Context-specific interaction networks from vector representation of words

Abstract

In recent years, the number of biomedical publications has steadfastly grown, resulting in a rich source of untapped new knowledge. Most biomedical facts are however not readily available, but buried in the form of unstructured text, and hence their exploitation requires the time-consuming manual curation of published articles. Here we present INtERAcT, a novel approach to extract protein-protein interactions from a corpus of biomedical articles related to a broad range of scientific domains in a completely unsupervised way. INtERAcT exploits vector representation of words, computed on a corpus of domain specific knowledge, and implements a new metric that estimates an interaction score between two molecules in the space where the corresponding words are embedded. We demonstrate the power of INtERAcT by reconstructing the molecular pathways associated to 10 different cancer types using a corpus of disease-specific articles for each cancer type. We evaluate INtERAcT using STRING database as a benchmark, and show that our metric outperforms currently adopted approaches for similarity computation at the task of identifying known molecular interactions in all studied cancer types. Furthermore, our approach does not require text annotation, manual curation or the definition of semantic rules based on expert knowledge, and hence it can be easily and efficiently applied to different scientific domains. Our findings suggest that INtERAcT may increase our capability to summarize the understanding of a specific disease using the published literature in an automated and completely unsupervised fashion.