Stephen X. Skapek
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Stephen X. Skapek has a total of 219 co-authors. Here are the top co-authors by number of shared publications:
- Douglas S. Hawkins
Seattle Children's Hospital Seattle Washington USA
64 shared publications - Jack F. Shern
Pediatric Oncology Branch, National Cancer Institute, Bethesda, USA
61 shared publications - Javed Khan
Oncogenomics Section, Genetics Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA
61 shared publications - Jun S. Wei
Genetics Branch, NCI, NIH, Bethesda, USA
60 shared publications - Corinne M. Linardic
Departments of Pediatrics and Pharmacology & Cancer Biology, Duke University School of Medicine, Durham, NC
37 shared publications - Ben Somerville
Genetics Branch, NCI, NIH, Bethesda, Maryland
36 shared publications
Latest Publications
- Open Access
- 10 June 2026
- Published by Wiley in Clinical and Translational Science
- Vol. 19 (6) , e70627
A Bayesian‐Based Integrative Bioinformatics Analysis Nominates Oncogenic Drivers in Neuroblastoma
Identifying targetable oncogenic drivers remains a challenge in neuroblastoma, the most common extracranial solid malignancy in children. We applied a Bayesian algorithm for integrative analysis of expression and copy‐number, iExCN, to nominate oncogenic drivers in neuroblastoma. The iExCN algorithm found 47 oncogenes from a dataset of 195 neuroblastoma biopsy specimens. The nominated oncogenes included some previously implicated in neuroblastoma, including ALK , MDM2 , MYCN , and XPO1 , but most have not been linked to this disease. A CRISPR/Cas9‐based screen testing those candidates revealed neuroblastoma cell line‐specific and shared vulnerabilities in three well‐characterized models, and dependencies were confirmed by complementary RNA knockdown. Analysis of more than 30 additional neuroblastoma cell lines using DepMap confirmed statistically significant dependency scores in the iExCN genes. Finally, analysis of two cohorts of children with neuroblastoma revealed a trend toward worse survival in cases in which more iExCN genes showed copy number gains. Our findings uncover multiple, potentially targetable oncogenic drivers that appear to influence neuroblastoma biology, demonstrating a generalizable capacity for iExCN to unmask disease genes and therapeutic targets in cancer.
- 10 June 2026
- Published by Wiley in Clinical and Translational Science
- Vol. 19 (6) , e70627
Open AccessA Bayesian‐Based Integrative Bioinformatics Analysis Nominates Oncogenic Drivers in Neuroblastoma
Identifying targetable oncogenic drivers remains a challenge in neuroblastoma, the most common extracranial solid malignancy in children. We applied a Bayesian algorithm for integrative analysis of expression and copy‐number, iExCN, to nominate oncogenic drivers in neuroblastoma. The iExCN algorithm found 47 oncogenes from a dataset of 195 neuroblastoma biopsy specimens. The nominated oncogenes included some previously implicated in neuroblastoma, including ALK , MDM2 , MYCN , and XPO1 , but most have not been linked to this disease. A CRISPR/Cas9‐based screen testing those candidates revealed neuroblastoma cell line‐specific and shared vulnerabilities in three well‐characterized models, and dependencies were confirmed by complementary RNA knockdown. Analysis of more than 30 additional neuroblastoma cell lines using DepMap confirmed statistically significant dependency scores in the iExCN genes. Finally, analysis of two cohorts of children with neuroblastoma revealed a trend toward worse survival in cases in which more iExCN genes showed copy number gains. Our findings uncover multiple, potentially targetable oncogenic drivers that appear to influence neuroblastoma biology, demonstrating a generalizable capacity for iExCN to unmask disease genes and therapeutic targets in cancer.
- Open Access
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Figure S1 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
Supplemental Figure S1. Performance of A.I. model in classifying multiple samples from the same patient.
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessFigure S1 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
Supplemental Figure S1. Performance of A.I. model in classifying multiple samples from the same patient.
- Open Access
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Figure 6 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
Deep learning algorithms can predict event-free and overall survival from H&E histology alone. A, Schematic for training a convolutional neural network for survival. Patients with FN-RMS (n = 264) were partitioned into three groups based on EFS length to ensure even sampling and fed into a deep learning architecture with a Cox proportional hazard layer to assess risk. B, Kaplan–Meier curves for EFS based on COG clinical risk group assessment. C, Kaplan–Meier curves for event-free survival based on A.I. hazard prediction. D, Kaplan–Meier curves for OS based on COG clinical risk group assessment. E, Kaplan–Meier curves for OS based on the same A.I.-predicted risk grouping as in C.
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessFigure 6 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
Deep learning algorithms can predict event-free and overall survival from H&E histology alone. A, Schematic for training a convolutional neural network for survival. Patients with FN-RMS (n = 264) were partitioned into three groups based on EFS length to ensure even sampling and fed into a deep learning architecture with a Cox proportional hazard layer to assess risk. B, Kaplan–Meier curves for EFS based on COG clinical risk group assessment. C, Kaplan–Meier curves for event-free survival based on A.I. hazard prediction. D, Kaplan–Meier curves for OS based on COG clinical risk group assessment. E, Kaplan–Meier curves for OS based on the same A.I.-predicted risk grouping as in C.
