The DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index; 4 of the 7 sources its claims cite were checked for support.
SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network
Open accessPublished version of a preprint
Abstract
Recent advances in spatially resolved transcriptomics (SRT) technologies have enabled comprehensive characterization of gene expression patterns in the context of tissue microenvironment. To elucidate spatial gene expression variation, we present SpaGCN, a graph convolutional network approach that integrates gene expression, spatial location and histology in SRT data analysis. Through graph convolution, SpaGCN aggregates gene expression of each spot from its neighboring spots, which enables the identification of spatial domains with coherent expression and histology. The subsequent domain guided differential expression (DE) analysis then detects genes with enriched expression patterns in the identified domains. Analyzing seven SRT datasets using SpaGCN, we show it can detect genes with much more enriched spatial expression patterns than competing methods. Furthermore, genes detected by SpaGCN are transferrable and can be utilized to study spatial variation of gene expression in other datasets. SpaGCN is computationally fast, platform independent, making it a desirable tool for diverse SRT studies.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
SpaGCN is a graph convolutional network method that integrates gene expression, spatial location, and histology to identify spatial domains and domain-enriched spatially variable genes (SVGs) or meta genes in spatial transcriptomics data. Across five datasets, it produced more spatially coherent domains and SVGs than K-means, Louvain, SPARK, and SpatialDE, and was computationally fast.
Key findings
- In mouse olfactory bulb (16,218 genes, 262 spots), SpaGCN detected 60 SVGs; SpatialDE detected 67 (12 overlapping) and SPARK detected 772 (49 overlapping). SpaGCN SVGs had median Moran’s I 0.20 versus 0.18 for SPARK and 0.25 for SpatialDE, but were domain-specific.
- In mouse posterior brain (3,353 spots, 31,053 genes), SpaGCN detected 523 SVGs versus 9,678 for SPARK and 12,676 for SpatialDE; median Moran’s I was 0.50 for SpaGCN versus 0.21 for SPARK and 0.16 for SpatialDE. SpaGCN completed spatial domain and SVG detection in less than one minute, versus ~13 minutes for SpatialDE and more than 18 hours for SPARK, using 1.3 GB memory versus >3.1 GB and >7.2 GB, respectively.
- In LIBD human DLPFC slice 151673 (3,639 spots, 33,538 genes), SpaGCN achieved an ARI of 0.42 versus 0.24 for K-means and 0.33 for Louvain; it detected 61 SVGs, with 53 specific to domain 4. Median Moran’s I was 0.39 for SpaGCN versus 0.09 for SPARK and 0.08 for SpatialDE. Transferring 18 SpaGCN-selected genes to slice 151676 gave an ARI of 0.25, versus 0.07 for SpatialDE top 18 and 0.05 for SPARK top 18; 806 SpatialDE SVGs gave ARI 0.14 and 1,114 SPARK SVGs gave ARI 0.15.
- In human primary pancreatic cancer (224 spots, 16,448 genes), SpaGCN detected 12 SVGs (3, 8, and 1 for domains 0, 1, and 2) and a KRT17 + MMP11 - SERPINA1 meta gene marked the cancer region; SPARK and SpatialDE detected 203 and 163 SVGs. In MERFISH mouse hypothalamus (5,665 cells, 161 genes), SpaGCN detected 19 SVGs including DGKK, ERMN, and SLN for domains 2, 3, and 7.
Methods
- SpaGCN builds an undirected weighted graph from spatial coordinates and histology RGB-derived coordinates, with edge weights based on Euclidean distance and a characteristic length scale; it uses PCA top 50 components and a graph convolutional layer, followed by unsupervised iterative clustering initialized by Louvain.
- For SVGs, SpaGCN performs domain-guided differential expression using Wilcoxon rank-sum tests between the target domain and neighboring domains, requiring FDR-adjusted p < 0.05, in-fraction > 80%, in/out fraction ratio > 1, and fold change > 1.5; meta genes are built iteratively from positive and negative genes when no single SVG marks a domain.
- The method was evaluated on five public datasets—four sequencing-based and one MERFISH—and compared with K-means, Louvain, SPARK, and SpatialDE using ARI, Moran’s I, runtime, and memory.
