Transforming the Language of Life
Ananthan Nambiar, Maeve Heflin, Simon Liu, Sergei Maslov, Mark Hopkins, Anna Ritz
Abstract
The scientific community is rapidly generating protein sequence information, but only a fraction of these proteins can be experimentally characterized. While promising deep learning approaches for protein prediction tasks have emerged, they have computational limitations or are designed to solve a specific task. We present a Transformer neural network that pre-trains task-agnostic sequence representations. This model is fine-tuned to solve two different protein prediction tasks: protein family classification and protein interaction prediction. Our method is comparable to existing state-of-the-art approaches for protein family classification while being much more general than other architectures. Further, our method outperforms all other approaches for protein interaction prediction. These results offer a promising framework for fine-tuning the pre-trained sequence representations for other protein prediction tasks.