EM-DeepSD: A Deep Neural Network Model Based on Cell-Free DNA End-Motif Signal Decomposition for Cancer Diagnosis
<b>Background and Objectives:</b> The accurate discrimination between patients with and without cancer using their cell-free DNA (cfDNA) is crucial for early cancer diagnosis. The end-motifs of cfDNA serve as significant cancer biomarkers, offering compelling prospects for cancer diagnos...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/9/1156 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850030328783044608 |
|---|---|
| author | Zhi-Yang Zhao Chang-Ling Huang Tong-Min Wang Shi-Hao Zhou Lu Pei Wen-Hui Jia Wei-Hua Jia |
| author_facet | Zhi-Yang Zhao Chang-Ling Huang Tong-Min Wang Shi-Hao Zhou Lu Pei Wen-Hui Jia Wei-Hua Jia |
| author_sort | Zhi-Yang Zhao |
| collection | DOAJ |
| description | <b>Background and Objectives:</b> The accurate discrimination between patients with and without cancer using their cell-free DNA (cfDNA) is crucial for early cancer diagnosis. The end-motifs of cfDNA serve as significant cancer biomarkers, offering compelling prospects for cancer diagnosis. This study proposes EM-DeepSD, a signal decomposition deep learning framework based on cfDNA end-motifs, which is aimed at improving the accuracy of cancer diagnosis and adapting to different sequencing modalities. <b>Materials and Methods:</b> This study included 146 patients diagnosed with cancer and 122 non-cancer controls. EM-DeepSD comprises three core modules. Initially, it utilizes a signal decomposition module to decompose and reconstruct the input end-motif profiles, thereby generating multiple regular subsequences that optimize the subsequent modeling process. Subsequently, both a machine learning module and a deep learning module are employed to improve the accuracy of cancer diagnosis. Furthermore, this paper compares the performance of EM-DeepSD with that of existing benchmarked methods to demonstrate its superiority. Based on the EM-DeepSD framework, we developed the EM-DeepSSA model and compared it with two benchmarked methods across different cfDNA sequencing datasets. <b>Results:</b> In the internal validation set, EM-DeepSSA outperformed the two benchmark methods for cancer diagnosis (area under the curve (AUC), 0.920; adjusted <i>p</i> value < 0.05). Meanwhile, EM-DeepSSA also exhibited the best performance on two independent external testing sets that were subjected to 5-hydroxymethylcytosine sequencing (5hmCS) and broad-range cell-free DNA sequencing (BR-cfDNA-Seq), respectively (test set-1: AUC = 0.933; test set-2: AUC = 0.956; adjusted <i>p</i> value < 0.05). <b>Conclusions:</b> In summary, we present a new framework which can achieve high classification performance in cancer diagnosis and which is applicable to different sequencing modalities. |
| format | Article |
| id | doaj-art-66fbb1ea5b0a4198a0d3ba545ba9f147 |
| institution | DOAJ |
| issn | 2075-4418 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-66fbb1ea5b0a4198a0d3ba545ba9f1472025-08-20T02:59:14ZengMDPI AGDiagnostics2075-44182025-05-01159115610.3390/diagnostics15091156EM-DeepSD: A Deep Neural Network Model Based on Cell-Free DNA End-Motif Signal Decomposition for Cancer DiagnosisZhi-Yang Zhao0Chang-Ling Huang1Tong-Min Wang2Shi-Hao Zhou3Lu Pei4Wen-Hui Jia5Wei-Hua Jia6School of Public Health, Sun Yat-sen University, Guangzhou 510080, ChinaSchool of Public Health, Sun Yat-sen University, Guangzhou 510080, ChinaSun Yat-sen University Cancer Center, Guangzhou 510060, ChinaSchool of Public Health, Sun Yat-sen University, Guangzhou 510080, ChinaSun Yat-sen University Cancer Center, Guangzhou 510060, ChinaSchool of Public Health, Sun Yat-sen University, Guangzhou 510080, ChinaSchool of Public Health, Sun Yat-sen University, Guangzhou 510080, China<b>Background and Objectives:</b> The accurate discrimination between patients with and without cancer using their cell-free DNA (cfDNA) is crucial for early