no code implementations • 7 Dec 2023 • Divya Nori, Simon V. Mathis, Amir Shanehsazzadeh
The success of therapeutic antibodies relies on their ability to selectively bind antigens.
no code implementations • 31 Oct 2020 • Amir Shanehsazzadeh, David Belanger, David Dohan
In this paper, we show that CNN models trained solely using supervised learning both compete with and sometimes outperform the best models from TAPE that leverage expensive pretraining on large protein datasets.
1 code implementation • 15 Oct 2020 • Amir Shanehsazzadeh, David Belanger, David Dohan
We consider transformer (BERT) protein language models that are pretrained on the TrEMBL data set and learn fixed-length embeddings on top of them with contextual lenses.