HistoAtlas: A Pan-Cancer Morphology Atlas Linking Histomics to Molecular Programs and Clinical Outcomes

Pierre-Antoine Bannier

Figure 1: The HistoAtlas pipeline and pan-cancer morphological landscape. (a) Overview of the computational pipeline. Diagnostic H&E-stained whole-slide images (

6,745

slides, 21 TCGA cancer types) are segmented into tissue compartments (tumor core, stroma, invasive front), followed by cell-level detection and classification of 9 cell types. From each slide, 38 quantitative histomic features are extracted spanning tissue composition, cell densities, nuclear morphology, spatial immune topology, microenvironment heterogeneity, and cell-type ratios. (b) Pairwise Spearman correlation matrix of the 38 features computed across all

6,745

slides. Ward-linkage hierarchical clustering reveals structured modules: density features form a tight positive-correlation block, morphology features cluster together, and cross-module anti-correlations delineate distinct biological axes. Left color bar indicates feature category. Diagonal entries are masked. (c) UMAP embedding of all

6,745

slides colored by cancer type. Cancer types with distinct morphological programs (e.g., THYM, THCA) occupy separated regions, while adenocarcinomas (BRCA, LUAD, STAD) partially overlap. Gray contour lines indicate point density. (d) Cancer type composition of each L1 morphological cluster (

K=10

, horizontal stacked bars), with cluster sizes indicated at left. Cancer types constituting more than 10% of a cluster are labeled within the bar. Right annotation shows overall survival direction per cluster (green arrow: significantly protective, HR

<1

; red arrow: significantly adverse, HR

>1

; gray dash: non-significant). (e) Heatmap of z-scored mean feature values per cluster, with Ward-linkage hierarchical clustering applied to both features (rows) and clusters (columns). Feature labels are colored by category. Red indicates elevated values; blue indicates suppressed values relative to the pan-cancer mean. Values are clipped at

z=\pm 2

for visualization.

N=

6,745$$ slides from 21 TCGA cancer types.

Figure 2: Spatial immune topology reveals compartment-specific prognostic effects. (a) Forest plot of hazard ratios (overall survival, covariate-adjusted Cox regression [age, sex, stage; stratified by TSS]) for intratumoral lymphocyte density (blue circles) and stromal lymphocyte density (orange diamonds) across cancer types and the pan-cancer cohort (

N=

4,560$$ ). Filled markers indicate moderate or strong evidence (BH-adjusted

P<0.05

with adequate power); hollow markers indicate suggestive or insufficient evidence. Intratumoral lymphocyte density is protective (HR

=0.87

[0.81,0.93]

,

P_{\mathrm{adj}}=9.8\times 10^{-4}

); stromal lymphocyte density shows a weaker protective effect (HR

=0.89

[0.83,0.97]

,

P_{\mathrm{adj}}=0.031

). Error bars represent 95% confidence intervals. Vertical dashed line indicates HR

=1.0

(null). (b) Kaplan–Meier curves for intratumoral lymphocyte density in BRCA (median split,

N=960

; High: 480, Low: 480), showing a protective association (HR

=0.72

[0.60,0.88]

,

P_{\mathrm{adj}}=0.018

). Shaded areas indicate 95% confidence intervals. Number at risk shown below. (c) Tumor–lymphocyte nearest-neighbor distance at the invasive front inversely correlates with CD8A expression in BRCA (Spearman

\rho=-0.53

,

P_{\mathrm{adj}}=1.8\times 10^{-68}

,

N=958

), demonstrating that spatial immune exclusion detected by histomics corresponds to reduced cytotoxic T-cell gene expression. Per-slide feature values averaged per case; both axes z-scored within BRCA. (d) Top gene correlates of intratumoral lymphocyte density in BRCA (

N=953

, adjusted model). Horizontal bar chart showing the top 10 positive and top 5 negative Spearman correlations among significantly associated genes (BH-adjusted

P<0.05

). Immune checkpoint genes (TIGIT, PDCD1, CTLA4) and T-cell markers (CD3E, CD3D, CD8A, CD8B) dominate the positive correlates, validating the biological identity of the histomic feature. Error bars represent 95% bootstrap confidence intervals. All

P

-values were calculated using Cox proportional hazards regression (a, b) or Spearman correlation with analytical

t

-test (c, d), with Benjamini–Hochberg correction for multiple testing within each cancer type.

