mosGraphGPT: a foundation model for multi-omic signaling graphs using generative AI
Heming Zhang1, Di Huang1, Emily Chen1,2,3
1Institute for Informatics, Data Science and Biostatistics (I2DB), Washington University School of Medicine.
Biorxiv : the Preprint Server for Biology
|August 16, 2024
Summary
This study introduces mosGraphGPT, a novel foundation model for multi-omic signaling graphs. It improves disease classification accuracy and interpretability by analyzing complex cellular signaling patterns.
Area of Science:
- Computational Biology
- Bioinformatics
- Genomics
Background:
- Generative pretrained models excel in NLP and computer vision.
- Foundation models for omics data can decode cellular signaling patterns.
- Existing models lack comprehensive integration of multi-omic data.
Purpose of the Study:
- To develop mosGraphGPT, a foundation model for multi-omic signaling (mos) graphs.
- To integrate and interpret multi-omic data using a multi-level signaling graph.
- To apply the model to cancer and Alzheimer's Disease data.
Main Methods:
- Pre-training mosGraphGPT on The Cancer Genome Atlas (TCGA) multi-omic cancer data.
- Fine-tuning the model on multi-omic data from Alzheimer's Disease (AD) studies.
- Utilizing a multi-level signaling graph for data integration and interpretation.
Main Results:
- The model significantly improved disease classification accuracy.
- mosGraphGPT demonstrated interpretability by identifying disease targets and signaling interactions.
- The developed model code is publicly available on GitHub.
Conclusions:
- mosGraphGPT offers a powerful new approach for analyzing multi-omic data.
- The model enhances understanding of complex cellular signaling in diseases.
- This work facilitates advancements in precision medicine and drug discovery.
Related Concept Videos
02:02Genomics
Genomics is the science of genomes: it is the study of all the genetic material of an organism. In humans, the genome consists of information carried in 23 pairs of chromosomes in the nucleus, as well as mitochondrial DNA. In genomics, both coding and non-coding DNA is sequenced and analyzed. Genomics allows a better understanding of all living things, their evolution, and their diversity. It has a myriad of uses: for example, to build phylogenetic trees, to improve productivity and...
01:18Signal Flow Graphs
Signal-flow graphs offer a streamlined and intuitive approach to representing control systems, providing an alternative to traditional block diagrams. These graphs use branches to symbolize systems and nodes to represent signals, effectively illustrating the relationships and interactions within the system.
In a signal-flow graph, branches denote the system's transfer functions, while nodes represent the signals. The direction of signal flow is indicated by arrows, with the corresponding...
In a signal-flow graph, branches denote the system's transfer functions, while nodes represent the signals. The direction of signal flow is indicated by arrows, with the corresponding...
01:24Sequence Networks of Rotating Machines
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...