Pengtao Dang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Pengtao Dang has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Chi Zhang
Department of Biomedical Engineering and Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
3 shared publications - Sha Cao
Department of Biomedical Engineering & Brenden-Colson Center for Pancreatic Care, Oregon Health and Science University, Portland, USA
2 shared publications - Anna Allsop
Indiana University Purdue University Indianapolis
1 shared publication - Changlin Wan
Department of Electrical and Computer Engineering, Purdue University
1 shared publication - Changlin Wan
Purdue University, West Lafayette, USA
1 shared publication - Clarisse M Fligor
Indiana University Purdue University Indianapolis
1 shared publication
Latest Publications
- 7 May 2024
- Published by Springer Nature in Journal of Applied and Computational Topology
- Vol. 8 (5) , 1333-1361
Ambiguities in neural-network-based hyperedge prediction
A hypergraph is a generalization of a graph that depicts higher-order relations. Predicting higher-order relations, i.e. hyperedges, is a fundamental problem in hypergraph studies, and has immense applications in multiple domains. Recent development of graph neural network (GNN) advanced the prediction of pair-wise relations in graphs. However, existing methods can hardly be extended to hypergraphs due to the lack of higher-order dependency in their graph embedding. In this paper, we mathematically formulate the ambiguity challenges of GNN-based representation of higher-order relations, namely node-level and hyperedge-level ambiguities. We further present HIGNN (Hyperedge Isomorphism Graph Neural Network) that utilizes bipartite graph neural network with hyperedge structural features to collectively tackle the two ambiguity issues in the hyperedge prediction problem. HIGNN achieves constant performance improvement compared with recent GNN-based models. In addition, we apply HIGNN to a new task, predicting genetic higher-order interactions on 3D genome organization data. HIGNN shows consistently higher prediction accuracy across different chromosomes, and generates novel findings on 4-way gene interactions, which is further validated by existing literature.
- 7 May 2024
- Published by Springer Nature in Journal of Applied and Computational Topology
- Vol. 8 (5) , 1333-1361
Ambiguities in neural-network-based hyperedge prediction
A hypergraph is a generalization of a graph that depicts higher-order relations. Predicting higher-order relations, i.e. hyperedges, is a fundamental problem in hypergraph studies, and has immense applications in multiple domains. Recent development of graph neural network (GNN) advanced the prediction of pair-wise relations in graphs. However, existing methods can hardly be extended to hypergraphs due to the lack of higher-order dependency in their graph embedding. In this paper, we mathematically formulate the ambiguity challenges of GNN-based representation of higher-order relations, namely node-level and hyperedge-level ambiguities. We further present HIGNN (Hyperedge Isomorphism Graph Neural Network) that utilizes bipartite graph neural network with hyperedge structural features to collectively tackle the two ambiguity issues in the hyperedge prediction problem. HIGNN achieves constant performance improvement compared with recent GNN-based models. In addition, we apply HIGNN to a new task, predicting genetic higher-order interactions on 3D genome organization data. HIGNN shows consistently higher prediction accuracy across different chromosomes, and generates novel findings on 4-way gene interactions, which is further validated by existing literature.
- Open Access
A graph neural network model to estimate cell-wise metabolic flux using single cell RNA-seq data
The metabolic heterogeneity, and metabolic interplay between cells and their microenvironment have been known as significant contributors to disease treatment resistance. However, with the lack of a mature high-throughput single cell metabolomics technology, we are yet to establish systematic understanding of intra-tissue metabolic heterogeneity and cooperation phenomena among cell populations. To mitigate this knowledge gap, we developed a novel computational method, namely scFEA (single cell Flux Estimation Analysis), to infer single cell fluxome from single cell RNA-sequencing (scRNA-seq) data. scFEA is empowered by a comprehensively reconstructed human metabolic map into a factor graph, a novel probabilistic model to leverage the flux balance constraints on scRNA-seq data, and a novel graph neural network based optimization solver. The intricate information cascade from transcriptome to metabolome was captured using multi-layer neural networks to fully capitulate the non-linear dependency between enzymatic gene expressions and reaction rates. We experimentally validated scFEA by generating an scRNA-seq dataset with matched metabolomics data on cells of perturbed oxygen and genetic conditions. Application of scFEA on this dataset demonstrated the consistency between predicted flux and metabolic imbalance with the observed variation of metabolite abundance in the matched metabolomics data. We also applied scFEA on five publicly available scRNA-seq and spatial transcriptomics datasets and identified context and cell group specific metabolic variations. The cell-wise fluxome predicted by scFEA empowers a series of downstream analysis including identification of metabolic modules or cell groups that share common metabolic variations, sensitivity evaluation of enzymes with regards to their impact on the whole metabolic flux, and inference of cell-tissue and cell-cell metabolic communications.
