Biology subjects

Heider, D.

Publications and source records attributed to Heider, D..

15 recordsLinked to original sources

bioRxiv2026

fourSynergy: Ensemble-based interaction calling on 4C-seq data using gradient-free optimization

MotivationChromatin organization plays a crucial role in gene regulation and is associated with various severe diseases like cancer. Since chromatin changes are potentially reversible, a deeper understanding of the alterations needs to be harnessed for the development of new therapies. Circular Chromosome Conformation Capture Sequencing (4C-seq) is a sequencing technique enabling the identification of chromatin interactions between genes and regulatory elements. This work aims to develop an ensemble algorithm that utilizes synergies among available 4C-seq tools, which in turn allows to achieve superior predictive performance in interaction calling. ResultsWe employed existing 4C-seq algorithms using a weighted-voting approach. By optimizing the tool weights according to various predictive metrics using gradient-free optimization strategies, we demonstrate the potential of combining multiple 4C-seq analysis tools for interaction calling. Our results indicate that a weighted-voting based ensemble approach can outperform individual algorithms in various datasets. Although the optimal solutions differ across the 4C-seq datasets, we successfully identified global solutions that outperform the individual algorithms for all datasets analyzed. Availabilityhttps://github.com/sophiewind/fourSynergy, https://github.com/sophiewind/fourSynergy_pip Contactsophie.wind@uni-muenster.de Supplementary informationSupplementary data are available at Journal Name online.

bioinformatics↗

bioRxiv2024

Single cell analysis of Barrett's esophagus and carcinoma reveals cell types conferring risk via genetic predisposition

Inherited genetic variants contribute to Barretts esophagus (BE) and esophageal adenocarcinoma (EAC) but it is unknown which cell types are involved in this process. We performed single cell RNA-sequencing of BE, EAC and paired normal tissues and integrated data of a genome-wide association study to determine cell type-specific genetic risk and cellular processes that contribute to BE and EAC. The analysis revealed that EAC development is driven to a greater extent by local cellular processes than BE development. One cell type of BE origin (BE-EAC) and cellular processes that control the differentiation of columnar cells are of particular relevance for EAC development. Further, specific subtypes of fibroblasts and endothelial cells contribute to BE and EAC development, while dendritic cells and CD4+ memory T cells contribute exclusively to BE development. The diagnostic use of markers characterizing the identified cell types and cellular processes should be explored in future for EAC prediction.

cancer biology↗

bioRxiv2024

gLinDA: global differential abundance analysis ofmicrobiomes

Microbiome composition plays a significant role in various diseases, including cancer, obesity, inflammatory bowel disease, and mental health disorders. Understanding the differences in microbial abundance between patients is key to uncovering the microbiomes impact on these conditions. Differential abundance analysis (DAA) can detect significant changes in microbiomes at the taxa level base. However, since individuals have unique microbial fingerprints that can potentially identify them, microbiome data must be treated as sensitive. We introduce gLinDA, a global differential abundance analysis software offering a swarm learning approach to analyzing distributed datasets while maintaining result accuracy without sharing patients raw data.

bioinformatics↗

bioRxiv2023

Autoturbo-DNA: Turbo-Autoencoders for the DNA data storage channel

DNA, with its high storage density and long-term stability, is a potential candidate for a next-generation storage device. The DNA data storage channel, comprised of synthesis, amplification, storage, and sequencing, exhibits error probabilities and error profiles specific to the components of the channel. Here, we present Autoturbo-DNA, a PyTorch framework for training error-correcting, overcomplete autoencoders specifically tailored for the DNA data storage channel. It allows training different architecture combinations and using a wide variety of channel component models for noise generation during training. It further supports training the encoder to generate DNA sequences that adhere to user-defined constraints.

bioinformatics↗

bioRxiv2023

Ensemble-GNN: federated ensemble learning with graph neural networks for disease module discovery and classification

