The DOI matches its Crossref record; 200 of the 218 references it cites were found in a registry or an index; 7 of the 169 sources its claims cite were checked for support.
Graph representation learning in biomedicine and healthcare
Open accessAbstract
Networks—or graphs—are universal descriptors of systems of interacting elements. In biomedicine and healthcare, they can represent, for example, molecular interactions, signalling pathways, disease co-morbidities or healthcare systems. In this Perspective, we posit that representation learning can realize principles of network medicine, discuss successes and current limitations of the use of representation learning on graphs in biomedicine and healthcare, and outline algorithmic strategies that leverage the topology of graphs to embed them into compact vectorial spaces. We argue that graph representation learning will keep pushing forward machine learning for biomedicine and healthcare applications, including the identification of genetic variants underlying complex traits, the disentanglement of single-cell behaviours and their effects on health, the assistance of patients in diagnosis and treatment, and the development of safe and effective medicines. This Perspective outlines the successes and limitations of graph deep learning for biomedical and healthcare applications.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This review argues that long-standing systems biology and medicine principles—such as the local hypothesis, shared components hypothesis, disease module hypothesis, and network parsimony—provide conceptual grounding for graph representation learning in biomedicine. It surveys shallow embeddings, graph neural networks, and generative graph models across molecular, genomic, therapeutic, and healthcare applications.
Key findings
- Graph representation learning learns compact vector embeddings in which nodes with similar network neighborhoods are placed close together, and it can be viewed as a differentiable engine of network biomedicine principles including the local hypothesis, shared components hypothesis, disease module hypothesis, and network parsimony.
- The reviewed methods span shallow graph embeddings (e.g., DeepWalk, node2vec, LINE, knowledge graph embeddings), graph neural networks with message passing, neighborhood aggregation, and representation updates, and deep generative graph models using variational autoencoders, generative adversarial networks, junction trees, and sequential node/edge sampling.
- Biomedical applications covered include protein structure, protein interactions, and protein function; gene expression, single-cell RNA sequencing, and spatial molecular profiling; drug-target, drug-drug, and drug-disease prediction; and patient-specific networks from histopathology images and electronic health records.
- No primary numerical results or benchmark performance numbers are reported in this review.
Methods
- Design: narrative review/survey, not a primary empirical study; it synthesizes graph representation learning approaches and biomedical applications.
- Data or sample: no new dataset is analyzed; the paper discusses published methods and application areas across molecular, genomic, therapeutic, and healthcare domains.
- Main analysis: conceptual synthesis linking graph representation learning to systems biology and medicine principles, organized into shallow graph embedding approaches, graph neural networks, and generative graph models.
Limitations
- Stated in the paper: graphs contain complex topographical structure, have no fixed node ordering or reference points, and comprise many different entity and edge types, which classic deep learning methods are unable to handle directly.
- Stated in the paper: biomedical networks are often incomplete or limited—for example, PPI networks are limited in nodes and edges due to experimental and resource constraints, gene expression data can be noisy and variational, and PPI networks cannot capture all gene regulatory activities.
- Evident from the text: as a review, it provides no empirical benchmark, systematic search protocol, or quantitative comparison; it also notes that explainability, fairness, and robustness of graph representations remain essential but unresolved needs in clinical applications.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
93 Not checked yet · 23 No basis given · 12 Own interpretation · 4 Partly supported · accuracy not yet measured
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Cell similarity graphs have also been created using autoencoders by first embedding gene expression readouts and then connecting genes based on how similar their embeddings are [157].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for genomics > Injecting single cell and spatial information into molecular networks
What the sources say
- Partly supportedcites [157] Thafar, M. A. et al. DTiGEMS+: drug–target interaction prediction using graph embedding, graph mining, and similarity-based techniques. J. Cheminformatics 12, 44 (2020). sourceExperimental — accuracy not yet measured
The Methods section, “Graph embedding for feature learning” (page unavailable), describes learning node2vec embeddings and using cosine similarity to add edges between drugs or between targets. This supports the general embedding-then-connect-by-similarity approach, but not the attributed use of autoencoders, gene-expression readouts, or cell similarity graphs. (LLM, conf=0.84)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In fact, as ligand-receptor interactions are directed, they could be used to infer causal interactions of previously unknown ligand-receptor pairs [161, 163].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for genomics > Injecting single cell and spatial information into molecular networks
What the sources say
- Partly supportedcites [161] Chen, L. et al. TransformerCPI: improving compound–protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments. Bioinformatics 36, 4406–4414 (2020). sourceExperimental — accuracy not yet measured
The Introduction describes predicting compound–protein interactions, and §2.2.2 describes predicting whether particular ligand–protein pairs interact. Neither passage says that ligand–receptor interactions are directed or that their direction can be used to infer causal interactions; that is the unsupported part of the claim. Page numbers are unavailable in our copy. (LLM, conf=0.84)
- Partly supportedcites [163] Tsubaki, M., Tomii, K. & Sese, J. Compound–protein interaction prediction with end-to-end learning of neural networks for graphs and sequences. Bioinformatics 35, 309–318 (2019). sourceExperimental — accuracy not yet measured
The Introduction (page unavailable) says that identifying previously unknown compound–protein interactions is useful, and describes methods for predicting them. It does not say that ligand–receptor interactions are directed or that their direction can be used to infer causal interactions. (LLM, conf=0.83)
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Two modes of patient data successfully integrated using deep graph learning are histopathological images [8, 185] and EHRs [186, 187].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for healthcare
What the sources say
- Supportedcites [8] Chen, R. J. et al. Pathomic fusion: an integrated framework for fusing histopathology and genomic features for cancer diagnosis and prognosis. In IEEE Transactions on Medical Imaging Vol. 41, 757–770 (IEEE, 2022). source
This source is cited for histopathological images, not EHRs, which have separate citations. In Methods, the paper describes constructing cell graphs from histopathology images and using graph convolutional networks to learn representations for outcome prediction; it also uses those representations in Pathomic Fusion. Page numbers are not available in our copy. (LLM, conf=0.90)
- Not checked yetcites [185] Levy, J., Haudenschild, C., Bar, C., Christensen, B. & Vaickus, L. Topological feature extraction and visualization of whole slide images using graph neural networks. Pac. Symp. Biocomput. 26, 285–296 (2021).
- Supportedcites [186] Hu, J. et al. SpaGCN: integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network. Nat. Methods 18, 1342–1351 (2021). source
The citation to this paper is attached to histopathological images, not EHRs. In “Overview of SpaGCN and evaluation,” the paper says SpaGCN uses histology information to build a graph and a graph convolutional layer to analyze gene expression. “Application to human primary pancreatic cancer tissue” reports that its detected domain corresponded better to the cancer region annotated on the histology image. (LLM, conf=0.91)
- Partly supportedcites [187] Rotmensch, M., Halpern, Y., Tlimat, A., Horng, S. & Sontag, D. Learning a health knowledge graph from electronic medical records. Sci. Rep. 7, 5994 (2017). sourceExperimental — accuracy not yet measured
The Contributions section reports learning a disease–symptom knowledge graph from electronic medical records, supporting the EHR portion of the cited sentence. But Methods > Algorithms for constructing a knowledge graph specifies logistic regression, naive Bayes, and a noisy-OR Bayesian network—not deep graph learning. The histopathological-image portion is cited to other sources and is not assessed here. (LLM, conf=0.89)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In contrast to shallow embeddings, GNNs can capture higher-order and non-linear patterns through multi-hop propagation within several layers of neural message passing.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning > Graph neural networks
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Given by the shared components and disease module hypotheses [13], cellular components associated with the same phenotype tend to cluster in the same network neighborhood [16].”
§ Graph Representation Learning in Biomedicine and Healthcare > Introduction
What the sources say
- Not checked yetcites [13] Barabási, A.-L., Gulbahce, N. & Loscalzo, J. Network medicine: a network-based approach to human disease. Nat. Rev. Genet. 12, 56–68 (2011). source
- Not checked yetcites [16] Agrawal, M., Zitnik, M. & Leskovec, J. Large-scale analysis of disease pathways in the human interactome. In Pac. Symp. Biocomput. 23, 111–122 (2018).
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“Topology-based methods have been shown to capture and leverage the dynamics of biological systems to enrich existing PPI networks [119].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for molecules > Quantifying protein interactions
What the sources say
- Not checked yetcites [119] Moreau, Y. & Tranchevent, L.-C. Computational tools for prioritizing candidate genes: boosting disease gene discovery. Nat. Rev. Genet. 13, 523–536 (2012). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Specifically, the inductive ability of graph convolution neural networks to generalize to data points unseen during model training (Section 2.2) and even generate new data points from scratch by decoding latent representation from the embedding space (Section 2.3) has enabled the discovery of new molecules, interactions, and functions [101, 108, 109].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for molecules
What the sources say
- Not checked yetcites [101] Huang, K., Xiao, C., Glass, L. M., Zitnik, M. & Sun, J. SkipGNN: predicting molecular interactions with skip-graph networks. Sci. Rep. 10, 21092 (2020). source
- Not checked yetcites [108] Fout, A., Byrd, J., Shariat, B. & Ben-Hur, A. Protein interface prediction using graph convolutional networks. In Proc. International Conference on Neural Information Processing Systems (eds Guyon, I. et al.) (Curran Associates, 2019).
- Not checked yetcites [109] Ingraham, J., Garg, V. K., Barzilay, R. & Jaakkola, T. S. Generative models for graph-based protein design. In Proc. International Conference on Neural Information Processing Systems (eds Wallach, H. et al.) (Curran Associates, 2019).
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“node embeddings can capture whether the nodes lie within a hub based on their degree, an important aspect of local neighborhood (e.g., strongly clustered gene embeddings indicate essential housekeeping roles)”
§ Graph Representation Learning in Biomedicine and Healthcare > Introduction
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“nodes in the same positional regions should have similar embeddings due to the local hypothesis (e.g., highly similar pairs of protein embeddings suggest similar phenotypic consequence)”
§ Graph Representation Learning in Biomedicine and Healthcare > Introduction
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Learned embeddings—using graph representation learning methods—that capture genome-wide interactions has enhanced disease predictions, even at the resolution of tissues and single cells.”
