1 January 2016 in International Journal of Genomics
Cancerlectins are cancer-related proteins that function as lectins. They have been identified through computational identification techniques, but these techniques have sometimes failed to identify proteins because of sequence diversity among the cancerlectins. Advanced machine learning identification methods, such as support vector machine and basic sequence features (n-gram), have also been used to identify cancerlectins. In this study, various protein fingerprint features and advanced classifiers, including ensemble learning techniques, were utilized to identify this group of proteins. We improved the prediction accuracy of the original feature extraction methods and classification algorithms by more than 10% on average. Our work provides a basis for the computational identification of cancerlectins and reveals the power of hybrid machine learning techniques in computational proteomics.
1 January 2020 in Journal of Cancer
Lung cancer is one of the most common malignant tumors in the world, with a high rate of malignancy and mortality. Seeking new biomarkers and potential drug targets is urgent for effective treatment of the disease. Deubiquitinase UCHL5/UCH37, as an important component of the 26S proteasome, plays critical roles in ubiquitinated substrate degradation. Although previous studies have shown that UCHL5 promotes tumorigenesis, its role in lung cancer remains largely unknown. In this study, we evaluated the expression and clinical significance of UCHL5 in non-small cell lung cancer (NSCLC). The results demonstrated that the UCHL5 expression level was significantly upregulated in NSCLC tissues compared with the adjacent noncancerous tissues. The level of UCHL5 was associated with tumor size, lymph node invasion, TNM stage and malignant tumor history in patients with lung adenocarcinoma (LUAD). Importantly, high UCHL5 expression predicted a poor overall survival (OS) and a poor disease-free survival (DFS) in patients with LUAD. Univariate regression analysis showed that tumor size, lymph node invasion, TNM stage and UCHL5 expression were associated with OS and DFS in patients with LUAD. The multivariate analysis indicated that the UCHL5 expression level was an independent prognostic factor for OS (HR=1.171, 95% CI=1.052-1.303) and DFS (HR=1.143, 95% CI=1.031-1.267) in these patients. UCHL5 knockdown in LUAD cells significantly inhibited cell proliferation and reduced the expression of key cell cycle proteins. These findings indicate that UCHL5 may serve as a potential prognostic marker and a new therapeutic target for patients with LUAD.