1
|
Su L, Hounye AH, Pan Q, Miao K, Wang J, Hou M, Xiong L. Explainable cancer factors discovery: Shapley additive explanation for machine learning models demonstrates the best practices in the case of pancreatic cancer. Pancreatology 2024; 24:404-423. [PMID: 38342661 DOI: 10.1016/j.pan.2024.02.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/12/2023] [Revised: 01/07/2024] [Accepted: 02/05/2024] [Indexed: 02/13/2024]
Abstract
Pancreatic cancer is one of digestive tract cancers with high mortality rate. Despite the wide range of available treatments and improvements in surgery, chemotherapy, and radiation therapy, the five-year prognosis for individuals diagnosed pancreatic cancer remains poor. There is still research to be done to see if immunotherapy may be used to treat pancreatic cancer. The goals of our research were to comprehend the tumor microenvironment of pancreatic cancer, found a useful biomarker to assess the prognosis of patients, and investigated its biological relevance. In this paper, machine learning methods such as random forest were fused with weighted gene co-expression networks for screening hub immune-related genes (hub-IRGs). LASSO regression model was used to further work. Thus, we got eight hub-IRGs. Based on hub-IRGs, we created a prognosis risk prediction model for PAAD that can stratify accurately and produce a prognostic risk score (IRG_Score) for each patient. In the raw data set and the validation data set, the five-year area under the curve (AUC) for this model was 0.9 and 0.7, respectively. And shapley additive explanation (SHAP) portrayed the importance of prognostic risk prediction influencing factors from a machine learning perspective to obtain the most influential certain gene (or clinical factor). The five most important factors were TRIM67, CORT, PSPN, SCAMP5, RFXAP, all of which are genes. In summary, the eight hub-IRGs had accurate risk prediction performance and biological significance, which was validated in other cancers. The result of SHAP helped to understand the molecular mechanism of pancreatic cancer.
Collapse
Affiliation(s)
- Liuyan Su
- School of Mathematics and Statistics, Central South University, Changsha, 410083, China
| | | | - Qi Pan
- School of Mathematics and Statistics, Central South University, Changsha, 410083, China
| | - Kexin Miao
- School of Mathematics and Statistics, Central South University, Changsha, 410083, China
| | - Jiaoju Wang
- School of Mathematics and Statistics, Central South University, Changsha, 410083, China
| | - Muzhou Hou
- School of Mathematics and Statistics, Central South University, Changsha, 410083, China.
| | - Li Xiong
- Department of General Surgery, The Second Xiangya Hospital, Central South University, Changsha, 410011, China; Hunan Clinical Research Center for Intelligent General Surgery, Changsha, 410011, China.
| |
Collapse
|
2
|
Li X, Li L, Xiong X, Kuang Q, Peng M, Zhu K, Luo P. Identification of the Prognostic Biomarkers CBX6 and CBX7 in Bladder Cancer. Diagnostics (Basel) 2023; 13:diagnostics13081393. [PMID: 37189494 DOI: 10.3390/diagnostics13081393] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2023] [Revised: 03/22/2023] [Accepted: 04/07/2023] [Indexed: 05/17/2023] Open
Abstract
BACKGROUND Chromobox (CBX) proteins are essential components of polycomb group proteins and perform essential functions in bladder cancer (BLCA). However, research on CBX proteins is still limited, and the function of CBXs in BLCA has not been well illustrated. METHODS AND RESULTS We analyzed the expression of CBX family members in BLCA patients from The Cancer Genome Atlas database. By Cox regression analysis and survival analysis, CBX6 and CBX7 were identified as potential prognostic factors. Subsequently, we identified genes associated with CBX6/7 and performed enrichment analysis, and they were enriched in urothelial carcinoma and transitional carcinoma. Mutation rates of TP53 and TTN correlate with expression of CBX6/7. In addition, differential analysis indicated that the roles played by CBX6 and CBX7 may be related to immune checkpoints. The CIBERSORT algorithm was used to screen out immune cells that play a role in the prognosis of bladder cancer patients. Multiplex immunohistochemistry staining confirmed a negative correlation between CBX6 and M1 macrophages, as well as a consistent alteration in CBX6 and regulatory T cells (Tregs), a positive correlation between CBX7 and resting mast cells, and a negative correlation between CBX7 and M0 macrophages. CONCLUSIONS CBX6 and CBX7 expression levels may assist in predicting the prognosis of BLCA patients. CBX6 may contribute to a poor prognosis in patients by inhibiting M1 polarization and promoting Treg recruitment in the tumor microenvironment, while CBX7 may contribute to a better prognosis in patients by increasing resting mast cell numbers and decreasing macrophage M0 content.
