Using Deep Learning to Annotate the Protein Universe

Abstract

Understanding the relationship between amino acid sequence and protein function is a long-standing problem in molecular biology with far-reaching scientific implications. Despite six decades of progress, state-of-the-art techniques cannot annotate 1/3 of microbial protein sequences, hampering our ability to exploit sequences collected from diverse organisms. To address this, we report a deep learning model that learns the relationship between unaligned amino acid sequences and their functional classification across all 17929 families of the Pfam database. Using the Pfam seed sequences we establish a rigorous benchmark assessment and find a dilated convolutional model that reduces the error of both BLASTp and pHMMs by a factor of nine. Using 80% of the full Pfam database we train a protein family predictor that is more accurate and over 200 times faster than BLASTp, while learning sequence features it was not trained on such as structural disorder and transmembrane helices. Our model co-locates sequences from unseen families in embedding space, allowing sequences from novel families to be accurately annotated. These results suggest deep learning models will be a core component of future protein function prediction tools.