SpaGFT is a graph Fourier transform for tissue module identification from spatially resolved transcriptomics
Chang, Y.; Liu, J.; Ma, A.; Li, Z.; Liu, B.; Ma, Q.
Show abstract
Tissue module (TM) is a spatially organized tissue region and executes specialized biological functions, recurring and varying at different tissue sites. However, the computational identification of TMs poses challenges due to their convoluted biological functions, poorly-defined molecular features, and varying spatially organized patterns. Here, we present a hypothesis-free graph Fourier transform model, SpaGFT, to represent spatially organized features using the Fourier coefficients, leading to an accurate representation of spatially variable genes and proteins and the characterization of TM at a fast computational speed. We implemented sequencing-based and imaging-based spatial transcriptomics, spatial-CITE-seq, and spatial proteomics to identify spatially variable genes and proteins, define TM identities, and infer convoluted functions among TMs in mouse brains and human lymph nodes. We collected a human tonsil sample and performed CODEX to accurately demonstrate molecular and cellular variability within the secondary follicle structure. The superior accuracy, scalability, and interpretability of SpaGFT indicate that it is an effective representation of spatially-resolved omics data and an essential tool for bringing new insights into molecular tissue biology.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- HEARTSVG: a fast and accurate method for spatially variable gene identification in large-scale spatial transcriptomic data 98%
- SiGra: Single-cell spatial elucidation through image-augmented graph transformer 97%
- stLearn: integrating spatial location, tissue morphology and gene expression to find cell types, cell-cell interactions and spatial trajectories within undissociated tissues 97%
Similar papers in this journal
- SOAPy: a Python package to dissect spatial architecture, dynamics and communication 97%
- stGCL: A versatile cross-modality fusion method based on multi-modal graph contrastive learning for spatial transcriptomics 97%
- High-precision cell-type mapping and annotation of single-cell spatial transcriptomics with STAMapper 96%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- DeDoc2 identifies and characterizes the hierarchy and dynamics of chromatin TAD-like domains in the single cells 96%
- NanoLoop: A deep learning framework leveraging Nanopore sequencing for chromatin loop prediction 95%
- Predicting MammaPrint Recurrence Risk from Breast Cancer Pathological Images Using a Weakly Supervised Transformer 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.