Open soerenab opened 4 months ago
Hi, thanks a lot for developing this package!
I have a question on the coexpression_similarity metric: why do you divide the coexpression difference matrix by 2? https://github.com/theislab/txsim/blob/dev/txsim/metrics/_coexpression_similarity.py#L208
I have also seen this on the main branch: https://github.com/theislab/txsim/blob/main/txsim/metrics/_coexpression_similarity.py#L281
I don't understand why this is necessary, doesn't this just (somewhat arbitrarily) scale down the actual differences?
Thank you for any explanation :)
Hi, thanks a lot for developing this package!
I have a question on the coexpression_similarity metric: why do you divide the coexpression difference matrix by 2? https://github.com/theislab/txsim/blob/dev/txsim/metrics/_coexpression_similarity.py#L208
I have also seen this on the main branch: https://github.com/theislab/txsim/blob/main/txsim/metrics/_coexpression_similarity.py#L281
I don't understand why this is necessary, doesn't this just (somewhat arbitrarily) scale down the actual differences?
Thank you for any explanation :)