1
|
Identification of Secondary Breast Cancer in Vital Organs through the Integration of Machine Learning and Microarrays. ELECTRONICS 2022. [DOI: 10.3390/electronics11121879] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
Breast cancer includes genetic and environmental factors and is the most prevalent malignancy in women contributing to the pathogenesis and progression of cancer. Breast cancer prognosis metastasizes towards bones, the liver, brain, and lungs, and is the main cause of death in patients. Furthermore, the selection of features and classification is significant in microarray data analysis, which suffers from huge time consumption. To address these issues, this research uniquely integrates machine learning and microarrays to identify secondary breast cancer in vital organs. This work firstly imputes the missing values using K-nearest neighbors and improves the recursive feature elimination with cross-validation (RFECV) using the random forest method. Secondly, the class imbalance is handled by employing K-means synthetic object oversampling technique (SMOTE) to balance minority class and prevent noise. We successfully identified the 16 most essential Entrez gene ids responsible for predicting metastatic locations in the bones, brain, liver, and lungs. Extensive experiments are conducted on NCBI Gene Expression Omnibus GSE14020 and GSE54323 datasets. The proposed methods have handled class imbalance, prevented noise, and appropriately reduced time consumption. Reliable results were obtained on four classification models: decision tree; K-nearest neighbors; random forest; and support vector machine. Results are presented having considered confusion matrices, accuracy, ROC-AUC and PR-AUC, and F1-score.
Collapse
|
2
|
Huang Z, Keramat S, Izadirad M, Chen ZS, Soukhtanloo M. The Potential Role of Exosomes in the Treatment of Brain Tumors, Recent Updates and Advances. Front Oncol 2022; 12:869929. [PMID: 35371984 PMCID: PMC8968044 DOI: 10.3389/fonc.2022.869929] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/05/2022] [Accepted: 02/21/2022] [Indexed: 12/05/2022] Open
Abstract
Exosomes are small endosomal derived membrane extracellular vesicles that contain cell-specific cargos such as lipid, protein, DNA, RNA, miRNA, long non-coding RNA, and some other cell components that are released into surrounding body fluids upon the fusion of multivesicular bodies (MVB) and the plasma membrane. Exosomes are a one-of-a-kind cell-to-cell communication mechanism that might pave the way for target therapy. The use of exosomes as a therapeutic potential in a variety of cancers has been and is still being investigated. One of the most important of these has been the use of exosomes in brain tumors therapy. Exosome contents play a crucial role in brain tumor progression by providing a favorable niche for tumor cell proliferation. Also, exosomes that are secreted from tumor cells, lead to the protection of tumor cells and their proliferation in the tumor environment by reducing the inflammatory response and suppression of the immune system. Although some treatment protocols such as surgery, chemotherapy, and radiotherapy are common in brain tumors, they do not result in complete remission in the treatment of some malignant and metastatic brain tumors. Identifying, targeting, and blocking exosomes involved in the progression of brain tumors could be a promising way to reduce brain tumor progression. On the other way, brain tumor therapy with effective therapeutic components such as siRNAs, mRNAs, proteins, could be developed. Finally, our research suggested that exosomes of nanoscale sizes might be a useful tool for crossing the blood-brain barrier and delivering effective content. However, further research is needed to fully comprehend the potential involvement of the exosome in brain tumor therapy protocols.
