Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 72 of the 72 references it cites were found in a registry or an index; 22 of the 60 sources its claims cite were checked for support.

Self-supervised learning reveals clinically relevant histomorphological patterns for therapeutic strategies in colon cancer

Open access

Published version of a preprint

Abstract

Unsupervised extraction of 47 histomorphological phenotype clusters (HPCs) from H&E reveals tumor stroma and immune landscape features that predict survival and treatment response in colon cancer.

Overview

CoChat Summary

TL;DR

The paper uses self-supervised learning on colon cancer H&E whole-slide images to derive 47 histomorphological phenotype clusters (HPCs) and shows they are reproducible across TCGA and the AVANT clinical trial. These HPCs were associated with overall survival, outperformed a clinical baseline model, and were linked to stromal, immune, and oncogenic features that may help explain treatment response.

Key findings

  • Trained on 435 TCGA-COAD WSIs from 428 patients, the Barlow Twins encoder produced 128-dimensional tile features, and Leiden clustering identified 47 HPCs.
  • In the external AVANT cohort (1,213 WSIs), HPCs transferred well: 17/47 HPCs had 100% identification in TCGA and 17/47 in AVANT; the remaining HPCs were identified at 84%–98% in TCGA and 88%–98% in AVANT.
  • An HPC-based OS model trained in TCGA achieved a test-set c-index of 0.65 (95% CI 0.55–0.74) in the AVANT control group, outperforming a clinical baseline model (c-index 0.58, 95% CI 0.49–0.67).
  • The HPC-based risk classifier remained independently prognostic in AVANT after adjustment: HR = 2.50 (95% CI 1.18–5.31) in the standard-care group and HR = 1.82 (95% CI 1.11–2.99) in the bevacizumab-treated experimental group.
  • Histology associated with better survival included healthy colon tissue and immune-cell-rich / aligned-stroma HPCs, while mucinous, poor-to-undifferentiated, and disorganized stroma-high patterns were associated with worse survival; the paper also reports links to immune fractions and oncogenic pathways such as VEGFa, hypoxia, angiogenesis, KRAS signaling, and cell-cycle/DNA-repair pathways.

Methods

  • Design: Retrospective multi-cohort analysis using SSL feature extraction plus unsupervised clustering, followed by survival modeling and biological annotation.
  • Data/sample: Training on TCGA-COAD H&E WSIs (final set 435 WSIs / 428 patients); external validation on AVANT colon cancer WSIs (1,213 WSIs, one per patient), with separate analyses for standard-care and bevacizumab-treated groups.
  • Main analysis: Barlow Twins SSL extracted tile embeddings from 224×224 tiles at 10x magnification; Leiden community detection formed HPCs; 5-fold CV L2-regularized Cox regression predicted OS; SHAP, Spearman correlations, and GSEA were used to interpret prognostic HPCs.

Limitations

  • The paper states that HPCs were derived from small image tiles, so larger contextual information is likely lost; this can make some tissue distinctions difficult.
  • The paper states that using TCGA as the training set may introduce bias and variability in data quality across participating institutions.
  • The paper states that it could predict overall survival rather than DFS because of data availability.
  • The paper states that, because of the AVANT regimen design, a separate analysis of bevacizumab vs oxaliplatin-based chemotherapy was not attainable.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1038/s41467-025-57541-y

