Moritz Hess

This paper introduces a latent-space calibration method for rare disease ODE models using synthetic data, improving parameter recovery and trajectory prediction from sparse clinical observations.

The paper introduces 1100 synthetic benchmark problems for dynamic cellular process modeling to improve algorithm evaluation.

This paper demonstrates that using stratified loss functions in deep learning improves survival prediction in multi-dataset settings by accounting for varying baseline hazards.

This study evaluates deep generative models for scRNA-seq data, finding that they can support experimental design but have limitations in capturing cell type proportions and bimodal gene distributions.

The paper evaluates generative models for binary omics data with small sample sizes, finding DBMs and VAEs perform better than GANs for recovering pairwise relationships.

The paper introduces a Julia package for deep Boltzmann machines to enable unsupervised learning on biomedical data.

This paper uses deep Boltzmann machines to model immune cell gene expression patterns in lung adenocarcinoma, linking hidden nodes to clinical characteristics and immune cell infiltration.

The paper identifies cerebral ischemia-induced genes as significantly overexpressed in the frontal cortex of acute schizophrenia patients, supporting the ischemia hypothesis for schizophrenia.

The paper introduces a partitioned learning approach for deep Boltzmann machines to analyze SNP data, showing it can uncover complex SNP patterns and improve survival prediction in acute myeloid lymphoma patients.