Open bschilder opened 1 year ago
I think we should be able to calculate the probability of enrichment based on gene list of length M theoretically although I would need to have a think of how. For example where there are an infinite number of bootstrap tests (N) and if M=1, it would be Prob(enrich)=rank of specificity of gene from M. For M>1, it gets a little more complex since it's the mean specificity of the gene list and bootstrap background gene list
I think the probability of finding significant hits with gene lists with length of one is very low.
It’s bootstrapping, so there are not really statistical ramifications. It is measuring empirically the distribution.
Sent from Outlook for iOShttps://aka.ms/o0ukef
From: Alan Murphy @.> Sent: Monday, April 3, 2023 12:42:34 PM To: NathanSkene/EWCE @.> Cc: Skene, Nathan G @.>; Mention @.> Subject: Re: [NathanSkene/EWCE] Consider removing <4 gene limit (Issue #79)
This email from @.*** originates from outside Imperial. Do not click on links and attachments unless you recognise the sender. If you trust the sender, add them to your safe senders listhttps://spam.ic.ac.uk/SpamConsole/Senders.aspx to disable email stamping for this address.
I think we should be able to calculate the probability of enrichment based on gene list of length M theoretically although I would need to have a think of how. For example where there are an infinite number of bootstrap tests (N) and if M=1, it would be Prob(enrich)=rank of specificity of gene from M. For M>1, it gets a little more complex since it's the mean specificity of the gene list and bootstrap background gene list
— Reply to this email directly, view it on GitHubhttps://github.com/NathanSkene/EWCE/issues/79#issuecomment-1494168541, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AH5ZPE3LBZXGAE3XFBINZWLW7KZSVANCNFSM6AAAAAAWRFW7QA. You are receiving this because you were mentioned.Message ID: @.***>
Currently
EWCE::bootstrap_enrichment_test
doesn't let you run tests where the number of hit genes is <4. @NathanSkene has noted this cutoff is arbitrary and could be removed. But we should first consider the potential statistical ramifications of small gene lists within theEWCE
framework.@bschilder
@Al-Murphy
We should
EWCE
p-values.