Cites

72 of 72 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Fig. 1 Overview of the Model Architecture: Training Barlow Twins and deriving Histomorphological Phenotype Clusters. a Training Barlow Twins with TCGA. WSIs from TCGA were processed to extract image tiles and normalize stain colors. The Barlow Twins network was employed to learn 128-dimensional z vectors from a random sample (N = 250,000 image tiles) of these image tiles. b Deriving HPCs. The tiles from TCGA were projected into z vector representations obtained from the trained Barlow Twins network. HPCs were defined by applying Leiden community detection to the nearest neighbor graph of z tile vector representations. Each WSI was represented by a compositional vector of the derived HPCs, indicating the percentage of each HPC with respect to the total tissue area. The Barlow Twins model and HPCs were then projected and integrated into the external AVANT trial. c Whole Slide Image Representation. The compositional HPC data represented the WSIs in the study. AVANT, Bevacizumab-Avastin® adjuVANT trial. HPC, histomorphological phenotype cluster. TCGA, The Cancer Genome Atlas. WSI, whole slide image. Source data are provided as a Source Data file.
Fig. 1 Overview of the Model Architecture: Training Barlow Twins and deriving Histomorphological Phenotype Clusters. a Training Barlow Twins with TCGA. WSIs from TCGA were processed to extract image tiles and normalize stain colors. The Barlow Twins network was employed to learn 128-dimensional z vectors from a random sample (N = 250,000 image tiles) of these image tiles. b Deriving HPCs. The tiles from TCGA were projected into z vector representations obtained from the trained Barlow Twins network. HPCs were defined by applying Leiden community detection to the nearest neighbor graph of z tile vector representations. Each WSI was represented by a compositional vector of the derived HPCs, indicating the percentage of each HPC with respect to the total tissue area. The Barlow Twins model and HPCs were then projected and integrated into the external AVANT trial. c Whole Slide Image Representation. The compositional HPC data represented the WSIs in the study. AVANT, Bevacizumab-Avastin® adjuVANT trial. HPC, histomorphological phenotype cluster. TCGA, The Cancer Genome Atlas. WSI, whole slide image. Source data are provided as a Source Data file.CC BY · PubMed Central
Fig. 2 Identification of HPCs in TCGA and subsequent classification into superclusters. a UMAP showing 47 HPCs identified from the TCGA dataset, each scatter representing an image tile. b PAGA plot of HPCs. Each node represented an HPC with edges representing connections between HPCs based on their vector representation similarity. The pie chart of each node represented the tissue composition for each HPC. c Grouping of HPCs into super-clusters according to histopathology tissue similarities. Representative tiles for each HPC were labeled with ID and a brief description. The image tiles (224-by-224 pixels), at a magnification level of 10x (pixel size approximate 1.0 um), correspond to 224 mm in size (see scale bar in c). HPC, histomorphological phenotype cluster. PAGA, partition-based abstraction graph. TCGA, The Cancer Genome Atlas. UMAP, uniform manifold approximation and projection plot. Source data are provided as a Source Data file.
Fig. 2 Identification of HPCs in TCGA and subsequent classification into superclusters. a UMAP showing 47 HPCs identified from the TCGA dataset, each scatter representing an image tile. b PAGA plot of HPCs. Each node represented an HPC with edges representing connections between HPCs based on their vector representation similarity. The pie chart of each node represented the tissue composition for each HPC. c Grouping of HPCs into super-clusters according to histopathology tissue similarities. Representative tiles for each HPC were labeled with ID and a brief description. The image tiles (224-by-224 pixels), at a magnification level of 10x (pixel size approximate 1.0 um), correspond to 224 mm in size (see scale bar in c). HPC, histomorphological phenotype cluster. PAGA, partition-based abstraction graph. TCGA, The Cancer Genome Atlas. UMAP, uniform manifold approximation and projection plot. Source data are provided as a Source Data file.CC BY · PubMed Central
