Biology subjects

Turewicz, M.

Publications and source records attributed to Turewicz, M..

4 recordsLinked to original sources

bioRxiv2026

DLDN-Bench: A Benchmark Framework for Deep Learning de Novo Peptide Sequencing in Proteomics

De novo peptide sequencing is an essential approach for analyzing mass spectrometry data because it enables the identification of novel peptides without relying on protein sequence databases. Recent advances in deep learning have substantially improved the performance of de novo sequencing methods, but the rapid emergence of new models has led to heterogeneous evaluation practices and limited comparability. To address this, we introduce DLDN-Bench, a benchmark framework including a set of benchmark datasets derived from human muscle biopsy mass spectrometry data retrieved from PRIDE and annotated through consensus across multiple widely used database search engines. Using these datasets, we systematically benchmark recent deep learning-based de novo sequencing tools alongside traditional approaches. Performance is assessed using established metrics, including precision and coverage relative to a pseudo-ground truth defined by cross-engine agreement. To demonstrate the utility of DLDN-Bench, we benchmark four recent deep learning models and make all results publicly available. This benchmark framework provides a standardized basis for comparing state-of-the-art methods and offers an extensible resource for evaluating future tools in de novo peptide sequencing. Code availabilityhttps://github.com/ddz-icb/DLDN-Bench Data availabilityhttps://doi.org/10.5281/zenodo.19627459

bioinformatics↗

bioRxiv2021

GoMi - A new gold standard corpus for miRNA Named Entity Recognition to test dictionary, rule-based and machine-learning approaches.

Biomarkers have been the focus of research for more than 30 years [REF1]. Paone et al. were among the first scientists to use the term biomarker in the course of a comparative study dealing with breast carcinoma [REF2]. In recent years, in addition to proteins and genes, miRNA or micro RNAs, which play an essential role in gene expression, have gained increased interest as valuable biomarkers. As a result, more and more information on miRNA biomarkers can be extracted via text mining approaches from the increasing amount of scientific literature. In the late 1990s the recognition of specific terms in biomedical texts has become a focus of bioinformatic research to automatically extract knowledge out of the increasing number of publications. For this, amongst other methods, machine learning algorithms are applied. However, the recognition (classification) capability of terms by machine learning or rule based algorithms depends on their correct and reproducible training and development. In the case of machine learning-based algorithms the quality of the available training and test data is crucial. The algorithms have to be tested and trained with curated and trustable data sets, the so-called gold or silver standards. Gold standards are text corpora, which are annotated by expertes, whereby silver standards are curated automatically by other algorithms. Training and calibration of neural networks is based on such corpora. In the literature there are some silver standards with approx. 500,000 tokens [REF3]. Also there are already published gold standards for species, genes, proteins or diseases. However, there is no corpus that has been generated specifically for miRNA. To close this gap, we have generated GoMi, a novel and manually curated gold standard corpus for miRNA. GoMi can be directly used to train ML-methods to calibrate or test different algorithms based on the rule-based approach or dictionary-based approach. The GoMi gold standard corpus was created using publicly available PubMed abstracts. GoMi can be downloaded here: https://github.com/mpc-bioinformatics/mirnaGS---GoMi.

bioinformatics↗

bioRxiv2021

Characterization of peptide-protein relationships in protein ambiguity groups via bipartite graphs

In bottom-up proteomics, proteins are enzymatically digested into peptides before measurement with mass spectrometry. The relationship between proteins and their corresponding peptides can be represented by bipartite graphs. We conduct a comprehensive analysis of bipartite graphs using quantified peptides from measured data sets as well as theoretical peptides from an in silico digestion of the corresponding complete taxonomic protein sequence databases. The aim of this study is to characterize and structure the different types of graphs that occur and to compare them between data sets. We observed a large influence of the accepted minimum peptide length during in silico digestion. When changing from theoretical peptides to measured ones, the graph structures are subject to two opposite effects. On the one hand, the graphs based on measured peptides are on average smaller and less complex compared to graphs using theoretical peptides. On the other hand, the proportion of protein nodes without unique peptides, which are a complicated case for protein inference and quantification, is considerably larger for measured data. Additionally, the proportion of graphs containing at least one protein node without unique peptides rises when going from database to quantitative level. The fraction of shared peptides and proteins without unique peptides as well as the complexity and size of the graphs highly depends on the data set and organism. Large differences between the structures of bipartite peptide-protein graphs have been observed between database and quantitative level as well as between analyzed species. In the analyzed measured data sets, the proportion of protein nodes without unique peptides ranged from 6.4% to 55.0%. This highlights the need for novel methods that can quantify proteins without unique peptides. The knowledge about the structure of the bipartite peptide-protein graphs gained in this study will be useful for the development of such algorithms.

bioinformatics↗

bioRxiv2021

A proteomics sample metadata representation for multiomics integration, and big data analysis.

The amount of public proteomics data is increasing at an extraordinary rate. Hundreds of datasets are submitted each month to ProteomeXchange repositories, representing many types of proteomics studies, focusing on different aspects such as quantitative experiments, post-translational modifications, protein-protein interactions, or subcellular localization, among many others. For every proteomics dataset, two levels of data are captured: the dataset description, and the data files (encoded in different file formats). Whereas the dataset description and data file formats are supported by all ProteomeXchange partner repositories, there is no standardized format to properly describe the sample metadata and their relationship with the dataset files in a way that fully allows their understanding or re-analysis. It is left to the users choice whether to provide or not an ad hoc document containing this information. Therefore, in many cases, understanding the study design and data requires going back to the associated publication. This can be tedious and may be restricted in the case of non-open access publications. In many cases, this problem limits the generalization and reuse of public proteomics data. Here we present a standard representation for sample metadata tailored to proteomics datasets produced by the HUPO Proteomics Standards Initiative and supported by ProteomeXchange resources. We repurposed the existing data format MAGE-TAB used routinely in the transcriptomics field to represent and annotate proteomics datasets. MAGETAB-Proteomics defines a set of annotation rules that the datasets submitted to ProteomeXchange should follow, ranging from sample properties to data analysis protocols. We also introduce a crowdsourcing project that enabled the manual curation of over 200 public datasets using MAGE-TAB-Proteomics. In addition, we describe an ecosystem of tools and libraries that were developed to validate and submit sample metadata-related information to ProteomeXchange. We expect that these tools will improve the reproducibility of published results and facilitate the reanalysis and integration of public proteomics datasets.

bioinformatics↗