Evaluating the performance of drug-repurposing technologies. Issue 1 (January 2022)

• Record Type: Journal Article
• Authors: Schuler, James; Falls, Zackary; Mangione, William; Hudson, Matthew L.; Bruggemann, Liana; Samudrala, Ram
• Is Part Of: Drug discovery today. Volume 27:Issue 1(2022)
• Page Start: 49
• Page End: 64
• Publication Date: 2022-01
• Subjects: Drug repurposing -- Computational drug repurposing -- Drug repositioning -- Computational drug repositioning -- Biomedical Informatics -- Performance evaluation -- Performance metrics -- Area under the curve -- Normalized discounted cumulative gain -- Validation; Drugs -- Design -- Periodicals; Drugs -- Research -- Periodicals; 615.1
• DOI: 10.1016/j.drudis.2021.08.002
• Languages: English
• ISSNs: 1359-6446

Abstract

Highlights: Drug repurposing technology comparison is enhanced by better metrics. We review and rate currently used performance metrics. We report performance of our repurposing technology CANDO with these metrics. Data, standards, and validation greatly impact performance. Best performance metrics to use are BEDROC and NDCG. Abstract: Drug-repurposing technologies are growing in number and maturing. However, comparisons to each other and to reality are hindered because of a lack of consensus with respect to performance evaluation. Such comparability is necessary to determine scientific merit and to ensure that only meaningful predictions from repurposing technologies carry through to further validation and eventual patient use. Here, we review and compare performance evaluation measures for these technologies using version 2 of our shotgun repurposing Computational Analysis of Novel Drug Opportunities (CANDO) platform to illustrate their benefits, drawbacks, and limitations. Understanding and using different performance evaluation metrics ensures robust cross-platform comparability, enabling us to continue to strive toward optimal repurposing by decreasing the time and cost of drug discovery and development.