Federated learning enables collaboration in medicine, where data is scattered across multiple centers without the need to aggregate the data in a central cloud. While, in general, machine learning models can be applied to a wide range of data types, graph neural networks (GNNs) are particularly developed for graphs, which are very common in the biomedical domain. For instance, a patient can be represented by a protein-protein interaction (PPI) network where the nodes contain the patient-specific omics features. Here, we present our Ensemble-GNN software package, which can be used to deploy federated, ensemble-based GNNs in Python. Ensemble-GNN allows to quickly build predictive models utilizing PPI networks consisting of various node features such as gene expression and/or DNA methylation. We exemplary show the results from a public dataset of 981 patients and 8469 genes from the Cancer Genome Atlas (TCGA).

bioinformatics↗

bioRxiv2023

Fetal liver macrophages contribute to the hematopoietic stem cell niche by controlling granulopoiesis

During embryogenesis, the fetal liver becomes the main hematopoietic organ, where stem and progenitor cells as well as immature and mature immune cells form an intricate cellular network. Hematopoietic stem cells (HSCs) reside in a specialized niche, which is essential for their proliferation and differentiation. However, the cellular and molecular determinants contributing to this fetal HSC niche remain largely unknown. Macrophages are the first differentiated hematopoietic cells found in the developing liver, where they are important for fetal erythropoiesis by promoting erythrocyte maturation and phagocytosing expelled nuclei. Yet, whether macrophages play a role in fetal hematopoiesis beyond serving as a niche for maturing erythroblasts remains elusive. Here, we investigate the heterogeneity of macrophage populations in the fetal liver to define their specific roles during hematopoiesis. Using a single-cell omics approach combined with spatial proteomics and genetic fate-mapping models, we found that fetal liver macrophages cluster into distinct yolk sac-derived subpopulations and that long-term HSCs are interacting preferentially with one of the macrophage subpopulations. Fetal livers lacking macrophages show a delay in erythropoiesis and have an increased number of granulocytes, which can be attributed to transcriptional reprogramming and altered differentiation potential of long-term HSCs. Together, our data provide a detailed map of fetal liver macrophage subpopulations and implicate macrophages as part of the fetal HSC niche.

developmental biology↗

bioRxiv2023

ODNA: Identification of Organellar DNA by Machine Learning

MotivationIdentifying organellar DNA, such as mitochondrial or plastid sequences, inside a whole genome assembly, remains challenging and requires biological background knowledge. To address this, we developed ODNA based on genome annotation and machine learning to fulfill. ResultsODNA is a software that performs organellar DNA sequence classification of a genome assembly by machine learning based on a pre-defined genome annotation workflow. We trained our model with 829,769 DNA sequences from 405 genome assemblies and achieved very high predictive performance (e.g., MCC of 0.61) on independent validation data, thus outperforming existing approaches significantly. AvailabilityOur software ODNA is freely accessible as a web service at https://odna.mathematik.uni-marburg.de and can also be run in a docker container. The source code can be found at https://gitlab.com/mosga/odna and the processed data at Zenodo (DOI: 10.5281/zenodo.7506483).

bioinformatics↗

bioRxiv2022

Unsupervised encoding selection through ensemble pruning for biomedical classification

BackgroundOwing to the rising levels of multi-resistant pathogens, antimicrobial peptides, an alternative strategy to classic antibiotics, got more attention. A crucial part is thereby the costly identification and validation. With the ever-growing amount of annotated peptides, researchers leverage artificial intelligence to circumvent the cumbersome, wet-lab-based identification and automate the detection of promising candidates. However, the prediction of a peptides function is not limited to antimicrobial efficiency. To date, multiple studies successfully classified additional properties, e.g., antiviral or cell-penetrating effects. In this light, ensemble classifiers are employed aiming to further improve the prediction. Although we recently presented a workflow to significantly diminish the initial encoding choice, an entire unsupervised encoding selection, considering various machine learning models, is still lacking. ResultsWe developed a workflow, automatically selecting encodings and generating classifier ensembles by employing sophisticated pruning methods. We observed that the Pareto frontier pruning is a good method to create encoding ensembles for the datasets at hand. In addition, encodings combined with the Decision Tree classifier as the base model are often superior. However, our results also demonstrate that none of the ensemble building techniques is outstanding for all datasets. ConclusionThe workflow conducts multiple pruning methods to evaluate ensemble classifiers composed from a wide range of peptide encodings and base models. Consequently, researchers can use the workflow for unsupervised encoding selection and ensemble creation. Ultimately, the extensible workflow can be used as a plugin for the PEPTIDE REACToR, further establishing it as a versatile tool in the domain.