Limitations
- The paper does not include a dedicated limitations section. Text-evident limitations include dependence on histology availability/quality and on user-set parameters such as the scaling factor, characteristic length scale, number of domains/resolution, and SVG filtering thresholds; for smFISH/MERFISH data without histology, the method must be adapted and neighbor contribution increased.
- Text-evident: some domains lack single SVGs and require meta genes, neuronal layer differences can be small and difficult to distinguish, and the evaluation is limited to five datasets with comparisons focused on selected methods.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
55 Own result · 20 Own interpretation · 14 No basis given · 3 Couldn’t confirm · 3 Own method · 2 Not checked yet · 1 Sources not found · 1 No full text of the sources · accuracy not yet measured
A result the paper reports from its own data — 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 further looked into the 55 genes detected exclusively by SpatialDE and found many of the genes are expressed in only a few spots or are highly expressed in most of the spots, leading to false detections of significant spatial patterns (Supplementary Fig. 3).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse olfactory bulb data
plaindirectSingle case- 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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“By contrast, the domains detected by SpaGCN agree better with the biologically known 5-layer structure of the MOB.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse olfactory bulb data
plaincorrelationalSingle case- 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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Next, we show that SpaGCN can also be applied to smFISH-based data.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to MERFISH mouse hypothalamus data
plainSingle case- 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 result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The p-value and q-value distributions of SPARK and SpatialDE are highly skewed toward 0 (Supplementary Fig. 10).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The Moran's I values of SpaGCN detected SVGs are much higher than those detected by SPARK and SpatialDE (median of 0.50 for SpaGCN against 0.21 for SPARK and 0.16 for SpatialDE).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The FDR-adjusted p-value distribution of SPARK and q-value distribution of SpatialDE are highly skewed toward 0, making it challenging to select informative SVGs based on their pvalues or q-values alone (Supplementary Fig. 5).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse olfactory bulb data
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Further examination revealed that some of these genes show spatial variability, but more than half of them are only expressed in a few spots or highly expressed in most of the spots (Supplementary Fig. 4).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse olfactory bulb data
plainSingle case- 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.
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
“SpaGCN did not identify any SVGs for domain 0.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
plainSingle case- 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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“First, by lowering the filtering thresholds, SpaGCN identified KLK6 which is highly expressed in the lower part of domain 0.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
plaindirectSingle case- 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.
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
“The spatial domains identified by SpaGCN agree better with known tissue layer structure than K-means and Louvain's clustering.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Overview of SpaGCN and evaluation
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.
- Probably not a substantial claim. 13
- It may state two separate claims as one. 40
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Previous studies have shown that KLK6 and MBP expression is restricted to oligodendrocytes, while ATP1B1 is mainly expressed in neurons and astrocytes 19 .”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
What the sources say
- Could not verifycites [19] Fu, X. et al. Continuous polony gels for tissue mapping with high resolution and RNA capture efficiency. Preprint at bioRxiv https://doi.org/10.1101/2021.03.17.435795 (2021). sourceExperimental — accuracy not yet measured
The passages on mouse brain expression patterns (Abstract, page unavailable) and the marker-gene list in Figure 3 (PIXEL-seq data analysis, page unavailable) discuss other genes, not the claimed cell-type distributions. Searches for KLK6, MBP, ATP1B1, and oligodendrocytes found no passage in our copy addressing the claim. (LLM, conf=0.76)
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.
