Published August 3, 2022
| Version v1
Journal article
Open
ContactLib-ATT: a structure-based search engine for homologous proteins
Creators
Description
We propose a two-level general-purpose protein structure embedding neural network, called ContactLib-ATT. On local embedding level, a biologically more meaningful contact context is introduced. On global embedding level, attention-based encoder layers are employed for better global representation learning. Thus, ContactLib-ATT is used to simulate a structure-based search engine for remote homologous proteins.
Files
Files
(211.1 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:9b9fcfc2cca8d57676a69f9855c14eb2
|
211.1 MB | Download |