bioinformatics↗

bioRxiv2021

The relationship between land cover and microbial community composition in European lakes

Microbes such as bacteria, archaea, and protists are essential for element cycling and ecosystem functioning, but many questions central to the understanding of the role of microbes in ecology are still open. Here, we analyze the relationship between lake microbiomes and the land cover surrounding the lakes. By applying machine learning methods, we quantify the covariance between land cover categories and the microbial community composition recorded in the largest amplicon sequencing dataset of European lakes available to date. We identify microbial bioindicators for these land cover categories. Combining land cover and physico-chemical bioindicators identified from the same amplicon sequencing dataset, we develop two novel similarity metrics that facilitate insights into the ecology of the lake microbiome. We show that the bioindicator network, i.e., the graph linking OTUs indicative of the same environmental parameters, corresponds to microbial co-occurrence patterns. Taken together, we demonstrate the strength of machine learning approaches to identify correlations between microbial diversity and environmental factors, potentially opening new approaches to integrate environmental molecular diversity into monitoring and water quality assessments.

ecology↗

bioRxiv2021

MOSGA 2: Comparative genomics and validation tools

Due to the highly growing number of available genomic information, the need for accessible and easy-to-use analysis tools is increasing. To facilitate eukaryotic genome annotations, we created MOSGA. In this work, we show how MOSGA 2 is developed by including several advanced analyses for genomic data. Since the genomic data quality greatly impacts the annotation quality, we included multiple tools to validate and ensure high-quality user-submitted genome assemblies. Moreover, thanks to the integration of comparative genomics methods, users can benefit from a broader genomic view by analyzing multiple genomic data sets simultaneously. Further, we demonstrate the new functionalities of MOSGA 2 by different use-cases and practical examples. MOSGA 2 extends the already established application to the quality control of the genomic data and inte-grates and analyzes multiple genomes in a larger context, e.g., by phylogenetics.

bioinformatics↗

bioRxiv2021

Transfer Learning Compensates Limited Data, Batch-Effects, And Technical Heterogeneity In Single-Cell Sequencing

AO_SCPLOWBSTRACTC_SCPLOWTremendous advances in next-generation sequencing technology have enabled the accumulation of large amounts of omics data in various research areas over the past decade. However, study limitations due to small sample sizes, especially in rare disease clinical research, technological heterogeneity, and batch effects limit the applicability of traditional statistics and machine learning analysis. Here, we present a meta-learning approach to transfer knowledge from big data and reduce the search space in data with small sample sizes. Few-shot learning algorithms integrate meta-learning to overcome data scarcity and data heterogeneity by transferring molecular pattern recognition models from datasets of unrelated domains. We explore few-shot learning models with large scale public dataset, TCGA (The Cancer Genome Atlas) and GTEx dataset, and demonstrate their potential as meta-learning dataset in other molecular pattern recognition tasks. Our results show that transfer learning is very effective for datasets with a limited sample size. Furthermore, we show that our approach can transfer knowledge across technological heterogeneity, e.g., from bulk cell to single-cell data. Our approach can overcome study size constraints, batch effects, and technological limitations in analyzing single-cell data by leveraging existing bulk-cell sequencing data.

bioinformatics↗

bioRxiv2020

Natrix: A Snakemake-based workflow for processing, clustering, and taxonomically assigning amplicon sequencing reads

