Biology subjects

Yurtseven, A.

Publications and source records attributed to Yurtseven, A..

4 recordsLinked to original sources

bioRxiv2025

ALPAR: Automated Learning Pipeline for Antimicrobial Resistance

The field of machine learning in antimicrobial resistance (AMR) research has experienced rapid growth, fueled by advancements in high-throughput genome sequencing and growing capacity of computational resources. However, the complexity and lack of standardized data preparation and bioinformatic analyses present significant challenges, especially to newcomers to the domain. In response to these challenges, we introduce ALPAR (Automated Learning Pipeline for Antimicrobial Resistance), a comprehensive AMR data analysis tool covering the entire process from processing of raw genomic data to training machine learning models to interpretation of results. Our method relies on a reproducible pipeline that integrates widely used bioinformatics tools, presenting a simplified, automatic workflow specifically tailored for single-reference AMR analysis. Accepting genomic data in the form of FASTA files as input, ALPAR facilitates generation of machine learning-ready data tables and both training of machine learning and execution of genome-wide association studies (GWAS) experiments. Additionally, our tool offers supplementary functionalities such as phylogeny-based analysis of distribution of mutations, enhancing its utility for researchers. Our tool is accessible through the ALPAR GitHub page (https://github.com/kalininalab/ALPAR) and installable via conda (https://anaconda.org/kalininalab/ALPAR).

bioinformatics↗

bioRxiv2025

ShiftSCAN, a program that predicts potential alternative sources of mass spectrometry-derived peptides, improves the accuracy of studies on novel amino acid sequences

Mass spectrometry (MS) proteomics is currently the most powerful tool for identifying both annotated proteins and proteins translated from non-canonical open reading frames or unusual genetic events. With this method, numerous novel protein-coding loci have been discovered by searching for short fragments of hypothetical longer peptides and polypeptides. Apart from the validation of translation from mRNA transcripts, MS proteomics has been instrumental for the detection of peptides encoded by non-mRNA transcripts. A special application field of MS proteomics is studies on programmed ribosomal frameshifting (PRF), where the detection of chimeric peptides produced from two different reading frames is vital. Each novel chimeric peptide is thought to originate from a certain genetic locus. However, due to the short length of MS peptides, there is a possibility that MS-supported chimeric peptides are produced by additional (alternative) loci via PRF. This scenario evaded due attention because the contribution of non-canonical peptides and proteins to the functional diversity of proteomes is still thought to be minor. Recent studies have challenged this paradigm. To the best of our knowledge, our group was the first to include alternative chimeric sources into the analysis pipeline. This resulted in a much higher certainty about loci responsible for the production of unusual peptides. This certainty is crucial for the functional characterization of such loci. At the same time, our study revealed enormous diversity of potential alternative sources for a subset of MS-supported non-canonical peptides. Here, we present a highly flexible program that predicts alternative chimeric and non-chimeric sources of peptides detected by MS proteomics.

bioinformatics↗

bioRxiv2025

A universal pipeline MosaicProt enables large-scale modeling and detection of chimeric protein sequences for studies on programmed ribosomal frameshifting

Peptides and proteins produced by programmed ribosomal frameshifting (PRF) are well-known in viruses. In non-viral systems, only a few examples of such chimeric sequences have been documented until recently. Two new studies, one in humans and one in plants, showed that chimeric peptides are numerous and diverse. In humans, their discovery was possible due to focusing on sequences with naturally repeated codons. This way, many candidate sequences with mass spectrometry (MS) proteomics-based support for translation have been identified. In the plant study, our group discovered MS-validated chimeric peptides using a unique modeling algorithm, which is described and made available here. Our pipeline enables the identification of chimeric peptides in any organism for which transcript sequences and MS proteomic data are available. By design, our approach does not require prior knowledge about sequence similarity to already characterized PRF sites and can detect forward and backward frameshifts by 1 and 2 nucleotides. Thus, our pipeline opens a path for uncovering previously unknown PRF events across various transcript types, potentially broadening our understanding of proteome diversity.

bioinformatics↗

bioRxiv2023

Machine learning and phylogenetic analysis allow for predicting antibiotic resistance in M. tuberculosis

Antimicrobial resistance (AMR) poses a significant global health threat, and an accurate prediction of bacterial resistance patterns is critical for effective treatment and control strategies. In recent years, machine learning (ML) approaches have emerged as powerful tools for analyzing large-scale bacterial AMR data. However, ML methods often ignore evolutionary relationships among bacterial strains, which can greatly impact performance of the ML methods, especially if resistance-associated features are attempted to be detected. Genomewide association studies (GWAS) methods like linear mixed models accounts for the evolutionary relationships in bacteria, but they uncover only highly significant variants which have already been reported in literature. In this work, we introduce a novel phylogeny-related parallelism score (PRPS), which measures whether a certain feature is correlated with the population structure of a set of samples. We demonstrate that PRPS can be used, in combination with SVM- and random forest-based models, to reduce the number of features in the analysis, while simultaneously increasing models performance. We applied our pipeline to publicly available AMR data from PATRIC database for Mycobacterium tuberculosis against six common antibiotics. Using our pipeline, we re-discovered known resistance-associated mutations as well as new candidate mutations which can be related to resistance and not previously reported in the literature.

bioinformatics↗