Figure 3: Morphological features recapitulate molecular programs. (a) Heatmap of mean Spearman correlation (across 21 cancer types) between 38 histomic features and 50 Hallmark pathway scores (unadjusted model). Rows and columns are hierarchically clustered (Ward linkage). Left color bar indicates pathway category (Immune, Proliferation, Signaling, Metabolic, Other); top color bar indicates histomic feature category (Composition, Density, Morphology, Spatial, Heterogeneity, Ratios). Structured correspondence is evident: immune cell density features cluster with immune pathway signatures; nuclear morphology and mitotic features cluster with cell cycle and proliferation pathways; invasion depth aligns with EMT. Colormap: RdBu_r, clipped at

\rho=\pm 0.3

. (b) Effect-size distributions for pan-cancer adjusted-model associations, stratified by molecular data type. Each histogram shows the distribution of Spearman

\rho

values; colored bars indicate significance at FDR

<0.05

, gray bars indicate non-significant associations. Vertical dashed lines at

\rho=\pm 0.3

. Gene expression:

4,371

/

5,453

significant (80%); Hallmark pathways:

1,692

/

2,050

(83%); copy-number variation:

2,845

/

5,453

(52%). The higher significance rate among pathway and expression associations, and the broader

\rho

distributions, reflect stronger morphology–transcriptomic coupling than morphology–genomic coupling. All correlations are Spearman with analytical

P

-values (

t

-distribution approximation) and Benjamini–Hochberg correction.

Figure 4: Morphological clusters map to distinct molecular archetypes. (a) Immune subtype enrichment per morphological cluster (L1, pan-cancer). Heatmap of

\log_{2}(\mathrm{OR})

from Fisher’s exact tests comparing the proportion of each Thorsson immune subtype within each cluster to the remaining cohort. Rows: 10 morphological clusters (labeled with cluster name and dominant cancer type). Columns: five Thorsson immune subtypes (C1 Wound Healing, C2 IFN-

\gamma

Dominant, C3 Inflammatory, C4 Lymphocyte Depleted, C6 TGF-

\beta

Dominant). Color scale: red–blue diverging, centered at 0. Black dots indicate BH-adjusted

P<0.05

. Cluster 6 (CRC-enriched) is dominated by C1 Wound Healing (OR

=5.59

,

P_{\mathrm{adj}}<10^{-88}

); Cluster 2 shows combined C4 Lymphocyte Depleted (OR

=7.14

) and C3 Inflammatory (OR

=4.99

) enrichment (85% combined); Cluster 8 (hormone-driven) is enriched for C3 Inflammatory. (b) Hallmark pathway enrichment (Cliff’s

\delta

from Mann–Whitney

U

tests) per morphological cluster. Rows: 50 Hallmark pathways, hierarchically clustered (Ward linkage). Columns: 10 morphological clusters. Black dots indicate BH-adjusted

P<0.05

. Cluster 4 (THYM-enriched) shows strong immune rejection pathway enrichment; Cluster 8 shows estrogen response enrichment (

\delta=0.52

) with suppressed proliferation (

\delta=-0.51

); Cluster 6 shows Wnt/

\beta

-catenin enrichment (

\delta=0.46

) consistent with CRC composition. Colormap centered at 0, range

[-0.5,0.5]

.

