Entering edit mode
4.0 years ago
thyleal
▴
160
Hello everyone,
What do you suggest for sub-group discovery and cluster validation for transcriptomics?
I have a group of patients that are classified into groups A and B, but there also a a second classification system that is: A1, A2, B1, B2, B3. However, this last grouping strategy is very old and inconsistent, so we thought about using unsupervised clustering to discovery a more data-driven cluster of patients, in addition to select the features responsible for such clusters. What you guys suggest?
Sample size is not large, aprox. 25 samples per main group (A or B) and we have two datasets: one microarray and one RNA-sequencing.
I only thought about k-means.
Thank you.
