Spatial Transcriptomics Analysis of Zero-shot Gene Expression Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yan, Hossain, Md Zakir, Li, Xuesong, Rahman, Shafin, Stone, Eric
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916106474618880
author Yang, Yan
Hossain, Md Zakir
Li, Xuesong
Rahman, Shafin
Stone, Eric
author_facet Yang, Yan
Hossain, Md Zakir
Li, Xuesong
Rahman, Shafin
Stone, Eric
contents Spatial transcriptomics (ST) captures gene expression within distinct regions (i.e., windows) of a tissue slide. Traditional supervised learning frameworks applied to model ST are constrained to predicting expression from slide image windows for gene types seen during training, failing to generalize to unseen gene types. To overcome this limitation, we propose a semantic guided network (SGN), a pioneering zero-shot framework for predicting gene expression from slide image windows. Considering a gene type can be described by functionality and phenotype, we dynamically embed a gene type to a vector per its functionality and phenotype, and employ this vector to project slide image windows to gene expression in feature space, unleashing zero-shot expression prediction for unseen gene types. The gene type functionality and phenotype are queried with a carefully designed prompt from a pre-trained large language model (LLM). On standard benchmark datasets, we demonstrate competitive zero-shot performance compared to past state-of-the-art supervised learning approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2401_14772
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Spatial Transcriptomics Analysis of Zero-shot Gene Expression Prediction
Yang, Yan
Hossain, Md Zakir
Li, Xuesong
Rahman, Shafin
Stone, Eric
Computer Vision and Pattern Recognition
Spatial transcriptomics (ST) captures gene expression within distinct regions (i.e., windows) of a tissue slide. Traditional supervised learning frameworks applied to model ST are constrained to predicting expression from slide image windows for gene types seen during training, failing to generalize to unseen gene types. To overcome this limitation, we propose a semantic guided network (SGN), a pioneering zero-shot framework for predicting gene expression from slide image windows. Considering a gene type can be described by functionality and phenotype, we dynamically embed a gene type to a vector per its functionality and phenotype, and employ this vector to project slide image windows to gene expression in feature space, unleashing zero-shot expression prediction for unseen gene types. The gene type functionality and phenotype are queried with a carefully designed prompt from a pre-trained large language model (LLM). On standard benchmark datasets, we demonstrate competitive zero-shot performance compared to past state-of-the-art supervised learning approaches.
title Spatial Transcriptomics Analysis of Zero-shot Gene Expression Prediction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.14772