Harald Binder

PEtab Select: specification standard and supporting software for automated model selection

PEtab Select provides a standardized format and software for automated model selection in systems biology, supporting diverse modeling frameworks and enabling efficient evaluation of large model spaces.

Coding agents author interpretable single-cell embedding models from the literature

This paper introduces coding agents that generate interpretable single-cell embeddings from literature-based gene programs without training data or databases.

TACR3 variant confers resilience to aging and Alzheimer's disease

This study identifies the TACR3 variant rs2765 as protective against age- and Alzheimer's-related cognitive decline, showing slower cognitive decline and younger epigenetic age in carriers.

mmContext: an open framework for multimodal contrastive learning of omics and text data

The paper introduces mmContext, a framework for multimodal contrastive learning of omics and text data, and demonstrates its utility in RNA-Seq and text integration tasks.

Synthetic-data augmented calibration for expert-informed rare disease models

This paper introduces a latent-space calibration method for rare disease ODE models using synthetic data, improving parameter recovery and trajectory prediction from sparse clinical observations.

Mapping spatial cell-cell communication programs by tailoring chains of cells for transformer neural networks

The paper introduces scCChain, a transformer-based framework for mapping spatial cell-cell communication programs in spatial transcriptomics data, identifying hotspots at single-cell and spot resolution.

Sparse dimensionality reduction for analyzing single-cell-resolved interactions

The paper introduces a sparse dimensionality reduction workflow for analyzing single-cell cell-cell interactions using the Boosting Autoencoder approach, with a Jupyter notebook for implementation.

Enhancement of network architecture alignment in comparative single-cell studies

This paper proposes a deep learning method to align neural network architectures across species for single-cell data, revealing commonalities and differences in gene expression.

Adding layers of information to scRNA-seq data using pre-trained language models

The paper fine-tunes biomedical language models to integrate text-based knowledge with scRNA-seq data, enhancing cell identity preservation and adding functional and disease-related context.

Evaluating discrepancies in dimensionality reduction for time-series single-cell RNA-sequencing data

The paper evaluates discrepancies in dimensionality reduction techniques for time-series scRNA-seq data using synthetic data and finds that different methods may not reliably represent dynamics when used alone.

Infusing structural assumptions into dimensionality reduction for single-cell RNA sequencing data to identify small gene sets

The paper introduces a boosting autoencoder method to incorporate structural assumptions into dimensionality reduction for single-cell RNA sequencing data, identifying small gene sets that explain latent dimensions.

The performance of deep generative models for learning joint embeddings of single-cell multi-omics data

This study evaluates deep generative models for integrating single-cell multi-omics data across varying sample sizes and provides recommendations for experimental design.

Designing Single-Cell RNA-Sequencing Experiments for Learning Latent Representations

This paper introduces scVIDE, a method to determine statistical power for cell group detection in scRNA-seq data by generating synthetic datasets and using permutation tests.

DOT1L activity affects cell lineage progression in the developing brain by controlling metabolic programs

This study shows that DOT1L activity regulates AP lineage progression in the developing mouse neocortex by controlling metabolic programs and gene expression.

Stratified neural networks in a time-to-event setting

This paper demonstrates that using stratified loss functions in deep learning improves survival prediction in multi-dataset settings by accounting for varying baseline hazards.

Single-cell transcriptomic resolution of stem cells and their developmental trajectories in the hippocampus reveals epigenetic control of cell state perseverance

The paper uses single-cell RNA sequencing to study hippocampal development in DOT1L-mutant mice, identifying distinct neural stem cell populations and their developmental trajectories, revealing DOT1L's role in cell state preservation and hippocampal maturation.

Incorporating structural knowledge into unsupervised deep learning for two-photon imaging data

The paper develops an unsupervised deep learning model for two-photon imaging data that incorporates structural knowledge to improve interpretability and modeling of neural activity.

Making many out of few: deep generative models for single-cell RNA-sequencing data

This study evaluates deep generative models for scRNA-seq data, finding that they can support experimental design but have limitations in capturing cell type proportions and bimodal gene distributions.

ideal: an R/Bioconductor package for Interactive Differential Expression Analysis

The paper introduces the ideal R/Bioconductor package for interactive and reproducible differential expression analysis of RNA-seq data, providing visualization tools and HTML report generation.

Synthetic observations from deep generative models and binary omics data with limited sample size

The paper evaluates generative models for binary omics data with small sample sizes, finding DBMs and VAEs perform better than GANs for recovering pairwise relationships.

pcaExplorer: an R/Bioconductor package for interacting with RNA-seq principal components

pcaExplorer provides an interactive R/Bioconductor tool for RNA-seq PCA analysis, enabling reproducible exploration and visualization of principal components.

Meta-analyses identify differentially expressed microRNAs in Parkinson’s disease

This paper identifies differentially expressed microRNAs in Parkinson’s disease through meta-analyses of multiple datasets, finding significant associations in brain and blood samples.

Unsupervised deep learning on biomedical data with BoltzmannMachines.jl

The paper introduces a Julia package for deep Boltzmann machines to enable unsupervised learning on biomedical data.

PCF11 connects alternative polyadenylation to formation and spontaneous regression of neuroblastoma

The paper identifies PCF11 as a critical regulator of alternative polyadenylation in neuroblastoma, linking it to cell fate reprogramming and spontaneous tumor regression.

A deep learning approach for uncovering lung cancer immunome patterns

This paper uses deep Boltzmann machines to model immune cell gene expression patterns in lung adenocarcinoma, linking hidden nodes to clinical characteristics and immune cell infiltration.

The exon junction complex regulates the release and phosphorylation of paused RNA polymerase II

The paper shows that the pre-EJC regulates RNA polymerase II pausing and prevents premature elongation, with consequences for exon skipping and differentiation.

Cerebral ischemia-induced genes are increased in acute schizophrenia: An opportunity for clinical translation of genomic research findings

The paper identifies cerebral ischemia-induced genes as significantly overexpressed in the frontal cortex of acute schizophrenia patients, supporting the ischemia hypothesis for schizophrenia.

Partitioned learning of deep Boltzmann machines for SNP data

The paper introduces a partitioned learning approach for deep Boltzmann machines to analyze SNP data, showing it can uncover complex SNP patterns and improve survival prediction in acute myeloid lymphoma patients.