Bilge Özlüer Başer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bilge Özlüer Başer has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Ahmet Avcı
Department of Biostatistics, Cerrahpaşa Faculty of Medicine, Istanbul University, Istanbul 34098, Turkey
1 shared publication - Ayça Çakmak Pehlivanlı
Mimar Sinan Guzel Sanatlar Universitesi
1 shared publication - E. Selin Sarıdaş
Mimar Sinan Guzel Sanatlar Universitesi
1 shared publication - Esma Gokcen Alper Acar
Epigenetic Coaching, London SW10 9EL, UK
1 shared publication - Fatma Karateke
MİMAR SİNAN ÜNİVERSİTESİ
1 shared publication - Gulsen Meral
Epigenetic Coaching, London SW10 9EL, UK
1 shared publication
Latest Publications
- Open Access
- 9 October 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (20) , 3277
Vitamin A and D Status, Selected Genetic Variants, and Allergy-Related Phenotypes: An Exploratory Retrospective Study
Background/Objectives: Vitamins A and D are critical regulators of immune function, and genetic variation in their metabolic pathways may influence vitamin status and immune responses. This study investigated the combined nutrigenetic roles of vitamins A and D and their association with allergy-related phenotypes. Methods: In this retrospective study, 80 individuals were included (40 with allergy-related phenotypes and 40 controls). Genetic polymorphisms in CYP2R1, GC, VDR, and BCMO1 were analyzed. Serum vitamin A and 25(OH)D concentrations were compared between groups, and multivariable analyses were performed to assess the effects of age and sex. Genotype distributions were evaluated using chi-square tests, and co-occurring genetic patterns were explored using the Apriori algorithm (p < 0.05). Results: Both serum vitamin A and 25(OH)D concentrations were significantly lower in the allergy-related phenotypes. Genotype differences were observed for CYP2R1 rs2060793 and BCMO1 rs12934922; however, only CYP2R1 rs2060793 remained significant after FDR correction. Although residual confounding cannot be ruled out, exploratory association rule mining identified co-occurrence patterns involving GC, VDR, and CYP2R1 variants with vitamin D deficiency and BCMO1 variants with vitamin A deficiency. These findings should be considered preliminary and hypothesis-generating rather than evidence of established or causal genetic effects. Conclusions: These preliminary findings indicate potential associations between vitamin status, specific genetic variants, and allergy-related phenotypes. Because of the study’s retrospective design and limited sample size, these genetic observations should be regarded as hypothesis-generating and warrant validation in larger, prospectively characterized cohorts.
- 9 October 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (20) , 3277
Open AccessVitamin A and D Status, Selected Genetic Variants, and Allergy-Related Phenotypes: An Exploratory Retrospective Study
Background/Objectives: Vitamins A and D are critical regulators of immune function, and genetic variation in their metabolic pathways may influence vitamin status and immune responses. This study investigated the combined nutrigenetic roles of vitamins A and D and their association with allergy-related phenotypes. Methods: In this retrospective study, 80 individuals were included (40 with allergy-related phenotypes and 40 controls). Genetic polymorphisms in CYP2R1, GC, VDR, and BCMO1 were analyzed. Serum vitamin A and 25(OH)D concentrations were compared between groups, and multivariable analyses were performed to assess the effects of age and sex. Genotype distributions were evaluated using chi-square tests, and co-occurring genetic patterns were explored using the Apriori algorithm (p < 0.05). Results: Both serum vitamin A and 25(OH)D concentrations were significantly lower in the allergy-related phenotypes. Genotype differences were observed for CYP2R1 rs2060793 and BCMO1 rs12934922; however, only CYP2R1 rs2060793 remained significant after FDR correction. Although residual confounding cannot be ruled out, exploratory association rule mining identified co-occurrence patterns involving GC, VDR, and CYP2R1 variants with vitamin D deficiency and BCMO1 variants with vitamin A deficiency. These findings should be considered preliminary and hypothesis-generating rather than evidence of established or causal genetic effects. Conclusions: These preliminary findings indicate potential associations between vitamin status, specific genetic variants, and allergy-related phenotypes. Because of the study’s retrospective design and limited sample size, these genetic observations should be regarded as hypothesis-generating and warrant validation in larger, prospectively characterized cohorts.
