Genomic Foundationless Models: Pretraining Does Not Promise Performance
Keywords: genomics, biology, deep learning, pretraining
TL;DR: Current pretrained Genomic Foundation Models offer little to no advantage over randomly initialized models on many genomic tasks.
Abstract: The success of Large Language Models has inspired the development of Genomic Foundation Models (GFMs) through similar pretraining techniques. However, the relationship between pretraining performance and effectiveness in downstream genomic tasks remains unclear. Additionally, the high computational cost of pretraining raises questions about its cost-efficiency. To assess the usefulness of pretraining in genomics, we evaluated seven different GFMs across various benchmarks, comparing them to their counterparts with randomly initialized weights. Surprisingly, we found that randomly initialized models can match or even surpass the performance of pretrained GFMs in finetuning and feature extraction tasks. We also discovered that pretrained GFMs fail to capture clinically relevant genetic mutations, which are crucial for understanding genetic disorders and phenotypic traits. Our results indicate that most of the current pretrained GFMs lack a ``foundational'' understanding of genomics and provide minimal utility, even for basic tasks such as sequence classification. These findings collectively highlight the need for critically rethinking the pretraining approaches for genomics. Our code is available at https://github.com/nxifemwt/GFMs.
Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6924
Loading