A Phylogenetic Approach to Genomic Language Modeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Albors, Carlos, Li, Jianan Canal, Benegas, Gonzalo, Ye, Chengzhong, Song, Yun S.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918398627151872
author Albors, Carlos
Li, Jianan Canal
Benegas, Gonzalo
Ye, Chengzhong
Song, Yun S.
author_facet Albors, Carlos
Li, Jianan Canal
Benegas, Gonzalo
Ye, Chengzhong
Song, Yun S.
contents Genomic language models (gLMs) have shown mostly modest success in identifying evolutionarily constrained elements in mammalian genomes. To address this issue, we introduce a novel framework for training gLMs that explicitly models nucleotide evolution on phylogenetic trees using multispecies whole-genome alignments. Our approach integrates an alignment into the loss function during training but does not require it for making predictions, thereby enhancing the model's applicability. We applied this framework to train PhyloGPN, a model that excels at predicting functionally disruptive variants from a single sequence alone and demonstrates strong transfer learning capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2503_03773
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Phylogenetic Approach to Genomic Language Modeling
Albors, Carlos
Li, Jianan Canal
Benegas, Gonzalo
Ye, Chengzhong
Song, Yun S.
Genomics
Machine Learning
Genomic language models (gLMs) have shown mostly modest success in identifying evolutionarily constrained elements in mammalian genomes. To address this issue, we introduce a novel framework for training gLMs that explicitly models nucleotide evolution on phylogenetic trees using multispecies whole-genome alignments. Our approach integrates an alignment into the loss function during training but does not require it for making predictions, thereby enhancing the model's applicability. We applied this framework to train PhyloGPN, a model that excels at predicting functionally disruptive variants from a single sequence alone and demonstrates strong transfer learning capabilities.
title A Phylogenetic Approach to Genomic Language Modeling
topic Genomics
Machine Learning
url https://arxiv.org/abs/2503.03773