OmniCellTOSG: The First Cell Text-Omic Signaling Graphs Dataset for Joint LLM and GNN Modeling

2025-04-02

AI Summary

This study addresses the modeling challenge posed by the extreme heterogeneity of cellular signaling systems—governed by multiple factors including age, sex, and disease status, and involving thousands of genes/proteins across diverse cell subtypes. We propose the first Text–Omics Signaling Graph (TOSG) paradigm. Leveraging 120 million single-cell RNA-seq profiles, we construct a large-scale heterogeneous graph dataset that uniquely integrates quantitative omics signals with rich biological semantic annotations (e.g., pathways, drugs, diseases). Methodologically, we innovatively couple text embeddings, graph neural networks (GNNs), and large language models (LLMs) within a unified PyTorch-based end-to-end framework. The released open-source TOSG dataset is extensible and plug-and-play, markedly enhancing interpretability in cellular signaling modeling. It further enables generalizable cross-organ, cross-disease, and cross-age analyses, establishing a novel paradigm for precision medicine.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Complex cell signaling systems -- governed by varying protein abundances and interactions -- generate diverse cell types across organs. These systems evolve under influences such as age, sex, diet, environmental exposures, and diseases, making them challenging to decode given the involvement of tens of thousands of genes and proteins. Recently, hundreds of millions of single-cell omics data have provided a robust foundation for understanding these signaling networks within various cell subpopulations and conditions. Inspired by the success of large foundation models (for example, large language models and large vision models) pre-trained on massive datasets, we introduce OmniCellTOSG, the first dataset of cell text-omic signaling graphs (TOSGs). Each TOSG represents the signaling network of an individual or meta-cell and is labeled with information such as organ, disease, sex, age, and cell subtype. OmniCellTOSG offers two key contributions. First, it introduces a novel graph model that integrates human-readable annotations -- such as biological functions, cellular locations, signaling pathways, related diseases, and drugs -- with quantitative gene and protein abundance data, enabling graph reasoning to decode cell signaling. This approach calls for new joint models combining large language models and graph neural networks. Second, the dataset is built from single-cell RNA sequencing data of approximately 120 million cells from diverse tissues and conditions (healthy and diseased) and is fully compatible with PyTorch. This facilitates the development of innovative cell signaling models that could transform research in life sciences, healthcare, and precision medicine. The OmniCellTOSG dataset is continuously expanding and will be updated regularly. The dataset and code are available at https://github.com/FuhaiLiAiLab/OmniCellTOSG.

Problem

• Decoding complex cell signaling systems influenced by genes and proteins
• Integrating text-omic data for joint LLM and GNN modeling
• Building scalable datasets for cell signaling research in healthcare

Innovation

• Integrates human-readable annotations with gene data
• Combines large language models and graph neural networks
• Built from 120 million single-cell RNA sequencing data