Deep Semantic Protein Representation for Annotation, Discovery, and Engineering

By Ariel S. Schwartz, Gregory Hannum, Zach Dwiel, Michael E. Smoot, A. Grant, Jason Knight, Scott A. Becker, Jonathan R Eads, M. LaFave, Harini Eavani and 3 more. 2018

21 citations recorded by the source corpus.

Computational assignment of function to proteins with no known homologs is still an unsolved problem. We have created a novel, function-based approach to protein annotation and discovery called D-SPACE (Deep Semantic Protein Annotation Classification and Exploration), comprised of a multi-task, multi-label deep neural network trained on over 70 million proteins. Distinct from homology and motif-based methods, D-SPACE encodes proteins in high-dimensional representations (embeddings), allowing the accurate assignment of over 180,000 labels for 13 distinct tasks. The embedding representation enables fast searches for functionally related proteins, including homologs undetectable by traditional approaches. D-SPACE annotates all 109 million proteins in UniProt in under 35 hours on a single computer and searches the entirety of these in seconds. D-SPACE further quantifies the relative functional effect of mutations, facilitating rapid in silico mutagenesis for protein engineering applications. D-SPACE incorporates protein annotation, search, and other exploratory efforts into a single cohesive model.

Subfields: Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

1. Kevin Kaichuang Yang
2. Zachary Wu
3. Frances H. Arnold
4. Bonnie Berger
5. Tristan Bepler

Citations in the corpus

• Machine-learning-guided directed evolution for protein engineering (2018, background): “If accuracy is insufficient, learned encodings may be able to improve performance 74,75 .”
• Machine learning in protein engineering (2018, background): “However, more sophisticated continuous vector encodings of sequences can be learned from patterns in unlabeled sequences (Asgari & Mofrad, 2015; Mazzaferro, 2017; Ng, 2017; Kimothi et al., 2016; Yang et al., 2018a; Schwartz et al., 2018).”