1
|
Xie J, Chen Y, Luo S, Yang W, Lin Y, Wang L, Ding X, Tong M, Yu R. Tracing unknown tumor origins with a biological-pathway-based transformer model. CELL REPORTS METHODS 2024; 4:100797. [PMID: 38889685 PMCID: PMC11228371 DOI: 10.1016/j.crmeth.2024.100797] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/23/2023] [Revised: 02/01/2024] [Accepted: 05/21/2024] [Indexed: 06/20/2024]
Abstract
Cancer of unknown primary (CUP) represents metastatic cancer where the primary site remains unidentified despite standard diagnostic procedures. To determine the tumor origin in such cases, we developed BPformer, a deep learning method integrating the transformer model with prior knowledge of biological pathways. Trained on transcriptomes from 10,410 primary tumors across 32 cancer types, BPformer achieved remarkable accuracy rates of 94%, 92%, and 89% in primary tumors and primary and metastatic sites of metastatic tumors, respectively, surpassing existing methods. Additionally, BPformer was validated in a retrospective study, demonstrating consistency with tumor sites diagnosed through immunohistochemistry and histopathology. Furthermore, BPformer was able to rank pathways based on their contribution to tumor origin identification, which helped to classify oncogenic signaling pathways into those that are highly conservative among different cancers versus those that are highly variable depending on their origins.
Collapse
Affiliation(s)
- Jiajing Xie
- National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, Fujian 361102, China
| | - Ying Chen
- School of Informatics, Xiamen University, Xiamen, Fujian 361005, China
| | - Shijie Luo
- National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, Fujian 361102, China
| | - Wenxian Yang
- Aginome Scientific, Xiamen, Fujian 361005, China
| | - Yuxiang Lin
- National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, Fujian 361102, China
| | - Liansheng Wang
- National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, Fujian 361102, China; School of Informatics, Xiamen University, Xiamen, Fujian 361005, China
| | - Xin Ding
- Department of Pathology, Zhongshan Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian 361004, China.
| | - Mengsha Tong
- National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, Fujian 361102, China; State Key Laboratory of Cellular Stress Biology, School of Life Sciences, Faculty of Medicine and Life Sciences, Xiamen University, Xiamen, Fujian 361102, China.
| | - Rongshan Yu
- National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, Fujian 361102, China; School of Informatics, Xiamen University, Xiamen, Fujian 361005, China; Aginome Scientific, Xiamen, Fujian 361005, China.
| |
Collapse
|
2
|
Shi J, Chen Y, Wang Y. Deep learning and machine learning approaches to classify stomach distant metastatic tumors using DNA methylation profiles. Comput Biol Med 2024; 175:108496. [PMID: 38657466 DOI: 10.1016/j.compbiomed.2024.108496] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2024] [Revised: 04/14/2024] [Accepted: 04/21/2024] [Indexed: 04/26/2024]
Abstract
Distant metastasis of cancer is a significant contributor to cancer-related complications, and early identification of unidentified stomach adenocarcinoma is crucial for a positive prognosis. Changes inDNA methylation are being increasingly recognized as a crucial factor in predicting cancer progression. Within this research, we developed machine learning and deep learning models for distinguishing distant metastasis in samples of stomach adenocarcinoma based on DNA methylation profile. Employing deep neural networks (DNN), support vector machines (SVM), random forest (RF), Naive Bayes (NB) and decision tree (DT), and models for forecasting distant metastasis in stomach adenocarcinoma. The results show that the performance of DNN is better than that of other models, AUC and AUPR achieving 99.9 % and 99.5 % respectively. Additionally, a weighted random sampling technique was utilized to address the issue of imbalanced datasets, enabling the identification of crucial methylation markers associated with functionally significant genes in stomach distant metastasis tumors with greater performance.
