A Universal Transformer encoder replaces the RNN in the RGN predictor, yielding reported dRMSD gains of 1.7 Å on CASP12 free-modeling and 0.7 Å on template-based targets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.BM 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Universal Transforming Geometric Network
A Universal Transformer encoder replaces the RNN in the RGN predictor, yielding reported dRMSD gains of 1.7 Å on CASP12 free-modeling and 0.7 Å on template-based targets.