Gary D. Bader

This study shows adversarial training improves robustness and interpretability in single-cell RNA-seq cell type classification models.

Fatecode predicts cell fate regulators using scRNA-seq data and deep learning, identifying known master regulators in blood and brain development datasets.

The paper uses single-cell transcriptomics to compare strain-specific differences in myeloid inflammatory potential in healthy rat livers, revealing strain-specific variations in inflammatory signaling pathways.

The paper maps neuron-specific protein networks of autism risk genes, identifies shared biological mechanisms, and links them to disease-relevant pathologies.

BIONIC integrates biological networks using deep learning to improve accuracy and scalability, identifying novel gene interactions in yeast.

This study creates a single-cell atlas of human liver development, identifying pathways and factors that guide hepatic cell fates and improving hepatocyte-like cell functionality.

The paper introduces Biofactoid, a tool that crowdsources structured biological knowledge from authors, enabling efficient human-computer interaction and expanding existing pathway databases.

The paper constructs a molecular atlas of the human brain vasculature using single-cell RNA sequencing, revealing molecular heterogeneity and disease-related alterations in vascular cells.

The paper examines whether ligand-receptor interactions have consistent transcriptional signatures across cell types and finds they are highly context-dependent.

The paper shows cell cycle duration influences gene expression and cell fate by acting as a transcriptional filter, supported by simulations and single-cell RNA-seq data.

The paper identifies a genetic variant in FBLN1 associated with nonverbal reasoning and links it to pathways, cell types, and diseases involved in cognition.

The paper introduces SBGN bricks and their ontology to provide structured semantics for recurring molecular network concepts, enabling better annotation and construction of molecular maps.

The paper constructs a single-cell atlas of SARS-CoV-2 entry factors and interaction partners in human and mouse brain vasculature, revealing distinct expression patterns of CTSB and CTSL in brain and peripheral vasculature.

Tempora infers cell trajectories from time-series scRNA-seq data, outperforming existing methods in human and mouse developmental processes.

The paper introduces the Cancer LncRNA Census (CLC), a curated resource of lncRNAs with causative roles in cancer, and shows their genomic and evolutionary features.

This study identifies germline genetic variants influencing somatic mutation patterns in 2,642 cancer genomes across 39 cancer types.

This study characterizes mitochondrial genomes in 2,700 cancer patients across 37 types using whole-genome sequencing and RNA-seq, revealing mutational patterns, truncating mutations, and nuclear transfer of mitochondrial DNA.

ActivePathways integrates multivariate omics data to identify enriched pathways, revealing cancer driver genes and prognostic pathways in breast cancer.

Pathway Commons updates its resource with integrated pathway data, tools, and software for biological pathway analysis.

This study uses single-cell transcriptomics to analyze aged mouse brains, identifying cell-type-specific aging signatures and highlighting molecular processes like ribosomal biogenesis.

The paper evaluates methods to improve generalization of deep learning models for biomedical named entity recognition (BioNER) and introduces an open-source tool for the task.

The paper presents HuRI, a comprehensive human protein-protein interaction map, and demonstrates its utility in understanding cellular function and disease mechanisms.

This study benchmarks four methods for assigning cell type labels to cell clusters in scRNA-seq data, showing high performance but variability in precision-recall across methods and datasets.

This paper introduces the Generalized Berk-Jones statistic for gene set analysis in GWAS, showing it increases power by incorporating multiple signals per gene and addressing confounding from gene set lists.

netDx is a supervised patient classification framework that integrates diverse data types and provides interpretable results, showing high performance in cancer survival prediction.

Step-by-step protocol for interpreting omics gene lists via g:Profiler or GSEA enrichment testing, then grouping redundant enriched pathways into themes with Cytoscape Enrichment Map.

This paper shows transfer learning improves biomedical named entity recognition by training a neural network on a large noisy dataset and fine-tuning it on a smaller reliable dataset.

This paper introduces DNF, a computational framework that classifies new drugs by integrating structural, perturbation, and sensitivity data to infer drug relationships and taxonomies.

This study identifies ARGLU1 as a glucocorticoid receptor coactivator and splicing modulator, showing its role in stress hormone signaling and brain development through genetic and transcriptomic analyses.