This is a test version of Biostars. For the public version, visit https://www.biostars.org.
Finding proper cut off for filtering?

I had a set of data (149876 rows and 1200 columns)and I have found outliers points for each row.

Now I want to determine a proper threshold for filtering my outliers. The distribution of my data is more look like gamma / weibull distribution.

Would you please help me which test or analysis can be useful for me?

outliers statistics r distribution analysis
• 966 views • link
updated by Ram Ram • written by star star

Hello star!

We believe that this post does not fit the main topic of this site.

This belongs at Cross Validated https://stats.stackexchange.com/

For this reason we have closed your question. This allows us to keep the site focused on the topics that the community can help with.

If you disagree please tell us why in a reply below, we'll be happy to talk about it.

Cheers!

• 0 views • link
written by Sukhi Singh Sukhi Singh

hi,

Is this by any chance RNA-seq (count/ FPKM) data? If it is gene expression data, then filtering out basal-level genes is a good idea, first. Log transform the data (add 1 to all if you have 0s) and then create a column containing mean value for each row, and then plot the col.. You should see a big peak hovering above 0 and then large tail extending ahead. You can then choose an arbitrary threshold to cut-off basal level 'row entities'.

You can of course use BioC packages like DESeq or Limma (Voom) to do the normalization.

• 5 views • link
updated by Ram Ram • written by Amitm Amitm

0 answers

No answers yet.

Log in to answer this question.

More posts like this