- 15 May 2026
- Published by Black Sea Journal of Engineering and Science in Black Sea Journal of Engineering and Science
- Vol. 9 (3) , 1150-1162
Gene Discovery in MALT Lymphoma Using Explainable Machine Learning on scRNA-seq Data
Mucosa-associated lymphoid tissue (MALT) lymphoma is an indolent and clinically heterogeneous B-cell malignancy. The lack of robust molecular biomarkers and the limited availability of high-resolution single-cell studies hinder the development of precise diagnostic and therapeutic strategies. To address this gap, an interpretable machine learning pipeline was developed and applied to single-cell RNA sequencing (scRNA-seq) data derived from MALT lymphoma patients and healthy donors. After quality control, normalization, and dimensionality reduction via truncated singular value decomposition (SVD), multiple tree-based classifiers were trained using stratified cross-validation and evaluated on a held-out balanced test set. Feature importance scores and SHapley Additive exPlanations (SHAP) values were integrated with Wilcoxon rank-sum testing to identify statistically supported gene markers. Among the classifiers, CatBoost, LightGBM, and Random Forest achieved the highest performance. Genes such as RPS4Y1, RGS1, XIST, CREM, and HSPH1 were consistently prioritized by both SHAP and statistical testing, indicating their biological relevance and differential expression. Notably, a divergence was observed between impurity-based feature importance rankings and the SHAP/Wilcoxon consensus, reflecting the complementary nature of these analytical approaches. This integrative framework provides a transparent and reproducible approach for gene discovery in scRNA-seq data and contributes computationally prioritized candidate genes warranting experimental validation for understanding MALT lymphoma pathogenesis and improving future molecular diagnostics.
- 15 May 2026
- Published by Black Sea Journal of Engineering and Science in Black Sea Journal of Engineering and Science
- Vol. 9 (3) , 1150-1162
Gene Discovery in MALT Lymphoma Using Explainable Machine Learning on scRNA-seq Data
Mucosa-associated lymphoid tissue (MALT) lymphoma is an indolent and clinically heterogeneous B-cell malignancy. The lack of robust molecular biomarkers and the limited availability of high-resolution single-cell studies hinder the development of precise diagnostic and therapeutic strategies. To address this gap, an interpretable machine learning pipeline was developed and applied to single-cell RNA sequencing (scRNA-seq) data derived from MALT lymphoma patients and healthy donors. After quality control, normalization, and dimensionality reduction via truncated singular value decomposition (SVD), multiple tree-based classifiers were trained using stratified cross-validation and evaluated on a held-out balanced test set. Feature importance scores and SHapley Additive exPlanations (SHAP) values were integrated with Wilcoxon rank-sum testing to identify statistically supported gene markers. Among the classifiers, CatBoost, LightGBM, and Random Forest achieved the highest performance. Genes such as RPS4Y1, RGS1, XIST, CREM, and HSPH1 were consistently prioritized by both SHAP and statistical testing, indicating their biological relevance and differential expression. Notably, a divergence was observed between impurity-based feature importance rankings and the SHAP/Wilcoxon consensus, reflecting the complementary nature of these analytical approaches. This integrative framework provides a transparent and reproducible approach for gene discovery in scRNA-seq data and contributes computationally prioritized candidate genes warranting experimental validation for understanding MALT lymphoma pathogenesis and improving future molecular diagnostics.
- 23 February 2026
- Published by Journal of Intelligent Systems: Theory and Applications, Harun TASKIN in Journal of Intelligent Systems: Theory and Applications
- Vol. 9 (2026) , 1-9
Statistical Learning-Based Prediction of Estrogen Receptor Alpha (ERα) Inhibitor Activities
Estrogen receptor alpha (ERα) is a protein that plays a role in processes such as cell growth and proliferation; however, it has become an important research topic due to its overexpression in 70% of breast cancers. ERα inhibitors stop the growth of cancer cells by blocking the activity of this protein. Traditional drug discovery methods are disadvantageous in terms of time and cost. Various approaches exist in the literature for the discovery of ERα inhibitors. Therefore, a machine learning-based Quantitative Structure-Activity Relationship (QSAR) approach was preferred in this study for the discovery of ERα inhibitors. In this study, a machine learning-based QSAR approach was preferred due to its capacity to extract structure-activity relationships from large chemical datasets and its ability to provide high-throughput screening opportunities. This method enables the prediction of biological activities by expressing the chemical structural properties of molecules through numerical descriptors. The ChEMBL206 target identifier was selected as the data source due to its widespread use, high data quality, and the opportunity for comparison with previous studies. The obtained molecules were classified according to their IC50 values, and their chemical space distributions were analyzed using Lipinski rules. Subsequently, 3153 molecular descriptors were calculated for 3053 molecules using the PADEL program. Feature importance analysis revealed that fingerprints such as PubchemFP667 and PubchemFP527, as well as APC2D atom pair descriptors that stood out in the LightGBM model, played critical roles in ERα inhibition. The developed models demonstrated superior performance with accuracy above 94%, sensitivity around 90%, specificity above 95%, and AUC values above 0.97. This study contributes to the efficiency of the drug discovery process by demonstrating that the activity of ERα inhibitors can be predicted with high accuracy rates.