Figure 5: Statistical framework and quality control. (a) PVCA variance decomposition per cancer type showing proportions of variance attributable to batch effects (tissue source site, red) and residual signal (gray). Pan-cancer analysis attributes 44.7% of variance to batch (TSS), 32.7% to biological signal (cancer type), and 22.6% to residual. Within individual cancer types, batch effects account for a median of 20.6% of variance. All per-cancer silhouette scores by TSS are negative (range

-0.18

to

-0.0004

), confirming minimal batch-driven clustering. (b) Minimum detectable effect size (MDES) for harmful hazard ratios across 21 cancer types, ordered by sample size (ascending from bottom). Box plots show the distribution of MDES across features within each cancer type. Well-powered cancer types (BRCA,

N=960

) can detect HR

\geq 1.62

; underpowered types (CHOL,

N=36

) require HR

\geq 3.75

for 80% power. Dashed line indicates the clinically meaningful threshold (HR

=1.5

).

N

values per panel: (a)

6,745

slides, 21 cancer types; (b)

5,623

survival associations across 22 cohorts.

Figure 6: From statistics to cells: spatial interpretability in HistoAtlas. (a) Tissue compartment map for a representative BRCA slide (TCGA-A1-A0SE), showing a nine-class segmentation overlay: tumor front (red), tumor core (dark red), peritumoral stroma at three distance bands (0–50 µm, 50–200 µm,

>

200 µm; blue shades), necrosis ring (brown), necrosis (gray), normal epithelium (green), and background (white). Numbered circles mark the tile regions shown in panels (c) and (d). Scale bar: 5 mm. (b) Survival association (covariate-adjusted Cox regression, overall survival) for intratumoral and stromal lymphocyte density in BRCA (

N=960

). Intratumoral lymphocyte density is protective (HR

=0.72

, 95% CI

[0.60,0.88]

,

P_{\mathrm{adj}}=0.018

); stromal lymphocyte density is not significant (HR

=0.93

, 95% CI

[0.77,1.12]

,

P_{\mathrm{adj}}=0.67

). (c) Top-3 ranked tissue tiles for intratumoral lymphocyte density from the same slide, shown as H&E (top) and cell-type prediction overlay (bottom) pairs. Dense green (lymphocyte) annotations among red (cancer cell) annotations confirm high intratumoral immune infiltration. Scale bar: 50 µm. (d) Top-3 ranked tiles for stromal lymphocyte density. Sparser lymphocyte annotations in stromal tissue visually mirror the weaker statistical association. Cell-type overlay legend (14 cell types) is shared between panels (c) and (d).

(A) Tissue composition
No.	Feature	Formula / definition	Unit
1	Tumor area fraction	$A(\Omega_{\mathrm{T}})/A(\Omega)$	fraction
2	Stroma area fraction	$A(\Omega_{\mathrm{S}})/A(\Omega)$	fraction
3	Normal epithelium area fraction †	$A(\Omega_{\mathrm{Norm}})/A(\Omega)$	fraction
4	Eosinophil-neutrophil ratio (peritumoral)	$[n_{\mathrm{Eos}}(B_{S}^{0\text{-}50})+\varepsilon]/[n_{\mathrm{Neu}}(B_{S}^{0\text{-}50})+\varepsilon]$	ratio
(B) Cell densities

Supplementary Table 1 : Definition of the 40 histomic features extracted per slide (38 used in downstream analyses). Features are organized into five categories: (A) tissue composition, (B) cell densities, (C) nuclear morphology and kinetics, (D) spatial organization, and (E) spatial heterogeneity.

\Omega_{\mathrm{T}}

: tumor compartment;

\Omega_{\mathrm{S}}

: stromal compartment;

B_{T}^{0\text{-}50}

/

B_{S}^{0\text{-}50}

: tumor/stromal band within 50 µm of the tumor-stroma boundary;

B_{S}^{50\text{-}200}

: stromal band 50–200 µm from boundary;

d_{T}

: signed distance to tumor boundary (µm);

L(\partial)

: boundary contact length (mm);

\rho_{k}(R)=n_{k}(R)/A(R)

: density of cell type

k

in region

R

. Features 3 and 24 carry zero signal (zero variance across all slides) and are excluded from all downstream analyses, reducing the working feature set to 38.

