Sanne Abeln

SST-MAE: Learning Spectral-Spatio-Temporal Representations from Plant Hyperspectral Time Series to Discover Complex Genotype-Phenotype Relations

DeepPheno: A Deep Learning Framework for Linking Hyperspectral Imaging and SNP Genotypes in Lettuce

DeepPheno links SNP genotypes to hyperspectral imaging in lettuce using deep learning, showing predictive performance for known and novel genotype-phenotype associations.

Beyond the annotated: protein foundation models enable robust prediction of microbial root competence

The paper uses protein foundation models to predict microbial root competence across bacteria, finding that these models outperform traditional methods when predicting traits in evolutionarily distant species.

Condition-dependent, amorphous protein agglomerates control cytoplasmic rheology

The paper shows that protein agglomerates in E. coli regulate cytoplasmic rheology, with diffusion inversely correlating with amino acid metabolism protein abundance.

Comparison of sequence- and structure-based antibody clustering approaches on simulated repertoire sequencing data

This study compares sequence- and structure-based antibody clustering methods on simulated repertoire data, finding structure-based methods identify more multiple-occupancy clusters but have length constraints.

Tumor break load quantitates structural variant-associated genomic instability with biological and clinical relevance across cancers

This study introduces tumor break load (TBL) as a measure of genomic instability across cancers, showing its association with gene expression changes and clinical outcomes.

Data-driven evaluation of suitable immunogens for improved antibody selection

This study evaluates immunogen properties to improve antibody selection by analyzing structural and functional features and developing a tool for applying these insights.

Proteome encoded determinants of protein sorting into extracellular vesicles

This study predicts protein association with extracellular vesicles using sequence-based models and identifies palmitoylation as a key determinant.

PIPENN: Protein Interface Prediction with an Ensemble of Neural Nets

The paper introduces an ensemble of deep learning models (PIPENNs) for predicting protein interface residues, showing improved performance over existing methods across different interaction types.

SeRenDIP-CE: Sequence-based Interface Prediction for Conformational Epitopes

The paper introduces SeRenDIP-CE, a sequence-based method for predicting conformational epitopes, achieving better performance than existing predictors on an antibody-antigen structure.