Fig. 3 Verification of HPCs in the TCGA training set and the external clinical AVANT trial. a–i Example tiles from TCGA (upper row) and AVANT (lower row) showcase the eight super-clusters with a zoomed-in representative tile. The image tiles (224-by-224 pixels), at a magnification level of 10x (pixel size approximate 1.0 um), correspond to 224 mm in size (see scale bar in a–i). The muscle tissue super-cluster is further divided into longitudinal and axial subgroups. j, k Stacked bar plots illustrate instances of misclassification for each HPC in TCGA training set and AVANT external test set. Green bars represent the percentage of correctly identified odd clusters, yellow bars indicate misclassifications within the tested HPC’s super-cluster, orange bars show misclassifications outside the super-cluster. l Box plots display similar distributions of success test rates (corresponding to the green bars in panels j and k) for HPCs in TCGA and AVANT cohorts (two-sided Wilcoxon signed-rank test, p = 0.534). Each blue point within each box plot represents the success test rate for a single HPC, calculated based on 50 tests per HPC. The central orange line within each box represents the median, while the bounds of the box indicate the 25th and 75th percentiles (interquartile range). Whiskers extend to the minima and maxima within 1.5 times the interquartile range. Points outside the whiskers represent outliers. HPC, histomorphological phenotype cluster. TCGA, The Cancer Genome Atlas. AVANT, Bevacizumab-Avastin® adjuVANT trial. Source data are provided as a Source Data file.
Fig. 3 Verification of HPCs in the TCGA training set and the external clinical AVANT trial. a–i Example tiles from TCGA (upper row) and AVANT (lower row) showcase the eight super-clusters with a zoomed-in representative tile. The image tiles (224-by-224 pixels), at a magnification level of 10x (pixel size approximate 1.0 um), correspond to 224 mm in size (see scale bar in a–i). The muscle tissue super-cluster is further divided into longitudinal and axial subgroups. j, k Stacked bar plots illustrate instances of misclassification for each HPC in TCGA training set and AVANT external test set. Green bars represent the percentage of correctly identified odd clusters, yellow bars indicate misclassifications within the tested HPC’s super-cluster, orange bars show misclassifications outside the super-cluster. l Box plots display similar distributions of success test rates (corresponding to the green bars in panels j and k) for HPCs in TCGA and AVANT cohorts (two-sided Wilcoxon signed-rank test, p = 0.534). Each blue point within each box plot represents the success test rate for a single HPC, calculated based on 50 tests per HPC. The central orange line within each box represents the median, while the bounds of the box indicate the 25th and 75th percentiles (interquartile range). Whiskers extend to the minima and maxima within 1.5 times the interquartile range. Points outside the whiskers represent outliers. HPC, histomorphological phenotype cluster. TCGA, The Cancer Genome Atlas. AVANT, Bevacizumab-Avastin® adjuVANT trial. Source data are provided as a Source Data file.CC BY · PubMed Central
Fig. 4 HPC-based classifier was associated with OS in patients treated with standard-of-care and AVANT-experimental treatment. a Ordinary Cox regression for OS, incorporating the HPC-based risk classifier, along with sex, age categories, tumor-stroma ratio, and AJCC TNM staging, was conducted within the external test set of the AVANT control group (N = 379 patients after excluding those with missing clinical information). Each point represents the point estimate of HR, and the horizontal whiskers depict the 95% CI. The HPC model-based classifier stands as an independent prognostic factor (HR = 2.50, 95% CI = 1.18–5.31) for OS. b Ordinary Cox regression for OS, incorporating the HPC-based risk classifier, along with sex, age categories, tumor-stroma ratio, and AJCC TNM staging, was conducted within the AVANT experimental group (N = 751 patients after excluding those with missing clinical information). Each point represents the point estimate of HR, and the horizontal whiskers depict the 95% CI. The HPC model-based classifier stands as an independent prognostic factor (HR = 1.82, 95% CI = 1.11–2.99) for OS. c and d The SHAP summary plots depict the relationship between the center-log-transformed compositional value of an HPC and its impact on death hazard prediction. Statistics estimated from AVANT control (N = 405 after excluding those with missing survival data) (c) and experimental groups (N = 780 patients after excluding those with missing survival data) (d). The color bar indicates the relative compositional value of an HPC, with red indicating higher and blue indicating lower composition. Higher compositions of the top 10 HPCs were associated with worse OS, while higher compositions of the bottom 10 HPCs were linked to improved OS. AJCC TNM, American Joint Committee on Cancer tumor-node-metastasis classification. AVANT, Bevacizumab-Avastin® adjuVANT trial. HPC, histomorphological phenotype cluster. OS, overall survival. SHAP, SHapley Additive exPlanations. TCGA, The Cancer Genome Atlas. Source data are provided as a Source Data file.