ID	Axis	Claim	Evid.	Key statistic	Cancer	References
1.1	Immune	Higher intratumoral TIL density $\to$ better OS in BRCA	WE	HR = 0.72 (0.60–0.88), adj.	BRCA	( 35 , 60 , 27 )
1.2	Immune	Higher intratumoral TIL density $\to$ better OS pan-cancer	WE	HR = 0.87 (0.81–0.93), adj.	PAN	( 35 , 37 )
1.3	Immune	Stromal lymphocyte density shows weaker protective effect than intratumoral pan-cancer	SUP	HR = 0.89 (0.83–0.97), adj.	PAN	( 27 )
1.4	Immune	Compartment-specific prognostic strength: intratumoral $>$ stromal	NP	IT HR = 0.87 vs S HR = 0.89, adj.	PAN	( 35 )
1.5	Immune	Immune desert fraction predicts worse OS in LIHC	SUP	HR = 1.29 (1.12–1.48)	LIHC	( 36 )
1.6	Immune	Deep intratumoral lymphocyte fraction protective in HNSC	SUP	HR = 0.79 (0.68–0.91)	HNSC	( 37 )

Supplementary Table 2 : Biological plausibility audit of 60 atlas-derived claims. Each atomic claim was assessed against the published literature and assigned an evidence level: WE = well-established (

>

3 independent confirmations); SUP = supported (1–3 prior studies consistent); NP = novel, biologically plausible (no prior report, mechanistically coherent); NU = novel, uncertain (no prior report, mechanism unclear); C = contradicted (apparent contradiction, resolved by category distinction). Overall: 27 WE (45%), 15 SUP (25%), 12 NP (20%), 5 NU (8%), 1 C (2%).

Abbreviation	Full name	$N$ slides	Status
ACC	Adrenocortical carcinoma	227	Included
BLCA	Bladder urothelial carcinoma	417	Included
BRCA	Breast invasive carcinoma	$1,037$	Included
CESC	Cervical squamous cell carcinoma	279	Included
CHOL	Cholangiocarcinoma	38	Included
COAD	Colon adenocarcinoma	441	Included

Supplementary Table 3 : TCGA cancer types included and excluded from the HistoAtlas analysis. Twenty-one solid-tumor cancer types were included. Twelve additional cancer types were excluded because their dominant cell morphologies fall outside the training domain of the cell detection model.

Category	Genes
Immune / checkpoint (36)	CD274 (PD-L1), PDCD1 (PD-1), PDCD1LG2 (PD-L2), CTLA4, LAG3, TIGIT, HAVCR2 (TIM-3), IDO1, CD8A, CD8B, CD4, CD3D, CD3E, FOXP3, CD19, CD79A, MS4A1 (CD20), CD14, CD68, CD163, CD40, CD80, CD86, ITGAM, NKG7, IFNG, GZMA, GZMB, PRF1, TNF, IL6, IL10, IL2, CXCL9, CXCL10, TGFB1
Proliferation / cell cycle (15)	MKI67, TOP2A, PCNA, CCNB1, CCND1, CCNE1, CDK1, CDK2, CDK4, CDK6, PLK1, AURKA, BIRC5, MCM2, E2F1
EMT / invasion / stemness (15)	CDH1, CDH2, VIM, SNAI1, SNAI2, ZEB1, ZEB2, TWIST1, FN1, ACTA2, ALDH1A1, CD44, SOX2, NANOG, PROM1
Apoptosis / DNA damage (19)	TP53, BCL2, BCL2L1, MCL1, BAX, CASP3, CASP8, FAS, BRCA1, BRCA2, ATM, CHEK1, CHEK2, RAD51, PARP1, MLH1, MSH2, MSH6, CDKN2A
Signaling / oncogenes (27)	EGFR, ERBB2 (HER2), MET, KRAS, NRAS, HRAS, BRAF, NF1, PIK3CA, PTEN, AKT1, MTOR, NOTCH1, FBXW7, CTNNB1, APC, SMAD4, RB1, MYC, ALK, RET, FGFR1, FGFR2, FGFR3, KIT, PDGFRA, JAK2
Hormone receptors (3)	ESR1, PGR, AR

Supplementary Table 4 : Curated gene panel (133 genes) used for molecular correlation analysis. Genes were selected from established cancer gene panels, immune checkpoint targets, and EMT/stemness markers. Functional categories are provided for annotation; genes may participate in multiple pathways.

