Multi-model biological and sequence information fusion for gene regulatory network inference from single-cell transcriptomics
- 1hunan normal university
Abstract
Identification of transcription factor target gene interactions and construction of the gene regulatory networks (GRNs) are essential for understanding the molecular mechanisms underlying transcriptional gene regulation. Large scale single cell transcriptomics across different tissues offers unprecedented resolution of cellular diversity and regulatory dynamics by capturing gene expression heterogeneity. However, existing methods often lack effective multimodal integration and fail to fully exploit the hierarchical structure in Gene Ontology (GO) and gene sequence level representations, which limits their ability for predictive performance and biological interpretability. We present scMGFGRN, a multi-model deep learning framework that integrates single-cell transcriptomic profiles with GO hierarchical relationships, gene sequences by leveraging denoising auto encoders, graph attention feature extraction and pertained DNA language model to capture multi-source dependencies within multi-model biological knowledge, while its gated multi head attention module effectively identifies informative regulatory signatures and integrate complementary features from different sources to predict accurate gene regulatory networks. Benchmarking on the seven datasets of human and mouse demonstrates that scMGFGRN outperforms state of the art methods in identifying GRNs. Further analyses reveal that scMGFGRN effectively identifies novel TF gene interactions (TGIs) and reconstructs cell type specific GRNs. Interpretability analysis reveals the contribution patterns of heterogeneous biological sources, demonstrating the ability of scMGFGRN to integrate transcriptomic profiles with multi model structure information.
Related
- DeepSCENIC: transfer learning from sequence-to-function models enables causal gene regulatory network inference
- Evidence for a regulatory role of the evolutionarily conserved sequence complementarity between tRNAs
- Biological and technical spatial variation in spatial transcriptomics
- Few-shot regulatory sequence design with a genomic language model
- Where single-cell foundation models help: a benchmark of annotation, perturbation and regulatory inference against simple baselines
BibTeX
@misc{zhong2026multimodel,
title = {{Multi-model biological and sequence information fusion for gene regulatory network inference from single-cell transcriptomics}},
author = {l. zhong and B. Yan and J. Wang and m. xie},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.13.751326},
url = {https://www.biorxiv.org/content/10.64898/2026.09.13.751326v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Multi-model biological and sequence information fusion for gene regulatory network inference from single-cell transcriptomics
AU - l. zhong
AU - B. Yan
AU - J. Wang
AU - m. xie
PY - 2026
DA - 2026/09/13
PB - bioRxiv
DO - 10.64898/2026.09.13.751326
UR - https://www.biorxiv.org/content/10.64898/2026.09.13.751326v1
AB - Identification of transcription factor target gene interactions and construction of the gene regulatory networks (GRNs) are essential for understanding the molecular mechanisms underlying transcriptional gene regulation. Large scale single cell transcriptomics across different tissues offers unprecedented resolution of cellular diversity and regulatory dynamics by capturing gene expression heterogeneity. However, existing methods often lack effective multimodal integration and fail to fully exploit the hierarchical structure in Gene Ontology (GO) and gene sequence level representations, which limits their ability for predictive performance and biological interpretability. We present scMGFGRN, a multi-model deep learning framework that integrates single-cell transcriptomic profiles with GO hierarchical relationships, gene sequences by leveraging denoising auto encoders, graph attention feature extraction and pertained DNA language model to capture multi-source dependencies within multi-model biological knowledge, while its gated multi head attention module effectively identifies informative regulatory signatures and integrate complementary features from different sources to predict accurate gene regulatory networks. Benchmarking on the seven datasets of human and mouse demonstrates that scMGFGRN outperforms state of the art methods in identifying GRNs. Further analyses reveal that scMGFGRN effectively identifies novel TF gene interactions (TGIs) and reconstructs cell type specific GRNs. Interpretability analysis reveals the contribution patterns of heterogeneous biological sources, demonstrating the ability of scMGFGRN to integrate transcriptomic profiles with multi model structure information.
ER -