Lars Juhl Jensen

SLIM predicts single-cell genetic perturbation responses using STRING embeddings and a closed-form ridge regression model, achieving competitive accuracy with low computational cost.

The paper constructs disease maps by integrating omics data with protein network embeddings, identifying more disease-relevant proteins than omics analysis alone.

PlasMAAG improves plasmid reconstruction from metagenomics data using assembly-alignment graphs and contrastive learning, outperforming existing methods in accuracy and efficiency.

ProteoBench provides a centralized platform for comparing proteomics data analysis workflows, enabling benchmarking and community collaboration.

The paper constructs a single-cell transcriptomic atlas of the human dorsolateral prefrontal cortex across neurodegenerative and neuropsychiatric diseases, revealing shared and distinct molecular mechanisms.

This study uses a ubiquitin replacement strategy to show K29-linked ubiquitylation regulates SUV39H1 stability and H3K9me3 levels in human cells.

The paper develops cross-species protein embeddings using network data and shows they improve subcellular localization and function prediction when combined with sequence embeddings.

The paper analyzes the DNA sequence and methylome of Jonathan, a 192-year-old giant tortoise, to identify epigenomic features associated with extreme longevity.

The paper develops a proteomics method to identify drug targets across the proteome, revealing organ-specific interactions and global drug effects.

The paper develops a Lifestyle Factor Ontology and annotated corpus for detecting lifestyle factors in biomedical texts, achieving 76% F-score with a transformer-based NER system.

The paper introduces a manually annotated corpus and a relation extraction model to identify physical protein interactions from biomedical literature, integrating results into the STRING database.

This paper introduces a deep learning method for imputing missing values in label-free quantitative proteomics data and shows its effectiveness in identifying differentially abundant proteins in alcohol-related liver disease.

The paper improves dictionary-based named entity recognition by using a Transformer model to automatically generate block lists, increasing precision in text mining.

The paper identifies 14,056 citrullination sites across 4,008 proteins using mass spectrometry, revealing widespread citrullination and its functional roles in histone marks and autoantigens.

FAVA infers high-quality functional protein interaction networks from scRNA-seq and proteomics data, outperforming existing methods and identifying interactions for understudied proteins.

This paper introduces a high-resolution spatial transcriptomics technology for mouse liver analysis, achieving 2 micrometer resolution and demonstrating significant advancements in spatial sequencing.

The paper introduces CoNECo, a corpus for NER and NEN of protein complexes, achieving F1-scores of 73.7% and 61.2% with transformer-based and dictionary-based taggers, respectively.

RegulaTome provides a comprehensive corpus of biomedical relations, enabling improved relation extraction with a Transformer model achieving 66.6% F1-score.

The paper introduces S1000, a new corpus for species name recognition in biomedical text, achieving high accuracy with both deep learning and dictionary-based methods.

This study identifies periosteal nerve sprouting and DRG metastasis in MM-induced bone pain, linking these changes to pain mechanisms and suggesting neuroprotective strategies.

TransporterPAL predicts transporters for compounds by integrating biosynthetic gene and transporter interaction data from public databases.

U-CIE encodes high-dimensional data as colors using UMAP and CIELAB to preserve structure for visualization.

Arena3Dweb provides an interactive 3D visualization tool for multi-layered networks with clustering, directional connections, and integration capabilities.

The paper presents a workflow for integrating diverse datasets to build a network pharmacology resource for COVID-19 research, resulting in a Neo4j graph database named Neo4COVID19.

DISEASES 2.0 updates a disease-gene association database by integrating text mining, curated data, and GWAS, increasing text-mined associations by 9-fold.

The paper investigates light-induced left-right asymmetries in the chick retina, finding transient gene expression changes and links to vascular and extracellular matrix pathways.

OnTheFly2.0 automates biomedical entity recognition and analysis from documents, revealing inflammatory and senescence pathways in severe COVID-19.

TIGA aggregates and ranks gene-trait associations from GWAS data to prioritize drug targets using statistical and bibliometric evidence.

This paper introduces a deep learning method using variational autoencoders to improve microbial genome binning from metagenomic data, achieving higher precision and completeness in reconstructed bins.

The paper identifies 51 differentially regulated genes in UC colon and blood by comparing a DSS-UC mouse model with human UC data, suggesting biomarkers and therapeutic targets.