MSigDB Hallmark pathway	Biological category
HALLMARK_ADIPOGENESIS	Metabolic
HALLMARK_ALLOGRAFT_REJECTION	Immune
HALLMARK_ANDROGEN_RESPONSE	Hormonal
HALLMARK_ANGIOGENESIS	Development
HALLMARK_APICAL_JUNCTION	Cellular component
HALLMARK_APICAL_SURFACE	Cellular component

Supplementary Table 5 : 50 MSigDB Hallmark pathways used for ssGSEA scoring. Pathway activity scores were computed via single-sample Gene Set Enrichment Analysis (ssGSEA) ( 7 , 42 ) using the 50 Hallmark gene sets from MSigDB ( 58 ) (collection identifier: h.all , available at https://www.gsea-msigdb.org/gsea/msigdb/collection_details.jsp ). Each Hallmark gene set contains

{\sim}

200 genes (range: 32–200) and represents a well-characterized biological process or state. Gene sets with fewer than 10 genes present in the expression matrix after intersection were excluded. Full gene lists for all 50 Hallmark pathways are available from MSigDB (Liberzon et al., 2015).

Analysis type	Family definition	Typical family size
Survival (Cox)	Cancer type $\times$ endpoint $\times$ model	36–38
Survival (RMST)	Cancer type $\times$ endpoint $\times$ model	36–38
Molecular correlations	Cancer type $\times$ target set $\times$ method $\times$ model	133–293
Categorical associations	Cancer type $\times$ variable $\times$ test type $\times$ model	36–38
Cluster survival (Cox)	Cluster level $\times$ analysis type $\times$ cancer $\times$ endpoint $\times$ model	10–69
Cluster survival (log-rank)	Cluster level $\times$ analysis type $\times$ cancer $\times$ endpoint	10–69

Supplementary Table 6 : Benjamini–Hochberg correction family definitions by analysis type. Each family groups biologically coherent tests to control the false discovery rate within meaningful contexts. Every adjusted

P

-value is stored alongside its correction family identifier and the number of tests in the family.

Cancer type	$N$ models	Pass (%)	Warn (%)	Fail (%)
ACC	114	112 (98)	2 (2)	0 (0)
BLCA	152	145 (95)	7 (5)	0 (0)
BRCA	152	141 (93)	9 (6)	2 (1)
CESC	152	135 (89)	8 (5)	9 (6)
CHOL	114	109 (96)	5 (4)	0 (0)
COAD	152	145 (95)	4 (3)	3 (2)

Supplementary Table 7 : Proportional hazards assumption violation prevalence. For each cancer type and survival endpoint, the fraction of fitted Cox models classified as “pass” (

P\geq 0.05

), “warn” (

0.01\leq P<0.05

), or “fail” (

P<0.01

) based on the Schoenfeld residual test. When the PH assumption failed, restricted mean survival time (RMST) was computed as a complementary summary. Values shown for the adjusted model (age, sex, stage; stratified by tissue source site); unadjusted models show similar patterns.

Cancer type	$n$ (unadjusted)	$n$ (adjusted)	MICE used
ACC	55	55	Yes
BLCA	348	348	Yes
BRCA	960	960	Yes
CESC	261	261	No ‡
CHOL	36	36	No
COAD	413	413	Yes

Supplementary Table 8 : Sample sizes per cancer type and model tier for overall survival. Sample sizes for the unadjusted (feature only) and adjusted (feature + age + sex + stage; TSS-stratified) models. When MICE imputation was used, sample sizes reflect the imputed dataset; differences between tiers reflect cancer types where the adjusted model was not fitted due to insufficient covariate data.

