EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cross-modal contrastive learning decodes developmental regulatory features through chromatin potential analysis

Yueyuxiao Yang iD, Chenxi Xie iD, Qiushun He iD, Meng Yang iD

GigaScience · 2025

DOI: 10.1093/gigascience/giaf053 ↗

Kurz gefasst

Fachartikel in der Zeitschrift GigaScience, 2025. Verfasst von Yueyuxiao Yang und 3 weiteren Autor:innen. Beteiligte Einrichtung: MGI Tech Co., Ltd., Shenzhen 518083, China. Hauptthemen laut MEDLINE: Chromatin, Computational Biology, Machine Learning, Transcription, Genetic. Die Arbeit nennt 99 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Emerging large-scale multimodal single-cell data jointly measure chromatin accessibility and transcription in the same cell, thus reconciling matched data paves an integrated route for comprehensive regulatory analysis.

Findings

Here, we introduce Attune, a cross-modal contrastive learning framework to align paired gene expression and accessibility information. Systematic benchmarking shows Attune’s superior performance for omics integration and gene expression prediction. We further introduce transformer-based cross-modal attention over fine-tuned gene and peak embeddings to infer regulatory interaction and discover significant differential signals of cell subtypes. Applied to a hair follicle maturation dataset, Attune reveals chromatin potential for the bifunctional transcription factor Gli3 at the gene level. In addition, the paired representations determine transmitted states across neonatal and mature cell types of cortical neuron differentiation at the cell level. Taken together, Attune offers an approach for regulatory inference across omics layers and enables more advanced omics analyses.

Conclusions

Attune offers a versatile framework for integrating gene expression and chromatin accessibility, enabling the inference of regulatory mechanisms and the prediction of gene expression from cross-modal data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ChromatinComputational BiologyMachine LearningTranscription, GeneticSingle-Cell Gene Expression AnalysisChromatin Immunoprecipitation SequencingDatasets as TopicGene Expression Regulation, DevelopmentalHumansAnimalsMiceZinc Finger Protein Gli3Cell DifferentiationHair FollicleNeuronsCerebral CortexNerve Tissue Proteins

Stichwörter der Autor:innen

chromatin potential analysiscontrastive learningdevelopmental regulationmultimodality

Substanzen

ChromatinGli3 protein, mouseZinc Finger Protein Gli3Nerve Tissue Proteins

Autor:innen und Institutionen

  • MGI Tech Co., Ltd., Shenzhen 518083, China.

ORCID-Profile: Yueyuxiao Yang, Chenxi Xie, Qiushun He, Meng Yang

Zitieren

APA

Yang, Y., Xie, C., He, Q., & Yang, M. (2025). Cross-modal contrastive learning decodes developmental regulatory features through chromatin potential analysis. GigaScience. https://doi.org/10.1093/gigascience/giaf053

Vancouver

Yang Y, Xie C, He Q, Yang M. Cross-modal contrastive learning decodes developmental regulatory features through chromatin potential analysis. GigaScience. 2025. doi:10.1093/gigascience/giaf053

BibTeX
@article{Yang2025,
  author = {Yang, Yueyuxiao and Xie, Chenxi and He, Qiushun and Yang, Meng},
  title = {Cross-modal contrastive learning decodes developmental regulatory features through chromatin potential analysis},
  journal = {GigaScience},
  year = {2025},
  doi = {10.1093/gigascience/giaf053}
}
Kostenlos starten →