Learning a functional grammar of protein domains using natural language word embedding techniques

Abstract

In this paper, using word2vec, a widely-used natural language processing method, we demonstrate that proteins domains may have a learnable implicit semantic "meaning" in the context of their functional contributions to multi-domain proteins in which they are found. Word2vec is a group of models which can be used to produce semantically meaningful embeddings of words or tokens in a fixed-dimension vector space. In this work, we treat multi-domain proteins as "sentences" where domain identifiers are tokens which may be considered as "words". Using all InterPro [1] pfam domain assignments we observe that the embedding could be used to suggest putative GO assignments for Pfam [2] Domains of Unknown Function. This article is protected by copyright. All rights reserved.