- 23 February 2026
- Published by Journal of Intelligent Systems: Theory and Applications, Harun TASKIN in Journal of Intelligent Systems: Theory and Applications
- Vol. 9 (2026) , 1-9
Statistical Learning-Based Prediction of Estrogen Receptor Alpha (ERα) Inhibitor Activities
Estrogen receptor alpha (ERα) is a protein that plays a role in processes such as cell growth and proliferation; however, it has become an important research topic due to its overexpression in 70% of breast cancers. ERα inhibitors stop the growth of cancer cells by blocking the activity of this protein. Traditional drug discovery methods are disadvantageous in terms of time and cost. Various approaches exist in the literature for the discovery of ERα inhibitors. Therefore, a machine learning-based Quantitative Structure-Activity Relationship (QSAR) approach was preferred in this study for the discovery of ERα inhibitors. In this study, a machine learning-based QSAR approach was preferred due to its capacity to extract structure-activity relationships from large chemical datasets and its ability to provide high-throughput screening opportunities. This method enables the prediction of biological activities by expressing the chemical structural properties of molecules through numerical descriptors. The ChEMBL206 target identifier was selected as the data source due to its widespread use, high data quality, and the opportunity for comparison with previous studies. The obtained molecules were classified according to their IC50 values, and their chemical space distributions were analyzed using Lipinski rules. Subsequently, 3153 molecular descriptors were calculated for 3053 molecules using the PADEL program. Feature importance analysis revealed that fingerprints such as PubchemFP667 and PubchemFP527, as well as APC2D atom pair descriptors that stood out in the LightGBM model, played critical roles in ERα inhibition. The developed models demonstrated superior performance with accuracy above 94%, sensitivity around 90%, specificity above 95%, and AUC values above 0.97. This study contributes to the efficiency of the drug discovery process by demonstrating that the activity of ERα inhibitors can be predicted with high accuracy rates.
- 1 September 2022
- Published by Gazi University Journal of Science in Gazi University Journal of Science
- Vol. 35 (3) , 1190-1198
Analyzing the Competition of HIV-1 Phenotypes with Quantum Game Theory
HIV-1 (Human Immunodeficiency Virus) is a virus that causes AIDS (Acquired Immunodeficiency Syndrome), which damages the immune system by reducing people's resistance to infections and diseases. Antiretroviral treatment methods are based on drug designs developed using inhibitors that suppress the dynamics that enable the maturation of the virus. However, studies are needed to improve treatment methods against infection because HIV-1 is frequently mutated and mutant viruses develop resistance to the treatment used. Therefore, it is important to model the evolutionary development of the virus. For this purpose, the developmental process and spread of HIV-1 are modeled as a game with the players of phenotypes in this study. The related searches known to be made so far have been carried out based on the rules of classical physics. However, games of survival are being played on the molecular level, where the rules of quantum mechanics work. Since the HIV-1 game is being played on the molecular level, the behaviors of the virus phenotypes are examined from the perspective of quantum computation.
