Your browser doesn't support javascript.
loading
HE2Gene: image-to-RNA translation via multi-task learning for spatial transcriptomics data.
Chen, Xingjian; Lin, Jiecong; Wang, Yuchen; Zhang, Weitong; Xie, Weidun; Zheng, Zetian; Wong, Ka-Chun.
Afiliación
  • Chen X; Cutaneous Biology Research Center, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02129, USA.
  • Lin J; Department of Computer Science, City University of Hong Kong, Kowloog Tong 999077, Hong Kong SAR.
  • Wang Y; Molecular Pathology Unit, Center for Cancer Research, Massachusetts General Hospital, Department of Pathology, Harvard Medical School, Boston, MA 02129, USA.
  • Zhang W; Department of Computer Science, The University of Hong Kong, Pokfulam 999077, Hong Kong SAR.
  • Xie W; Department of Computer Science, City University of Hong Kong, Kowloog Tong 999077, Hong Kong SAR.
  • Zheng Z; Department of Computer Science, City University of Hong Kong, Kowloog Tong 999077, Hong Kong SAR.
  • Wong KC; Department of Computer Science, City University of Hong Kong, Kowloog Tong 999077, Hong Kong SAR.
Bioinformatics ; 40(6)2024 06 03.
Article en En | MEDLINE | ID: mdl-38837395
ABSTRACT
MOTIVATION Tissue context and molecular profiling are commonly used measures in understanding normal development and disease pathology. In recent years, the development of spatial molecular profiling technologies (e.g. spatial resolved transcriptomics) has enabled the exploration of quantitative links between tissue morphology and gene expression. However, these technologies remain expensive and time-consuming, with subsequent analyses necessitating high-throughput pathological annotations. On the other hand, existing computational tools are limited to predicting only a few dozen to several hundred genes, and the majority of the methods are designed for bulk RNA-seq.

RESULTS:

In this context, we propose HE2Gene, the first multi-task learning-based method capable of predicting tens of thousands of spot-level gene expressions along with pathological annotations from H&E-stained images. Experimental results demonstrate that HE2Gene is comparable to state-of-the-art methods and generalizes well on an external dataset without the need for re-training. Moreover, HE2Gene preserves the annotated spatial domains and has the potential to identify biomarkers. This capability facilitates cancer diagnosis and broadens its applicability to investigate gene-disease associations. AVAILABILITY AND IMPLEMENTATION The source code and data information has been deposited at https//github.com/Microbiods/HE2Gene.
Asunto(s)
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Transcriptoma Límite: Humans Idioma: En Revista: Bioinformatics Asunto de la revista: INFORMATICA MEDICA Año: 2024 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Reino Unido
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Transcriptoma Límite: Humans Idioma: En Revista: Bioinformatics Asunto de la revista: INFORMATICA MEDICA Año: 2024 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Reino Unido