Ig-VAE: Generative modeling of protein structure by direct 3D coordinate generation.
PLoS Comput Biol
; 18(6): e1010271, 2022 06.
Artigo
em Inglês
| MEDLINE | ID: covidwho-1910466
ABSTRACT
While deep learning models have seen increasing applications in protein science, few have been implemented for protein backbone generation-an important task in structure-based problems such as active site and interface design. We present a new approach to building class-specific backbones, using a variational auto-encoder to directly generate the 3D coordinates of immunoglobulins. Our model is torsion- and distance-aware, learns a high-resolution embedding of the dataset, and generates novel, high-quality structures compatible with existing design tools. We show that the Ig-VAE can be used with Rosetta to create a computational model of a SARS-CoV2-RBD binder via latent space sampling. We further demonstrate that the model's generative prior is a powerful tool for guiding computational protein design, motivating a new paradigm under which backbone design is solved as constrained optimization problem in the latent space of a generative model.
Texto completo:
Disponível
Coleções:
Bases de dados internacionais
Base de dados:
MEDLINE
Assunto principal:
RNA Viral
/
COVID-19
Limite:
Humanos
Idioma:
Inglês
Revista:
PLoS Comput Biol
Assunto da revista:
Biologia
/
Informática Médica
Ano de publicação:
2022
Tipo de documento:
Artigo
País de afiliação:
Journal.pcbi.1010271
Similares
MEDLINE
...
LILACS
LIS