The state of clinical data is a barrier to the development of machine learning models to improve healthcare. Uncontrolled clinical freetext is common in both the patient and clinical trials: the resulting spelling, grammatical errors, phrasing variation, and other resulting variability results in difficult-to-leverage data. As part of our effort to harmonize the Aggregate Analysis of ClinicalTrials.gov (AACT) drop-withdrawal reasons to a controlled vocabulary, we explored two solutions. Elastic's fuzzy matching capability matched entries in the AACT Drop-Withdrawal table to a list of user-specified terms (74.6% coverage). The second approach was a custom pipeline employing NLP preprocessing, Levenshtein Distance (Fuzzy Matching), and semantic similarity mapping using a pre-trained FastText Model (98% coverage). Although manual oversight is still required, the amount of effort to harmonize with a controlled vocabulary is notably reduced. This work enables the rapid harmonization of clinical databases, allowing them to be leveraged for machine learning and analytics.

MOTIVATION: The growth of sequence data has been accompanied by an increasing need to analyze data on distributed computer clusters. The use of these systems for routine analysis requires scalable and robust software for data management of large datasets. Software is also needed to simplify data management and make large-scale bioinformatics analysis accessible and reproducible to a wide class of target users. RESULTS: We have developed a workflow management system named Ergatis that enables users to build, execute and monitor pipelines for computational analysis of genomics data. Ergatis contains preconfigured components and template pipelines for a number of common bioinformatics tasks such as prokaryotic genome annotation and genome comparisons. Outputs from many of these components can be loaded into a Chado relational database. Ergatis was designed to be accessible to a broad class of users and provides a user friendly, web-based interface. Ergatis supports high-throughput batch processing on distributed compute clusters and has been used for data management in a number of genome annotation and comparative genomics projects. AVAILABILITY: Ergatis is an open-source project and is freely available at http://ergatis.sourceforge.net.