Collapse
Affiliation(s)
- Zoufang Huang
- Ganzhou Key Laboratory of Hematology, Department of Hematology, The First Affiliated Hospital of Gannan Medical University, Ganzhou, China
| | - Shayan Keramat
- Department of Hematology and Blood Bank, Faculty of Medicine, Mashhad University of Medical Science, Mashhad, Iran
| | - Mehrdad Izadirad
- Department of Hematology and Blood Bank, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Zhe-Sheng Chen
- Department of Pharmaceutical Sciences, St John’s University, New York, NY, United States
| | - Mohammad Soukhtanloo
- Department of Clinical Biochemistry, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran
- Pharmacological Research Center of Medicinal Plants, Mashhad University of Medical Sciences, Mashhad, Iran
| |
Collapse
|
3
|
Rudat V, El-Sweilmeen H, Brune-Erber I, Nour AA, Almasri N, Altuwaijri S, Fadel E. Identification of breast cancer patients with a high risk of developing brain metastases: a single-institutional retrospective analysis. BMC Cancer 2014; 14:289. [PMID: 24761771 PMCID: PMC4006960 DOI: 10.1186/1471-2407-14-289] [Citation(s) in RCA: 18] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2013] [Accepted: 04/22/2014] [Indexed: 09/02/2023] Open
Abstract
Background The objective of this study was to identify breast cancer patients with a high risk of developing brain metastases who may benefit from pre-emptive medical intervention. Methods Medical records of 352 breast cancer patients with local or locoregional disease at diagnosis were retrospectively analysed. The brain metastasis-free survival was estimated using the Kaplan-Meier method and patient groups were compared using the log rank test. The simultaneous relationship of multiple prognostic factors was assessed using Cox’s proportional hazard regression analysis. The Fisher exact test was used to test the difference of proportions for statistical significance. Results On univariate analysis, statistically highly significant unfavourable risk factors for the brain metastasis-free survival were negative ER status, negative PR status, and triple negative tumor subtype. Young age at diagnosis (≤35 years) and advanced disease stage were not statistically significant (p = 0.10). On multivariate analysis, the only independent significant factor was the ER status (negative ER status; hazard radio (95% confidence interval), 5.1 (1.8-14.6); p = 0.003). In the subgroup of 168 patients with a minimum follow-up of 24 months, 49 patients developed extracranial metastases as first metastatic event. Of those, 7 of 15 (46.6%) with a negative ER status developed brain metastases compared to 5 of 34 (14.7%) with a positive ER status (Fisher exact test, p = 0.03). The median time interval (minimum-maximum) between the diagnosis of extracranial and brain metastases was 7.5 months (1-30 months). Conclusions Breast cancer patients with extracranial metastasis and negative ER status exhibited an almost 50% risk of developing brain metastasis during their course of disease. Future studies are highly desired to evaluate the efficacy of pre-emptive medical intervention such as prophylactic treatment or diagnostic screening for high risk breast cancer patients.
Collapse
Affiliation(s)
- Volker Rudat
- Department of Radiation Oncology, Saad Specialist Hospital, P,O, Box 30353, Al Khobar 31952, Saudi Arabia.
| | | | | | | | | | | | | |
Collapse
|
4
|
Bachmann C, Schmidt S, Staebler A, Schittenhelm J, Wallwiener D, Grischke EM. Risk factors and survival outcome in cerebral metastatic breast cancer. Med Oncol 2014; 31:862. [PMID: 24504842 DOI: 10.1007/s12032-014-0862-2] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2013] [Accepted: 01/23/2014] [Indexed: 11/26/2022]
Abstract
The development of brain metastases (BM) of primary breast cancer patients leads to limited survival. HER2-positive and triple-negative status are risk factors for the development of BM. Estrogen receptor (ER)/progesterone receptor (PR)/HER2 are important prognostic markers and are essential for effective treatment decisions. We retrospectively analyzed the impact of known risk factors and the outcome after the development of BM. Eighty consecutive patients, treated between January 1, 2001, and June 30, 2012, on the basis of primary non-metastatic operable breast cancer and who developed BM, were enrolled. Clinical parameters (TNM; ER, PR, HER2) and their impact on the occurrence of BM and additionally their prognostic influence after the occurrence of BM were investigated. A small tumor size, ductal histology, grade 3, hormone receptor-negative, triple-negative and HER2+ tumors were associated with BM. Median time from breast cancer diagnosis to BM was 35 months (range 26.2-43.8). Grade 3 versus 2 has significantly negative prognostic impact with earlier development of BM (median 23 vs. 41 months; p=0.033). HER2-positive patients had significantly longer survival after the occurrence of BM than HER2-negative patients (p=0.009). The risk of BM varies significantly by subtype. In high-risk patients, the occurrence of BM must be considered, and possibly, general screening in these patients is warranted. The survival advantage of HER2-positive breast cancer patients compared with HER2-negative patients after the occurrence of BM is possibly explainable by systemic control of disease. Standard of care for patients with BM is whole-brain radiotherapy, with/without surgery, or stereotactic radiosurgery. Perhaps novel therapies may additionally improve survival in these patients.