Probably not a substantial claim. It may state two separate claims as one.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“KRT17 functions as a tumor promoter and regulates proliferation in pancreatic cancer 21 , and MMP11 has been found to be a prognostic biomarker for pancreatic cancer 22 .”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to human primary pancreatic cancer tissue
What the sources say
- Could not verifycites [21] Liu, Y. et al. High-spatial-resolution multi-omics sequencing via deterministic barcoding in tissue. Cell 183, 1665–1681 e1618 (2020). sourceExperimental — accuracy not yet measured
The Results sections on whole mouse embryos and internal-organ development discuss spatial gene-expression mapping, not pancreatic cancer. Searches for KRT17 as a tumor promoter and MMP11 as a prognostic biomarker found no passage addressing either claim in our copy. (LLM, conf=0.76)
- Could not verifycites [22] Cho, C. S. et al. Microscopic examination of spatial transcriptome using Seq-Scope. Cell 184, 3559–3572 e3522 (2021). sourceExperimental — accuracy not yet measured
The Results passages describe Seq-Scope findings in liver and colon tissue, including Mmp7 expression in hepatic progenitor cells, but do not address pancreatic cancer. Searches for KRT17 and MMP11 found no passage supporting either the tumor-promoter/proliferation claim or the prognostic-biomarker claim. (LLM, conf=0.75)
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.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“This unsupervised iterative clustering algorithm has been previously utilized for scRNA-seq analysis and showed superior performance over Louvain's method 25,26 .”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Spatial domain identification by clustering
What the sources say
- Could not verifycites [25] Sun, S., Zhu, J. & Zhou, X. Statistical analysis of spatial expression patterns for spatially resolved transcriptomic studies. Nat. Methods 17, 193–200 (2020). sourceExperimental — accuracy not yet measured
The Results (Simulations; page unavailable) compare methods for detecting spatially expressed genes, not clustering algorithms. Searches for iterative clustering, scRNA-seq clustering, and Louvain found no passage in our copy addressing the claimed prior use or performance comparison. (LLM, conf=0.74)
- Not checked — no full text of the sourcecites [26] Xie, J., Girshick, R. & Farhadi, A. Unsupervised deep embedding for clustering analysis. In Proc. 33rd International Conference on Machine Learning Vol. 48 (JMLR: W&CP, 2016). 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.
- Could not verify
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In total, SpaGCN detected 12 SVGs, with 3, 8, and 1 SVGs for domains 0, 1, and 2, respectively (Fig. 5b; Supplementary Fig. 21).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to human primary pancreatic cancer tissue
plainSingle case- 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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Using this approach, SpaGCN detected spatial domains that agreed well with the annotated hypothalamic nuclei (Fig. 6a), with domain 2 corresponding to ACA, domain 3 corresponding to PS, and domain 7 corresponding to MnPo.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to MERFISH mouse hypothalamus data
boostedcorrelationalSingle case- 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.
- Rests on an assumption: In MERFISH data, the captured tissue area is much smaller and fewer genes are measured, making it difficult to detect spatial domains because cells within such a small area are more similar to each other.
A result the paper reports from its own data — 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 shown in Fig. 3c, PVALB is enriched in domain 1, and TRM62 is enriched in domain 8.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
plaincorrelationalSingle case- 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
“Louvain's method identified 5 main spatial domains.However, since it does not consider spatial and histology information, domains 2, 3, and 4 have blurred boundaries and more outliers than SpaGCN.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse olfactory bulb data
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.
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
“SpaGCN is applicable to both sequencing-based and smFISH-based data.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Overview of SpaGCN and evaluation
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“When only using their top 18 SVGs, the ARI is only 0.07 for SpatialDE and 0.05 for SPARK.Even when using the 806 most significant SpatialDE detected SVGs, the ARI is only 0.14.When using the 1,114 most significant SPARK detected SVGs, the ARI is 0.15 (Fig. 4e).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to LIBD human dorsolateral prefrontal cortex data
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In total, SpaGCN detected 61 SVGs, with 53 of them specific to domain 4, which corresponds to the white matter region (Supplementary Fig. 14).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to LIBD human dorsolateral prefrontal cortex data
plainSingle case- 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 result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SPARK and SpatialDE detected 203 and 163 SVGs, respectively (Supplementary Fig. 22).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to human primary pancreatic cancer tissue
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.
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, the SpaGCN detected SVGs and meta genes are transferrable and can be utilized for downstream analyses in independent tissue sections.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Discussion
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: 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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Using this meta gene detection procedure, we also detected meta genes for domains 2, 7, 8 and 9, and found that these meta genes are transferrable to an adjacent tissue slice (Supplementary Fig. 13).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
plaincorrelationalSingle case- 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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“By contrast, the SVGs detected by SpaGCN were enriched in specific spatial domains (Supplementary Fig. 11) and their expression patterns are transferable to an adjacent tissue slice in the mouse posterior brain (Supplementary Fig. 12).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
plaincorrelationalSingle case- 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 result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“K-means only identified 3 main spatial domains, with only few spots assigned to domains 1 and 3.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse olfactory bulb data
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.
