Knowledge synthesis from 100 million biomedical documents augments the deep expression profiling of coronavirus receptors

AJ Venkatakrishnan; Arjun Puranik; Akash Anand; David Zemmour; Xiang Yao; Xiaoying Wu; Ramakrishna Chilaka; Dariusz K Murakowski; Kristopher Standish; Bharathwaj Raghunathan; Tyler Wagner; Enrique Garcia-Rivera; Hugo Solomon; Abhinav Garg; Rakesh Barve; Anuli Anyanwu-Ofili; Najat Khan; Venky Soundararajan

The nferX platform also supports a logical thought engine that enables AND (conjunction), OR (disjunction), and NOT (negation) queries -the universal logic gates. This engine is referred to as "dynamic adjacency" and leverages a highly distributed main memory approach that allows the computation of local scores for any type of logical query in real time. Fundamentally, this system allows a user to extract all 100-word fragments of text which meet the specified logical query. We then calculate local scores for all other tokens occurring within these fragments, which quantifies the likelihood (i.e. odds) of each token occurring this frequently within these textual fragments by chance.