Collapse
Affiliation(s)
- Jing Shi
- Department of Medical Oncology, The First Hospital of China Medical University, Shenyang, China
| | - Ying Chen
- Department of Medical Oncology, The First Hospital of China Medical University, Shenyang, China
| | - Ying Wang
- Department of Endoscopy, The First Hospital of China Medical University, Shenyang, China.
| |
Collapse
|
3
|
Nicu AT, Ionel IP, Stoica I, Burlibasa L, Jinga V. Recent Advancements in Research on DNA Methylation and Testicular Germ Cell Tumors: Unveiling the Intricate Relationship. Biomedicines 2024; 12:1041. [PMID: 38791003 PMCID: PMC11117643 DOI: 10.3390/biomedicines12051041] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2024] [Revised: 04/30/2024] [Accepted: 05/02/2024] [Indexed: 05/26/2024] Open
Abstract
Testicular germ cell tumors (TGCTs) are the most common type of testicular cancer, with a particularly high incidence in the 15-45-year age category. Although highly treatable, resistance to therapy sometimes occurs, with devastating consequences for the patients. Additionally, the young age at diagnosis and the treatment itself pose a great threat to patients' fertility. Despite extensive research concerning genetic and environmental risk factors, little is known about TGCT etiology. However, epigenetics has recently come into the spotlight as a major factor in TGCT initiation, progression, and even resistance to treatment. As such, recent studies have been focusing on epigenetic mechanisms, which have revealed their potential in the development of novel, non-invasive biomarkers. As the most studied epigenetic mechanism, DNA methylation was the first revelation in this particular field, and it continues to be a main target of investigations as research into its association with TGCT has contributed to a better understanding of this type of cancer and constantly reveals novel aspects that can be exploited through clinical applications. In addition to biomarker development, DNA methylation holds potential for developing novel treatments based on DNA methyltransferase inhibitors (DNMTis) and may even be of interest for fertility management in cancer survivors. This manuscript is structured as a literature review, which comprehensively explores the pivotal role of DNA methylation in the pathogenesis, progression, and treatment resistance of TGCTs.
Collapse
Affiliation(s)
- Alina-Teodora Nicu
- Genetics Department, Faculty of Biology, University of Bucharest, 030018 Bucharest, Romania; (A.-T.N.); (I.S.)
| | - Ileana Paula Ionel
- Department of Specific Disciplines, Faculty of Midwifery and Nursing, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, Romania
| | - Ileana Stoica
- Genetics Department, Faculty of Biology, University of Bucharest, 030018 Bucharest, Romania; (A.-T.N.); (I.S.)
| | - Liliana Burlibasa
- Genetics Department, Faculty of Biology, University of Bucharest, 030018 Bucharest, Romania; (A.-T.N.); (I.S.)
| | - Viorel Jinga
- Department of Urology, Faculty of Medicine, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, Romania;
- The Academy of Romanian Scientists, 050044 Bucharest, Romania
| |
Collapse
|
4
|
Lorkowski SW, Dermawan JK, Rubin BP. The practical utility of AI-assisted molecular profiling in the diagnosis and management of cancer of unknown primary: an updated review. Virchows Arch 2024; 484:369-375. [PMID: 37999736 DOI: 10.1007/s00428-023-03708-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2023] [Revised: 11/07/2023] [Accepted: 11/14/2023] [Indexed: 11/25/2023]
Abstract
Cancer of unknown primary (CUP) presents a complex diagnostic challenge, characterized by metastatic tumors of unknown tissue origin and a dismal prognosis. This review delves into the emerging significance of artificial intelligence (AI) and machine learning (ML) in transforming the landscape of CUP diagnosis, classification, and treatment. ML approaches, trained on extensive molecular profiling data, have shown promise in accurately predicting tissue of origin. Genomic profiling, encompassing driver mutations and copy number variations, plays a pivotal role in CUP diagnosis by providing insights into tumor type-specific oncogenic alterations. Mutational signatures (MS), reflecting somatic mutation patterns, offer further insights into CUP diagnosis. Known MS with established etiology, such as ultraviolet (UV) light-induced DNA damage and tobacco exposure, have been identified in cases of dedifferentiated/transdifferentiated melanoma and carcinoma. Deep learning models that integrate gene expression data and DNA methylation patterns offer insights into tissue lineage and tumor classification. In digital pathology, machine learning algorithms analyze whole-slide images to aid in CUP classification. Finally, precision oncology, guided by molecular profiling, offers targeted therapies independent of primary tissue identification. Clinical trials assigning CUP patients to molecularly guided therapies, including targetable alterations and tumor mutation burden as an immunotherapy biomarker, have resulted in improved overall survival in a subset of patients. In conclusion, AI- and ML-driven approaches are revolutionizing CUP management by enhancing diagnostic accuracy. Precision oncology utilizing enhanced molecular profiling facilitates the identification of targeted therapies that transcend the need to identify the tissue of origin, ultimately improving patient outcomes.
