Markus Kollmann

The paper investigates circadian rhythms in Synechocystis PCC 6803 under continuous light, finding self-sustained 24-hour oscillations without light-dark cycles.

This work explores creating negative samples for medical image abnormality detection using self-supervised self-distillation, showing improved performance on pneumonia, polyp, and glaucoma detection.

This paper designs bi-stable RNA molecules using deep learning by optimizing sequences through gradient-guided search based on superimposed target structures.

This paper develops an abnormality detection method for pneumonia using self-supervised contrastive learning and Mahalanobis distance scores, outperforming previous unsupervised methods.

This paper introduces a deep learning method to predict RNA 3D structures from sequences, achieving new benchmarks in simulated blind tests.

This paper introduces circular filters for CNNs to improve motif inference from ChIP-seq data by enabling non-truncated and interpretable motif learning.

The paper develops PGExpress, a tool to predict translation efficiency in E. coli using mRNA sequence features, achieving 74% accuracy and 0.81 AUC.