§ Graph Representation Learning in Biomedicine and Healthcare > Application areas in biology and medicine
What the sources say
- Not checked yetcites [16] Agrawal, M., Zitnik, M. & Leskovec, J. Large-scale analysis of disease pathways in the human interactome. In Pac. Symp. Biocomput. 23, 111–122 (2018).
- Not checked yetcites [45] Menche, J. et al. Uncovering disease-disease relationships through the incomplete interactome. Science 347, 1257601 (2015). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- It may state two separate claims as one. 27
- Probably not a substantial claim. 42
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Further, essential genes are often found in hubs of a molecular network whereas non-essential genes (e.g., those associated with disease) are located on the periphery [13].”
§ Graph Representation Learning in Biomedicine and Healthcare > Introduction
What the sources say
- Partly supportedcites [13] Barabási, A.-L., Gulbahce, N. & Loscalzo, J. Network medicine: a network-based approach to human disease. Nat. Rev. Genet. 12, 56–68 (2011). sourceExperimental — accuracy not yet measured
The ‘Location of disease genes within networks’ section says essential genes tend to be associated with hubs, while non-essential disease genes tend toward the functional periphery. The citing sentence broadens that second finding to non-essential genes generally, which the passage does not establish. (LLM, conf=0.86)
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Partly supported
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“As a result, diagnosing diseases requires knowledge about alterations in the transcription of coding genes to capture genome-wide associations driving disease acquisition and progression.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for genomics
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Graph representation learning is challenging because graphs contain complex topographical structure, have no fixed node ordering or reference points, and are comprised of many different kinds of entities (nodes) and various types of interactions (edges) relating them to each other.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We also capture the breadth of ways in which representation learning has dramatically improved the state-of-the-art in biomedical machine learning.”
§ Graph Representation Learning in Biomedicine and Healthcare > Abstract
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Biomedical networks (or graphs) are universal descriptors for systems of interacting elements, from molecular interactions and disease co-morbidity to healthcare systems and scientific knowledge.”
§ Graph Representation Learning in Biomedicine and Healthcare > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“These approaches are transductive embedding methods where the encoder function is a simple embedding lookup (Figure 2).”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning > Shallow graph embedding approaches
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Graph neural networks (GNNs) are a class of neural networks designed for graph-structured datasets (Figure 2).”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning > Graph neural networks
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Such functions are optimized to embed the input network so that nodes with similar network neighborhoods are embedded close together in the embedding space, and algebraic operations performed in this learned space reflect the network’s topology.”
§ Graph Representation Learning in Biomedicine and Healthcare > Introduction
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we put forward an observation that long-standing principles of systems biology and medicine—while often unspoken in machine learning research—provide the conceptual grounding for representation learning on graphs, explain its current successes and limitations, and even inform future advancements.”
§ Graph Representation Learning in Biomedicine and Healthcare > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Graph representation learning methods allow us to analyze heterogeneous networks of multimodal data and make predictions across domains, from genomic level data (e.g., gene expression, copy number information) to clinically relevant data (e.g., pathophysiology, tissue localization).”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for genomics
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Its core idea is to learn how to represent nodes (or larger graph structures) in a network as points in a low-dimensional space, where the geometry of this space is optimized to reflect the structure of interactions between nodes.”
§ Graph Representation Learning in Biomedicine and Healthcare > Introduction
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Comparing transcriptomic profiles from healthy individuals to those of patients with a specific disease informs clinicians of its causal genes.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for genomics > Leveraging gene expression measurements
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We synthesize a spectrum of algorithmic approaches that, at their core, leverage graph topology to embed networks into compact vector spaces.”
§ Graph Representation Learning in Biomedicine and Healthcare > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
None of the sources cited for this claim have been checked yet.
In the paper
“GNNs (as described in Section 4.1) are commonly used to generate representations of proteins based on chemical (e.g., free electrons’ and protons donors’ locations) and geometric (e.g., distance-dependent curvature) features to predict protein pocket-ligand and protein-protein interactions sites [116]; intra- and inter-molecule residue contact graphs to predict intra- and inter-molecular energies,”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for molecules > Quantifying protein interactions
What the sources say
- Not checked yetcites [116] Li, D. & Gao, J. Towards perturbation prediction of biological networks using deep learning. Sci. Rep. 9, 11941 (2019). source
- Not checked yetcites [117] Liu, Y., Yuan, H., Cai, L., & Ji, S. Deep learning of high-order interactions for protein interface prediction. In Proc. ACM SIGKDD Conference on Knowledge Discovery and Data Mining 679–687 (ACM, 2020). source
- Not checked yetcites [111] Elton, D. C., Boukouvalas, Z., Fuge, M. D. & Chung, P. W. Deep learning for molecular design—a review of the state of the art. Mol. Syst. Des. Eng. 4, 828–849 (2019). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Further, injecting gene expression data into PPI networks has identified disease biomarkers, which are then used to more accurately classify diseases of interest.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for genomics > Leveraging gene expression measurements
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“They learn compact representations of graph elements, their attributes, and supervised labels if any.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning > Graph neural networks
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Akin to how deep learning on images and sequences has revolutionized image analysis and natural language processing, graph representation learning is poised to transform the study of complex systems.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Shallow embedding methods optimize a compact vector space such that points that are close in the graph are mapped to nearby points in the embedding space, which is measured by a predefined distance function or an outer product.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning > Shallow graph embedding approaches
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Deep generative models address the challenge by estimating distributional graph properties based on a dataset of graphs 𝒢 and inferring graph structures using such optimized distributions.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning > Generative graph models
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Additionally, GNNs can optimize supervised signals and graph structure simultaneously, whereas shallow embedding approaches require a two-stage approach to achieve the same.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning > Graph neural networks
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Since protein structures are folded into complex 3D structures, it is natural to represent them as graphs.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for molecules > Modeling protein molecular graphs
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Gene Ontology (GO) terms [125] are a standardized vocabulary for describing molecular functions, biological processes, and cellular locations of gene products [126].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for molecules > Interpreting protein functions and cellular phenotypes
What the sources say
- Not checked yetcites [125] Hasibi, R. & Michoel, T. A Graph feature auto-encoder for the prediction of unobserved node features on biological networks. BMC Bioinform 22, 525 (2021). source
- Not checked yetcites [126] Cao, M. et al. Going the distance for protein function prediction: a new distance metric for protein interaction networks. PLoS ONE 8, e76339 (2013). source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Learning the topology of graphs containing drug, protein, and disease nodes has improved predictions of candidate drugs for treating a disease, identification of potential off-target effects, and prioritization of novel drug combinations.”
§ Graph Representation Learning in Biomedicine and Healthcare > Application areas in biology and medicine
What the sources say
- Not checked yetcites [103] Fan, K. & Zhang, Y. Pseudo2GO: A graph-based deep learning method for pseudogene function prediction by borrowing information from coding genes. Front. Genet. 11, 807 (2020). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Hence, artificial intelligence methods that produce representations can be thought of as differentiable engines of key network biomedicine principles.”
§ Graph Representation Learning in Biomedicine and Healthcare > Introduction
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Diseases are classified based on the presenting symptoms of patients, which can be caused by molecular dysfunctions, such as genetic mutations.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for genomics
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“More concretely, representation learning specifies deep, non-linear transformation functions that map nodes to points in a compact vector space, termed embeddings.”
§ Graph Representation Learning in Biomedicine and Healthcare > Introduction
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As biomedical networks can be multimodal and massive, special consideration is needed to scale GNNs to large and heterogeneous networks.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning > Graph neural networks
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“They have been built as a hierarchical graph that GNNs then leverage to learn dependencies of the terms [126], or directly used as protein function labels [106, 127].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for molecules > Interpreting protein functions and cellular phenotypes
What the sources say
- Not checked yetcites [126] Cao, M. et al. Going the distance for protein function prediction: a new distance metric for protein interaction networks. PLoS ONE 8, e76339 (2013). source
- Not checked yetcites [106] Hamilton, W. L., Ying, Z. & Leskovec, J. Inductive representation learning on large graphs. In Proc. International Conference on Neural Information Processing Systems (eds Guyon, I. et al.) (Curran Associates, 2017).
- Not checked yetcites [127] Dey, T. K. & Mandal, S. Protein classification with improved topological data analysis. In 18th International Workshop on Algorithms in Bioinformatics (WABI) (eds Parida, L. & Ukkonen, E.) 6:1–6:13 (Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik, 2018).
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Similar to proteins, small compounds are modeled as 2D and 3D molecular graphs such that nodes are atoms and edges are bonds.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for therapeutics > Modeling compound molecular graphs
What the sources say
- Not checked yetcites [83] Schlichtkrull, M. et al. Modeling relational data with graph convolutional networks. In European Semantic Web Conference (eds Gangemi, A. et al.) 593–607 (Springer, 2018). source
- Not checked yetcites [166] Wang, R., Li, S., Cheng, L., Wong, M. H. & Leung, K. S. Predicting associations among drugs, targets and diseases by tensor decomposition for drug repositioning. BMC Bioinf. 20, 628 (2019). source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Applied to such networks, graph representation learning can impute scRNA-seq data [156, 157], predict cell clusters [157, 158], etc.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for genomics > Injecting single cell and spatial information into molecular networks
What the sources say
- Not checked yetcites [156] Alagappan, M., Jiang, D., Denko, N. & Koong, A. C. in Tumor Microenvironment (eds Koumenis, C. et al.) 253–268 (Springer, 2016). source
- Not checked yetcites [157] Thafar, M. A. et al. DTiGEMS+: drug–target interaction prediction using graph embedding, graph mining, and similarity-based techniques. J. Cheminformatics 12, 44 (2020). source
- Not checked yetcites [158] Thafar, M. A. et al. DTi2Vec: Drug–target interaction prediction using network embedding and ensemble learning. J. Cheminformatics 13, 71 (2021). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: A predominant approach to analyze single-cell RNA sequencing datasets is to transform them into gene similarity networks or cell similarity networks by correlating gene expression readouts across individual cells.
