ITIlka Tsvetkova

Ilka Tsvetkova

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ilka Tsvetkova has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Modification-free Negative Control Defines the Operating Points at Which 5mC and 6mA Can Be Called from R9.4.1 Nanopore Data

    by Antonina Gospodinova, Ilka Tsvetkova, Radostina Tsvetankova, Yuliia Mariienko, Krassimira Todorova, Soren Hayrabedyan

    Nanopore sequencing reads DNA base modifications from the ionic-current signal, but the R9.4.1 chemistry has no vendor model for N6-methyladenine (6mA), and third-party models are applied without an absolute error estimate. We measured the false-positive rate of two 6mA callers and of one all-context 5-methylcytosine (5mC) caller against a negative control that cannot carry either mark: PCR-amplified cDNA, in three independent controls from two cell lines. False-positive rates were resolved per 5-mer context and compared with the specificity that each modification’s prevalence demands. For CpG methylation, the measured false-positive rate remained approximately two orders of magnitude below the maximum rate permitted under the stated assumptions, and no context restriction was required. For 6mA, the pooled false-positive rate at the commonly used probability threshold of 0.7 was 23.2-fold higher than the maximum admissible rate. Most of the excess background was contributed by 30 of the 256 adenine-centred contexts, none of which carries a cytosine immediately 5′ of the called base; excluding them improves specificity 5.9-fold at threshold 0.95 and brings the caller inside the requirement there. The rank ordering of context-specific false-positive rates was correlated between cell lines (Spearman ρ = 0.862), although absolute rates were not identical. Under the tested Dorado/NEMO configuration, a second 6mA caller classified 0.63% of adenines as modified in amplified DNA even at threshold 0.99, corresponding to 277 times the admissible false-positive rate and insufficient specificity for rare 6mA detection. Genomic DNA prepared with the FFPE repair step omitted, so that 8-oxo-dG is preserved, inflates apparent 6mA 9- to 15-fold while leaving CpG calls unaffected.


  • Open Access

    Machine Learning Approach for Muscovy Duck (Cairina moschata) Semen Quality Assessment

    by Desislava Abadjieva, Boyko Georgiev, Vasko Gerzilov, Ilka Tsvetkova, Paulina Taushanova, Krassimira Todorova, Soren Hayrabedyan

    This study aimed to develop a comprehensive approach for assessing fresh ejaculate from Muscovy duck (Cairina moschata) drakes to fulfil the requirements of artificial insemination in farm practices. The approach combines sperm kinetics (CASA) with non-kinetic parameters, such as vitality, enzyme activities (alkaline phosphatase (AP), creatine kinase (CK), lactate dehydrogenase (LDH), and γ-glutamyl-transferase (GGT)), and total DNA methylation as training features for a set of machine learning (ML) models designed to enhance the predictive capacity of sperm parameters. Samples were classified based on their progressive motility and DNA methylation features, exhibiting significant differences in total and progressive motility, curvilinear velocity (VCL), velocity of the average path (VAP), linear velocity (VSL), amplitude of lateral head displacement (ALH), beat-cross frequency (BCF), and live normal sperm cells in favour of fast motility ones. Additionally, there were significant differences in enzyme activities for AP and CK, with correlations to LDH and GGT levels. Although motility showed no correlation with total DNA methylation, ALH, wobble of the curvilinear trajectory (WOB), and VCL were significantly different in the newly introduced classification for “suggested good quality”, where both motility and methylation were high. The performance differences observed while training various ML classifiers using different feature subsets highlight the importance of DNA methylation for achieving more accurate sample quality classification, even though there is no correlation between motility and DNA methylation. The parameters ALH, VCL, triton extracted LDH, and VAP were top-ranking for “suggested good quality” predictions by the neural network and gradient boosting models. In conclusion, integrating non-kinetic parameters into machine-learning-based sample classification offers a promising approach for selecting kinetically and morphologically superior duck sperm samples that might otherwise be hindered by a predominance of lowly methylated cells.