mxfold2
mxfold2 copied to clipboard
mxfold
mxfold2 output
Hi, I am wondering if you could clarify what the output from mxfold2 represents? Specifically the numbers in the parenthesis at the bottom right? Are these a score or metric of some kind? Is a larger number better or worse for a given output?
Apologies if this is stated somewhere, but I couldn't find it!
Me too. Though I found it's probably self.calculate_differentiable_score()
It is the folding score, which corresponds to Eq. (1) in the paper (http://dx.doi.org/10.1038/s41467-021-21194-4). A large value means a stable structure.
To hijack the thread, how do those numbers(scores) compare to the numbers obtained by ViennaRNA MFE calculations, in which more negative numbers mean a more stable structure? Is there any point in comparing the numbers or should we just use them to compare the rankings of different sequences i.e?
The default model of MXfold2 was trained to be as close as possible to the sign-reversed value of the thermodynamic energy using thermodynamic regularization. See Table 3 in the paper for its evaluation.