DiaDeL: An Accurate Deep Learning-Based Model With Mutational Signatures for Predicting Metastasis Stage and Cancer Types

Abdollahi, Sina; Lin, Pin–Wen; Chiang, Jung-Hsien

doi:10.1109/tcbb.2021.3115504

Cited by 5 publications

(15 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1). Comparing with existing model 17 , our model has a better performance in the identification of metastatic tumors from primary tumors with an averaged accuracy of 86% on the test sets. Furthermore, we extracted several signatures that are the most informative for our model using SHAP 18 and LIME 19 methods (Fig.…”

Section: Introductionmentioning

confidence: 86%

“…The DRF analysis of mutational signatures is adjusted from previous study 17 . We used an equation as below: …”

Section: Methodsmentioning

confidence: 99%

“…In this research, we proposed a ten-layered fully connected DNN model to differentiate the mutation profiles between primary and metastatic tumors based on multiple cancer datasets. Furthermore, we applied an existing method (DiaDeL model) 17 for comparison.…”

Section: Methodsmentioning

confidence: 99%

“…To study the mutational landscape, we conducted mutational signature analysis of the somatic mutations from primary and metastatic tumors (Methods). Using the same procedures described in previous study 17 , we extracted 30 de novo SBS mutational signatures from these data using SigProfiler 13,28 . The Catalogue Of Somatic Mutations In Cancer (COSMIC) website has also curated 78 SBS, 11 DBS and 18 ID mutational signatures, some of which associated with known etiologies (V3.3) 13 .…”

Section: Mutational Landscape Of Primary and Metastatic Tumorsmentioning

confidence: 99%

“…Analysis of the matched primary and metastatic tumors further demonstrated the transformed profiles of mutational signatures from primary to metastatic tumors in colorectal 15 and papillary thyroid cancers 16 . Additionally, based on SBS mutational signature, Sina Abdollahi, et al distinguished later stage cancers from tumors of other stages using a feed-forward neural network 17 .…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Deep Learning model accurately classifies metastatic tumors from primary tumors based on mutational signatures

Zheng

et al. 2022

Preprint

View full text Add to dashboard Cite

Metastatic propagation is the leading cause of death for most cancers. Prediction and elucidation of metastatic process is crucial for the therapeutic treatment of cancers. Even though somatic mutations have been directly linked to tumorigenesis and metastasis, it is less explored whether the metastatic events can be identified through genomic mutation signatures, a concise representation of the mutational processes. Here, applying mutation signatures as input features calculated from Whole-Exome Sequencing (WES) data of TCGA and other metastatic cohorts, we developed MetaWise, a Deep Neural Network (DNN) model. This model accurately classified metastatic tumors from primary tumors. Signatures of non-coding mutations also have a major impact on the model performance. SHapley Additive exPlanations (SHAP) and Local Surrogate (LIME) analysis into the MetaWise model identified several mutational signatures directly correlated to metastatic spread in cancers, including APOBEC-mutagenesis, UV-induced signatures and DNA damage response deficiency signatures.

show abstract

Section: Introductionmentioning

confidence: 86%

“…The DRF analysis of mutational signatures is adjusted from previous study 17 . We used an equation as below: …”

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Mutational Landscape Of Primary and Metastatic Tumorsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning model accurately classifies metastatic tumors from primary tumors based on mutational signatures

Zheng

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Unveiling pathogenesis and therapeutic targets of metastatic breast cancer through sparse modeling of genomic landscape

Pu,

Tian,

Zheng

et al. 2024

Computational and Structural Biotechnology Reports

View full text Add to dashboard Cite

Deep learning model accurately classifies metastatic tumors from primary tumors based on mutational signatures

Zheng

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Metastatic propagation is the leading cause of death for most cancers. Prediction and elucidation of metastatic process is crucial for the treatment of cancer. Even though somatic mutations have been linked to tumorigenesis and metastasis, it is less explored whether metastatic events can be identified through genomic mutational signatures, which are concise descriptions of the mutational processes. Here, we developed MetaWise, a Deep Neural Network (DNN) model, by applying mutational signatures as input features calculated from Whole-Exome Sequencing (WES) data of TCGA and other metastatic cohorts. This model can accurately classify metastatic tumors from primary tumors and outperform traditional machine learning (ML) models and a deep learning (DL) model, DiaDeL. Signatures of non-coding mutations also have a major impact on the model’s performance. SHapley Additive exPlanations (SHAP) and Local Surrogate (LIME) analyses identify several mutational signatures which are directly correlated to metastatic spread in cancers, including APOBEC-mutagenesis, UV-induced signatures, and DNA damage response deficiency signatures.

show abstract

DiaDeL: An Accurate Deep Learning-Based Model With Mutational Signatures for Predicting Metastasis Stage and Cancer Types

Cited by 5 publications

References 22 publications

Deep Learning model accurately classifies metastatic tumors from primary tumors based on mutational signatures

Deep Learning model accurately classifies metastatic tumors from primary tumors based on mutational signatures

Unveiling pathogenesis and therapeutic targets of metastatic breast cancer through sparse modeling of genomic landscape

Deep learning model accurately classifies metastatic tumors from primary tumors based on mutational signatures

Contact Info

Product

Resources

About