None of the sources cited for this claim have been checked yet.
In the paper
“To this end, graph representation learning methods, such as GNNs, have been developed to learn robust and meaningful representations of molecules despite the incomplete interactome [102] and to inductively infer new edges between pairs of nodes [154].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for genomics > Leveraging gene expression measurements
What the sources say
- Not checked yetcites [102] Yin, N. et al. Synergistic and antagonistic drug combinations depend on network topology. PLoS ONE 9, e93960 (2014). source
- Not checked yetcites [154] Coley, C. W. et al. A graph-convolutional neural network model for the prediction of chemical reactivity. Chem. Sci. 10, 370–377 (2019). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Spatial molecular profiling can measure both gene expression at the cellular level and location of cells in a tissue [160].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for genomics > Injecting single cell and spatial information into molecular networks
What the sources say
- Not checked yetcites [160] Jiang, M. et al. Drug–target affinity prediction using graph neural network and contact maps. RSC Adv 10, 20701–20712 (2020). source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Edges can also be added to indicate pairwise spatial distance between two atoms [72], or directed with information on bond angles and rotations incorporated into the molecular graph [84].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for therapeutics > Modeling compound molecular graphs
What the sources say
- Not checked yetcites [72] Hu, Z., Dong, Y., Wang, K. & Sun, Y. Heterogeneous graph transformer. In Proc. ACM Web Conference 2704–2710 (ACM, 2020). source
- Not checked yetcites [84] Wang, X. et al. Heterogeneous graph attention network. In Proc. ACM Web Conference (eds Liu, L. & White, R.) 2022–2032 (ACM, 2019). source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Creating cell neighborhood and spatial gene expression graphs require a distance metric, as edges are determined based on spatial proximity, while gene co-expression and molecular similarity graphs need a threshold applied on the gene expression data [35].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for genomics > Injecting single cell and spatial information into molecular networks
What the sources say
- Not checked yetcites [35] Hetzel, L., Fischer, D. S., Günnemann, S. & Theis, F. J. Graph representation learning for single cell biology. Curr. Opin. Syst. Biol. 28, 100347 (2021). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“As a result, spatial transcriptomics data can be used to construct cell graphs [161], spatial gene expression graphs [162], gene co-expression networks, or molecular similarity graphs [35].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for genomics > Injecting single cell and spatial information into molecular networks
What the sources say
- Not checked yetcites [161] Chen, L. et al. TransformerCPI: improving compound–protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments. Bioinformatics 36, 4406–4414 (2020). source
- Not checked yetcites [162] Quan, Z., Guo, Y., Lin, X., Wang, Z.-J. & Zeng, X. GraphCPI: Graph neural representation learning for compound-protein interaction. In BIBM 717–722 (2019). source
- Not checked yetcites [35] Hetzel, L., Fischer, D. S., Günnemann, S. & Theis, F. J. Graph representation learning for single cell biology. Curr. Opin. Syst. Biol. 28, 100347 (2021). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Modern drug discovery requires elucidating a candidate drug’s chemical structure, identifying its drug targets, quantifying its efficacy and toxicity, and detecting its potential side effects [13, 14, 32, 164].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for therapeutics
What the sources say
- Not checked yetcites [13] Barabási, A.-L., Gulbahce, N. & Loscalzo, J. Network medicine: a network-based approach to human disease. Nat. Rev. Genet. 12, 56–68 (2011). source
- Not checked yetcites [14] Hu, J. X., Thomas, C. E. & Brunak, S. Network biology concepts in complex disease comorbidities. Nat. Rev. Genet. 17, 615–629 (2016). source
- Not checked yetcites [32] Rai, A., Shinde, P. & Jalan, S. Network spectra for drug-target identification in complex diseases: new guns against old foes. Appl. Netw. Sci. 3, 51 (2018). source
- Not checked yetcites [164] Lin, X. et al. DeepGS: Deep representation learning of graphs and sequences for drug-target binding affinity prediction. ECAI (2020).
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Each atom and bond may include features, such as atomic mass, atomic number, and bond type, to be included in the model [83, 166].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for therapeutics > Modeling compound molecular graphs
What the sources say
- Not checked yetcites [83] Schlichtkrull, M. et al. Modeling relational data with graph convolutional networks. In European Semantic Web Conference (eds Gangemi, A. et al.) 593–607 (Springer, 2018). source
- Not checked yetcites [166] Wang, R., Li, S., Cheng, L., Wong, M. H. & Leung, K. S. Predicting associations among drugs, targets and diseases by tensor decomposition for drug repositioning. BMC Bioinf. 20, 628 (2019). source
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Also, two separate GNNs may be used to learn representations of protein and small molecule graphs for predicting drug-target affinity [173].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for therapeutics > Quantifying drug-drug and drug-target interactions
What the sources say
- Not checked yetcites [173] Choi, E., Bahadori, M. T., Song, L., Stewart, W. F. & Sun, J. GRAM: graph-based attention model for healthcare representation learning. In Proc. 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 787–795 (ACM, 2017). source
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Medical images of patients, including histopathology slides, enable clinicians to comprehensively observe the effects of a disease on the patient’s body [188].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for healthcare > Leveraging networks for diagnostic imaging
What the sources say
- Not checked yetcites [188] Wu, T. et al. Representation learning of EHR data via graph-based medical entity embedding. In Advances in Neural Information Processing Systems Graph Representation Learning Workshop (2019).
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“For instance, Medical Subject Headings (MeSH) terms may be used to construct a drug-disease graph, from which latent representations of drugs and diseases are learned using various graph embedding algorithms, including DeepWalk and LINE (Section 2.1) [178].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for therapeutics > Identifying drug-disease associations and biomarkers for complex disease
What the sources say
- Not checked yetcites [178] Zhou, Y. et al. CGC-Net: cell graph convolutional network for grading of colorectal cancer histology images. In IEEE International Conference on Computer Vision Workshops (IEEE, 2019). source
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Concretely, TDA (refer to SI Note 3) transforms experimental data into a graph where nodes represent compounds and edges indicate a level of similarity between them [169].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for therapeutics > Quantifying drug-drug and drug-target interactions
What the sources say
- Not checked yetcites [169] Alsentzer, E., Finlayson, S. G., Li, M. M. & Zitnik, M. Subgraph neural networks. In Proc. International Conference on Neural Information Processing Systems (eds Larochelle, H. et al.) 8017–8029 (Curran Associates, 2020).
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Graph representation learning methods enables in silico modeling of drug action, which allows for more efficient ranking of candidate drugs for repurposing, such as by considering gene expression data, gene ontologies, drug similarity, and other clinically relevant data regarding side effects and indications.”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for therapeutics > Identifying drug-disease associations and biomarkers for complex disease
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“K-nearest neighbors, for instance, is a common used method to construct drug and target similarity networks [171].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for therapeutics > Quantifying drug-drug and drug-target interactions
What the sources say
- Not checked yetcites [171] Barisoni, L., Lafata, K. J., Hewitt, S. M., Madabhushi, A. & Balis, U. G. Digital pathology and computational image analysis in nephropathology. Nat. Rev. Nephrol. 16, 669–685 (2020). source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Further, cell morphology and interactions, tissue morphology and spatial distribution, cell-to-tissue hierarchies, and spatial distribution of cells with respect to tissues can be captured in a cell-to-tissue graph, upon which a hierarchical GNN can learn representations using these different data modalities [189].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for healthcare > Leveraging networks for diagnostic imaging
What the sources say
- Not checked yetcites [189] Mao, C., Yao, L. & Luo, Y. MedGCN: medication recommendation and lab test imputation via graph convolutional networks. J. Biomed. Inform. 127, 104000 (2022). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Intuitively, message passing steps (i.e., in GNNs (Section 2.2)) aggregate information from neighboring atoms and bonds to learn the local chemistry of each atom [166].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for therapeutics > Modeling compound molecular graphs
What the sources say
- Not checked yetcites [166] Wang, R., Li, S., Cheng, L., Wong, M. H. & Leung, K. S. Predicting associations among drugs, targets and diseases by tensor decomposition for drug repositioning. BMC Bioinf. 20, 628 (2019). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Part of the drug discovery pipeline is minimizing adverse drug events [33, 34].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for therapeutics > Identifying drug-disease associations and biomarkers for complex disease
What the sources say
- Not checked yetcites [33] David, L., Thakkar, A., Mercado, R. & Engkvist, O. Molecular representations in AI-driven drug discovery: a review and practical guide. J. Cheminformatics 12, 56 (2020). source
- Not checked yetcites [34] Wieder, O. et al. A compact review of molecular property prediction with graph neural networks. Drug Discov. Today. Technol. 37, 1–12 (2020). source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“EHRs are often supplemented with other modalities, such as diseases, symptoms, molecular data, drug interactions, etc [7, 206, 211, 212].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for healthcare > Personalizing medical knowledge networks with patient records
What the sources say
- Not checked yetcites [7] Nelson, C. A., Butte, A. J. & Baranzini, S. E. Integrating biomedical research and electronic health records to create knowledge-based biologically meaningful machine-readable embeddings. Nat. Commun. 10, 3045 (2019). source
- Not checked yetcites [206] Lanchantin, J. & Qi, Y. Graph convolutional networks for epigenetic state prediction using both sequence and 3D genome data. Bioinformatics 36, i659–i667 (2020). source
- Not checked yetcites [211] Ying, Z., Bourgeois, D., You, J., Zitnik, M. & Leskovec, J. GNNExplainer: generating explanations for graph neural networks. In Proc. International Conference on Neural Information Processing Systems (ed Wallach, H. et al.) (Curran Associates, 2019).
