OSPREY: protein design with ensembles, flexibility, and provable algorithms.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Evolutionary context-integrated deep sequence modeling for protein engineering (2020, background): “, FoldX [42] and OSPREY [4] ).”
Algorithms for Protein Design (2016, methodology): “These algorithms are implemented in the Toulbar2 program [53 ,54,55], with support only for discrete flexibility models, and in the Osprey protein design program [39,68] (with full support for continuous flexibility models, described in the next section [64 ,69 ]).”
MolProbity’s Ultimate Rotamer-Library Distributions for Model Validation (2016, methodology): “…in v space around the low-energy mean of each rotamer, which allowed development of the influential Dead-End Elimination method in protein design.22 ,23 A third type of rotamer soft-ware19,24 evaluates a given side-chain conformation by its position in a multi-dimensional probability distribution.”
De Novo Protein Design for Novel Folds using Guided Conditional Wasserstein Generative Adversarial Networks (gcWGAN) (2019, unknown): “Currentprotein(re)designalgorithmsfall inthreeclasses: 1)exactalgorithmssuchasdead-endelimination, A ∗ , and costfunctionnetworks(Gainza etal.”