In general, if you are unsure whether a question is the sort of thing we are going to want to see here, is it better to ask it on the main site and see if it gets closed, or enquire on meta first if it is in-scope?
How to correlate of two zero inflated bedgraph-like signals?
I have iCLIP read counts accross the transcriptome and I wish to know if the signals are correlated - that is, where one of them is high, is the other likely to be high.
Often when dealing with such data (e.g. iCLIP data) we know that the data is generally sparse - that is at most positions both signals are zero and this is correct, and also zero-inflated - that is many bases that "should" have a signal are missing that data. So just calucalting the spearmans correlation is likely to give an artifically low value.
These problems are also present if you want to correlate ChIP-seq signals or Mutation frequencies.
What might be a way to address this?
I asked a question similar to this on Cross-validated, but didn't get any response. I feel it might be of more interest to a bioinformatics crowd as it is a problem that seems to come up frequently in bioinformatics. But I wonder if it is too "stats-y" for here.
Anyway, my question is: Should I just post questions like this, where I am unsure, and see if people think it is good. Or should I ask for everyone on Meta to see if people think its good?
Pro's for asking first:
- We don't pollute the site with low-quality, closed questions
- We build a bank of reasoning why a question would be allowed or not allowed that can be reffered to in the future.
Pro's for just posting:
- Might lead to a lot of boring repetative questions on meta all basically asking "Is this allowed? How about this? Not sure about this one?"
- Will slow down the accumulation of questions on the site as it will take people time to answer the pre-enquiries before the question is actaully asked.