Spatio-relational inductive biases in spatial cell-type deconvolution

Spatial transcriptomic technologies profile gene expression in-situ, facilitating the spatial characterisation of molecular phenomena within tissues, yet often at multi-cellular resolution. Computational approaches have been developed to infer fine-grained cell-type compositions across locations, but they frequently treat neighbouring spots independently of each other. Here we present GNN-C2L, a flexible deconvolution approach that leverages proximal inductive biases to propagate information along adjacent spots. In performance comparison on simulated and semisimulated datasets, GNN-C2L achieves increased deconvolution performance over spatial-agnostic variants. We believe that accounting for spatial inductive biases can yield improved characterisation of cell-type heterogeneity in tissues.

[1]  Fabian J Theis,et al.  Best practices for single-cell analysis across modalities , 2023, Nature Reviews Genetics.

[2]  Fabian J Theis,et al.  Modeling intercellular communication in tissues using spatial graphs of cells , 2022, Nature Biotechnology.

[3]  Fabian J Theis,et al.  Squidpy: a scalable framework for spatial omics analysis , 2022, Nature Methods.

[4]  Jana M. Braunger,et al.  decoupleR: ensemble of computational methods to infer biological activities from omics data , 2021, bioRxiv.

[5]  Eran Yahav,et al.  How Attentive are Graph Attention Networks? , 2021, ICLR.

[6]  Guocheng Yuan,et al.  SpatialDWLS: accurate deconvolution of spatial transcriptomic data , 2021, Genome Biology.

[7]  William L. Hamilton.  Graph Representation Learning , 2020, Synthesis Lectures on Artificial Intelligence and Machine Learning.

[8]  Eran Yahav,et al.  On the Bottleneck of Graph Neural Networks and its Practical Implications , 2020, ICLR.

[9]  Holger Heyn,et al.  Seeded NMF regression to Deconvolute Spatial Transcriptomics Spots with Single-Cell Transcriptomes , 2020 .

[10]  Rafael A. Irizarry,et al.  Robust decomposition of cell type mixtures in spatial transcriptomics , 2020, Nature Biotechnology.

[11]  Pietro Lio',et al.  Decoupling feature propagation from the design of graph auto-encoders , 2019, ArXiv.

[12]  Kilian Q. Weinberger,et al.  Simplifying Graph Convolutional Networks , 2019, ICML.

[13]  Nimrod D. Rubinstein,et al.  Molecular, spatial, and functional single-cell profiling of the hypothalamic preoptic region , 2018, Science.

[14]  Noah D. Goodman,et al.  Pyro: Deep Universal Probabilistic Programming , 2018, J. Mach. Learn. Res..

[15]  Zena Werb,et al.  Roles of the immune system in cancer: from tumor initiation to metastatic progression , 2018, Genes & development.

[16]  George P Chrousos,et al.  Dynamic aberrant NF-κB spurs tumorigenesis: a new model encompassing the microenvironment. , 2015, Cytokine & growth factor reviews.

[17]  Thiago G. Martins,et al.  Penalising Model Component Complexity: A Principled, Practical Approach to Constructing Priors , 2014, 1403.4630.

[18]  M. Karin,et al.  Implications of anti-cytokine therapy in colorectal cancer and autoimmune diseases , 2012, Annals of the rheumatic diseases.

[19]  M. Karin,et al.  JNK1 in hematopoietically derived cells contributes to diet-induced inflammation and insulin resistance without affecting obesity. , 2007, Cell metabolism.