- Not checked yetcites [212] Agarwal, C., Lakkaraju, H. & Zitnik, M. Towards a unified framework for fair and stable graph representation learning. In Proc. Machine Learning Research (eds de Campos, C. & Maathuis, M. H.) 2114–2124 (PMLR, 2021).
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Alternatively, a patient graph may be constructed based on the similarity of patients, and patient embeddings learned by an LSTM-GNN architecture are optimized to predict patient outcomes [210].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for healthcare > Personalizing medical knowledge networks with patient records
What the sources say
- Not checked yetcites [210] Machens, A. et al. An infectious disease model on empirical networks of human contact: bridging the gap between dynamic network data and contact matrices. BMC Infect. Dis. 13, 185 (2013). source
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“An ST-GCN [78] is designed to utilize the underlying spatial and temporal dependencies of EHR data for generating patient diagnoses [187].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for healthcare > Personalizing medical knowledge networks with patient records
What the sources say
- Not checked yetcites [187] Rotmensch, M., Halpern, Y., Tlimat, A., Horng, S. & Sontag, D. Learning a health knowledge graph from electronic medical records. Sci. Rep. 7, 5994 (2017). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Alternatively, TDA can generate graphs of whole-slide images, which include tissues from various patient sources (SI Note 3), and GNNs are then used to classify the stage of colon cancer [199].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for healthcare > Leveraging networks for diagnostic imaging
What the sources say
- Not checked yetcites [199] Li, L. et al. A method to learn embedding of a probabilistic medical knowledge graph: algorithm development. JMIR Med. Inf. 8, e17645 (2020). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Meta-paths may alternatively be exploited in an EHR-derived KG to leverage higher order, semantically important relations for disease classification [214].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for healthcare > Personalizing medical knowledge networks with patient records
What the sources say
- Not checked yetcites [214] Obermeyer, Z., Powers, B., Vogeli, C. & Mullainathan, S. Dissecting racial bias in an algorithm used to manage the health of populations. Science 366, 447–453 (2019). source
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Node features for drugs and diseases can be initialized using Skipgram and then a GNN leveraging multi-layer message-passing can be applied to predict adverse drug events [211].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for healthcare > Personalizing medical knowledge networks with patient records
What the sources say
- Not checked yetcites [211] Ying, Z., Bourgeois, D., You, J., Zitnik, M. & Leskovec, J. GNNExplainer: generating explanations for graph neural networks. In Proc. International Conference on Neural Information Processing Systems (ed Wallach, H. et al.) (Curran Associates, 2019).
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“In public health, spatial and temporal networks can model space- and time-dependent observations (e.g., disease states, susceptibility to infection [225]) to spot trends, detect anomalies, and interpret temporal dynamics.”
§ Graph Representation Learning in Biomedicine and Healthcare > Outlook
What the sources say
- Not checked yetcites [225] Tran, D. et al. Fast and precise single-cell data analysis using a hierarchical autoencoder. Nat. Commun. 12, 1029 (2021). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Since multimodal data enables more robust predictions, GNNs (Section 2.2) have been applied to generate cell spatial graphs from histopathology images and then fuse genomic and transcriptomic data for predicting treatment response and resistance, histopathology grading, and patient survival [8].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for healthcare > Leveraging networks for diagnostic imaging
What the sources say
- Not checked yetcites [8] Chen, R. J. et al. Pathomic fusion: an integrated framework for fusing histopathology and genomic features for cancer diagnosis and prognosis. In IEEE Transactions on Medical Imaging Vol. 41, 757–770 (IEEE, 2022). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Alternatively, attention mechanisms may be applied on EHR data and medical ontologies to capture the parent-child relationships [186, 204, 205].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for healthcare > Personalizing medical knowledge networks with patient records
What the sources say
- Not checked yetcites [186] Hu, J. et al. SpaGCN: integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network. Nat. Methods 18, 1342–1351 (2021). source
- Not checked yetcites [204] Wang, T., Peng, Q., Liu, B., Liu, Y. & Wang, Y. Disease module identification based on representation learning of complex networks integrated from GWAS, eQTL summaries, and human interactome. Front. Bioeng. Biotechnol. 8, 418 (2020). source
- Not checked yetcites [205] Dekker, J. & Misteli, T. Long-range chromatin interactions. Cold Spring Harb. Perspect. Biol. 7, a019356 (2015). source
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Additionally, because graphs can model long-range dependencies or interactions, we can model chromatin elements and the effects of their binding to regions across the genome as a network [220, 221].”
§ Graph Representation Learning in Biomedicine and Healthcare > Outlook
What the sources say
- Not checked yetcites [220] Stark, C. et al. BioGRID: a general repository for interaction datasets. Nucleic Acids Res 34, D535–D539 (2006). source
- Not checked yetcites [221] Efremova, M., Vento-Tormo, M., Teichmann, S. A. & Vento-Tormo, R. Cellphonedb: inferring cell–cell communication from combined expression of multi-subunit ligand–receptor complexes. Nat. Protoc. 15, 1484–1506 (2020). source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“A probabilistic KG of EHR data, which include medical history, drug prescriptions, and laboratory examination results, has been used to consider the semantic relations between EHR entities in a shallow network embedding method (Section 2.1) [213].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for healthcare > Personalizing medical knowledge networks with patient records
What the sources say
- Not checked yetcites [213] Zhang, X. & Zitnik, M. GNNGuard: defending graph neural networks against adversarial attacks. In Proc. International Conference on Neural Information Processing Systems (eds Larochelle, H. et al.) 9263–9275 (Curran Associates, 2020).
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper relies on this without support.
A predominant approach to analyze single-cell RNA sequencing datasets is to transform them into gene similarity networks or cell similarity networks by correlating gene expression readouts across individual cells.
“In particular, a predominant approach to analyze scRNA-seq datasets is to transform them into gene similarity networks, such as gene co-expression networks, or cell similarity networks by correlating gene expression readouts across individual cells.”
The paper relies on this without support.
Cross-domain expertise is necessary to develop a drug with optimal binding affinity and specificity to biomarkers, maximal therapy efficacy, and minimal adverse effects.
“However, cross-domain expertise is necessary to develop a drug with the optimal binding affinity and specificity to biomarkers, maximal therapy efficacy, and minimal adverse effects.”
The paper relies on this without support.
It is critical to integrate chemical structure information, protein interactions, and clinically relevant data into predictive models for drug discovery and repurposing.
“As a result, it is critical to integrate chemical structure information, protein interactions, and clinically relevant data (e.g., indications and reported side effects) into predictive models for drug discovery and repurposing.”
The paper relies on this without support.
The hierarchical information inherent to ICD codes naturally lends itself to creating a rich network of medical knowledge.
“The hierarchical information inherent to ICD codes (medical ontologies) naturally lend itself to creating a rich network of medical knowledge.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“In the context of biomedical applications, these graph structures can represent various associations, including gene functions, drug responses, medical image patches, and cellular similarity [64].”
From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [64]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“This evaluation method aligns with the approach predominantly used in the literature12,14–16,18–20.”
From A foundation model for clinician-centered drug repurposing (2024) · cites this paper as [15]
Experimental — accuracy not yet measuredIn the citing paper
“To provide therapeutic predictions, geometric deep-learning models optimized on large medical KGs15 can match disease signatures to therapeutic candidates based on networks perturbed in disease15–18.”
From A foundation model for clinician-centered drug repurposing (2024) · cites this paper as [15]
In the citing paper
“TxGNN achieves state-of-the-art performance in drug repurposing by leveraging a network medicine principle focusing on disease–treatment mechanisms15.”
From A foundation model for clinician-centered drug repurposing (2024) · cites this paper as [15]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for genomics > Injecting single cell and spatial information into molecular networks
“Cell similarity graphs have also been created using autoencoders by first embedding gene expression readouts and then connecting genes based on how similar their embeddings are [157].”
§ Graph Representation Learning in Biomedicine and Healthcare > Graph representation learning for genomics > Injecting single cell and spatial information into molecular networks
“cell similarity networks by correlating gene expression readouts across individual cells”
Citations
Cites
Statistical mechanics of complex networks
Albert, R., & Barabási, A.-L. (2002) · Reviews of Modern Physics · doi:10.1103/revmodphys.74.47 · Cited by 20,471
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2017) · arXiv · doi:10.48550/arxiv.1710.10903 · Cited by 12,107 · cited 1×
“…class of GNNs 67 ), GAT (an architecture that stacks layers in which nodes are able to up-weight and down-weight other nodes in their neighbourhoods 71 ) and JK-Net (a jumping-knowledge network that flexibly leverages, for each node, neighbourhoods of different size to enable better…”
A Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000 · cited 1×
“…of graph representation learning have been covered extensively in the literature: deep learning on structured data 17,18 ; graph neural networks 19–21 (GNNs); representation learning for homogeneous and heterogeneous graphs 22–24 , solely heterogeneous graphs 25 and dynamic graphs 26 ; data…”
node2vec: Scalable Feature Learning for Networks
Grover, A., & Leskovec, J. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939754 · Cited by 10,926 · cited 2×
“Topological data analysis 156 and shallow network embedding 57 have been used to learn representations of drugs and targets.”
DeepWalk: online learning of social representations
Perozzi, B., Al-Rfou, R., & Skiena, S. (2014) · Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2623330.2623732 · Cited by 10,123 · cited 1×
“55 ).”
Dynamic Graph CNN for Learning on Point Clouds
Wang, Y., Sun, Y., Liu, Z., Sarma, S. E., Bronstein, M. M., & Solomon, J. M. (2019) · ACM Transactions on Graphics · doi:10.1145/3326362 · Cited by 7,199
Dissecting racial bias in an algorithm used to manage the health of populations
Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019) · Science · doi:10.1126/science.aax2342 · Cited by 7,137 · cited 1×
“…are increasingly employed in biomedicine and healthcare, it is essential to ensure that the representations are explainable 211 , fair 212 and robust 213 , and that the algorithms are revisited to minimize health disparities 214 and to take into account new information on algorithmic biases.”