A result the paper reports from its own data — 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 compared SVGs detected by SpaGCN with those detected by SPARK 14 and SpatialDE 13 , and found that the SVGs detected by SpaGCN have more coherent expression patterns and better biological interpretability than the other two methods.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Overview of SpaGCN and evaluation
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.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, we found that the SPARK results indicate that 274 genes have FDR-adjusted p-values less than 0.00001 with 14 of them having the smallest identical FDR-adjusted p-value of 4.42e-13.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse olfactory bulb data
hedged- 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 result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although all SpaGCN detected SVGs have clear spatial patterns, their Moran's I values are not significantly higher than the SVGs detected by SPARK and SpatialDE (median of 0.20 for SpaGCN against 0.18 for SPARK and 0.25 for SpatialDE).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse olfactory bulb data
plain- 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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The Adjusted Rand Indexes (ARIs) for the SpaGCN, K-means, and Louvain identified domains are 0.42, 0.24, and 0.33, respectively, suggesting that the SpaGCN results better agree with the manually curated layer structure reported in the original study.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to LIBD human dorsolateral prefrontal cortex data
hedgedcorrelationalSingle case- 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.
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
“Fig. 3a shows that Louvain's clustering is similar to SpaGCN, but the spatial domains detected by SpaGCN are more spatially contiguous than Louvain's results.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
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.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SPARK detected 772 genes, with 49 overlapping with SapGCN (Supplementary Fig. 2).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse olfactory bulb data
plain- 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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SpaGCN detected 523 SVGs for the 10 spatial domains while SPARK and SpatialDE detected 9,678 and 12,676 SVGs, respectively (Supplementary Fig. 7).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
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.
A result the paper reports from its own data — 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 shown in Fig. 4a, K-means and Louvain failed to separate the tissue into layers with clear boundary.By contrast, SpaGCN successfully identified layer structures with clear boundaries.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to LIBD human dorsolateral prefrontal cortex data
plaindirectSingle case- 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.
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
“The spatial domain-specific DE analysis described above typically detects SVGs with enriched expression for the majority of the domains.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Detection of spatially variable meta genes
plaincorrelational- 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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SPARK detected 3,187 SVGs with 1,131 of them having FDR-adjusted p-values equal to 0, most of which only marked the white matter region.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Additional information
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.
A result the paper reports from its own data — 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 shown in Supplementary Fig. 24, SpaGCN completed spatial domain and SVG detection in less than one minute, whereas the computing time is ~13 minutes for SpatialDE and more than 18 hours for SPARK.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Supplementary Files
plainSingle case- 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 result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Furthermore, SpaGCN only required 1.3 GB of memory, whereas SpatialDE and SPARK required more than 3.1 GB and 7.2 GB of memory, respectively.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Supplementary Files
plainSingle case- 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 result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SpaGCN is computationally fast and memory efficient.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Supplementary Files
plainSingle case- 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 result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although it is difficult to identify single genes to mark the other neuronal layers, SpaGCN was able to find layer-specific meta genes.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Additional information
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SpatialDE detected 3,654 SVGs with 806 of them having q-values equal to 0, but these genes do not necessarily show better spatial pattern than genes with larger q-values (Supplementary Fig. 16).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Additional information
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although SPARK and SpatialDE detected much larger numbers of SVGs than SpaGCN (Supplementary Fig. 17), the genes detected by these two methods lack ability to distinguish different degrees of spatial variability in expression as their p-value and q-value distributions are highly skewed toward 0 (Supplementary Fig. 18).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Additional information
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.
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
“Another limitation of these two methods is that the FDR-adjusted p-value from SPARK and q-value from SpatialDE are not informative.Genes with similar p-values/q-values do not necessarily show similar spatial pattern and a smaller p-value/q-value does not guarantee a better spatial pattern (Supplementary Fig. 8 and Supplementary Fig. 9).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
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.
