Classification of high-dimensional data set is a big challenge for statistical learning and data mining algorithms. To effectively apply classification methods to high-dimensional data sets, feature selection is an indispensable pre-processing step of learning process. In this study, we consider the problem of constructing an effective feature selection and classification scheme for data set which has a small number of sample size with a large number of features. A novel feature selection approach, named four-Staged Feature Selection, has been proposed to overcome high-dimensional data classification problem by selecting informative features. The proposed method first selects candidate features with number of filtering methods which are based on different metrics, and then it applies semi-wrapper, union and voting stages, respectively, to obtain final feature subsets. Several statistical learning and data mining methods have been carried out to verify the efficiency of the selected features. In order to test the adequacy of the proposed method, 10 different microarray data sets are employed due to their high number of features and small sample size.
We report the molecular characterization of an ethyl methanesulfonate (EMS)-induced mutation that causes albinism and lethality at the seedling stage in Arabidopsis thaliana. We identified the mutation using a mapping-by-sequencing approach that uses Fisher’s exact tests to detect changes in allele frequencies among the seedlings of an F2 mapping population, which had been pooled according to their phenotypes (wild-type or mutant). After purifying genomic DNA from the plants of both pools, the two samples were sequenced using the Illumina HiSeq 2500 next-generation sequencing platform. The bioinformatic analysis allowed us to identify a point mutation that damages a conserved residue at the acceptor site of an intron of the At2g04030 gene, which encodes the chloroplast-localized AtHsp90.5 protein, a member of the HSP90 family of heat shock proteins. Our RNA-seq analysis demonstrates that the new allele alters the splicing of At2g04030 transcripts in multiple ways, leading to massive deregulation of genes encoding plastid-localized proteins. A search for protein–protein interactions using the yeast two-hybrid method allowed us to identify two members of the GrpE superfamily as potential interactors of AtHsp90.5, as has previously been reported for green algae.
20 August 2021 in SDÜ Fen Bilimleri Enstitüsü Dergisi
Among the toxicity tests, mutagenicity defined as a genetic change that can occur due to an agent, has an important place. In this study, statistical learning algorithms were used within the scope of in-silico approach in order to improve the mutagenicity determination process in general. This approach has been applied to the set of molecules containing mutagenicity information obtained by experiments and remarkable classification success were achieved. In order to use in this study, Bursi and Benchmark data sets consisting of molecules found in the literature were combined and the properties of molecules were calculated by means of the Molecular Operating Environment (MOE). As a result of the calculation, decision trees algorithms were applied on the data set with 10835 molecules and 193 variables and parameter selection was performed with grid search approach. The selection of variables was made according to their level of importance in predicting mutagenicity as a result of models established with the best parameters obtained, and the number of descriptors variables was reduced to the 72 most effective descriptor variables. Various statistical learning algorithms were applied to the reduced data set consisting of the selected variables, and five classification algorithms with the best results were decided. By the algorithms whose model performances were increased by means of parameter optimization, accurate prediction rates were obtained approximately 90% for mutagenicity classification. Toksisite testleri arasında, bir etken nedeniyle ortaya çıkabilecek genetik değişim (mutasyon) olarak tanımlanabilen mutajenisite önemli yer tutmaktadır. Bu çalışmada genel olarak mutajenisite belirleme sürecini iyileştirebilmek adına in-silico yaklaşım kapsamında istatistiksel öğrenme algoritmaları kullanılmıştır. Söz konusu yaklaşım deneyler ile elde edilen mutajenisite bilgisi içeren molekül setine uygulanmış ve dikkate değer sınıflama başarıları elde edilmiştir. Çalışmada kullanılmak üzere literatürde bulunan, moleküllerden oluşan Bursi ile Benchmark veri setleri birleştirilmiş ve Molecular Operating Environment (MOE) programı aracılığı ile moleküllerin özellikleri hesaplanmıştır. Hesaplama sonucunda 10835 gözleme ve 193 değişkene sahip veri seti üzerinde karar ağaçları algoritmaları uygulanarak grid arama yaklaşımı ile parametre seçimi gerçekleştirilmiştir. Elde edilen en iyi parametreler ile kurulan modeller sonucunda değişkenlerin seçimi mutajenisiteyi tahmin etmedeki önem düzeylerine göre yapılmış ve verinin boyutu en etkili 72 değişkene indirgenmiştir. Seçilen değişkenlerden oluşan yeni veriye farklı istatistiksel öğrenme algoritmaları uygulanmış ve içlerinden en iyi sonuç veren beş sınıflama algoritmasına karar verilmiştir. Parametre en iyilemesi ile model başarımları arttırılan bu algoritmalar kullanılarak yaklaşık %90 mutajenisiteyi doğru sınıflama oranları elde edilmiştir.
Manufacturing of and medication with generic drugs is increasing around the world. Bioequivalence (BE) studies are being performed routinely by Contract Research Organisations (CROs) in Turkey. However, an overall evaluation for the attended volunteers, examined Active Pharmaceutical Ingredients (APIs) and the observed adverse events have not been studied in the field. Our aim was to revisit and compile the BE studies carried out between the years 2000–2013 of a CRO (N-CRO) in Turkey. A dataset of 261 BE studies has been created for the observed adverse events with regards to the frequency, type, and drug subgroups. As an advanced evaluation, the Gini Index method has been used in the 63 available BE studies to obtain split points for two pharmacokinetic parameters, area under the plasma/serum concentration (AUC) and maximum plasma/serum concentration (Cmax), in order to investigate their likely effect on the adverse events. Thousand six hundred and forty two adverse events were found in the 261 BE studies involving 7828 volunteers with the frequency of 6.29 per study and 0.21 per volunteer. The most frequently observed adverse events were; headache, somnolence, nausea, dizziness and vomiting, respectively. Hundred and nine different APIs were observed. ‘Genitourinary system and sex hormones’ subgroup drugs had the highest frequency of the adverse events. Adverse event frequencies above the identified split points for Cmax and AUC values were higher than the frequencies below them. The review of 13 years period of BE studies revealed that the demographic properties of the volunteers and the study designs were in compliance with national and international guidelines. The promising outcome could be showing the increase of the adverse event frequencies above the obtained split points as the reflection of the likely individual pharmacokinetic differences in the adverse event occurence.