Egils Vjaters
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Egils Vjaters has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Dmitrijs Bliznuks
Institute of Applied Computer Systems, Riga Technical University, LV-1048 Riga, Latvia
1 shared publication - Edvins Miklasevics
Faculty of Medicine, Riga Stradins University, LV-1007 Riga, Latvia
1 shared publication - Janis Gardovskis
Department of Surgery, Riga Stradins University, Dzirciema Street 16, LV-1007 Riga, Latvia
1 shared publication - Juris Plonis
Institute of Oncology and Molecular Genetics, Riga Stradins University, LV-1002 Riga, Latvia
1 shared publication - Mihails Šatcs
Institute of Oncology and Molecular Genetics, Riga Stradins University, Pilsonu Street 13, Block 13, LV-1002 Riga, Latvia
1 shared publication - Mikhail Baryshev
Institute of Microbiology and Virology, Riga Stradins University, Ratsupites Str 5, LV-1067 Riga, Latvia
1 shared publication
Latest Publications
- Open Access
- 18 February 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (4) , 492
Liquid Biopsy Based Bladder Cancer Diagnostic by Machine Learning
Background/Objectives: The timely diagnostics of bladder cancer is still a challenge in clinical settings. The reliability of conventional testing methods does not reach desirable accuracy and sensitivity, and it has an invasive nature. The present study examines the application of machine learning to improve bladder cancer diagnostics by integrating miRNA expression levels, demographic routine laboratory test results, and clinical data. We proposed that merging these datasets would enhance diagnostic accuracy. Methods: This study combined molecular biology methods for liquid biopsy, routine clinical data, and application of machine learning approach for the acquired data analysis. We evaluated urinary exosome miRNA expression data in combination with patient test results, as well as clinical and demographic data using three machine learning models: Random Forest, SVM, and XGBoost classifiers. Results: Based solely on miRNA data, the SVM model achieved an ROC curve area of 0.75. Patient analysis’ clinical and demographic data obtained ROC curve area of 0.80. Combining both data types enhanced performance, resulting in an F1 score of 0.79 and an ROC of 0.85. The feature importance analysis identified key predictors, including erythrocytes in urine, age, and several miRNAs. Conclusions: Our findings indicate the potential of a multi-modal approach to improve the accuracy of bladder cancer diagnosis in a non-invasive manner.
- 18 February 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (4) , 492
Open AccessLiquid Biopsy Based Bladder Cancer Diagnostic by Machine Learning
Background/Objectives: The timely diagnostics of bladder cancer is still a challenge in clinical settings. The reliability of conventional testing methods does not reach desirable accuracy and sensitivity, and it has an invasive nature. The present study examines the application of machine learning to improve bladder cancer diagnostics by integrating miRNA expression levels, demographic routine laboratory test results, and clinical data. We proposed that merging these datasets would enhance diagnostic accuracy. Methods: This study combined molecular biology methods for liquid biopsy, routine clinical data, and application of machine learning approach for the acquired data analysis. We evaluated urinary exosome miRNA expression data in combination with patient test results, as well as clinical and demographic data using three machine learning models: Random Forest, SVM, and XGBoost classifiers. Results: Based solely on miRNA data, the SVM model achieved an ROC curve area of 0.75. Patient analysis’ clinical and demographic data obtained ROC curve area of 0.80. Combining both data types enhanced performance, resulting in an F1 score of 0.79 and an ROC of 0.85. The feature importance analysis identified key predictors, including erythrocytes in urine, age, and several miRNAs. Conclusions: Our findings indicate the potential of a multi-modal approach to improve the accuracy of bladder cancer diagnosis in a non-invasive manner.
- Open Access
- 31 January 2025
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 26 (3) , 1243
Allele-Specific CG/CCWGG Methylation of the PSA Promoter Discriminates Aggressive, Indolent, and Benign Prostate Cell Lines and Is Involved in the Regulation of PSA Expression
Prostate-specific antigen remains a cornerstone biomarker for prostate cancer diagnosis and management. However, the molecular mechanisms regulating its expression, particularly through DNA methylation, are not fully understood. Here, we report a comprehensive analysis of allele-specific CpG and CCWGG methylation in the proximal PSA promoter across aggressive (PC3), indolent (LNCaP), benign (BPH1), and normal (HPrEpiC) prostate cell lines and provide insights into the unique methylation patterns associated with these states. Our findings reveal that PC3 cells, representing an aggressive PCa phenotype, exhibit complete biallelic methylation of the PSA promoter, leading to PSA gene silencing. Conversely, LNCaP cells display a fully unmethylated promoter with biallelic PSA expression. Interestingly, BPH1 cells display a monoallelic CG/CCWGG methylation pattern, yet fail to express PSA, suggesting imprinting defects or RNA decay mechanisms. Notably, acquisition of biallelic PSA promoter methylation status in PC3 was accompanied by upregulation of DNMT1, whereas unmethylated PSA promoter state in LNCaP was associated with downregulation of DNMT1. These findings highlight distinct methylation patterns in the PSA promoter that differentiate between aggressive, indolent, and benign prostate states. Translating this epigenetic insight into clinical diagnostics could enhance the precision of PSA-based diagnostics, addressing limitations such as false negatives in PSA testing for aggressive PCa. Further exploration of CCWGG methylation’s role in imprinting and monoallelic expression is warranted, particularly in patient-derived samples.
- 31 January 2025
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 26 (3) , 1243
Open AccessAllele-Specific CG/CCWGG Methylation of the PSA Promoter Discriminates Aggressive, Indolent, and Benign Prostate Cell Lines and Is Involved in the Regulation of PSA Expression
Prostate-specific antigen remains a cornerstone biomarker for prostate cancer diagnosis and management. However, the molecular mechanisms regulating its expression, particularly through DNA methylation, are not fully understood. Here, we report a comprehensive analysis of allele-specific CpG and CCWGG methylation in the proximal PSA promoter across aggressive (PC3), indolent (LNCaP), benign (BPH1), and normal (HPrEpiC) prostate cell lines and provide insights into the unique methylation patterns associated with these states. Our findings reveal that PC3 cells, representing an aggressive PCa phenotype, exhibit complete biallelic methylation of the PSA promoter, leading to PSA gene silencing. Conversely, LNCaP cells display a fully unmethylated promoter with biallelic PSA expression. Interestingly, BPH1 cells display a monoallelic CG/CCWGG methylation pattern, yet fail to express PSA, suggesting imprinting defects or RNA decay mechanisms. Notably, acquisition of biallelic PSA promoter methylation status in PC3 was accompanied by upregulation of DNMT1, whereas unmethylated PSA promoter state in LNCaP was associated with downregulation of DNMT1. These findings highlight distinct methylation patterns in the PSA promoter that differentiate between aggressive, indolent, and benign prostate states. Translating this epigenetic insight into clinical diagnostics could enhance the precision of PSA-based diagnostics, addressing limitations such as false negatives in PSA testing for aggressive PCa. Further exploration of CCWGG methylation’s role in imprinting and monoallelic expression is warranted, particularly in patient-derived samples.