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
“The high expression of NRGN in domains 5 and 7 also indicate that these two domains are neuroanatomically similar -both consisting of cortex and the pyramidal layer of the hippocampus.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
hedgedcorrelationalSingle case- 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.
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 shown in Fig. 3e, domain 2 was separated into 5 sub-domains which are located either in the center or different boundary regions of domain 2, suggesting that differences in the neighborhoods of spots contribute to within-domain heterogeneity.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
hedgedconditionalSingle case- 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.
- Rests on an assumption: The expression profile and biological function of a spot is heavily influenced by its neighboring spots.
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
“By varying 𝑙𝑙, users can get spatial domain separations with different patterns in which a higher 𝑙𝑙 will result in spatial domains with higher contiguity.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Discussion
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.
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
“These results indicate that gene expression profiles of spots from white matter are distinct from spots in the neuronal layers, while gene expression differences among the six neuronal layers are much smaller and more difficult to distinguish”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to LIBD human dorsolateral prefrontal cortex data
hedgedSingle case- 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
“The ARIs of both SpatialDE and SPARK are much lower than SpaGCN, even though both used many more SVGs than SpaGCN, which further confirmed the lack of spatial expression specificity for genes detected by these methods.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to LIBD human dorsolateral prefrontal cortex data
boosteddirect- 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
“However, the Moran's I values for their SVGs are much lower than those detected by SpaGCN, suggesting their lack of spatial expression patterns (Fig. 5d).”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to human primary pancreatic cancer tissue
hedgedcorrelational- 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.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Further, multiple domain adaptive filtering criteria implemented in SpaGCN allow it to eliminate false positive SVGs and ensure all detected SVGs have clear spatial expression patterns.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
plaindirectSingle case- 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
“The results consistently showed that SpaGCN can identify spatial domains with coherent gene expression and histology and detect SVGs and meta genes that have much clearer spatial expression patterns and biological interpretations than genes detected by SPARK and SpatialDE.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Discussion
boosteddirect- 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
“Results from SpaGCN will enable researchers to accurately identify spatial domains and SVGs in their studies.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Supplementary Files
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.
In the paper
“The graph convolutional layer was implemented based on Kipf and Welling 23 , where the backpropagation is operated via a localized first-order approximation of spectral graph convolution.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Discussion
What the sources say
- Not matchedcites Kipf and Welling 23
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
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.
- Not matched
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
“Although they are not uniquely expressed in a particular domain, these genes are still useful for understanding spatial variation of gene expression and can be used to form meta genes that are uniquely expressed in a specific domain.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Detection of spatially variable genes
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.
- Rests on an assumption: Some genes may be expressed in multiple but disconnected domains.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The top 50 principal components are used as input, which work well for all datasets analyzed in this paper.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Discussion
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: 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.
In the paper
“A similar function has been employed in SpatialDE 13 .”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Additional information
What the sources say
- Not checked — no full text of the sourcecites [13] Moncada, R. et al. Integrating microarray-based spatial transcriptomics and single-cell RNA-seq reveals tissue architecture in pancreatic ductal adenocarcinomas. Nat. Biotechnol. 38, 333–342 (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.
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
“Since layer 1 only has few spots, it is difficult to find a highly enriched gene.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Additional information
plaindirectSingle case- 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
“which upweights spots assigned with high confidence, and normalizes the contribution of each centroid to the overall loss function to prevent large clusters from distorting the hidden feature space.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Spatial domain identification by clustering
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.
The paper relies on this without support.
The difference of gene expression between different domains is mainly driven by cell type composition variation due to spatial variation of cell types in tissue.
“Due to spatial variation of cell types in tissue, the difference of gene expression between different domains is mainly driven by cell type composition variation.”
The paper relies on this without support.
The expression profile and biological function of a spot is heavily influenced by its neighboring spots.
“The expression profile and biological function of a spot is heavily influenced by its neighboring spots.”
The paper relies on this without support.
The cancer region in the histology image is darker in color than non-cancer regions, making it informative for clustering.
“Since the cancer region in the histology image is darker in color than non-cancer regions, it is informative for clustering.”
The paper relies on this without support.
