Saved in:
Bibliographic Details
Main Authors: Mupparapu, Sohan, Krishnamurthy, Parameswari, Puduppully, Ratish
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.17766
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913906602016768
author Mupparapu, Sohan
Krishnamurthy, Parameswari
Puduppully, Ratish
author_facet Mupparapu, Sohan
Krishnamurthy, Parameswari
Puduppully, Ratish
contents Pretraining DNA language models (DNALMs) on the full human genome is resource-intensive, yet often considered necessary for strong downstream performance. Inspired by recent findings in NLP and long-context modeling, we explore an alternative: self-pretraining on task-specific, unlabeled data. Using the BEND benchmark, we show that DNALMs trained with self-pretraining match or exceed the performance of models trained from scratch under identical compute. While genome-scale pretraining may still offer higher absolute performance, task-specific self-pretraining provides a practical and compute-efficient strategy for building stronger supervised baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17766
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Genomic Models via Task-Specific Self-Pretraining
Mupparapu, Sohan
Krishnamurthy, Parameswari
Puduppully, Ratish
Genomics
Pretraining DNA language models (DNALMs) on the full human genome is resource-intensive, yet often considered necessary for strong downstream performance. Inspired by recent findings in NLP and long-context modeling, we explore an alternative: self-pretraining on task-specific, unlabeled data. Using the BEND benchmark, we show that DNALMs trained with self-pretraining match or exceed the performance of models trained from scratch under identical compute. While genome-scale pretraining may still offer higher absolute performance, task-specific self-pretraining provides a practical and compute-efficient strategy for building stronger supervised baselines.
title Improving Genomic Models via Task-Specific Self-Pretraining
topic Genomics
url https://arxiv.org/abs/2506.17766