BEND: Benchmarking DNA Language Models on biologically meaningful tasks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917634563375104 |
|---|---|
| author | Marin, Frederikke Isa Teufel, Felix Horlacher, Marc Madsen, Dennis Pultz, Dennis Winther, Ole Boomsma, Wouter |
| author_facet | Marin, Frederikke Isa Teufel, Felix Horlacher, Marc Madsen, Dennis Pultz, Dennis Winther, Ole Boomsma, Wouter |
| contents | The genome sequence contains the blueprint for governing cellular processes. While the availability of genomes has vastly increased over the last decades, experimental annotation of the various functional, non-coding and regulatory elements encoded in the DNA sequence remains both expensive and challenging. This has sparked interest in unsupervised language modeling of genomic DNA, a paradigm that has seen great success for protein sequence data. Although various DNA language models have been proposed, evaluation tasks often differ between individual works, and might not fully recapitulate the fundamental challenges of genome annotation, including the length, scale and sparsity of the data. In this study, we introduce BEND, a Benchmark for DNA language models, featuring a collection of realistic and biologically meaningful downstream tasks defined on the human genome. We find that embeddings from current DNA LMs can approach performance of expert methods on some tasks, but only capture limited information about long-range features. BEND is available at https://github.com/frederikkemarin/BEND. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_12570 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | BEND: Benchmarking DNA Language Models on biologically meaningful tasks Marin, Frederikke Isa Teufel, Felix Horlacher, Marc Madsen, Dennis Pultz, Dennis Winther, Ole Boomsma, Wouter Genomics Machine Learning The genome sequence contains the blueprint for governing cellular processes. While the availability of genomes has vastly increased over the last decades, experimental annotation of the various functional, non-coding and regulatory elements encoded in the DNA sequence remains both expensive and challenging. This has sparked interest in unsupervised language modeling of genomic DNA, a paradigm that has seen great success for protein sequence data. Although various DNA language models have been proposed, evaluation tasks often differ between individual works, and might not fully recapitulate the fundamental challenges of genome annotation, including the length, scale and sparsity of the data. In this study, we introduce BEND, a Benchmark for DNA language models, featuring a collection of realistic and biologically meaningful downstream tasks defined on the human genome. We find that embeddings from current DNA LMs can approach performance of expert methods on some tasks, but only capture limited information about long-range features. BEND is available at https://github.com/frederikkemarin/BEND. |
| title | BEND: Benchmarking DNA Language Models on biologically meaningful tasks |
| topic | Genomics Machine Learning |
| url | https://arxiv.org/abs/2311.12570 |