In MERFISH data, the captured tissue area is much smaller and fewer genes are measured, making it difficult to detect spatial domains because cells within such a small area are more similar to each other.
“One important difference between MERFISH and sequencing-based spatial transcriptomics data is that the captured tissue area is much smaller and less genes are measured, making it difficult to detect spatial domains since the cells within such a small area are more similar to each other.”
The paper relies on this without support.
Some genes may be expressed in multiple but disconnected domains.
“We note that some genes may be expressed in multiple but disconnected domains.”
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
“Two modes of patient data successfully integrated using deep graph learning are histopathological images [8, 185] and EHRs [186, 187].”
From Graph representation learning in biomedicine and healthcare (2022) · cites this paper as [186]
In the citing paper
“Alternatively, attention mechanisms may be applied on EHR data and medical ontologies to capture the parent-child relationships [186, 204, 205].”
From Graph representation learning in biomedicine and healthcare (2022) · cites this paper as [186]
In the citing paper
“Electronic health records are typically represented by ICD (International Classification of Disease) codes [186, 187].”
From Graph representation learning in biomedicine and healthcare (2022) · cites this paper as [186]
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
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Discussion
“𝑨𝑨 is a 50 × 50 matrix representing filter parameters of the convolutional layer”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Additional information
“The graph structure 𝐺𝐺 is stored in an 𝑁𝑁 × 𝑁𝑁 adjacency matrix 𝑨𝑨 = [𝑤𝑤(𝑢𝑢, 𝑣𝑣)]”
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
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to LIBD human dorsolateral prefrontal cortex data
“SpaGCN also showed advantage over competing methods when evaluated on the LIBD human dorsolateral prefrontal cortex (DLPFC) data 20 .”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > References
“20. Li, D., et al. KRT17 Functions as a Tumor Promoter and Regulates Proliferation, Migration and Invasion in Pancreatic Cancer via mTOR/S6k1 Pathway. Cancer Manag Res 12, 2087-2095 (2020).”
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
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Application to mouse posterior brain data
“As shown in Fig. 3c, PVALB is enriched in domain 1, and TRM62 is enriched in domain 8.”
§ Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network > Discussion
“Spatial expression patterns of SVGs detected by SpaGCN for domain 1 (PVALB), 8 (TRIM62), and 5 (NRGN).”
Citations
Cites
Semi-supervised classification with graph convolutional networks
Kipf, T. N., & Welling, M. (2016) · arXiv · doi:10.48550/arxiv.1609.02907 · Cited by 24,853
Fast unfolding of communities in large networks
Blondel, V. D., Guillaume, J.-L., Lambiotte, R., & Lefebvre, E. (2008) · Journal of Statistical Mechanics: Theory and Experiment · doi:10.1088/1742-5468/2008/10/p10008 · Cited by 21,424
Silhouettes: A graphical aid to the interpretation and validation of cluster analysis
Rousseeuw, P. J. (1987) · Journal of Computational and Applied Mathematics · doi:10.1016/0377-0427(87)90125-7 · Cited by 21,392
Visualization and analysis of gene expression in tissue sections by spatial transcriptomics
Ståhl, P. L., Salmén, F., Vickovic, S., Lundmark, A., Navarro, J. F., Magnusson, J., Giacomello, S., Asp, M., Westholm, J. O., Huss, M., et al. (2016) · Science · doi:10.1126/science.aaf2403 · Cited by 3,834
Spatially resolved, highly multiplexed RNA profiling in single cells
Chen, K. H., Boettiger, A. N., Moffitt, J. R., Wang, S., & Zhuang, X. (2015) · Science · doi:10.1126/science.aaa6090 · Cited by 2,969
Proceedings of the 23rd international conference on Machine learning
