Ole Lund

This paper introduces a downsampling method for bacterial genomes using k-mer representations, showing that ensemble models outperform deep learning on phenotype prediction tasks.

This paper presents a weakly supervised deep learning approach for breast cancer molecular subtyping using tile-level pathology images without tumor annotations, achieving high accuracy and interpretability.

MAGinator quantifies strain-level abundance of metagenome-assembled genomes and infers their functional and phylogenetic profiles from shotgun metagenomics data.

The paper introduces a deep learning framework for polygenic risk score prediction, showing improved performance over traditional methods for various diseases.

This study uses deep learning to predict blood and urine biomarkers from genetic data, outperforming linear methods and capturing non-linear and epistatic effects.

This paper develops a random forest model to predict plasmid hosts, achieving 0.662 and 0.867 Matthews correlation coefficients at species and order levels, respectively.

MINTyper is a SNP typing method that clusters DNA isolates using a mix of short and long reads, showing accurate clustering even with lower-quality long reads.

CCMetagen improves metagenomic classification by using weighted read mappings, outperforming existing tools in precision and F1 scores for species-level identification.

The paper introduces a bioinformatics pipeline for rapid phylogenomic analysis of bacterial whole-genome isolates, enabling large-scale surveillance and real-time outbreak detection.

This paper demonstrates that malaria rapid diagnostic tests can be used for large-scale molecular surveillance of antimalarial resistance markers using next-generation sequencing.

The paper describes an informatics platform for structured data storage and pre-publication sharing of pathogen sequencing data with stakeholders.

KmerFinderJS improves bacterial species typing by reducing data transfer and increasing speed over slow internet connections.