Sequencing of marker genes amplified from environmental samples, known as amplicon sequencing, allows us to resolve some of the hidden diversity and elucidate evolutionary relationships and ecological processes among complex microbial communities. The analysis of large numbers of samples at high sequencing depths generated by high throughput sequencing technologies requires effcient, flexible, and reproducible bioinformatics pipelines. Only a few existing workflows can be run in a user-friendly, scalable, and reproducible manner on different computing devices using an effcient workflow management system. We present Natrix, an open-source bioinformatics workflow for preprocessing raw amplicon sequencing data. The workflow contains all analysis steps from quality assessment, read assembly, dereplication, chimera detection, split-sample merging, sequence representative assignment (OTUs or ASVs) to the taxonomic assignment of sequence representatives. The workflow is written using Snakemake, a workflow management engine for developing data analysis workflows. In addition, Conda is used for version control. Thus, Snakemake ensures reproducibility and Conda offers version control of the utilized programs. The encapsulation of rules and their dependencies support hassle-free sharing of rules between workflows and easy adaptation and extension of existing workflows. Natrix is freely available on GitHub (https://github.com/MW55/Natrix).

bioinformatics↗

bioRxiv2019

Four high-quality draft genome assemblies of the marine heterotrophic nanoflagellate Cafeteria roenbergensis

The heterotrophic stramenopile Cafeteria roenbergensis is a globally distributed marine bacterivorous protist. This unicellular flagellate is host to the giant DNA virus CroV and the virophage mavirus. We sequenced the genomes of four cultured C. roenbergensis strains and generated 23.53 Gb of Illumina MiSeq data (99-282 x coverage per strain) and 5.09 Gb of PacBio RSII data (13-54 x coverage). Using the Canu assembler and customized curation procedures, we obtained high-quality draft genome assemblies with a total length of 34-36 Mbp per strain and contig N50 lengths of 148 kbp to 464 kbp. The C. roenbergensis genome has a GC content of ~70%, a repeat content of ~28%, and is predicted to contain approximately 7857-8483 protein-coding genes based on a combination of de novo, homology-based and transcriptome-supported annotation. These first high-quality genome assemblies of a Bicosoecid fill an important gap in sequenced Stramenopile representatives and enable a more detailed evolutionary analysis of heterotrophic protists.

genomics↗

bioRxiv2019

γBOriS: Identification of Origins of Replication in Gammaproteobacteria using Motif-based Machine Learning

The biology of bacterial cells is, in general, based on the information encoded on circular chromosomes. Regulation of chromosome replication is an essential process which mostly takes place at the origin of replication (oriC). Identification of high numbers of oriC is a prerequisite to enable systematic studies that could lead to insights of oriC functioning as well as novel drug targets for antibiotic development. Current methods for identyfing oriC sequences rely on chromosome-wide nucleotide disparities and are therefore limited to fully sequenced genomes, leaving a superabundance of genomic fragments unstudied. Here, we present{gamma} BOriS (Gammaproteobacterial oriC Searcher), which accurately identifies oriC sequences on gammaproteobacterial chromosomal fragments by employing motif-based DNA classification. Using{gamma} BOriS, we created BOriS DB, which currently contains 25,827 oriC sequences from 1,217 species, thus making it the largest available database for oriC sequences to date.

bioinformatics↗

bioRxiv2019

Deep Learning on Chaos Game Representation for Proteins

Classification of protein sequences is one big task in bioinformatics and has many applications. Different machine learning methods exist and are applied on these problems, such as support vector machines (SVM), random forests (RF), and neural networks (NN). All of these methods have in common that protein sequences have to be made machine-readable and comparable in the first step, for which different encodings exist. These encodings are typically based on physical or chemical properties of the sequence. However, due to the outstanding performance of deep neural networks (DNN) on image recognition, we used frequency matrix chaos game representation (FCGR) for encoding of protein sequences into images. In this study, we compare the performance of SVMs, RFs, and DNNs, trained on FCGR encoded protein sequences. While the original chaos game representation (CGR) has been used mainly for genome sequence encoding and classification, we modified it to work also for protein sequences, resulting in n-flakes representation, an image with several icosagons.\n\nWe could show that all applied machine learning techniques (RF, SVM, and DNN) show promising results compared to the state-of-the-art methods on our benchmark datasets, with DNNs outperforming the other methods and that FCGR is a promising new encoding method for protein sequences.

bioinformatics↗