Browsing by Author "Uzut, Ommu Gulsum"

Now showing 1 - 3 of 3

Combining Classifiers for Protein Secondary Structure Prediction
(IEEE345 E 47TH ST, NEW YORK, NY 10017 USA, 2017) Aydin, Zafer; Uzut, Ommu Gulsum; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü
Protein secondary structure prediction is an important step in estimating the three dimensional structure of proteins. Among the many methods developed for predicting structural properties of proteins, hybrid classifiers and ensembles that combine predictions from several models are shown to improve the accuracy rates. In this paper, we train, optimize and combine a support vector machine, a deep convolutional neural field and a random forest in the second stage of a hybrid classifier for protein secondary structure prediction. We demonstrate that the overall accuracy of the proposed ensemble is comparable to the success rates of the state-of-the-art methods in the most difficult prediction setting and combining the selected models have the potential to further improve the accuracy of the base learners.
Correlation of PAPP-A values with maternal characteristics, biochemical and ultrasonographic markers of pregnancy
(MARMARA UNIV, FAC MEDICINEHAYDARPASA, ISTAN, 34668, TURKEY, 2021) Kaymakcalan, Hande; Uzut, Ommu Gulsum; Harkonen, Juho; Bakir Gungor, Burcu; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Bakir Gungor, Burcu
Objective: Our aim is to investigate whether there is a correlation of pregnancy-associated plasma protein A (PAPP-A) values with other variables in pregnancy and maternal characteristics. Materials and Methods: We retrospectively analyzed the relation between the PAPP-A levels, demographics, biochemical and ultrasonographic markers of the first trimester screening of 11,842 pregnant women seen at a tertiary hospital between November 2002 and November 2008. Results: A significant difference between PAPP-A values of the diabetic and non-diabetic pregnant women were observed (p=0.0005, Mann-Whitney U test). In terms of weight, crown-rump length, Beta-hCG values, significant differences were observed between low and medium level PAPP-A subgroups and between low and high level PAPP-A subgroups. PAPP-A levels were found to differ significantly between the pregnant women of Caucasian origin and other racial origins. Conclusions: Pregnant women with different ethnic and medical backgrounds have different PAPP-A values and other markers of the aneuploidy screening. 'lb make patient specific risk predictions, understanding these interactions and differences is important. Future studies are needed to understand the pathopyhsiology behind these differences.
The relationship between PAPP-A levels, maternal characteristics, gestational diabetes and other biochemical markers of the aneuploidy screening
(IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA, 2018) Uzut, Ommu Gulsum; Celebiler, Hande Kaymakcalan; Harkonen, Juho; Bakir-Gungor, Burcu; 0000-0002-2272-6270; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü
First trimester aneuploidy screening is routinely used in pregnancy follow-ups. In this screening, free /l-hCG and pregnancy-associated plasma protein A (PAPP-A) levels in the blood of the pregnant woman arc measured. The aim of this study is to investigate the relationship between PAPP-A levels, maternal characteristics, diabetes, ultrasound measurements of the fetus and other biochemical markers of the aneuploidy screening. In this study, we used the dataset of 12 428 pregnant women, who arc followed by some of our researchers at the Prenatal Unit of Yale University Hospital in USA. The correlation of free-13-hCG, PAPP-A and Down syndrome risk with thyroid stimulating hormone (TSH), glucose and hematocrit was analyzed. A statistically significant correlation (p=0.0005) was found between the PAPP-A levels in the group of diabetic pregnant% and PAPP-A levels in non diabetic pregnant group. Detailed studies on the effect of PAPP-A on insulin growth factor could make it possible to use PAPP-A levels to predict gestational diabetes.