HIGHLIGHTS
SUMMARY
Interestingly, the results depend on the choice of the positive set and, to a lesser extent on the choice of the negative set. After each step the authors end up with k set of values for the optimised 6 of 21 parameters, maximised AUC on the training set and estimated AUC (and MCC) on the test set. The PASTA-complemented scoring function then backfires for some sequences with a disorder content again lower than the average one in the full positive set, classifying them as too dangerous for the droplet state. The authors studied . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.