Published March 18, 2022
| Version 1.0.0
Dataset
Open
Convolutions are competitive with transformers for protein sequence pretraining
Creators
Description
- Pretrained models of protein sequences. See https://github.com/microsoft/protein-sequence-models for instructions on how to load models.
- IDR datasets used for evaluation.
- March 2020 version of UniRef50 with splits used for training.
Files
cdc28_binding.csv
Files
(11.8 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:a5fdc095531e3742d1484d508b9c7c3c
|
151.6 MB | Download |
|
md5:54701ac812658debb909f835927724e0
|
2.5 MB | Download |
|
md5:2601f6b9971fe5ea1733067eb87a3398
|
2.6 GB | Download |
|
md5:68e67c7ecb8c300e1c652c4ae091d218
|
303.1 MB | Download |
|
md5:fd0ef9a4415167e5fc0afa50b3204c57
|
631.7 kB | Preview Download |
|
md5:62f16ce55c55cad4a75d8cfdbff945ac
|
637.1 kB | Preview Download |
|
md5:e2278f1d93836e8309cf4192b8455828
|
8.7 GB | Download |