Deep Graph Mapper: Seeing Graphs Through the Neural Lens

Bodnar, Cristian; Cangea, Cătălina; Lió, Píetro

doi:10.3389/fdata.2021.680535

Cited by 15 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We note also that techniques for high-dimensional information retrieval and clustering ( Agrawal et al, 2005 ; Beyer et al, 1998 ; Hinneburg & Keim, 1999 ; Indyk & Motwani, 1998 ; Radovanović et al, 2010 ) could potentially be used to develop a unified computational framework for the binning stage of the Mapper algorithm that scales well with dimension, and use this work to invite future progress in developing Mapper applications that do not use low-dimensional embeddings at the outset. Recent works have fused graph neural network techniques with Mapper to consume graph-structured data as input and return meaningful embeddings ( Bodnar et al, 2020 ), and such a module could be easily inserted between the reciprocal k NN and intrinsic binning steps in our framework to take advantage of the representational power of neural networks. Along the lines of hardware-driven scalability, Mapper Interactive ( Zhou et al, n.d. ) provides state-of-the-art GPU implementations of the Mapper algorithm for embedding dimensions 1 and 2, and our method could be adapted to fit into such a pipeline.…”

Section: Discussionmentioning

confidence: 99%

NeuMapper: A scalable computational framework for multiscale exploration of the brain’s dynamical organization

Geniesse

Chowdhury

Saggar

2022

Network Neuroscience

View full text Add to dashboard Cite

For better translational outcomes researchers and clinicians alike demand novel tools to distil complex neuroimaging data into simple yet behaviorally relevant representations at the single-participant level. Recently, the Mapper approach from topological data analysis (TDA) has been successfully applied on noninvasive human neuroimaging data to characterize the entire dynamical landscape of whole-brain configurations at the individual level without requiring any spatiotemporal averaging at the outset. Despite promising results, initial applications of Mapper to neuroimaging data were constrained by (1) the need for dimensionality reduction, and (2) lack of a biologically grounded heuristic for efficiently exploring the vast parameter space. Here, we present a novel computational framework for Mapper—designed specifically for neuroimaging data—that removes limitations and reduces computational costs associated with dimensionality reduction and parameter exploration. We also introduce new meta-analytic approaches to better anchor Mapper-generated representations to neuroanatomy and behavior. Our new NeuMapper framework was developed and validated using multiple fMRI datasets where participants engaged in continuous multitask experiments that mimic “ongoing” cognition. Looking forward, we hope our framework could help researchers push the boundaries of psychiatric neuroimaging towards generating insights at the single-participant level while scaling across consortium-size datasets.

show abstract

Section: Discussionmentioning

confidence: 99%

NeuMapper: A scalable computational framework for multiscale exploration of the brain’s dynamical organization

Geniesse

Chowdhury

Saggar

2022

Network Neuroscience

View full text Add to dashboard Cite

show abstract

“…Topological methods of data analysis excel at distilling representation invariant information from large datasets [40,27,21]. However, topological data analysis (TDA) of these complex predictive models such as deep learning remains in its infancy [26,3].…”

Section: Overview and Central Resultsmentioning

confidence: 99%

Topological structure of complex predictions

Li¹,

Dey²,

Gleich³

2022

Preprint

View full text Add to dashboard Cite

Complex prediction models such as deep learning are the output from fitting machine learning, neural networks, or AI models to a set of training data. These are now standard tools in science. A key challenge with the current generation of models is that they are highly parameterized, which makes describing and interpreting the prediction strategies difficult. We use topological data analysis to transform these complex prediction models into pictures representing a topological view. The result is a map of the predictions that enables inspection. The methods scale up to large datasets across different domains and enable us to detect labeling errors in training data, understand generalization in image classification, and inspect predictions of likely pathogenic mutations in the BRCA1 gene.

show abstract

“…There are growing efforts to make neural networks more interpretable in order to keep the human (doctors and patients) in the loop. The interpretability could be improved by using parallel mechanistic computational modeling and simulations (Milanesi et al, 2009 ; Bartocci and Lió, 2016 ), model extraction libraries (see, for instance, Kazhdan et al, 2020 ), and visual inference tools (Bodnar et al, 2020 ). This tool could also be complemented by clinical decision support systems such as Müller and Lio ( 2020 ).…”

Section: Discussionmentioning

confidence: 99%

Graph Representation Forecasting of Patient's Medical Conditions: Toward a Digital Twin

2021

View full text Add to dashboard Cite

Objective: Modern medicine needs to shift from a wait and react, curative discipline to a preventative, interdisciplinary science aiming at providing personalized, systemic, and precise treatment plans to patients. To this purpose, we propose a “digital twin” of patients modeling the human body as a whole and providing a panoramic view over individuals' conditions.Methods: We propose a general framework that composes advanced artificial intelligence (AI) approaches and integrates mathematical modeling in order to provide a panoramic view over current and future pathophysiological conditions. Our modular architecture is based on a graph neural network (GNN) forecasting clinically relevant endpoints (such as blood pressure) and a generative adversarial network (GAN) providing a proof of concept of transcriptomic integrability.Results: We tested our digital twin model on two simulated clinical case studies combining information at organ, tissue, and cellular level. We provided a panoramic overview over current and future patient's conditions by monitoring and forecasting clinically relevant endpoints representing the evolution of patient's vital parameters using the GNN model. We showed how to use the GAN to generate multi-tissue expression data for blood and lung to find associations between cytokines conditioned on the expression of genes in the renin–angiotensin pathway. Our approach was to detect inflammatory cytokines, which are known to have effects on blood pressure and have previously been associated with SARS-CoV-2 infection (e.g., CXCR6, XCL1, and others).Significance: The graph representation of a computational patient has potential to solve important technological challenges in integrating multiscale computational modeling with AI. We believe that this work represents a step forward toward next-generation devices for precision and predictive medicine.

show abstract

Deep Graph Mapper: Seeing Graphs Through the Neural Lens

Cited by 15 publications

References 24 publications

NeuMapper: A scalable computational framework for multiscale exploration of the brain’s dynamical organization

NeuMapper: A scalable computational framework for multiscale exploration of the brain’s dynamical organization

Topological structure of complex predictions

Graph Representation Forecasting of Patient's Medical Conditions: Toward a Digital Twin

Contact Info

Product

Resources

About