Molecular Biology and Genetics / Moleküler Biyoloji ve Genetik

Permanent URI for this collectionhttps://hdl.handle.net/11147/9

Browse

Filters

2010 - 20165

Settings

Scopus Q: search.filters.scopusQuartile.N/ASubject: search.filters.subject.Bioinformatics

Search Results

Now showing 1 - 5 of 5
  • Conference Object
    Citation - Scopus: 13
    Feature Selection for Microrna Target Prediction Comparison of One-Class Feature Selection Methodologies
    (Hindawi Publishing Corporation, 2016) Yousef, Malik; Allmer, Jens; Khalifa, Waleed
    Traditionally, machine learning algorithms build classification models from positive and negative examples. Recently, one-class classification (OCC) receives increasing attention in machine learning for problems where the negative class cannot be defined unambiguously. This is specifically problematic in bioinformatics since for some important biological problems the target class (positive class) is easy to obtain while the negative one cannot be measured. Artificially generating the negative class data can be based on unreliable assumptions. Several studies have applied two-class machine learning to predict microRNAs (miRNAs) and their target. Different approaches for the generation of an artificial negative class have been applied, but may lead to a biased performance estimate. Feature selection has been well studied for the two-class classification problem, while fewer methods are available for feature selection in respect to OCC. In this study, we present a feature selection approach for applying one-class classification to the prediction of miRNA targets. A comparison between one-class and two-class approaches is presented to highlight that their performance are similar while one-class classification is not based on questionable artificial data for training and performance evaluation. We further show that the feature selection method we tried works to a degree, but needs improvement in the future. Perhaps it could be combined with other approaches.
  • Conference Object
    Citation - WoS: 6
    Citation - Scopus: 8
    Comparison of Four Ab Initio Microrna Prediction Tools
    (SciTePress, 2013) Saçar, Müşerref Duygu; Allmer, Jens
    MicroRNAs are small RNA sequences of 18-24 nucleotides in length, which serve as templates to drive post transcriptional gene silencing. The canonical microRNA pathway starts with transcription from DNA and is followed by processing by the Microprocessor complex, yielding a hairpin structure. This is then exported into the cytosol where it is processed by Dicer and next incorporated into the RNA induced silencing complex. All of these biogenesis steps add to the overall specificity of miRNA production and effect. Unfortunately, experimental detection of miRNAs is cumbersome and therefore computational tools are necessary. Homology-based miRNA prediction tools are limited by fast miRNA evolution and by the fact that they are template driven. Ab initio miRNA prediction methods have been proposed but they have not been analyzed competitively so that their relative performance is largely unknown. Here we implement the features proposed in four miRNA ab initio studies and evaluate them on two data sets. Using the features described in Bentwich 2008 leads to the highest accuracy but still does not provide enough confidence into the results to warrant experimental validation of all predictions in a larger genome like the human genome. Copyright © 2013 SCITEPRESS - Science and Technology Publications.
  • Conference Object
    Citation - WoS: 4
    Citation - Scopus: 4
    Mining Frequent Patterns From Microarray Data
    (Institute of Electrical and Electronics Engineers Inc., 2011) Yıldız, Barış; Şelale, Hatice
    The rapid development of computers and increasing amount of collected data made data mining a popular analysis tool. Data mining research is interrelated to many fields and one of the most important ones is bioinformatics. Among many techniques, mining association rules or frequent patterns is one of the most studied techniques in computer science and it is applicable to bioinformatics. Association analysis of gene expressions may be used as decision support mechanism for finding genes that are in same pathway. In this work, publicly available yeast microarray data has been analyzed using an efficient frequent pattern mining algorithm Matrix Apriori and frequently co-over-expressed genes have been identified. © 2011 IEEE.
  • Conference Object
    Citation - Scopus: 17
    Systematic Computational Analysis of Potential Rnai Regulation in Toxoplasma Gondii
    (Institute of Electrical and Electronics Engineers Inc., 2010) Çakır, Mehmet Volkan; Allmer, Jens
    RNA interference (RNAi) is the mechanism through which RNA interferes with the production of other RNAs in a sequence specific manner. Micro RNA (miRNA) is a type of RNA which is transcribed as pri-miRNAs and processed to premiRNAs in the nucleus. These pre-miRNAs are then exported from the nucleus and processed in the cytoplasm to double stranded RNA with one strand providing target specificity.. Toxoplasma gondii is a parasitic apicomplexan which causes several diseases. T. gondii is a good candidate for computational efforts with its small and publicly available genome files and extensive information about its gene structure. Although the existence of RNA interference in T. gondii is being debated, establishment of its complete potential RNAi regulatory network may be beneficial for further investigations into the topic. ©2009 IEEE.
  • Conference Object
    Relative Protein Quantitation With Post Translational Modifications in Mass Spectrometry Based Proteomics
    (Institute of Electrical and Electronics Engineers Inc., 2010) Allmer, Jens
    Mass spectrometry has become the tool of choice for most investigations in proteomics. Identification of proteins from complex mixtures has long been achieved and is now routinely used in countless high throughput studies. Quantitation by mass spectrometry is comparably newer and many different strategies have been proposed. One such strategy quantitates the difference in protein expression level among samples via extracted ion chromatograms, or spectral counts or a combination thereof. Another strategy involves mass modifications of the analytes in one or more of the samples under investigation. MSMAG has been developed as an extension to 2DB and it has been shown that it can aid in quantitation of data from experiments employing label-free quantitation. Recently, it has been extended to allow for analysis of data based on labelling strategies. This also makes it possible to quickly visualize and investigate inherent mass differences as presented by post translational modifications. ©2009 IEEE.