Modeling Relational Data with Graph Convolutional Networks
Schlichtkrull, M., Kipf, T. N., Bloem, P., van den Berg, R., Titov, I., & Welling, M. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-93417-4_38 · Cited by 5,570
LINE: Large-scale Information Network Embedding
Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., & Mei, Q. (2015) · Proceedings of the 24th International Conference on World Wide Web · doi:10.1145/2736277.2741093 · Cited by 5,416
Research works printed but not linked: 39
- Hamilton, W. L., Ying, R. & Leskovec, J. Representation learning on graphs: methods and applications. IEEE Data Eng. Bull 40, 52–74 (2017).
- Hamilton, W. L. in Synthesis Lectures on Artificial Intelligence and Machine Learning Vol. 14, 1–159 (Morgan and Claypool, 2020).
- Kazemi, S. M. et al. Representation learning for dynamic graphs: a survey. J Mach. Learn. Res. 21, 1–73 (2020).
- Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S. & Dean, J. Distributed representations of words and phrases and their compositionality. In Proc. 26th International Conference on Neural Information Processing Systems Vol. 2 (eds Burges, C. J. et al.) 3111–3119 (Curran Associates, 2013).
- Bordes, A., Usunier, N., García-Durán, A., Weston, J. & Yakhnenko, O. Translating embeddings for modeling multi-relational data. In Proc. 26th International Conference on Neural Information Processing Systems Vol. 2 (eds Burges, C. J. et al.) 2787–2795 (Curran Associates, 2013).
- Nickel, M., Tresp, V. & Kriegel, H. A three-way model for collective learning on multi-relational data. In Proc. 28th International Conference on International Conference on Machine Learning 809–816 (PMLR, 2011).
- Trouillon, T., Welbl, J., Riedel, S., Gaussier, É. & Bouchard, G. Complex embeddings for simple link prediction. In Proc. 33rd International Conference on International Conference on Machine Learning Vol. 48 (eds Balcan, M. F. & Weinberger, K. Q.) 2071–2080 (PMLR, 2016).
- Sun, Z., Deng, Z., Nie, J. & Tang, J. RotatE: knowledge graph embedding by relational rotation in complex space. In International Conference on Learning Representations (2019).
- Yang, B., Yih, W., He, X., Gao, J. & Deng, L. Embedding entities and relations for learning and inference in knowledge bases. In International Conference on Learning Representations (2015).
- Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O. & Dahl, G. E. Neural message passing for quantum chemistry. In Proc. 34th International Conference on Machine Learning Vol. 70, 1263–1272 (PMLR, 2017).
- Kipf, T. N. & Welling, M. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations (2017).
- Xu, K., Hu, W., Leskovec, J. & Jegelka, S. How powerful are graph neural networks? In International Conference on Learning Representations (2019).
- Vinyals, O., Bengio, S. & Kudlur, M. Order matters: sequence to sequence for sets. In International Conference on Learning Representations (2016).
- Defferrard, M., Bresson, X. & Vandergheynst, P. Convolutional neural networks on graphs with fast localized spectral filtering. In Proc. International Conference on Neural Information Processing Systems (eds Lee, D. et al.) 3844–3852 (Curran Associates, 2016).
- Yun, S., Jeong, M., Kim, R., Kang, J. & Kim, H. J. Graph transformer networks. In Proc. 33rd Conference on Neural Information Processing Systems (eds Wallach, H. et al.) (Curran Associates, 2019).
- Klicpera, J., Groß, J. & Günnemann, S. Directional message passing for molecular graphs. In International Conference on Learning Representations (2020).
- Zeng, H., Zhou, H., Srivastava, A., Kannan, R. & Prasanna, V. K. GraphSAINT: graph sampling based inductive learning method. In International Conference on Learning Representations (2020).
- Huang, K. & Zitnik, M. Graph meta learning via local subgraphs. In Proc. International Conference on Neural Information Processing Systems (eds Larochelle, H. et al.) 5862–5874 (Curran Associates, 2020).
- Hu, W. et al. Strategies for pre-training graph neural networks. In International Conference on Learning Representations (2020).
- Barabási A.-L. et al. Network Science (Cambridge Univ. Press, 2016).
- Jin, W., Barzilay, R. & Jaakkola, T. S. Junction tree variational autoencoder for molecular graph generation. In International Conference on Machine Learning (PMLR, 2018).
- Kipf, T. N. & Welling, M. Variational graph auto-encoders. In Advances in Neural Information Processing Systems Bayesian Deep Learning Workshop (2016).
- You, J., Liu, B., Ying, R., Pande, V. & Leskovec, J. Graph convolutional policy network for goal-directed molecular graph generation. In Proc. International Conference on Neural Information Processing Systems (eds Bengio S. et al.) (Curran Associates, 2018).
- You, J., Ying, R., Ren, X., Hamilton, W. L. & Leskovec, J. GraphRNN: generating realistic graphs with deep auto-regressive models. In International Conference on Machine Learning (2018).
- Dutil, F., Cohen, J. P., Weiss, M., Derevyanko, G. & Bengio, Y. Towards gene expression convolutions using gene interaction graphs. In International Conference on Machine Learning Workshop on Computational Biology (2018).
- Hamilton, W. L., Ying, Z. & Leskovec, J. Inductive representation learning on large graphs. In Proc. International Conference on Neural Information Processing Systems (eds Guyon, I. et al.) (Curran Associates, 2017).
- Fout, A., Byrd, J., Shariat, B. & Ben-Hur, A. Protein interface prediction using graph convolutional networks. In Proc. International Conference on Neural Information Processing Systems (eds Guyon, I. et al.) (Curran Associates, 2019).
- Ingraham, J., Garg, V. K., Barzilay, R. & Jaakkola, T. S. Generative models for graph-based protein design. In Proc. International Conference on Neural Information Processing Systems (eds Wallach, H. et al.) (Curran Associates, 2019).
- Jin, W., Barzilay, R. & Jaakkola, T. Hierarchical generation of molecular graphs using structural motifs. In International Conference on Machine Learning 4552–4561 (2020).
- Dey, T. K. & Mandal, S. Protein classification with improved topological data analysis. In 18th International Workshop on Algorithms in Bioinformatics (WABI) (eds Parida, L. & Ukkonen, E.) 6:1–6:13 (Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik, 2018).
- Yang, C., Zhuang, P., Shi, W., Luu, A. & Li, P. Conditional structure generation through graph variational generative adversarial nets. In Proc. International Conference on Neural Information Processing Systems (eds Wallach, H. et al.) 124632 (Curran Associates, 2019).
- Liu, S., Grau, B., Horrocks, I. & Kostylev, E. INDIGO: GNN-based inductive knowledge graph completion using pair-wise encoding. In Proc. International Conference on Neural Information Processing Systems (eds Ranzato, S. et al.) 2034–2045 (Curran Associates, 2021).
- Huang, K. scGNN: scRNA-seq dropout imputation via induced hierarchical cell similarity graph. In International Conference on Machine Learning Workshop on Computational Biology (2020).
- Alsentzer, E., Finlayson, S. G., Li, M. M. & Zitnik, M. Subgraph neural networks. In Proc. International Conference on Neural Information Processing Systems (eds Larochelle, H. et al.) 8017–8029 (Curran Associates, 2020).
- Bonito, P. et al. in Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, and Graphs in Biomedical Image Analysis (eds Sudre, C. H. et al.) 208–219 (Springer, 2020).
- Zhang, X. & Zitnik, M. GNNGuard: defending graph neural networks against adversarial attacks. In Proc. International Conference on Neural Information Processing Systems (eds Larochelle, H. et al.) 9263–9275 (Curran Associates, 2020).
- Xu, K. et al. Representation learning on graphs with jumping knowledge networks. In Proc. 35th International Conference on MachineLearning (PMLR, 2018).
- Li, M. M. & Zitnik, M. Deep contextual learners for protein networks. In International Conference on Machine Learning Workshop on Computational Biology (2021).
- National Research Council (US) Committee on A Framework for Developing a New Taxonomy of Disease Toward Precision Medicine: Building a Knowledge Network for Biomedical Research and a new Taxonomy of Disease (National Academies Press, 2011).
Cited by
Sorted by citations
Scientific discovery in the age of artificial intelligence.
Wang, H., Fu, T., Du, Y., Gao, W., Huang, K., Liu, Z., Chandak, P., Liu, S., Van Katwyk, P., Deac, A., et al. (2023) · Nature · doi:10.1038/s41586-023-06221-2 · Cited by 1,823
Self-citationBuilding a knowledge graph to enable precision medicine
Chandak, P., Huang, K., & Zitnik, M. (2023) · Scientific Data · doi:10.1038/s41597-023-01960-3 · Cited by 522
Self-citationA foundation model for clinician-centered drug repurposing
Huang, K., Chandak, P., Wang, Q., Havaldar, S., Vaid, A., Leskovec, J., Nadkarni, G. N., Glicksberg, B. S., Gehlenborg, N., & Zitnik, M. (2024) · Nature Medicine · doi:10.1038/s41591-024-03233-x · Cited by 249
“We also envision integrating patient information with medical KGs to provide personalized drug-repurposing predictions.”
BackgroundMethodInfluentialSelf-citationWu, Y., & Xie, L. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.12.030 · Cited by 220
“Graph (network) representation has been widely applied in systems biology to represent biological organizations and interactions[83].”
Multimodal data integration for oncology in the era of deep neural networks: a review
Waqas, A., Tripathi, A., Ramachandran, R. P., Stewart, P. A., & Rasool, G. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1408843 · Cited by 165
“…2021; Ma and Tang, 2021; Ma Y. et al., 2021; Park et al., 2021; Yang T. et al., 2021; Almasan et al., 2022; Jiao et al., 2022; Jin et al., 2022; Li M. et al., 2022; Waikhom and Patgiri, 2022; Waqas et al., 2022; Yi et al., 2022; Ektefaie et al., 2023; Fathinezhad et al., 2023; Nie et al., 2023…”
Woodman, R. J., & Mangoni, A. A. (2023) · Aging Clinical and Experimental Research · doi:10.1007/s40520-023-02552-2 · Cited by 163
Graph machine learning for integrated multi-omics analysis
Valous, N. A., Popp, F., Zörnig, I., Jäger, D., & Charoentong, P. (2024) · British Journal of Cancer · doi:10.1038/s41416-024-02706-7 · Cited by 152
“Graph machine learning methods [13] ( b ) are developed/applied for unsupervised, semi-supervised, and supervised learning [5, 6, 24] between omics sets are either inferred or retrieved from databases) allows for several methods to explore the network ’ s topology including shortest paths and…”
BackgroundMethodTransformer models in biomedicine
Madan, S., Lentzen, M., Brandt, J., Rueckert, D., Hofmann‐Apitius, M., & Fröhlich, H. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02600-5 · Cited by 146
Digital twins as global learning health and disease models for preventive and personalized medicine
Li, X., Loscalzo, J., Mahmud, A. K. M. F., Aly, D. M., Rzhetsky, A., Žitnik, M., & Benson, M. (2025) · Genome Medicine · doi:10.1186/s13073-025-01435-7 · Cited by 135
Self-citationCurrent and future directions in network biology
Žitnik, M., Li, M. M., Wells, A., Glass, K., Gysi, D. M., Krishnan, A., Murali, T. M., Predrag Radivojac, A., Roy, S., Baudot, A., et al. (2024) · Bioinformatics Advances · doi:10.1093/bioadv/vbae099 · Cited by 128
“Link prediction is a self-supervised edge classification task that predicts whether an edge exists between a pair of nodes [199, 225]”
BackgroundMethodInfluentialSelf-citationA comprehensive review on triboelectric sensors and AI-integrated systems
Duan, S., Zhang, H., Liu, L., Lin, Y., Zhao, F., Chen, P., Cao, S., Zhou, K., Gao, C., Liu, Z., et al. (2024) · Materials Today · doi:10.1016/j.mattod.2024.08.013 · Cited by 102
Recent Advances in Deep Learning for Protein-Protein Interaction Analysis: A Comprehensive Review
Lee, M. (2023) · Molecules · doi:10.3390/molecules28135169 · Cited by 97
GTC: GNN-Transformer co-contrastive learning for self-supervised heterogeneous graph representation
Sun, Y., Zhu, D., Wang, Y., Fu, Y., & Tian, Z. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106645 · Cited by 86
Simon, B. D., Ozyoruk, K. B., Gelikman, D. G., Harmon, S. A., & Türkbey, B. (2024) · Diagnostic and Interventional Radiology · doi:10.4274/dir.2024.242631 · Cited by 73
“39 There are several methodologies for fusing modalities.”
MethodChallenges in AI-driven Biomedical Multimodal Data Fusion and Analysis
Liu, J., Cen, X., Yi, C., Wang, F.-A., Ding, J., Cheng, J., Wu, Q., Gai, B., Zhou, Y., He, R., et al. (2025) · Genomics, Proteomics & Bioinformatics · doi:10.1093/gpbjnl/qzaf011 · Cited by 75
“In the context of biomedical applications, these graph structures can represent various associations, including gene functions, drug responses, medical image patches, and cellular similarity [64].”
A review of mechanistic learning in mathematical oncology
Metzcar, J., Jutzeler, C. R., Macklin, P., Köhn‐Luque, A., & Brüningk, S. C. (2024) · Frontiers in Immunology · doi:10.3389/fimmu.2024.1363144 · Cited by 79
“For instance, while convolutional blocks are the staple for computer vision tasks, similar approaches exist for sequential data (e.g. sequence-to-sequence transformers, recurrent neural networks, or graph-based models (51, 52)).”
BackgroundDemocratizing knowledge representation with BioCypher
Lobentanzer, S., Aloy, P., Baumbach, J., Bohár, B., Carey, V. J., Charoentong, P., Danhauser, K., Doğan, T., Dréo, J., Dunham, I., et al. (2023) · Nature Biotechnology · doi:10.1038/s41587-023-01848-y · Cited by 68
Shin, J., Piao, Y., Bang, D., Kim, S., & Jo, K. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms232213919 · Cited by 60
Molecular pixelation: spatial proteomics of single cells by sequencing
Karlsson, F., Kallas, T., Thiagarajan, D., Karlsson, M., Schweitzer, M., Navarro, J. F., Leijonancker, L., Geny, S., Pettersson, E., Rhomberg-Kauert, J., et al. (2024) · Nature Methods · doi:10.1038/s41592-024-02268-9 · Cited by 53
Brain-GCN-Net: Graph-Convolutional Neural Network for brain tumor identification
Gürsoy, E., & Kaya, Y. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108971 · Cited by 53
HMSG: Heterogeneous Graph Neural Network based on Metapath Subgraph Learning
Guan, M.-Y., Cai, X., Shang, J., Hao, F., Liu, D., Jiao, X.-L., & Ni, W.-C. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110930 · Cited by 44
Gao, R., Yuan, X., Ma, Y., Wei, T., Johnston, L., Shao, Y., Lv, W., Zhu, T., Zhang, Y., Zheng, J., et al. (2024) · Cell Reports Medicine · doi:10.1016/j.xcrm.2024.101536 · Cited by 45
Graph Neural Networks: Architectures, Applications, and Future Directions
Ponzi, V., & Napoli, C. (2025) · IEEE Access · doi:10.1109/access.2025.3558752 · Cited by 61
“By treating each drug as a node and modeling their interactions as edges, GNNs can help identify potential adverse reactions that may not be detected in clinical trials Li et al. [48].”
Bafna, M., Li, H., & Zhang, X. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad269 · Cited by 45
GraphXAI: a survey of graph neural networks (GNNs) for explainable AI (XAI)
Nandan, M., Mitra, S., & De, D. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11054-3 · Cited by 46
KG-Hub—building and exchanging biological knowledge graphs
Caufield, J. H., Putman, T., Schaper, K., Unni, D., Hegde, H., Callahan, T. J., Cappelletti, L., Moxon, S. A. T., Ravanmehr, V., Carbon, S., et al. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad418 · Cited by 42
Mi, H., Sivagnanam, S., Ho, W. J., Zhang, S., Bergman, D. R., Deshpande, A. M., Baras, A. S., Jaffee, E. M., Coussens, L. M., Fertig, E. J., et al. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae421 · Cited by 38
“Generative adversarial networks (GANs) are being used as data augmentation tools for algorithmic validations [241–244]; guided by spatial information, graph learning is leading the way in modeling of TME structures with increased interpretability [226, 230, 231, 245].”
MethodLiu, Y., Chen, Y., & Han, L. (2023) · The Innovation Medicine · doi:10.59717/j.xinn-med.2023.100012 · Cited by 36
Vanea, C., Džigurski, J., Rukins, V., Dodi, O., Siigur, S., Salumäe, L., Meir, K. S., Parks, W. T., Hochner‐Celnikier, D., Fraser, A., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-46986-2 · Cited by 38
Graph Artificial Intelligence in Medicine
Johnson, R., Li, M. M., Noori, A., Queen, O., & Žitnik, M. (2024) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-110723-024625 · Cited by 46
“Although there are many innovative biomedical applications of graph representation in genomics (14–16), proteomics (17, 18), and therapeutics (19–21), we focus on applications utilizing clinical data collected in the health care setting.”
Self-citationGraph Anomaly Detection in Time Series: A Survey
Ho, T. K. K., Karami, A., & Armanfard, N. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3566620 · Cited by 68
“For instance, Graph-based Approaches (GA) surveys [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35] cover a broad range of graph structure learning techniques for various tasks such as classification, clustering, and prediction, without focusing specifically on AD.”
Molecular hypergraph neural networks
Chen, J., & Schwaller, P. (2024) · The Journal of Chemical Physics · doi:10.1063/5.0193557 · Cited by 45
An ontology-based knowledge graph for representing interactions involving RNA molecules
Cavalleri, E., Cabri, A., Soto-Gomez, M., Bonfitto, S., Perlasca, P., Gliozzo, J., Callahan, T. J., Reese, J., Robinson, P. N., Casiraghi, E., et al. (2024) · Scientific Data · doi:10.1038/s41597-024-03673-7 · Cited by 33
“In particular we foresee that Graph Representation Learning methods, by leveraging the topology of the complex bio-medical heterogeneous graphs to embed them into compact vectorial spaces, could be the most promising choice to properly analyze the complex heterogeneous structure of RNA-KG 57 .”
Fu, X., Sahai, E. A., & Wilkins, A. C. (2023) · The Journal of Pathology · doi:10.1002/path.6153 · Cited by 37
“Graph neural networks (GNNs) have been widely applied in other biological research fields, such as protein structure predictions [82].”
MethodRu, B., Tan, X., Liu, Y., Kannapur, K., Ramanan, D., Kessler, G. N., Lautsch, D., & Fonarow, G. C. (2023) · JMIR Formative Research · doi:10.2196/41775 · Cited by 30
Perspectives on Advancing Multimodal Learning in Environmental Science and Engineering Studies
Liu, W., Chen, J., Wang, H., Fu, Z., Peijnenburg, W. J. G. M., & Hong, H. (2024) · Environmental Science & Technology · doi:10.1021/acs.est.4c03088 · Cited by 34
Ratajczak, F., Joblin, M., Hildebrandt, M. E., Ringsquandl, M., Falter‐Braun, P., & Heinig, M. (2023) · Nature Communications · doi:10.1038/s41467-023-42975-z · Cited by 30
“With the uptake of graph representation learning in biomedicine 27 , novel options exist to process networks alongside the input features in a joint ML model, thus approaching an in silico representation of biological regulation.”
A survey on graph embedding techniques for biomedical data: Methods and applications
Wu, Y., Chen, Y., Yin, Z., Ding, W., & King, I. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101909 · Cited by 33
Multi-Domain Based Dynamic Graph Representation Learning for EEG Emotion Recognition
Tang, H., Xie, S., Xie, X., Cui, Y., Li, B., Zheng, D., Hao, Y., Wang, X., Jiang, Y., & Tian, Z. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3415163 · Cited by 27
“This graph-based methodology leverages the principles of graph theory to more accurately map the neural interactions and dynamics underlying emotional states, offering a promising avenue for advancing EEG-based emotion recognition research [15].”
MethodIdentifying autism spectrum disorder from multi-modal data with privacy-preserving
Wang, H., Jing, H., Yang, J., Liu, C., Hu, L., Tao, G., Zhao, Z., & Shen, N. (2024) · npj Mental Health Research · doi:10.1038/s44184-023-00050-x · Cited by 27
“To learn the complex relationships and information from the multi-modal data, graph structure has been employed in the medical fi eld 11,12 .”
MethodMultimodal learning on graphs for disease relation extraction
Lin, Y., Lu, K., Yu, S., Cai, T., & Žitnik, M. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104415 · Cited by 35
Self-citationAn edge-weighted graph triumvirate to represent modular building layouts
Lin, X., Chen, J., Lu, W., & Guo, H. (2023) · Automation in Construction · doi:10.1016/j.autcon.2023.105140 · Cited by 25
Hu, X., Sun, Z., Nian, Y., Wang, Y., Dang, Y., Li, F., Feng, J., Yu, E., & Tao, C. (2024) · JMIR Aging · doi:10.2196/54748 · Cited by 34
“A value of 0 in W means that the relationship does not affect a patient with ADRD.”
BackgroundMultimodal Learning for Multi-omics: A Survey
Tabakhi, S., Suvon, M. N. I., Ahadian, P., & Lu, H. (2022) · World Scientific Annual Review of Artificial Intelligence · doi:10.1142/s2811032322500047 · Cited by 27
“Then, latent representations are combined to perform the downstream task.(87,88) Amor et al.”
BackgroundMethodHuang, Z. Z., Jiang, Y. Y., Jiang, Y. Y., et al. (2023) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2023.10.013 · Cited by 23
Hybrid-attention mechanism based heterogeneous graph representation learning
Wang, X., Deng, W., Meng, Z., & Chen, D. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123963 · Cited by 23
Enhancing Robotic Tactile Exploration With Multireceptive Graph Convolutional Networks
Liao, J., Xiong, P., Liu, P. X., et al. (2023) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2023.3323695 · Cited by 23
“In contrast to CNNs that operate on regular grids, GCNs process non-Euclidean data on graphs and use the relationships among nodes to extract features [24], [25], [26], [27].”
BackgroundArtificial intelligence (AI) meets biomaterials and biomedicine
Han, S., & Wu, J. (2024) · Smart Materials in Medicine · doi:10.1016/j.smaim.2024.03.001 · Cited by 22
Enhancing Precision Drug Recommendations via In-Depth Exploration of Motif Relationships
Zhao, C., Zhao, H., Zhou, X., et al. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3437775 · Cited by 22
Navigating the Expansive Landscapes of Soft Materials: A User Guide for High-Throughput Workflows
Day, E. C., Chittari, S. S., Bogen, M. P., & Knight, A. (2023) · ACS Polymers Au · doi:10.1021/acspolymersau.3c00025 · Cited by 26
Unveiling the frontiers of deep learning: Innovations shaping diverse domains
Ahmed, S. F., Alam, M. S. B., Kabir, M., Afrin, S., Rafa, S. J., Mehjabin, A., & Gandomi, A. H. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06259-x · Cited by 30
“it is essential to examine the recent advancements and applications of deep learning in the potential fields, including audiovisual data processing [2][3][4], agriculture [5][6][7][8], transportation prediction [9][10][11], natural language [12][13], biomedicine [14][15], disaster management [16][17], bioinformatics […”
Deep representation learning of protein-protein interaction networks for enhanced pattern discovery
Yan, R., Islam, M. T., & Xing, L. (2024) · Science Advances · doi:10.1126/sciadv.adq4324 · Cited by 21
“Network embedding, a process where interconnected nodes within a network are mapped into vectors in a lower dimension while preserving certain network structure properties and node relationships, is a commonly used approach to discern patterns within biological networks ( 9 – 11 ).”
An update on knowledge graphs and their current and potential applications in drug discovery
Serra, A., Fratello, M., Federico, A., & Greco, D. (2025) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2025.2490253 · Cited by 22
Sex differences in bladder cancer: understanding biological and clinical implications
Chaudhary, P., Singha, B., Abdel-Hafiz, H. A., Velegraki, M., Sundi, D., Satturwar, S. P., Parwani, A. V., Grivennikov, S. I., You, S., Goodridge, H. S., et al. (2025) · Biology of Sex Differences · doi:10.1186/s13293-025-00715-6 · Cited by 25
Liu, S., Zhou, J., Zhu, X., Zhang, Y. L., Zhou, X., Zhang, S., Yang, Z., Wang, Z., Wang, R., Yuan, Y., et al. (2024) · Patterns · doi:10.1016/j.patter.2024.101081 · Cited by 23
“67 Our approachalignswithand expands upon the current insights into MDD diagnostic models, emphasizing the advantages of both local and global perspective-based GNN depression diagnostic models.”
Opportunities and challenges of 5G network technology toward precision medicine
Kang, C. C., Lee, T. Y., Lim, W. F., & Yeo, W. W. Y. (2023) · Clinical and Translational Science · doi:10.1111/cts.13640 · Cited by 20
“61,62 DL is a type of ML that mimics the workings of the human brain to understand and then analyze the data.”
BackgroundAyuso-Muñoz, A., Santamaría, L. P., Carro, E. U., Serrano, E., & Rodríguez‐González, A. (2023) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2023.102687 · Cited by 18
Morphological map of under- and overexpression of genes in human cells
Chandrasekaran, S. N., Alix, E., Arévalo, J., Borowa, A., Byrne, P. J., Charles, W. G., Chen, Z., Cimini, B. A., Deng, B., Doench, J. G., et al. (2025) · Nature Methods · doi:10.1038/s41592-025-02753-9 · Cited by 21
Graph Neural Networks in Medical Imaging: Methods, Applications and Future Directions
Mienye, I. D., & Viriri, S. (2025) · Information · doi:10.3390/info16121051 · Cited by 17
Connecting AI: Merging Large Language Models and Knowledge Graph
Jovanovic, M., & Campbell, M. (2023) · Computer · doi:10.1109/mc.2023.3305206 · Cited by 19
Hu, D., Jiang, Z., Shi, J., Xie, F., Wu, K., Tang, K., Cao, M. W., Huai, J., & Zheng, Y. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103163 · Cited by 20
Wang, H., Chen, B., Sun, H., & Zhang, Y. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108531 · Cited by 18
Wang, G., Chen, H., Wang, H., Gao, H., Hu, X., & Cao, C. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3550019 · Cited by 17
“Graph-based methodologies excel in capturing intricate relationships between drug features and molecular interactions by learning sophisticated representations from complex molecular structures [19].”
Heterogeneous graph construction and HinSAGE learning from electronic medical records
Cho, H. N., Ahn, I., Gwon, H., Kang, H., Kim, Y., Seo, H., Choi, H., Kim, M., Han, J., Kee, G., et al. (2022) · Scientific Reports · doi:10.1038/s41598-022-25693-2 · Cited by 16
Woodman, R. J., Koczwara, B., & Mangoni, A. A. (2024) · Frontiers in Medicine · doi:10.3389/fmed.2023.1302844 · Cited by 15
“…can be used to integrate knowledge from different medical domains, including diseases and drugs, and incorporate their complex interactions (20), and machine learning (ML) methods, including graph neural networks, are now being applied to multimorbidity disease networks to improve disease…”
BackgroundMethodInfluentialChowdhury, S., Chen, Y., Li, P., Rajaganapathy, S., Wen, A., Ma, X., Dai, Q., Yu, Y., Fu, S., Jiang, X., et al. (2024) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae137 · Cited by 16
StaVia: spatially and temporally aware cartography with higher-order random walks for cell atlases
Stassen, S. V., Kobashi, M., Lam, E. Y. M., Huang, Y., Ho, J. W. K., & Tsia, K. K. (2024) · Genome biology · doi:10.1186/s13059-024-03347-y · Cited by 17
“For effective visualization of complex trajectories at an atlas scale, it is imperative to establish a linkage between the overall network structure and the fine-grained transcriptomic signature [56].”
BackgroundHausleitner, C., Mueller, H., Holzinger, A., & Pfeifer, B. (2024) · Scientific Reports · doi:10.1038/s41598-024-72748-7 · Cited by 15
Fei, Y., Fang, H., Yan, Z., Qi, L., Bilal, M., Li, Y., Xu, X., & Zhou, X. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3535753 · Cited by 15
“However, the limited computational capacity and battery life of these devices pose substantial constraints, making it impractical to process extensive volumes of heterogeneous data exclusively on them [12].”
