Calling this 2.0 to recognize that MHCflurry has evolved quite a bit. This release itself is not a major departure from the 1.6.0 version, however.
Version 2.0 introduces new models (BA/AP/PS). These follow the same overall design as in 1.6.0 but incorporate updated training data and some small tweaks:
BA predictor: MS hits are assigned < 100 nM affinity instead of < 50 nM for training
AP predictor: flanking window size decreased to 5 amino acids per flank from 15. Not seeing an accuracy decrease and it makes the models faster.
The code has finally been ported to tensorflow 2.0. This will mean you will need to upgrade to a recent tensorflow to use MHCflurry.
Calling this 2.0 to recognize that MHCflurry has evolved quite a bit. This release itself is not a major departure from the 1.6.0 version, however.
Version 2.0 introduces new models (BA/AP/PS). These follow the same overall design as in 1.6.0 but incorporate updated training data and some small tweaks:
The code has finally been ported to tensorflow 2.0. This will mean you will need to upgrade to a recent tensorflow to use MHCflurry.
Other changes: