My lab has some RNA secondary structure data on a number of virus RNA segments from a method called SHAPE-MaP, which gives each nucleotide in a sequence a reactivity value. We would like to make a 2D plot that clusters segments with similar reactivity value profiles together. However, each segment has a different number of nucleotides, and so we can't figure out how to use standard tools like PCA or t-SNE because each dataset has a different number of dimensions. Is there a way to perform dimensionality reduction on a data set where each point has a different number of dimensions?
•
written
by
rtrende •
1 answer
Not sure whether what you want to do will be informative. That aside, UMAP works with sparse data. Simply insert missing values for shorter sequences to make the length identical to the longest sequence.
You can try DNA/RNA language models and extract their embeddings based on your sequences. Those should be of the same length and presumably can be used for dimensionality reduction.
Log in to answer this question.
-
clustering of genome segments
written by Bogdan
-
How to compare Sars-Cov-2 RefSeq to Influenza A RefSeq
written by bwillkie •
-
PCA to find clusters in gene expression data
written by Hashirama •
-
how to find each cluster in single-cell represent which cell type?
written by Raz •
-
News: [Webinar] Using t-SNE for data analysis : An Introduction by Dr. Laurens van der Maaten (Inve…
written by Jennifer Pham
-
Force directed graphs compared to other dimensionality reduction methods for scRNA-seq
written by MutationalMeltdown
-
PCA vs ICA prior to t-SNE or UMAP
written by rtrende •
-
Number of Probes per Segment for TCGA CNVs
written by jrlarsen •
-
genomic characteristics between copy number gain and loss
written by mangfu100
-
Why Next Generation Sequencing Data Is High-Dimensional ( Or Ultra High Dimensional) ??
written by lavya3 •