Collapse
Affiliation(s)
- Xinxin Li
- Department of Urology, Wuhan Third Hospital and Tongren Hospital of Wuhan University, Wuhan 430060, China
| | - Lili Li
- Central Laboratory, Renmin Hospital of Wuhan University, Wuhan 430060, China
| | - Xi Xiong
- Department of Urology, Wuhan Third Hospital, School of Medicine, Wuhan University of Science and Technology, Wuhan 430060, China
| | - Qihui Kuang
- Department of Urology, Wuhan Third Hospital and Tongren Hospital of Wuhan University, Wuhan 430060, China
| | - Min Peng
- Department of Oncology, Renmin Hospital of Wuhan University, Wuhan 430060, China
| | - Kai Zhu
- Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan 430060, China
| | - Pengcheng Luo
- Department of Urology, Wuhan Third Hospital and Tongren Hospital of Wuhan University, Wuhan 430060, China
| |
Collapse
|
3
|
Lai HC, Kuo YW, Huang YH, Chan SM, Cheng KI, Wu ZF. Pancreatic Cancer and Microenvironments: Implications of Anesthesia. Cancers (Basel) 2022; 14:cancers14112684. [PMID: 35681664 PMCID: PMC9179559 DOI: 10.3390/cancers14112684] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2022] [Revised: 05/25/2022] [Accepted: 05/25/2022] [Indexed: 11/21/2022] Open
Abstract
Simple Summary Pancreatic cancer is a lethal malignant neoplasm with less than 10% 5-year relative survival after the initial diagnosis. Several factors may be related to the poor prognosis of pancreatic cancer, including the rapid tumor progression, increased metastatic propensity, insignificant symptoms, shortage of early diagnostic biomarkers, and its tendency toward resistance to both chemotherapy and radiotherapy. Pancreatic neoplastic cells interact intimately with a complicated microenvironment that can foster drug resistance, metastasis, or relapse in pancreatic cancer. In addition, evidence shows that perioperative factors, including surgical manipulation, anesthetics, or analgesics, might alter the tumor microenvironment and cancer progression. This review outlines the up-to-date knowledge of anesthesia implications in the pancreatic microenvironment and provides future anesthetic strategies for improving pancreatic cancer survival. Abstract Pancreatic malignancy is a lethal neoplasm, as well as one of the leading causes of cancer-associated mortality, having a 5-year overall survival rate of less than 10%. The average life expectancy of patients with advanced pancreatic cancer does not exceed six months. Although surgical excision is a favorable modality for long-term survival of pancreatic neoplasm, metastasis is initially identified in nearly 80% of the patients by the time of diagnosis, making the development of therapeutic policy for pancreatic cancer extremely daunting. Emerging evidence shows that pancreatic neoplastic cells interact intimately with a complicated microenvironment that can foster drug resistance, metastasis, or relapse in pancreatic cancer. As a result, the necessity of gaining further insight should be focused on the pancreatic microenvironment contributing to cancer progression. Numerous evidence reveals that perioperative factors, including surgical manipulation and anesthetics (e.g., propofol, volatile anesthetics, local anesthetics, epidural anesthesia/analgesia, midazolam), analgesics (e.g., opioids, non-steroidal anti-inflammatory drugs, tramadol), and anesthetic adjuvants (such as ketamine and dexmedetomidine), might alter the tumor microenvironment and cancer progression by affecting perioperative inflammatory or immune responses during cancer surgery. Therefore, the anesthesiologist plays an important role in perioperative management and may affect surgical outcomes. However, the literature on the impact of anesthesia on the pancreatic cancer microenvironment and progression is limited. This review summarizes the current knowledge of the implications of anesthesia in the pancreatic microenvironment and provides future anesthetic strategies for improving pancreatic cancer survival rates.
Collapse
Affiliation(s)
- Hou-Chuan Lai
- Department of Anesthesiology, Tri-Service General Hospital and National Defense Medical Center, Taipei 114, Taiwan; (H.-C.L.); (Y.-H.H.); (S.-M.C.)
| | - Yi-Wei Kuo
- Department of Anesthesiology, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung 807, Taiwan; (Y.-W.K.); (K.-I.C.)
| | - Yi-Hsuan Huang
- Department of Anesthesiology, Tri-Service General Hospital and National Defense Medical Center, Taipei 114, Taiwan; (H.-C.L.); (Y.-H.H.); (S.-M.C.)
| | - Shun-Ming Chan
- Department of Anesthesiology, Tri-Service General Hospital and National Defense Medical Center, Taipei 114, Taiwan; (H.-C.L.); (Y.-H.H.); (S.-M.C.)
| | - Kuang-I Cheng
- Department of Anesthesiology, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung 807, Taiwan; (Y.-W.K.); (K.-I.C.)
- Department of Anesthesiology, Faculty of Medicine, College of Medicine, Kaohsiung Medical University, Kaohsiung 807, Taiwan
| | - Zhi-Fu Wu
- Department of Anesthesiology, Tri-Service General Hospital and National Defense Medical Center, Taipei 114, Taiwan; (H.-C.L.); (Y.-H.H.); (S.-M.C.)
- Department of Anesthesiology, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung 807, Taiwan; (Y.-W.K.); (K.-I.C.)
- Department of Anesthesiology, Faculty of Medicine, College of Medicine, Kaohsiung Medical University, Kaohsiung 807, Taiwan
- Center for Regional Anesthesia and Pain Medicine, Wan Fang Hospital, Taipei Medical University, Taipei 116, Taiwan
- Correspondence:
| |
Collapse
|