cancer diagnosis. The end-motifs of cfDNA serve as significant cancer biomarkers, offering compelling prospects for cancer diagnosis. This study proposes EM-DeepSD, a signal decomposition deep learning framework based on cfDNA end-motifs, which is aimed at improving the accuracy of cancer diagnosis and adapting to different sequencing modalities. <b>Materials and Methods:</b> This study included 146 patients diagnosed with cancer and 122 non-cancer controls. EM-DeepSD comprises three core modules. Initially, it utilizes a signal decomposition module to decompose and reconstruct the input end-motif profiles, thereby generating multiple regular subsequences that optimize the subsequent modeling process. Subsequently, both a machine learning module and a deep learning module are employed to improve the accuracy of cancer diagnosis. Furthermore, this paper compares the performance of EM-DeepSD with that of existing benchmarked methods to demonstrate its superiority. Based on the EM-DeepSD framework, we developed the EM-DeepSSA model and compared it with two benchmarked methods across different cfDNA sequencing datasets. <b>Results:</b> In the internal validation set, EM-DeepSSA outperformed the two benchmark methods for cancer diagnosis (area under the curve (AUC), 0.920; adjusted <i>p</i> value < 0.05). Meanwhile, EM-DeepSSA also exhibited the best performance on two independent external testing sets that were subjected to 5-hydroxymethylcytosine sequencing (5hmCS) and broad-range cell-free DNA sequencing (BR-cfDNA-Seq), respectively (test set-1: AUC = 0.933; test set-2: AUC = 0.956; adjusted <i>p</i> value < 0.05). <b>Conclusions:</b> In summary, we present a new framework which can achieve high classification performance in cancer diagnosis and which is applicable to different sequencing modalities.https://www.mdpi.com/2075-4418/15/9/1156cell-free DNAcancer diagnosissignal decompositiondeep neural network |
| spellingShingle | Zhi-Yang Zhao Chang-Ling Huang Tong-Min Wang Shi-Hao Zhou Lu Pei Wen-Hui Jia Wei-Hua Jia EM-DeepSD: A Deep Neural Network Model Based on Cell-Free DNA End-Motif Signal Decomposition for Cancer Diagnosis Diagnostics cell-free DNA cancer diagnosis signal decomposition deep neural network |
| title | EM-DeepSD: A Deep Neural Network Model Based on Cell-Free DNA End-Motif Signal Decomposition for Cancer Diagnosis |
| title_full | EM-DeepSD: A Deep Neural Network Model Based on Cell-Free DNA End-Motif Signal Decomposition for Cancer Diagnosis |
| title_fullStr | EM-DeepSD: A Deep Neural Network Model Based on Cell-Free DNA End-Motif Signal Decomposition for Cancer Diagnosis |
| title_full_unstemmed | EM-DeepSD: A Deep Neural Network Model Based on Cell-Free DNA End-Motif Signal Decomposition for Cancer Diagnosis |
| title_short | EM-DeepSD: A Deep Neural Network Model Based on Cell-Free DNA End-Motif Signal Decomposition for Cancer Diagnosis |
| title_sort | em deepsd a deep neural network model based on cell free dna end motif signal decomposition for cancer diagnosis |
| topic | cell-free DNA cancer diagnosis signal decomposition deep neural network |
| url | https://www.mdpi.com/2075-4418/15/9/1156 |
| work_keys_str_mv | AT zhiyangzhao emdeepsdadeepneuralnetworkmodelbasedoncellfreednaendmotifsignaldecompositionforcancerdiagnosis AT changlinghuang emdeepsdadeepneuralnetworkmodelbasedoncellfreednaendmotifsignaldecompositionforcancerdiagnosis AT tongminwang emdeepsdadeepneuralnetworkmodelbasedoncellfreednaendmotifsignaldecompositionforcancerdiagnosis AT shihaozhou emdeepsdadeepneuralnetworkmodelbasedoncellfreednaendmotifsignaldecompositionforcancerdiagnosis AT lupei emdeepsdadeepneuralnetworkmodelbasedoncellfreednaendmotifsignaldecompositionforcancerdiagnosis AT wenhuijia emdeepsdadeepneuralnetworkmodelbasedoncellfreednaendmotifsignaldecompositionforcancerdiagnosis AT weihuajia emdeepsdadeepneuralnetworkmodelbasedoncellfreednaendmotifsignaldecompositionforcancerdiagnosis |