Word and Sentence Embedding Tools to Measure Semantic Similarity of Gene Ontology Terms by Their Definitions

Abstract

The gene ontology (GO) database contains GO terms that describe biological functions of genes. Previous methods for comparing GO terms have relied on the fact that GO terms are organized into a tree structure. Under this paradigm, the locations of two GO terms in the tree dictate their similarity score. In this article, we introduce two new solutions for this problem by focusing instead on the definitions of the GO terms. We apply neural networkbased techniques from the natural language processing (NLP) domain. The first method does not rely on the GO tree, whereas the second indirectly depends on the GO tree. In our first approach, we compare two GO definitions by treating them as two unordered sets of words. The word similarity is estimated by a word embedding model that maps words into an N-dimensional space. In our second approach, we account for the word-ordering within a sentence. We use a sentence encoder to embed GO definitions into vectors and estimate how likely one definition entails another. We validate our methods in two ways. In the first experiment, we test the model's ability to differentiate a true protein-protein network from a randomly generated network. In the second experiment, we test the model in identifying orthologs from randomly matched genes in human, mouse, and fly. In both experiments, a hybrid of NLP and GO tree-based method achieves the best classification accuracy.

Evaluating Representations for Gene Ontology Terms

“…This paper will focus on the second data resource, the Gene Ontology itself. On this end, there have been efforts in developing distance metric for GO terms [7,12,14,16,18,21,28]. Most traditional methods for computing semantic similarity of GO terms rely on the Information Content (IC) and the GO tree.…”

“…Methods based on shared ancestors and IC values have two drawbacks. First, they do not consider the definitions of the GO terms which have been shown to yield better semantic similarity scores in many cases [7,14]. Second, they are unable to create vector representations of GO terms which then can be integrated into other annotation models to predict functions for protein sequences.…”

“…In recent years, with the advancement of computing power, neural network (NN) encoders have been introduced to map GO terms into vectors based on the principle that the vectors of related GO terms should have similar values [7,21]. Once the GO vectors are created, then their distance metric naturally follows; for example, cosine similarity or Euclidean distance can be applied.…”

“…GO names) into vectors. For example, consider two recent methods [7] and [21]. [7] apply Long-short Term Memory on the GO definitions; whereas, Onto2vec in [21] apply Word2vec on axioms, for example "GO:0060611 is_subclass GO:0060612", to capture relatedness of GO entities by using the vectors representing their GO names.…”

“…Moreover, despite these methods providing the GO vectors, there have not been works assessing how do these vectors affect the prediction of GO labels for protein sequences; for example, do these GO vectors indeed increase the function annotation accuracy? Also, the recent GO definition encoder in [7] uses LSTM as its key component. In the past year, a new NN method Bidirectional Encoder Representations from Transformers (BERT) has achieved the state-of-the-art results when compared to LSTM-based models in several language tasks such as textual entailment, name entity recognition, sentimental analysis, and language translation [6].…”