Collapse
MESH Headings
- Adenocarcinoma, Mucinous/metabolism
- Adenocarcinoma, Mucinous/mortality
- Adenocarcinoma, Mucinous/secondary
- Adult
- Breast Neoplasms/metabolism
- Breast Neoplasms/mortality
- Breast Neoplasms/pathology
- Carcinoma, Ductal, Breast/metabolism
- Carcinoma, Ductal, Breast/mortality
- Carcinoma, Ductal, Breast/secondary
- Carcinoma, Lobular/metabolism
- Carcinoma, Lobular/mortality
- Carcinoma, Lobular/secondary
- Female
- Follow-Up Studies
- Humans
- Immunoenzyme Techniques
- Middle Aged
- Neoplasm Grading
- Neoplasm Staging
- Prognosis
- Receptor, ErbB-2/metabolism
- Receptors, Estrogen/metabolism
- Receptors, Progesterone/metabolism
- Retrospective Studies
- Risk Factors
- Survival Rate
Collapse
Affiliation(s)
- C Bachmann
- Department of Gynecology, University Tübingen, Calwer Str. 7, 72070, Tübingen, Germany,
| | | | | | | | | | | |
Collapse
|
5
|
Thorsen F, Fite B, Mahakian LM, Seo JW, Qin S, Harrison V, Johnson S, Ingham E, Caskey C, Sundstrøm T, Meade TJ, Harter PN, Skaftnesmo KO, Ferrara KW. Multimodal imaging enables early detection and characterization of changes in tumor permeability of brain metastases. J Control Release 2013; 172:812-22. [PMID: 24161382 DOI: 10.1016/j.jconrel.2013.10.019] [Citation(s) in RCA: 33] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2013] [Revised: 10/14/2013] [Accepted: 10/15/2013] [Indexed: 12/31/2022]
Abstract
Our goal was to develop strategies to quantify the accumulation of model therapeutics in small brain metastases using multimodal imaging, in order to enhance the potential for successful treatment. Human melanoma cells were injected into the left cardiac ventricle of immunodeficient mice. Bioluminescent, MR and PET imaging were applied to evaluate the limits of detection and potential for contrast agent extravasation in small brain metastases. A pharmacokinetic model was applied to estimate vascular permeability. Bioluminescent imaging after injecting d-luciferin (molecular weight (MW) 320 D) suggested that tumor cell extravasation had already occurred at week 1, which was confirmed by histology. 7T T1w MRI at week 4 was able to detect non-leaky 100 μm sized lesions and leaky tumors with diameters down to 200 μm after contrast injection at week 5. PET imaging showed that (18)F-FLT (MW 244 Da) accumulated in the brain at week 4. Gadolinium-based MRI tracers (MW 559 Da and 2.066 kDa) extravasated after 5 weeks (tumor diameter 600 μm), and the lower MW agent cleared more rapidly from the tumor (mean apparent permeabilities 2.27 × 10(-5)cm/s versus 1.12 × 10(-5)cm/s). PET imaging further demonstrated tumor permeability to (64)Cu-BSA (MW 65.55 kDa) at week 6 (tumor diameter 700 μm). In conclusion, high field T1w MRI without contrast may improve the detection limit of small brain metastases, allowing for earlier diagnosis of patients, although the smallest lesions detected with T1w MRI were permeable only to d-luciferin and the amphipathic small molecule (18)F-FLT. Different-sized MR and PET contrast agents demonstrated the gradual increase in leakiness of the blood tumor barrier during metastatic progression, which could guide clinicians in choosing tailored treatment strategies.