Collapse
Affiliation(s)
- Shuhui Wang Lorkowski
- Department of Cardiovascular and Metabolic Sciences, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, 44195, USA
| | - Josephine K Dermawan
- Robert J. Tomsich Pathology and Laboratory Medicine Institute, Cleveland Clinic, Cleveland, OH, 44195, USA
| | - Brian P Rubin
- Robert J. Tomsich Pathology and Laboratory Medicine Institute, Cleveland Clinic, Cleveland, OH, 44195, USA.
| |
Collapse
|
5
|
Ma W, Wu H, Chen Y, Xu H, Jiang J, Du B, Wan M, Ma X, Chen X, Lin L, Su X, Bao X, Shen Y, Xu N, Ruan J, Jiang H, Ding Y. New techniques to identify the tissue of origin for cancer of unknown primary in the era of precision medicine: progress and challenges. Brief Bioinform 2024; 25:bbae028. [PMID: 38343328 PMCID: PMC10859692 DOI: 10.1093/bib/bbae028] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/16/2023] [Revised: 12/10/2023] [Accepted: 01/11/2024] [Indexed: 02/15/2024] Open
Abstract
Despite a standardized diagnostic examination, cancer of unknown primary (CUP) is a rare metastatic malignancy with an unidentified tissue of origin (TOO). Patients diagnosed with CUP are typically treated with empiric chemotherapy, although their prognosis is worse than those with metastatic cancer of a known origin. TOO identification of CUP has been employed in precision medicine, and subsequent site-specific therapy is clinically helpful. For example, molecular profiling, including genomic profiling, gene expression profiling, epigenetics and proteins, has facilitated TOO identification. Moreover, machine learning has improved identification accuracy, and non-invasive methods, such as liquid biopsy and image omics, are gaining momentum. However, the heterogeneity in prediction accuracy, sample requirements and technical fundamentals among the various techniques is noteworthy. Accordingly, we systematically reviewed the development and limitations of novel TOO identification methods, compared their pros and cons and assessed their potential clinical usefulness. Our study may help patients shift from empirical to customized care and improve their prognoses.
Collapse
Affiliation(s)
- Wenyuan Ma
- Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Hui Wu
- Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Yiran Chen
- Department of Surgical Oncology, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou, Zhejiang, China
| | - Hongxia Xu
- Zhejiang University-University of Edinburgh Institute (ZJU-UoE Institute), Zhejiang University School of Medicine, Zhejiang University, Haining, China
| | - Junjie Jiang
- Department of Gastroenterology, Affiliated Hangzhou First People's Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Bang Du
- Real Doctor AI Research Centre, School of Medicine, Zhejiang University, Hangzhou 310058, China
| | - Mingyu Wan
- Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Xiaolu Ma
- Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Xiaoyu Chen
- Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Lili Lin
- Department of Nuclear Medicine, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Xinhui Su
- Department of Nuclear Medicine, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Xuanwen Bao
- Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Yifei Shen
- Department of Laboratory Medicine, the First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Nong Xu
- Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Jian Ruan
- Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Haiping Jiang
- Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Yongfeng Ding
- Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| |
Collapse
|