Workflow from Scientific Research

Pipeline for semi-automated curation of COVID-19 immune signatures. Data acquisition utilized CORD-19 which required prepossessing; including substantially filtering of the dataset and removing duplicate entries. Triage divides the articles into one of 3 relevant (Type A, Type B and Type C) or 2 not-relevant (review article and no signature) classes, which are then used to build a classifier to provide further articles for triage as well as directly for solicitation. Solicitation is done in a semi-automated fashion using an email template and an online form for the author to complete. After solicitation the information is made available via covid-signatures.org .

DOI