Collapse
Affiliation(s)
- Frits Thorsen
- Department of Biomedicine, University of Bergen, Bergen, Norway.
| | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
6
|
Bachmann C, Grischke EM, Staebler A, Schittenhelm J, Wallwiener D. Receptor change-clinicopathologic analysis of matched pairs of primary and cerebral metastatic breast cancer. J Cancer Res Clin Oncol 2013; 139:1909-16. [DOI: 10.1007/s00432-013-1511-4] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2013] [Accepted: 08/30/2013] [Indexed: 10/26/2022]
|
7
|
Inhibition of type I insulin-like growth factor receptor signaling attenuates the development of breast cancer brain metastasis. PLoS One 2013; 8:e73406. [PMID: 24039934 PMCID: PMC3764163 DOI: 10.1371/journal.pone.0073406] [Citation(s) in RCA: 28] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2013] [Accepted: 07/22/2013] [Indexed: 02/01/2023] Open
Abstract
Brain metastasis is a common cause of mortality in cancer patients, yet potential therapeutic targets remain largely unknown. The type I insulin-like growth factor receptor (IGF-IR) is known to play a role in the progression of breast cancer and is currently being investigated in the clinical setting for various types of cancer. The present study demonstrates that IGF-IR is constitutively autophosphorylated in brain-seeking breast cancer sublines. Knockdown of IGF-IR results in a decrease of phospho-AKT and phospho-p70s6k, as well as decreased migration and invasion of MDA-MB-231Br brain-seeking cells. In addition, transient ablation of IGFBP3, which is overexpressed in brain-seeking cells, blocks IGF-IR activation. Using an in vivo experimental brain metastasis model, we show that IGF-IR knockdown brain-seeking cells have reduced potential to establish brain metastases. Finally, we demonstrate that the malignancy of brain-seeking cells is attenuated by pharmacological inhibition with picropodophyllin, an IGF-IR-specific tyrosine kinase inhibitor. Together, our data suggest that the IGF-IR is an important mediator of brain metastasis and its ablation delays the onset of brain metastases in our model system.
Collapse
|
8
|
Garnier D, Jabado N, Rak J. Extracellular vesicles as prospective carriers of oncogenic protein signatures in adult and paediatric brain tumours. Proteomics 2013; 13:1595-607. [PMID: 23505048 DOI: 10.1002/pmic.201200360] [Citation(s) in RCA: 22] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2012] [Revised: 10/06/2012] [Accepted: 10/24/2012] [Indexed: 01/06/2023]
Abstract
Extracellular vesicles (EVs), including exosomes, act as biological effectors and as carriers of oncogenic signatures in human cancer. The molecular composition and accessibility of EVs in biofluids open unprecedented diagnostic opportunities in malignancies where tumour tissue is difficult to sample, especially in primary and metastatic brain tumours. The ongoing genetic discovery of driver mutations defines the ever increasing numbers of distinct molecular subtypes of brain tumours (orphan diseases), a complexity that may soon be translated into alterations in functional proteins and their oncogenic networks. This may likely be extended to real time changes engendered by the disease progression, tumour heterogeneity, inter-individual variations and therapeutic responses. Meeting these challenges through EV analysis is dependent on technological progress in such areas as generation of mutation- and phospho-specific antibodies, antibody array platforms, nanotechnology, microfluidics, NMR spectroscopy, MS and MRM approaches of quantitative proteomics, which should not be underestimated. Still, vesiculation emerges as a unique process that could be harnessed for the benefit of more individualised patient care.
Collapse
Affiliation(s)
- Delphine Garnier
- Montreal Children's Hospital, RI MUHC, McGill University, Montreal, Quebec, Canada
| | | | | |
Collapse
|
9
|
Bachmann C, Grischke EM, Fehm T, Staebler A, Schittenhelm J, Wallwiener D. CNS metastases of breast cancer show discordant immunohistochemical phenotype compared to primary. J Cancer Res Clin Oncol 2012; 139:551-6. [DOI: 10.1007/s00432-012-1358-0] [Citation(s) in RCA: 19] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2012] [Accepted: 11/23/2012] [Indexed: 10/27/2022]
|