AI Article Synopsis
- A new approach to genomics experiments involves doing fewer experiments and using computational methods to fill in the gaps, but there are still uncertainties about which imputation methods work best and how to evaluate their performance effectively.* -
- The study reviews 23 different methods from the ENCODE Imputation Challenge and discovers that assessing these methods is complicated by factors like changes in data collection practices, varying amounts of data, and overlapping evaluation metrics.* -
- The authors suggest practical solutions to these challenges and highlight promising areas for future research to improve the robustness of imputation methods in genomics.*
Article Abstract
A promising alternative to comprehensively performing genomics experiments is to, instead, perform a subset of experiments and use computational methods to impute the remainder. However, identifying the best imputation methods and what measures meaningfully evaluate performance are open questions. We address these questions by comprehensively analyzing 23 methods from the ENCODE Imputation Challenge. We find that imputation evaluations are challenging and confounded by distributional shifts from differences in data collection and processing over time, the amount of available data, and redundancy among performance measures. Our analyses suggest simple steps for overcoming these issues and promising directions for more robust research.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10111747 | PMC |
| http://dx.doi.org/10.1186/s13059-023-02915-y | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!