Fig. 4 HPC-based classifier was associated with OS in patients treated with standard-of-care and AVANT-experimental treatment. a Ordinary Cox regression for OS, incorporating the HPC-based risk classifier, along with sex, age categories, tumor-stroma ratio, and AJCC TNM staging, was conducted within the external test set of the AVANT control group (N = 379 patients after excluding those with missing clinical information). Each point represents the point estimate of HR, and the horizontal whiskers depict the 95% CI. The HPC model-based classifier stands as an independent prognostic factor (HR = 2.50, 95% CI = 1.18–5.31) for OS. b Ordinary Cox regression for OS, incorporating the HPC-based risk classifier, along with sex, age categories, tumor-stroma ratio, and AJCC TNM staging, was conducted within the AVANT experimental group (N = 751 patients after excluding those with missing clinical information). Each point represents the point estimate of HR, and the horizontal whiskers depict the 95% CI. The HPC model-based classifier stands as an independent prognostic factor (HR = 1.82, 95% CI = 1.11–2.99) for OS. c and d The SHAP summary plots depict the relationship between the center-log-transformed compositional value of an HPC and its impact on death hazard prediction. Statistics estimated from AVANT control (N = 405 after excluding those with missing survival data) (c) and experimental groups (N = 780 patients after excluding those with missing survival data) (d). The color bar indicates the relative compositional value of an HPC, with red indicating higher and blue indicating lower composition. Higher compositions of the top 10 HPCs were associated with worse OS, while higher compositions of the bottom 10 HPCs were linked to improved OS. AJCC TNM, American Joint Committee on Cancer tumor-node-metastasis classification. AVANT, Bevacizumab-Avastin® adjuVANT trial. HPC, histomorphological phenotype cluster. OS, overall survival. SHAP, SHapley Additive exPlanations. TCGA, The Cancer Genome Atlas. Source data are provided as a Source Data file.CC BY · PubMed Central
Fig. 5 PAGA plots highlighted with important HPCs related to OS in the standard-of-care and experimental treated group. a Standard treated group: HPCs colored in the red are linked to worse survival and HPCs colored in blue are linked to better survival. b AVANTexperimental treated group: HPCs colored in the red are linked to worse survival and HPCs colored in blue are linked to better survival. The image tiles (224-by-224 pixels), at a magnification level of 10x (pixel size approximate 1.0 um), correspond to 224 mm in size (see scale bar in a and b). AVANT, Bevacizumab-Avastin® adjuVANT trial. HPC, histomorphological phenotype cluster. PAGA, partition-based graph abstraction. Source data are provided as a Source Data file.
Fig. 5 PAGA plots highlighted with important HPCs related to OS in the standard-of-care and experimental treated group. a Standard treated group: HPCs colored in the red are linked to worse survival and HPCs colored in blue are linked to better survival. b AVANTexperimental treated group: HPCs colored in the red are linked to worse survival and HPCs colored in blue are linked to better survival. The image tiles (224-by-224 pixels), at a magnification level of 10x (pixel size approximate 1.0 um), correspond to 224 mm in size (see scale bar in a and b). AVANT, Bevacizumab-Avastin® adjuVANT trial. HPC, histomorphological phenotype cluster. PAGA, partition-based graph abstraction. Source data are provided as a Source Data file.CC BY · PubMed Central