A Knowledge‐Guided Graph Learning Approach Bridging Phenotype‐ and Target‐Based Drug Discovery
Ye, Q., Zeng, Y., Jiang, L., Kang, Y., Pan, P., Chen, J., Deng, Y., Zhao, H., He, S., Hou, T., et al. (2025) · Advanced Science · doi:10.1002/advs.202412402 · Cited by 16
Hu, J., Liu, Y., Zeng, X., Zou, Q., Su, R., & Wei, L. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3553217 · Cited by 15
Responsible adoption of multimodal artificial intelligence in health care: promises and challenges
Azarfar, G., Naimimohasses, S., Rambhatla, S., Komorowski, M., Ferro, D., Lewis, P. R., Gates, D., Shara, N. M., Gascon, G. M., Chang, A. C., et al. (2025) · The Lancet Digital Health · doi:10.1016/j.landig.2025.100917 · Cited by 22
Sivarajkumar, S., Huang, Y., & Wang, Y. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104544 · Cited by 14
MPGAAN: Effective and Efficient Heterogeneous Information Network Classification
Wu, Z. (2024) · Journal of Computer Science and Technology Studies · doi:10.32996/jcsts.2024.6.4.2 · Cited by 13
“…combines node feature extraction and neighborhood information aggregation, considers not only the attributes of the node itself but also the geometric characteristics of the graph, and significantly improves the accuracy and robustness of node classification[Li, 2022, Xiao, 2022, Maurya, 2022].”
BackgroundPapillon, M., Sanborn, S., Mathe, J., Cornelis, L., Bertics, A., Buracas, D., Lillemark, H. J., Shewmake, C., Dinç, F., Xavier Pennec, B., et al. (2025) · Machine Learning Science and Technology · doi:10.1088/2632-2153/adf375 · Cited by 44
“…to domains that do not neatly fall into these categories, such as GNNs for arrival time forecasting (Derrow-Pinion et al., 2021), weather forecasting (Keisler, 2022, Lam et al., 2023), materials science (Reiser et al., 2022), patient electronic health records (Li et al., 2022a), and many more.”
Enhancing Molecular Representations Via Graph Transformation Layers
Ren, G., Wu, K., & He, Y. (2023) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c00059 · Cited by 14
A Survey of Large Language Models on Generative Graph Analytics: Query, Learning, and Applications
Shang, W., & Huang, X. S. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3609877 · Cited by 33
“In healthcare networks, nodes link patients, doctors, diseases, and treatments, incorporating the text attributes of medical records to enhance patient care [37], [38], [39].”
Fouladvand, S., Gomez, F. R., Nilforoshan, H., Schwede, M., Noshad, M., Jee, O., You, J., Sosič, R., Leskovec, J., & Chen, J. H. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104407 · Cited by 12
“application of machine learning in healthcare [34].”
Causal diagramming for assessing human system risk in spaceflight
Antonsen, E., Reynolds, R. J., Charvat, J. M., Connell, E., Monti, A., Petersen, D., Nartey, N., Anton, W., Abukmail, A., Marotta, K., et al. (2024) · npj Microgravity · doi:10.1038/s41526-024-00375-7 · Cited by 12
“Graphs have been used extensively in other areas of health and medicine to link related concepts 11 – 15 .”
MethodXu, D., Xiao, X., & Zhang, J. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108220 · Cited by 12
Knowledge graphs in psychiatric research: Potential applications and future perspectives
Freidel, S., & Schwarz, E. (2024) · Acta Psychiatrica Scandinavica · doi:10.1111/acps.13717 · Cited by 13
Cao, Z., Chen, R., Xu, L., Zhou, X., Fu, X., Zhong, W., & Grima, R. (2024) · Mathematical Biosciences · doi:10.1016/j.mbs.2024.109248 · Cited by 12
Yang, H., Chang, J., He, W., Wee, C. F., Soong, J. T. Y., & Feng, M. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3430226 · Cited by 14
“Graph Neural Networks (GNNs) [92], [93] represent innovative machine learning approaches designed for the analysis of graph data, and they have found applications in the field of healthcare [94], [95], [96].”
Fallani, A., Ирекович, Н. Р., Arjona-Medina, J. A., Wegner, J. K., Tkatchenko, A., & Chernichenko, K. (2025) · Journal of Cheminformatics · doi:10.1186/s13321-025-00970-0 · Cited by 21
Shi, H., Xu, T., Li, X., Gao, Q., Xiong, Z., Xia, J., & Yue, Z. (2025) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2025.103101 · Cited by 14
“The field of graph-based learning has witnessed rapid-developed interest among researchers, leading to its rapid-developed application in the realm of bioinformatics [14, 15, 16, 17].”
Vaida, M. L., & Huang, Z. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1716706 · Cited by 12
Davis, M. J., Srinivasan, G., Chacko, R., Chen, S., Suvarna, A., Vaickus, L. J., Torres, V. C., Hodge, S., Chen, E. Y., Preum, S., et al. (2024) · Experimental Dermatology · doi:10.1111/exd.14949 · Cited by 11
“A convolutional neural network (CNN) workflow was used to extract histomorphological features predictive of cSCC at 50-micron resolution, and area under the receiver operating curve (AUC) was used to assess model performance.”
MethodHybrid Quantum-Classical Graph Neural Networks for Tumor Classification in Digital Pathology
Ray, A., Madan, D., Patil, S., Pati, P., Rapsomaniki, M., Kohlakala, A., Dlamini, T. R., Muller, S., Rhrissorrakrai, K., Utro, F., et al. (2024) · IEEE International Conference on Quantum Computing and Engineering (QCE) · doi:10.1109/qce60285.2024.00188 · Cited by 14
“As a result, GNNs can elegantly integrate cellular information with tumor morphology, topology, and interactions among cells and/or tissue structures [6].”
Network-based analyses of multiomics data in biomedicine
Kumar, R., Romano, J. D., & Ritchie, M. D. (2025) · BioData Mining · doi:10.1186/s13040-025-00452-x · Cited by 15
“These networks can then be used alongside graph machine learning and traditional network analyses to explicitly incorporate known relationships into analyses [24, 25, 26].”
Knowledge-augmented Graph Machine Learning for Drug Discovery: A Survey
Zhong, Z., Barkova, A., & Mottin, D. (2025) · ACM Computing Surveys · doi:10.1145/3744237 · Cited by 20
Li, F., Nian, Y., Sun, Z., & Tao, C. (2023) · Yearbook of Medical Informatics · doi:10.1055/s-0043-1768735 · Cited by 10
“…of graph elements, their attributes, and supervised labels (if any), GNNs surpass shallow node embeddings in their ability to perform inductive reasoning and capture higher-order and nonlinear patterns through multi-hop propagation within several layers of neural message passing [27, 34].”
BackgroundMethodUnsupervised Graph Transformer With Augmentation-Free Contrastive Learning
Zhao, H., Yang, X., Wei, K., et al. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3386984 · Cited by 10
GraphScope Flex: LEGO-like Graph Computing Stack
He, T., Hu, S., Lai, L., et al. (2024) · Proceedings - ACM-SIGMOD International Conference on Management of Data · doi:10.1145/3626246.3653383 · Cited by 10
“Graphs are increasingly becoming the backbone of numerous real-world applications, permeating diverse fields such as social networks,e-commerce,bioinformatics,fintech,andknowledgebase [31, 56,78,86,90].”
BackgroundFaviez, C., Chen, X., Garcelon, N., Zaidan, M., Billot, K., Petzold, F., Faour, H., Douillet, M., Rozet, J., Cormier‐Daire, V., et al. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02538-8 · Cited by 10
“A more sophisticated solution consists in using graphs to represent complex systems such as interactions between proteins, comorbidities between diseases, or healthcare knowledge [62].”
BackgroundAqil, K. H., Dumpuri, P., Ram, K., & Sivaprakasam, M. (2024) · Intelligence-Based Medicine · doi:10.1016/j.ibmed.2024.100159 · Cited by 10
Multi-Modal Disease Prediction With Hierarchical Self-Supervised Learning
Qu, Z., Chen, T., Zhou, X., Zhu, F., Guo, W., Xu, Y., Zhang, Y., & Cui, L. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3561546 · Cited by 11
“Furthermore, inspired by the success of Graph Neural Networks (GNNs) [12], [13], [14], both hand-designed graph structures [15], [16], [17] and adaptive graph structures [18], [19], [20] have been explored in GNN-based methods, which construct population graphs and update each patient’s features by…”
Inter-structure and intra-semantics graph contrastive learning for disease prediction
Kang, Y., Zheng, J., Yang, M., & An, N. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112059 · Cited by 9
Graph generative adversarial networks with evolutionary algorithm
Wang, P., Liu, Z., Wang, Z., et al. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111981 · Cited by 8
Adaptive Joint Estimation of Temporal Vertex and Edge Signals
Yan, Y., Xie, T., & Kuruoğlu, E. E. (2025) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2025.3536084 · Cited by 8
“[7 ],functionalbrainimaging[8], andbiomedicine[9].”
Structure-Based Drug Design with Geometric Deep Learning: A Comprehensive Survey
Zhang, Z., Yan, J., Huang, Y., Liu, Q., Chen, E., Wang, M., & Žitnik, M. (2025) · ACM Computing Surveys · doi:10.1145/3769677 · Cited by 33
Self-citation
Metadata
- Authors
- Li, M. M., Huang, K., & Zitnik, M.
- Affiliations
- Harvard University (US)
- Venue
- Nature Biomedical Engineering
- Published
- 2022-10-31
- Volume
- 6
- Issue
- 12
- Pages
- 1353-1369
- ISSN
- 2157-846X (ISSN-L)
- PMC
- PMC10699434
- OpenAlex
- W4307717106
- Semantic Scholar
- 167c4607722d10f350c320bc36a5612e72deba00
- Cited by
- 294
- References
- 218
- Citations by year
- 2026: 66 · 2025: 85 · 2024: 93 · 2023: 42 · 2022: 8
- FWCI
- 4.00
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- Locations
- Nature Biomedical Engineering (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- National Science Foundation (2030459, 2033384)
- AstraZeneca
- U.S. Air Force (FA8702‐15‐D‐0001)
- Harvard Data Science Initiative, Harvard University
- National Human Genome Research Institute (T32HG002295)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
- Keywords
- graph representation learning, network medicine, biomedical networks, graph embedding, molecular interaction networks, signaling pathways, health care system, genetic variant identification, complex traits, diagnosis and treatment, drug development
- MeSH terms
- Machine Learning, Delivery of Health Care, Humans
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