Open AccessA graph neural network model to estimate cell-wise metabolic flux using single cell RNA-seq data
The metabolic heterogeneity, and metabolic interplay between cells and their microenvironment have been known as significant contributors to disease treatment resistance. However, with the lack of a mature high-throughput single cell metabolomics technology, we are yet to establish systematic understanding of intra-tissue metabolic heterogeneity and cooperation phenomena among cell populations. To mitigate this knowledge gap, we developed a novel computational method, namely scFEA (single cell Flux Estimation Analysis), to infer single cell fluxome from single cell RNA-sequencing (scRNA-seq) data. scFEA is empowered by a comprehensively reconstructed human metabolic map into a factor graph, a novel probabilistic model to leverage the flux balance constraints on scRNA-seq data, and a novel graph neural network based optimization solver. The intricate information cascade from transcriptome to metabolome was captured using multi-layer neural networks to fully capitulate the non-linear dependency between enzymatic gene expressions and reaction rates. We experimentally validated scFEA by generating an scRNA-seq dataset with matched metabolomics data on cells of perturbed oxygen and genetic conditions. Application of scFEA on this dataset demonstrated the consistency between predicted flux and metabolic imbalance with the observed variation of metabolite abundance in the matched metabolomics data. We also applied scFEA on five publicly available scRNA-seq and spatial transcriptomics datasets and identified context and cell group specific metabolic variations. The cell-wise fluxome predicted by scFEA empowers a series of downstream analysis including identification of metabolic modules or cell groups that share common metabolic variations, sensitivity evaluation of enzymes with regards to their impact on the whole metabolic flux, and inference of cell-tissue and cell-cell metabolic communications.
- Open Access
- 29 October 2019
- Published by Cold Spring Harbor Laboratory in bioRxiv
- p. 820159
Retinal ganglion cells harboring the OPTN(E50K) mutation exhibit neurodegenerative phenotypes when derived from hPSC-derived three dimensional retinal organoids
Summary: Retinal ganglion cells (RGCs) serve as the primary connection between the eye and the brain, with this connection disrupted in glaucoma. Numerous cellular mechanisms have been associated with glaucomatous neurodegeneration, and useful models of glaucoma allow for the precise analysis of degenerative phenotypes. Human pluripotent stem cells (hPSCs) serve as powerful tools for studying human neurodegenerative diseases, particularly cellular mechanisms underlying degeneration. Thus, efforts were initially focused upon the use of hPSCs with an E50K mutation in the Optineurin (OPTN) gene. CRISPR/Cas9 gene editing was used to introduce the OPTN(E50K) mutation into existing lines of hPSCs, as well as the generation of isogenic control lines from OPTN(E50K) patient-derived hPSC lines. OPTN(E50K) RGCs exhibited numerous neurodegenerative deficits, including neurite retraction, autophagy dysfunction, apoptosis, and increased excitability. The results of this study provide an extensive analysis of the OPTN(E50K) mutation in hPSC-derived RGCs, with the opportunity to develop novel treatments for glaucoma.
- 29 October 2019
- Published by Cold Spring Harbor Laboratory in bioRxiv
- p. 820159
Open AccessRetinal ganglion cells harboring the OPTN(E50K) mutation exhibit neurodegenerative phenotypes when derived from hPSC-derived three dimensional retinal organoids
Summary: Retinal ganglion cells (RGCs) serve as the primary connection between the eye and the brain, with this connection disrupted in glaucoma. Numerous cellular mechanisms have been associated with glaucomatous neurodegeneration, and useful models of glaucoma allow for the precise analysis of degenerative phenotypes. Human pluripotent stem cells (hPSCs) serve as powerful tools for studying human neurodegenerative diseases, particularly cellular mechanisms underlying degeneration. Thus, efforts were initially focused upon the use of hPSCs with an E50K mutation in the Optineurin (OPTN) gene. CRISPR/Cas9 gene editing was used to introduce the OPTN(E50K) mutation into existing lines of hPSCs, as well as the generation of isogenic control lines from OPTN(E50K) patient-derived hPSC lines. OPTN(E50K) RGCs exhibited numerous neurodegenerative deficits, including neurite retraction, autophagy dysfunction, apoptosis, and increased excitability. The results of this study provide an extensive analysis of the OPTN(E50K) mutation in hPSC-derived RGCs, with the opportunity to develop novel treatments for glaucoma.