Browsing by Author "Küçükhüseyin Ö."

Now showing 1 - 2 of 2

Predicting the predisposition to colorectal cancer based on SNP profiles of immune phenotypes using supervised learning models
(2023-01-01) Cakmak A.; Ayaz H.; Arıkan S.; Ibrahimzada A.R.; Demirkol Ş.; Sönmez D.; Hakan M.T.; Sürmen S.T.; Horozoğlu C.; Doğan M.B.; Küçükhüseyin Ö.; Cacına C.; Kıran B.; Zeybek Ü.; Baysan M.; Yaylım İ.
This study explores the machine learning-based assessment of predisposition to colorectal cancer based on single nucleotide polymorphisms (SNP). Such a computational approach may be used as a risk indicator and an auxiliary diagnosis method that complements the traditional methods such as biopsy and CT scan. Moreover, it may be used to develop a low-cost screening test for the early detection of colorectal cancers to improve public health. We employ several supervised classification algorithms. Besides, we apply data imputation to fill in the missing genotype values. The employed dataset includes SNPs observed in particular colorectal cancer-associated genomic loci that are located within DNA regions of 11 selected genes obtained from 115 individuals. We make the following observations: (i) random forest-based classifier using one-hot encoding and K-nearest neighbor (KNN)-based imputation performs the best among the studied classifiers with an F1 score of 89% and area under the curve (AUC) score of 0.96. (ii) One-hot encoding together with K-nearest neighbor-based data imputation increases the F1 scores by around 26% in comparison to the baseline approach which does not employ them. (iii) The proposed model outperforms a commonly employed state-of-the-art approach, ColonFlag, under all evaluated settings by up to 24% in terms of the AUC score. Based on the high accuracy of the constructed predictive models, the studied 11 genes may be considered a gene panel candidate for colon cancer risk screening. Graphical Abstract: [Figure not available: see fulltext.].
The effect of CTLA-4 and CD28 gene variants and circulating protein levels in patients with gastric cancer
(2017-10-01) Arikan S.; Gümüş A.; Küçükhüseyin Ö.; Coşkun C.; Turan S.; Cacina C.; Talu C.K.; Akyüz F.; Farooqi A.A.; Kıran B.; Yaylım İ.
Objective: Gastric cancer is one of the most common malignancies worldwide. The risk factors for gastric cancer include environmental and genetic factors. Inflammation and the immune system are known to contribute to the development of the gastric cancer. We examined the influence of critical polymorphisms of CTLA-4 and CD28 genes and circulating protein levels on the etiology of gastric cancer. Methods: Genotyping of SNPs was performed in 55 gastric cancer patients and 105 healthy individuals using the PCR-RFLP method, and circulating levels of sCTLA-4 and sCD28 were measured. Results: There were no significant differences in the genotype and allele distributions of the evaluated SNPs [CTLA- 4-318 C > T (rs5742909), CTLA-4 + 49 A > G (rs231775), CD28 C > T (rs3116496)] between gastric cancer patients and controls (p = 0.36, p = 0.78, and p = 0.80, respectively). The circulating levels of sCTLA-4 and sCD28 were significantly different between the gastric cancer group and the control group (p < 0.001 and p < 0.001, respectively). Conclusion: The present results suggest that the CTLA-4 and CD28 gene polymorphisms that were evaluated do not play an important role in Turkish patients with gastric cancer. However, sCTLA4 and sCD28 levels were higher in cancer patients and may be useful as an auxiliary parameter in the diagnosis and monitoring of gastric cancer.