days ago by
Raheleh • 90
4
votes
1
answer
130
views
7 follow
1
answer
... Hi Folks,
I ploted a heatmap for all probes of PARK7 gene to see how they are expressing in three different groups of tumor data. I expected that all probes for the same gene show a similar pattern. However, surprisingly I saw they have huge difference expression value.
![enter image description ...
0
votes
0
answers
234
views
0
answers
... Hi Kevin. Thanks for the point!
I defined it as "not good" because in the first figure the samples from two different groups are not separated from each other as good as in the second figure. Isn't like this? If I am wrong please correct me. Thanks! ...
written 20 days ago by
Raheleh • 90
6
votes
0
answers
234
views
0
answers
... I have expression profile of 27 samples (10 normal, 17 tumors). I did PCA analysis to check the quality of the samples to see them clustered in 2 different groups. I did it in two ways after RMA normalization and log2 transformation.
1. I did it without centring the data and the result showed that t ...
written 5 weeks ago by
Raheleh • 90
Latest awards to Raheleh
Supporter
8 days ago,
voted at least 25 times.
Popular Question
6 months ago,
created a question with more than 1,000 views.
For Why some probes have "NA" for gene symbol and Entrez ID?
Student
10 months ago,
asked a question with at least 3 up-votes.
For Why some probes have "NA" for gene symbol and Entrez ID?
Popular Question
20 months ago,
created a question with more than 1,000 views.
For Why some probes have "NA" for gene symbol and Entrez ID?
Use of this site constitutes acceptance of our User
Agreement
and Privacy
Policy.
Powered by Biostar
version 2.3.0
Traffic: 2278 users visited in the last hour