Whole Genome Transformers for Gene Interaction Effects in Microbiome Habitat Prediction
MCML Authors
Zhufeng Li
Niki Kilbertus
Prof. Dr.
Core PI
Abstract
Zhufeng Li
Niki Kilbertus
Prof. Dr.
Core PI
Abstract
Leveraging the vast genetic diversity within microbiomes offers unparalleled insights into complex phenotypes, yet the task of accurately predicting and understanding such traits from genomic data remains challenging. We propose a framework that leverages existing large models for gene vectorization to predict habitat specificity from entire microbial genome sequences. Based on our model, we develop attribution techniques to elucidate gene interaction effects that drive microbial adaptation to diverse environments. We train and validate our approach on a large dataset of high-quality microbiome genomes from different habitats. We not only demonstrate solid predictive performance but also pioneer leveraging sequence-level information of entire genomes to reveal the genetic foundations of complex phenotypes. Our attribution recovers known important interaction networks and proposes new candidates for experimental follow-up.
inproceedings LCY+24
MLGenX @ICLR 2024
Workshop Machine Learning for Genomics Explorations at the 12th International Conference on Learning Representations. Vienna, Austria, May 07-11, 2024.Authors
Z. Li • S. S. Cranganore • N. Youngblut • N. KilbertusLinks
URLResearch Area
BibTeXKey: LCY+24