Hi! Thank you for your quick response. Yes. PCA reduces dimensionality while keeping the variability, right? I am reading more about it. By reducing the dimensionality, would I remove gene dimensions or would I create parameters (no gene loci, e.g. z1, z2,...)? Sorry if I am confused.
How to select the optimal genes for neural network analysis?
Hi everyone!
I am working with a cancer mouse model that produced tumors, and we have performed gene expression profiling on all of them. I would be interested in building a classifier to identify human tumors, based on their gene expression, that are similar to my model (i.e. "mouse-like"). The microarrays have 27000+ features. I suspect that I don't need as many features. Hence, I was wondering if there were a methodology to pick the best number/nature of parameters? I know that it is counter-intuitive because I shouldn't look at the data before I apply machine learning. I am currently reading papers.
Thank you for your input!
1 answer
Have you considered reducing the number of features by doing some kind of PCA (Principal Component Analysis) approach?
• 0 views
•
link
updated
by
Ram
•
written
by
jgbradley1 •
•
written
by
jgbradley1 •
Log in to answer this question.
More posts like this
-
Well-established methods to distinguish malignant vs normal epithelial cells in mouse scRNA-seq dat…
written by andromeda.milky42 •
-
which data type I can use to bulid machine learning.
written by Qiang •
-
RNA-seq data from human tumors in mice (PDTX)
written by Tom_L
-
Resources for machine learning prediction of phenotypes from omics data
written by enricoferrero
-
Best approach to compare human and mouse gene expression quantified by RNA-seq
written by samuelrivero •
-
Possible methodology-R package for simulating a microarray dataset with both gene and clinical cont…
written by svlachavas
-
Basic idea of applying a gene signature
written by Avro
-
Naive Bayes classifier for identification of human tumors
written by Avro
-
How to identify human samples with a specific mouse gene expression signature?
written by Avro
-
JISTIC excluded regions
written by Avro
It IS safe to filter genes to those with high variance; this would be a quick and easy way to get a reasonable set for classification.
Hi! Thank you for your quick response. Could I use a nonparamteric ranking test (e.g. Wilcoxon) to get the genes with the highest variance?
No. You may not use any measure of variability that includes the classes.
Thank you! Is there a way to have a cutoff for the variance? I am asking because the variance values will be continous. Bootstrap resampling?
There is no "cutoff". I suspect that you'll find that there is a pretty broad range that can result in similar performance.