Tim Beißbarth

Benchmarking the Intratumoral Microbiome in Pancreatic Ductal Adenocarcinoma: A Longitudinal Assessment of Contamination Sources and Decontamination Strategies

This study benchmarks decontamination methods for intratumoral microbiome analysis in PDAC, finding the Nj pipeline outperforms others in reducing contamination while preserving tumor signals.

A Comparative Survey of Functional Evidence Use in Hearing and Vision Loss Genetics

The paper surveys genetics professionals on their use of functional evidence in variant classification for hearing and vision loss, highlighting challenges in data quality, accessibility, and integration into clinical practice.

FusionPath: Gene fusion pathogenicity prediction using protein structural data and contextual protein embeddings

FusionPath predicts gene fusion pathogenicity using protein structural data and contextual embeddings, outperforming existing methods with AUC scores of 0.95 and 0.87.

HIDE: Hierarchical cell-type Deconvolution

HIDE improves cell-type deconvolution by incorporating a cell hierarchy, showing better performance in simulations and applied to breast cancer data.

TCRanalyzer: A user-friendly tool for comprehensive analysis of T-cell diversity, dynamics and potential antigen targets

TCRanalyzer provides a user-friendly tool for analyzing TCR diversity, clonal expansion, and antigen specificity across tumor datasets.

DynaMiCs - Dynamic cell-type deconvolution ensembles for Mapping in mixed Conditions

DynaMiCs integrates single-cell and bulk transcriptomics data to improve cell-type deconvolution and map population changes between phenotypes.

DNA-binding domain-aware classification enables systematic annotation of the regulatory genome

TFClassPredict is a DNABERT-based framework that classifies DNA-binding domains to annotate regulatory elements, outperforming existing methods and enabling lineage-specific TF program reconstruction.

Deconvolution of omics data in Python with Deconomix -- cellular compositions, cell-type specific gene regulation, and background contributions

Deconomix deconvolves bulk transcriptomics data to estimate cell compositions, background contributions, and cell-type-specific gene regulation.

Deciphering BRCAness Phenotype in Cancer: A Graph Convolutional Neural Network Approach with Layer-wise Relevance Propagation Analysis

The paper uses graph convolutional neural networks with layer-wise relevance propagation to analyze gene expression data and identify genes and pathways associated with BRCAness, outperforming traditional methods.

The importance of DNA sequence for nucleosome positioning in transcriptional regulation

The paper evaluates the role of DNA sequence in nucleosome positioning during transcription and identifies sequence-intrinsic factors that influence nucleosome stability and competition with cis-regulatory elements.

CODEX: COunterfactual Deep learning for the in-silico EXploration of cancer cell line perturbations

CODEX models causal effects of perturbations on cancer cell lines using counterfactual reasoning, enabling in-silico exploration of drug combinations and genetic modifications.

Adaptive Digital Tissue Deconvolution

ADTD improves estimation of cellular compositions from bulk transcriptomics data by adapting reference profiles to the molecular environment and identifying hidden contributions.

Stability of feature selection utilizing Graph Convolutional Neural Network and Layer-wise Relevance Propagation

The paper evaluates the stability of feature selection using GCNN+LRP and GCNN+SHAP for gene expression data, comparing them to classical ML methods.

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

Ensemble-GNN enables federated, ensemble-based graph neural networks for disease module discovery using patient-specific PPI networks and omics data.

Adaptation of Graph Convolutional Neural Networks and Graph Layer-wise Relevance Propagation to the Spektral library with application to gene expression data of Colorectal Cancer patients

The paper adapts graph convolutional neural networks and graph layer-wise relevance propagation to the Spektral library for analyzing gene expression data from colorectal cancer patients, identifying relevant genes and subnetworks.

SpaCeNet: Spatial Cellular Networks from omics data

SpaCeNet identifies intracellular and intercellular molecular networks from spatial omics data by analyzing conditional independence relations between variables within and across cells.

Explaining decisions of Graph Convolutional Neural Networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer

The paper introduces GLRP, a method to explain Graph-CNN decisions in breast cancer metastasis prediction, identifying patient-specific molecular subnetworks that align with clinical knowledge.

Text mining-based word representations for biomedical data analysis and machine learning tasks

The paper develops word2vec-based embeddings from PubMed abstracts to capture biological relationships and improves metastatic event prediction using graph convolutional networks.

NERO: A Biomedical Named-entity (Recognition) Ontology with a Large, Annotated Corpus Reveals Meaningful Associations Through Text Embedding

This paper introduces NERO, a biomedical named-entity ontology with an annotated corpus, and demonstrates its utility through text embedding for discovering associations.