Automated assembly of molecular mechanisms at scale from text mining and curated databases

Abstract

The analysis of omic data depends on machine‐readable information about protein interactions, modifications, and activities as found in protein interaction networks, databases of post‐translational modifications, and curated models of gene and protein function. These resources typically depend heavily on human curation. Natural language processing systems that read the primary literature have the potential to substantially extend knowledge resources while reducing the burden on human curators. However, machine‐reading systems are limited by high error rates and commonly generate fragmentary and redundant information. Here, we describe an approach to precisely assemble molecular mechanisms at scale using multiple natural language processing systems and the Integrated Network and Dynamical Reasoning Assembler (INDRA). INDRA identifies full and partial overlaps in information extracted from published papers and pathway databases, uses predictive models to improve the reliability of machine reading, and thereby assembles individual pieces of information into non‐redundant and broadly usable mechanistic knowledge. Using INDRA to create high‐quality corpora of causal knowledge we show it is possible to extend protein–protein interaction databases and explain co‐dependencies in the Cancer Dependency Map. image INDRA assembles molecular mechanisms from text mining and databases by normalizing entities, resolving redundancies and estimating technical reliability. These mechanisms can be used to extend existing databases and generate mechanistic explanations for high‐throughput experimental data. Molecular and mechanistic biology knowledge is found in redundant fragments across both the literature and databases. INDRA integrates multiple text mining systems and information in curated databases using a principled approach to allow the assembly of fragmentary knowledge. Predictive models of text mining reliability are developed using frequencies of literature mentions, overlap among multiple reading systems, and other features. Assembled knowledge extends protein‐protein interactions in BioGRID and can provide explanations for co‐dependencies in the Cancer Dependency Map.