Fig. 6 Survival-associated HPCs in relation to immune and genetic profile. a Standard-of-care group: Spearman’s correlations between top 20 OS-related HPCs and immune landscape features. HPCs (columns of the matrix) were colored according to the beta-coefficients estimated from the optimized regularised Cox regression, with red indicating HPCs related to worse survival and green indicating HPCs related to better survival. The color bar at the upper left corner indicates the value of correlation coefficients with red denoting positive and blue denoting negative correlations. b AVANT-experimental treated group: Spearman’s correlations between top 20 OS-related HPCs and immune landscape features. c Standard-of-care group GSEA between the top OS-related HPCs and major cancer hallmark pathways. HPCs (columns of the matrix) were colored according to the beta coefficients estimated from the optimized regularized Cox regression, with red indicating HPCs related to worse survival and green indicating HPCs related to better survival. The color bar at the upper left corner indicates the value of the correlation coefficients with red denoting enrichment and blue denoting underrepresentation in a gene pathway. d AVANT-experimental treated group GSEA for the top 20 OS-related HPCs. The immune landscape analysis (N = 355 patients) and GSEA analysis (N = 265 patients) were performed using data available from TCGA. AVANT, Bevacizumab-Avastin® adjuVANT trial. GSEA, gene set enrichment analysis. HPC, histomorphological phenotype cluster. OS, overall survival. Source data are provided as a Source Data file.
Fig. 6 Survival-associated HPCs in relation to immune and genetic profile. a Standard-of-care group: Spearman’s correlations between top 20 OS-related HPCs and immune landscape features. HPCs (columns of the matrix) were colored according to the beta-coefficients estimated from the optimized regularised Cox regression, with red indicating HPCs related to worse survival and green indicating HPCs related to better survival. The color bar at the upper left corner indicates the value of correlation coefficients with red denoting positive and blue denoting negative correlations. b AVANT-experimental treated group: Spearman’s correlations between top 20 OS-related HPCs and immune landscape features. c Standard-of-care group GSEA between the top OS-related HPCs and major cancer hallmark pathways. HPCs (columns of the matrix) were colored according to the beta coefficients estimated from the optimized regularized Cox regression, with red indicating HPCs related to worse survival and green indicating HPCs related to better survival. The color bar at the upper left corner indicates the value of the correlation coefficients with red denoting enrichment and blue denoting underrepresentation in a gene pathway. d AVANT-experimental treated group GSEA for the top 20 OS-related HPCs. The immune landscape analysis (N = 355 patients) and GSEA analysis (N = 265 patients) were performed using data available from TCGA. AVANT, Bevacizumab-Avastin® adjuVANT trial. GSEA, gene set enrichment analysis. HPC, histomorphological phenotype cluster. OS, overall survival. Source data are provided as a Source Data file.CC BY · PubMed Central
Fig. 7 Clinical application of AI-derived HPCs in prediction of patient outcomes. The clinical algorithm consists of three key stages: data preparation, cancer patient characterization, and AI-supported multidisciplinary treatment meetings. Data preparation involves collecting histopathology WSIs, segmenting them into small image tiles. Patient characterization encompasses SSL model training, yielding HPCs via clustering. HPCs are easily interpretable by pathologists, linkable to omic data. Most importantly, HPCs are valuable for predicting diagnosis, patient outcomes, and treatment responses. In treatment-related outcomes, AI-predicted high/low risk groups aid multidisciplinary meetings, enabling personalized treatment plans by oncologists, pathologists, and other physicians. AI, artificial intelligence. HPC, histomorphological phenotype cluster. SSL, self-supervised learning, WSI, whole slide image.
Fig. 7 Clinical application of AI-derived HPCs in prediction of patient outcomes. The clinical algorithm consists of three key stages: data preparation, cancer patient characterization, and AI-supported multidisciplinary treatment meetings. Data preparation involves collecting histopathology WSIs, segmenting them into small image tiles. Patient characterization encompasses SSL model training, yielding HPCs via clustering. HPCs are easily interpretable by pathologists, linkable to omic data. Most importantly, HPCs are valuable for predicting diagnosis, patient outcomes, and treatment responses. In treatment-related outcomes, AI-predicted high/low risk groups aid multidisciplinary meetings, enabling personalized treatment plans by oncologists, pathologists, and other physicians. AI, artificial intelligence. HPC, histomorphological phenotype cluster. SSL, self-supervised learning, WSI, whole slide image.CC BY · PubMed Central