Cohen, W. W., & Moore, A. (2006) · Cited by 2,647
Unsupervised deep embedding for clustering analysis
Xie, J., Girshick, R., & Farhadi, A. (2015) · arXiv · doi:10.48550/arxiv.1511.06335 · Cited by 2,476
Slide-seq: A scalable technology for measuring genome-wide expression at high spatial resolution
Rodriques, S. G., Stickels, R. R., Goeva, A., Martin, C. A., Murray, E., Vanderburg, C. R., Welch, J., Chen, L. M., Chen, F., & Macosko, E. Z. (2019) · Science · doi:10.1126/science.aaw1219 · Cited by 2,424
Zhang, Y., Sloan, S. A., Clarke, L. E., Caneda, C., Plaza, C. A., Blumenthal, P. D., Vogel, H., Steinberg, G. K., Edwards, M. S. B., Li, G., et al. (2016) · Neuron · doi:10.1016/j.neuron.2015.11.013 · Cited by 2,295
Transcriptome-scale super-resolved imaging in tissues by RNA seqFISH
Eng, C.-H. L., Lawson, M., Zhu, Q., Dries, R., Koulena, N., Takei, Y., Yun, J., Cronin, C., Karp, C., Yuan, G.-C., et al. (2019) · Nature · doi:10.1038/s41586-019-1049-y · Cited by 1,754
Cited by
Sorted by citations
Spatiotemporal transcriptomic atlas of mouse organogenesis using DNA nanoball-patterned arrays
Chen, A., Liao, S., Cheng, M., Ma, K., Wu, L., Lai, Y., Qiu, X., Yang, J., Xu, J., Hao, S., et al. (2022) · Cell · doi:10.1016/j.cell.2022.04.003 · Cited by 1,784
Self-citationBest practices for single-cell analysis across modalities
Heumos, L., Schaar, A. C., Lance, C., Litinetskaya, A., Drost, F., Zappia, L., Lücken, M. D., Strobl, D. C., Henao, J., Curion, F., et al. (2023) · Nature Reviews Genetics · doi:10.1038/s41576-023-00586-w · Cited by 1,051
“Our work represents an entry point”
MethodDong, K., & Zhang, S. (2022) · Nature Communications · doi:10.1038/s41467-022-29439-6 · Cited by 761
Long, Y., Ang, K. S., Li, M., Chong, K. L. K., Sethi, R., Zhong, C., Xu, H., Ong, Z., Sachaphibulkij, K., Chen, A., et al. (2023) · Nature Communications · doi:10.1038/s41467-023-36796-3 · Cited by 700
Self-citationSpatially informed cell-type deconvolution for spatial transcriptomics
Ma, Y., & Zhou, X. (2022) · Nature Biotechnology · doi:10.1038/s41587-022-01273-7 · Cited by 525
Metadata
- Authors
- Hu, J., Li, X., Coleman, K., Schroeder, A., Ma, N., Irwin, D. J., Lee, E. B., Shinohara, R. T., & Li, M.
- Affiliations
- University of Pennsylvania (US)
- Nankai University (CN)
- Corresponding author
- Hu, Jian
- Li, Mingyao
- ORCID
- Venue
- Nature Methods
- Published
- 2021-10-28
- Volume
- 18
- Issue
- 11
- Pages
- 1342-1351
- ISSN
- 1548-7091 (ISSN-L)
- 1548-7105
- OpenAlex
- W3108118546
- Semantic Scholar
- 81b66947d0fdfb0e05cd21446a1f1bd7010f5f59
- Cited by
- 1,113
- References
- 44
- Citations by year
- 2026: 331 · 2025: 288 · 2024: 273 · 2023: 133 · 2022: 80 · 2021: 7
- FWCI
- 33.95
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Locations
- Nature Methods (publishedVersion)
- Research Square (acceptedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- U.S. Department of Health & Human Services | NIH | National Institute of General Medical Sciences (R01GM125301)
- U.S. Department of Health & Human Services | NIH | National Eye Institute (R01EY030192, R01EY031209)
- U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (R01HL113147, R01HL150359)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Single-cell and spatial transcriptomics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Chromatin Dynamics
- Keywords
- spatial transcriptomics, graph convolutional networks, spatial domain, spatially variable genes, spatial gene expression, tissue microenvironment
- MeSH terms
- Dorsolateral Prefrontal Cortex, Algorithms, Animals, Brain, Gene Expression Regulation, Genes, Humans, Pancreatic Neoplasms, Software, Visual Cortex, Cluster Analysis, Neural Networks, Computer, Computational Biology, Mice, Transcriptome, Spatial Analysis
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 2026-10-20, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-20 (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
