T. Andermann

Estimating alpha, beta, and gamma diversity through deep learning

This paper develops a deep learning method to estimate alpha, beta, and gamma plant diversity by predicting species richness from spatial variables, without requiring individual species range mapping.

The evolution of open habitats in North America revealed by deep learning models

This paper uses a deep learning model to reconstruct the evolution of open habitats in North America, finding they originated 25-20 Ma and expanded rapidly starting 8 Ma.

IUCNN - deep learning approaches to approximate species' extinction risk

IUCNN uses deep learning to predict species' extinction risk from occurrence data, outperforming existing methods on orchid datasets.

Rare transmission of commensal and pathogenic bacteria in the gut microbiome of hospitalized adults

This study identifies potential bacterial transmission between hospitalized HCT patients through metagenomic sequencing, finding shared strains in some pairs but not widespread colonization.

iucn_sim: A new program to simulate future extinctions based on IUCN threat status

The paper introduces a software tool to simulate future species extinctions using IUCN threat status and generation length data, predicting bird extinction rates and biodiversity loss over 100 years.

Combined use of metagenomic sequencing and host response profiling for the diagnosis of suspected sepsis.

This study combines metagenomic sequencing and host response profiling to improve sepsis diagnosis by detecting pathogens and guiding clinical decisions.

Allele Phasing Greatly Improves the Phylogenetic Utility of Ultraconserved Elements

This paper develops a pipeline to recover allele sequences from sequence capture data and shows that phased allele sequences improve phylogenetic accuracy compared to contig sequences.