Verification

Claims the paper makes

16 Valid · 1 Not valid · 10 Not checked · 122 Own results and interpretations

85 more claims

Create a free account to see all 149 claims and to verify the 12 references still open.

See all claims — free account
  • It may state two separate claims as one. 36
  • Probably not a substantial claim. 33
  • The quote only partly states this claim. 1

Create a free account to see these claims.

Citations

Cites

Show all 68 references

Research works printed but not linked: 3

  1. Chen, R. J. & Krishnan, R. G. Self-supervised vision transformers learn visual concepts in histopathology. Learning Meaningful Representations of Life, NeurIPS (2021).
  2. Gueréndel C., Arnold P., & Torben-Nielsen B. Creating small but meaningful representations of digital pathology images. In Atzori M., et al., editors, Proceedings of the MICCAI Workshop on Computational Pathology, volume 156 of Proceedings of Machine Learning Research, pages 206–215. (PMLR, 27, 2021).
  3. Nagtegaal I. D., Arends M., & Odze R. Tumours of the colon and rectum: Who classification of tumours of the colon and rectum, tnm staging of carcinomas of the colon and rectum and the introduction. In World Health Organization Classification of Tumours of the Digestive System, pages 157–162. (IARC Press, 2019_.

Cited by

See all 25

Metadata

Authors
Liu, B., Polack, M., Coudray, N., Claudio Quiros, A., Sakellaropoulos, T., Le, H., Karimkhan, A., Crobach, A. S. L. P., van Krieken, J. H. J. M., Yuan, K., Tollenaar, R. A. E. M., Mesker, W. E., & Tsirigos, A.
Affiliations
  • Karolinska Institutet (SE)
  • Leiden University Medical Center (NL)
  • New York University (US)
  • University of Glasgow (GB)
  • NYU Langone Health (US)
Corresponding author
Tsirigos, Aristotelis
Venue
Nature Communications
Published
2025-03-08
Volume
16
Issue
1
Pages
2328-2328
ISSN
2041-1723 (ISSN-L)
OpenAlex
W4408246989
Cited by
25
References
68
Citations by year
2026: 16 · 2025: 6
FWCI
8.76
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Communications (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam) (acceptedVersion, cc-by-sa)
  • Leiden Repository (Leiden University) (submittedVersion, cc-by)
  • PubMed Central (submittedVersion, cc-by-nc-nd)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Leiden Repository (Leiden University) (submittedVersion)
Funders
  • Vetenskapsrådet (2019-06360)
  • National Institutes of Health
  • Genentech
  • National Cancer Institute (P30CA016087)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Single-cell and spatial transcriptomics
Keywords
colon adenocarcinoma, self-supervised learning, Barlow Twins, whole slide images, tumor stroma, immune landscape, adjuvant chemotherapy response, overall survival prediction, personalized treatment

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.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Self-supervised learning reveals clinically relevant histomorphological patterns for therapeutic strategies in colon cancer. https://app.cochat.ai/papers/10.1038/s41467-025-57541-y
The paper
Liu, B., Polack, M., Coudray, N., Claudio Quiros, A., Sakellaropoulos, T., Le, H., Karimkhan, A., Crobach, A. S. L. P., van Krieken, J. H. J. M., Yuan, K., Tollenaar, R. A. E. M., Mesker, W. E., & Tsirigos, A. (2025). Self-supervised learning reveals clinically relevant histomorphological patterns for therapeutic strategies in colon cancer. Nature Communications. https://doi.org/10.1038/s41467-025-57541-y

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.