- 1 September 2022
- Published by Gazi University Journal of Science in Gazi University Journal of Science
- Vol. 35 (3) , 1190-1198
Analyzing the Competition of HIV-1 Phenotypes with Quantum Game Theory
HIV-1 (Human Immunodeficiency Virus) is a virus that causes AIDS (Acquired Immunodeficiency Syndrome), which damages the immune system by reducing people's resistance to infections and diseases. Antiretroviral treatment methods are based on drug designs developed using inhibitors that suppress the dynamics that enable the maturation of the virus. However, studies are needed to improve treatment methods against infection because HIV-1 is frequently mutated and mutant viruses develop resistance to the treatment used. Therefore, it is important to model the evolutionary development of the virus. For this purpose, the developmental process and spread of HIV-1 are modeled as a game with the players of phenotypes in this study. The related searches known to be made so far have been carried out based on the rules of classical physics. However, games of survival are being played on the molecular level, where the rules of quantum mechanics work. Since the HIV-1 game is being played on the molecular level, the behaviors of the virus phenotypes are examined from the perspective of quantum computation.
- 20 April 2021
- Published by SDU Journal of Natural and Applied Sciences in SDÜ Fen Bilimleri Enstitüsü Dergisi
- Vol. 25 (1) , 112-120
Makine Öğrenmesi Teknikleriyle Diyabet Hastalığının Sınıflandırılması
Diyabet, dünya çapında artan ve gerçekleşen ölümlerin önde gelen nedenlerinden biridir. Sürekli artan vaka sayısı diyabetin önlenmesi, erken teşhisi, tedavisi ve takibi konularında bilimsel çalışmalara ihtiyaç duyulduğunu göstermektedir. Son dönemlerde medikal alanda yaşanan teknolojik gelişmeler sayesinde elde edilen verinin analiz edilmesi, hastalıkların tanı ve tedavi sürecine olumlu katkılar yapmaktadır. Diyabet hastalığı kapsamında da araştırmacılar, hastalığın teşhis edilmesine yönelik, veriye dayalı sistematik yaklaşımlar geliştirmeye çalışmaktadırlar. Bu amaç doğrultusunda çalışmada, 1999-2008 yılları arasında ABD’de bulunan 130 hastanedeki 70000 kayda ait sağlık vakalarından elde edilmiş veri seti düzenlenerek, bireylerin diyabet durumuna göre sınıflandırılması hedeflenmiştir. Sınıflandırma için veri setine uygun makine öğrenmesi algoritmalarından yararlanılmış ve bu algoritmaların sonuçları performans ölçütlerine göre karşılaştırılmıştır. Elde edilen sonuçlara göre, en iyi performans gösteren beş sınıflandırma algoritması (Karar ağaçları, k-en yakın komşuluk, Lojistik regresyon, Naive Bayes ve Rastgele orman) değerlendirmeye alınmış olup en iyi doğru sınıflandırma performansı Rastgele orman algoritması ile elde edilmiştir.
- 20 April 2021
- Published by SDU Journal of Natural and Applied Sciences in SDÜ Fen Bilimleri Enstitüsü Dergisi
- Vol. 25 (1) , 112-120
Makine Öğrenmesi Teknikleriyle Diyabet Hastalığının Sınıflandırılması
Diyabet, dünya çapında artan ve gerçekleşen ölümlerin önde gelen nedenlerinden biridir. Sürekli artan vaka sayısı diyabetin önlenmesi, erken teşhisi, tedavisi ve takibi konularında bilimsel çalışmalara ihtiyaç duyulduğunu göstermektedir. Son dönemlerde medikal alanda yaşanan teknolojik gelişmeler sayesinde elde edilen verinin analiz edilmesi, hastalıkların tanı ve tedavi sürecine olumlu katkılar yapmaktadır. Diyabet hastalığı kapsamında da araştırmacılar, hastalığın teşhis edilmesine yönelik, veriye dayalı sistematik yaklaşımlar geliştirmeye çalışmaktadırlar. Bu amaç doğrultusunda çalışmada, 1999-2008 yılları arasında ABD’de bulunan 130 hastanedeki 70000 kayda ait sağlık vakalarından elde edilmiş veri seti düzenlenerek, bireylerin diyabet durumuna göre sınıflandırılması hedeflenmiştir. Sınıflandırma için veri setine uygun makine öğrenmesi algoritmalarından yararlanılmış ve bu algoritmaların sonuçları performans ölçütlerine göre karşılaştırılmıştır. Elde edilen sonuçlara göre, en iyi performans gösteren beş sınıflandırma algoritması (Karar ağaçları, k-en yakın komşuluk, Lojistik regresyon, Naive Bayes ve Rastgele orman) değerlendirmeye alınmış olup en iyi doğru sınıflandırma performansı Rastgele orman algoritması ile elde edilmiştir.