Cancer type	Horizon (days)	Rationale
PAAD	730 (2 yr)	Aggressive; short median survival
MESO	730 (2 yr)	Aggressive; short median survival
THCA	1825 (5 yr)	Indolent; long median survival
PRAD	1825 (5 yr)	Indolent; long median survival
All others	1095 (3 yr)	Default

Supplementary Table 9 : Cancer-type-specific RMST time horizons. The restricted mean survival time (RMST) was computed using cancer-type-specific truncation horizons chosen to ensure adequate follow-up and at-risk populations.

No.	Feature	Min	Max	Mean	Std	Median	IQR
(A) Tissue composition
1	Tumor area fraction	0.04	0.93	0.45	0.20	0.43	0.29–0.60
2	Stroma area fraction	0.02	0.92	0.45	0.22	0.46	0.28–0.62
4	Eos/neu ratio (peritumoral)	0.00	2.70	0.40	0.47	0.22	0.09–0.52
(B) Cell densities (log scale)
5	Cancer cell density (IT)	5.15	9.39	8.37	0.58	8.47	8.10–8.75

Supplementary Table 10 : Descriptive statistics for the 38 histomic features across

6,745

slides. Feature numbering follows Supplementary Table 1; features 3 and 24 (zero variance) are excluded. Cell density, nearest-neighbor distance, and heterogeneity features are reported on a

\log_{e}

-transformed scale (see Methods, § 4.3 ). IQR: interquartile range (Q1–Q3).

Cancer	$n$	Expression		CNV		Pathway		Immune		Total		%
ACC	52	370/	$10,640$	0/	$10,640$	139/	$4,000$	62/	480	571/	$25,760$	2.2
BLCA	344	$3,916$ /	$10,640$	421/	$10,640$	$1,718$ /	$4,000$	299/	480	$6,354$ /	$25,760$	24.7
BRCA	953	$6,547$ /	$10,906$	$2,967$ /	$10,906$	$2,735$ /	$4,100$	346/	492	$12,595$ /	$26,404$	47.7
CESC	259	$1,052$ /	$5,320$	1/	$5,320$	444/	$2,000$	83/	240	$1,580$ /	$12,880$	12.3
CHOL	36	168/	$10,640$	0/	$10,640$	0/	0	39/	480	207/	$21,760$	1.0
COAD	405	$2,856$ /	$10,640$	429/	$10,640$	$1,214$ /	$4,000$	238/	480	$4,737$ /	$25,760$	18.4

Supplementary Table 11 : Significant Spearman correlations per cancer type and molecular data type. Each cell shows the number of significant correlations (false discovery rate

<0.05

after Benjamini–Hochberg correction within predefined families) out of the total tested. Totals include all adjustment models. Significance rates vary with sample size: PANCAN (

n=

4,654$$ ) and BRCA (

n=953

) show the highest yield, while small cohorts (UCS,

n=53

; CHOL,

n=36

) have low power.

Endpoint	Available pairs	Replicated ( $n$ )	Replication rate
OS (reference)	60	60	100%
DSS	59	37	62.7%
PFS	60	32	53.3%
DSS & PFS	59	29	49.2% a

Supplementary Table 12 : Cross-endpoint replication of OS-significant survival associations. Replication requires the same HR direction and FDR

<0.05

for the secondary endpoint. DFS is excluded from per-pair counts because it was not available in the get_endpoint_concordance output for this analysis.

HistoAtlas: A Pan-Cancer Morphology Atlas Linking Histomics to Molecular Programs and Clinical Outcomes

Abstract

Figures & tables

Computational Pathology

Atlas H&E-TME: Scalable AI-Based Tissue Profiling at Expert Pathologist-Level Accuracy

MoSPR: Histology-to-Gene Expression Prediction with Morpho-Spatial Macrostates and Low-Rank Molecular Programs

Data-Efficient Multimodal Alignment for Histopathology-based Molecular Prediction

Abstract

Computational Pathology

Explore similar work

Atlas H&E-TME: Scalable AI-Based Tissue Profiling at Expert Pathologist-Level Accuracy

MoSPR: Histology-to-Gene Expression Prediction with Morpho-Spatial Macrostates and Low-Rank Molecular Programs

Data-Efficient Multimodal Alignment for Histopathology-based Molecular Prediction