Joint representation learning for retrieval and annotation of genomic interval sets
Preprint
Abstract
Motivation: As available genomic interval data increases in scale, we require fast systems to search it. A common approach is simple string matching to compare a search term to metadata, but this is limited by incomplete or inaccurate annotations. An alternative is to compare data directly through genomic region overlap analysis, but these approaches lead to challenges like sparsity, high dimensionality, and computational expense. We require novel methods to quickly and flexibly query large, messy genomic interval databases. Results: Here, we develop a genomic interval search system using representation learning. We train numerical embeddings for a collection of region sets simultaneously with their metadata labels, capturing similarity between region sets and their metadata in a low-dimensional space. Using these learned co-embeddings, we develop a system that solves three related information retrieval tasks using embedding distance computations: retrieving region sets related to a user query string; suggesting new labels for database region sets; and retrieving database region sets similar to a query region set. We evaluate these use cases and show that jointly learned representations of region sets and metadata are a promising approach for fast, flexible, and accurate genomic region information retrieval.Keywords
All Related Versions
- Published version: Bioengineering, 11 (3), 263.
This publication has 31 references indexed in Scilit:
- Epigenomic annotation-based interpretation of genomic data: from enrichment analysis to machine learningBioinformatics, 2017
- DATS, the data tag suite to enable discoverability of datasetsScientific Data, 2017
- Finding useful data across multiple biomedical data repositories using DataMedNature Genetics, 2017
- The NIH Big Data to Knowledge (BD2K) initiativeJournal of the American Medical Informatics Association, 2015
- Ontology-Based Search of Genomic MetadataIEEE/ACM Transactions on Computational Biology and Bioinformatics, 2015
- SRAdb: query and use public next-generation sequencing data from within RBMC Bioinformatics, 2013
- Tabix: fast retrieval of sequence features from generic TAB-delimited filesBioinformatics, 2011
- Breast and prostate cancer: more similar than differentNature Reviews Cancer, 2010
- BEDTools: a flexible suite of utilities for comparing genomic featuresBioinformatics, 2010
- A re-examination of text categorization methods1999