- Open Access
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Figure 4 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
Prediction of RAS pathway mutations using a trained CNN. A, Workflow for deep learning of RAS pathway mutations from FN-RMS WSIs. B and C, Representative (B) H&E images and (C) class activation maps of a RAS pathway wild-type tumor and a tumor with a KRAS p.G12C mutation (VAF = 0.659). D, Confusion matrix for predictions on a test dataset. Micro F1, Macro F1, and Matthew's correlation coefficient shown below. E, Statistics for confusion matrix. F, Average ROC curve from holdout test data.
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessFigure 4 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
Prediction of RAS pathway mutations using a trained CNN. A, Workflow for deep learning of RAS pathway mutations from FN-RMS WSIs. B and C, Representative (B) H&E images and (C) class activation maps of a RAS pathway wild-type tumor and a tumor with a KRAS p.G12C mutation (VAF = 0.659). D, Confusion matrix for predictions on a test dataset. Micro F1, Macro F1, and Matthew's correlation coefficient shown below. E, Statistics for confusion matrix. F, Average ROC curve from holdout test data.
- Open Access
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Figure S4 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
Supplemental Figure S4. Sample partitioning for training a MYOD1 mutation predictive model using K-fold cross-validation.
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessFigure S4 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
Supplemental Figure S4. Sample partitioning for training a MYOD1 mutation predictive model using K-fold cross-validation.
- Open Access
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Figure 2 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
Fusion status prediction from H&E images. A, Workflow for deep learning of normal tissue, FN-RMS, and FP-RMS. B and C, Representative (B) H&E images and (C) class activation maps as predicted by the trained model. D, Confusion matrix for predictions on a test dataset. Micro F1, Macro F1, and Matthew's correlation coefficient shown below. E, Performance statistics for FP-RMS and FN-RMS prediction. Note: Normal tissues (n = 15) were classified with 100% sensitivity and 100% specificity and are included in performance metric calculations. F, Average ROC curve for FP-RMS vs. FN-RMS vs. normal predictions using holdout test data. G, Workflow for testing the trained algorithm against an independent RMS TMA dataset. H, Confusion matrix for predictions on a test dataset. Micro F1, Macro F1, and Matthew's correlation coefficient shown below. I, Performance statistics for FP-RMS and FN-RMS predictions on an independent dataset. J, Average ROC curve for FP-RMS vs. FN-RMS using an independent RMS tissue dataset.
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessFigure 2 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
Fusion status prediction from H&E images. A, Workflow for deep learning of normal tissue, FN-RMS, and FP-RMS. B and C, Representative (B) H&E images and (C) class activation maps as predicted by the trained model. D, Confusion matrix for predictions on a test dataset. Micro F1, Macro F1, and Matthew's correlation coefficient shown below. E, Performance statistics for FP-RMS and FN-RMS prediction. Note: Normal tissues (n = 15) were classified with 100% sensitivity and 100% specificity and are included in performance metric calculations. F, Average ROC curve for FP-RMS vs. FN-RMS vs. normal predictions using holdout test data. G, Workflow for testing the trained algorithm against an independent RMS TMA dataset. H, Confusion matrix for predictions on a test dataset. Micro F1, Macro F1, and Matthew's correlation coefficient shown below. I, Performance statistics for FP-RMS and FN-RMS predictions on an independent dataset. J, Average ROC curve for FP-RMS vs. FN-RMS using an independent RMS tissue dataset.
- Open Access
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Supplementary_Methods1 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
Supplemental Description of the Rhabdomyosarcoma Web-based Application
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary_Methods1 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
Supplemental Description of the Rhabdomyosarcoma Web-based Application
- Open Access
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Figure S2 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
Supplemental Figure S2. Sample partitioning for training and testing a TP53 mutation predictive model using K-fold cross-validation.
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessFigure S2 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
Supplemental Figure S2. Sample partitioning for training and testing a TP53 mutation predictive model using K-fold cross-validation.
- Open Access
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Figure 3 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
TP53 gene mutation prediction from H&E images. A, Workflow for deep learning of TP53 mutations from FN-RMS WSIs. B and C, Representative (B) H&E images and (C) class activation maps of a TP53 wild-type tumor and a tumor with a TP53 p.P278T mutation (VAF = 0.474). D, Confusion matrix for predictions on a test dataset. Micro F1, Macro F1, and Matthew's correlation coefficient shown below. E, Performance statistics for TP53 mutation prediction. F, Average ROC curve for TP53 mutation prediction using holdout test data. G, Dot plot of TP53 mutant samples (n = 15) showing relationship between TP53 mutation VAF and A.I. positive prediction probability. Statistical analysis was performed using the Mann–Whitney U test.
- 25 November 2025
- Published by American Association for Cancer Research (AACR)
Open AccessFigure 3 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group
TP53 gene mutation prediction from H&E images. A, Workflow for deep learning of TP53 mutations from FN-RMS WSIs. B and C, Representative (B) H&E images and (C) class activation maps of a TP53 wild-type tumor and a tumor with a TP53 p.P278T mutation (VAF = 0.474). D, Confusion matrix for predictions on a test dataset. Micro F1, Macro F1, and Matthew's correlation coefficient shown below. E, Performance statistics for TP53 mutation prediction. F, Average ROC curve for TP53 mutation prediction using holdout test data. G, Dot plot of TP53 mutant samples (n = 15) showing relationship between TP53 mutation VAF and A.I. positive prediction probability. Statistical analysis was performed using the Mann–Whitney U test.