01/2022 - A Deep Variational Approach to Clustering Survival Data
In this work, we study the problem of clustering survival data — a challenging and so far under-explored task. We introduce a novel semi-supervised probabilistic approach to cluster survival data by leveraging recent advances in stochastic gradient variational inference. In contrast to previous work, our proposed method employs a deep generative model to uncover the […]
01/2022 - Leveraging crosslinking mass spectrometry in structural and cell biology
Crosslinking mass spectrometry (crosslinking-MS) is a versatile tool providing structural insights into protein conformation and protein-protein interactions. Its medium-resolution residue-residue distance restraints have been used to validate protein structures proposed by other methods and have helped derive models of protein complexes by integrative structural biology approaches. The use of crosslinking-MS in integrative approaches is underpinned by […]
01/2022 - Roots of the Malformations of Cortical Development in the Cell Biology of Neural Progenitor Cells
The cerebral cortex is a structure that underlies various brain functions, including cognition and language. Mammalian cerebral cortex starts developing during the embryonic period with the neural progenitor cells generating neurons. Newborn neurons migrate along progenitors’ radial processes from the site of their origin in the germinal zones to the cortical plate, where they mature […]
12/2021 - Novel longitudinal Multiple Overall Toxicity (MOTox) score to quantify adverse events experienced by patients during chemotherapy treatment: a retrospective analysis of the MRC BO06 trial in osteosarcoma
Objectives This study aims at exploring and quantifying multiple types of adverse events (AEs) experienced by patients during cancer treatment. A novel longitudinal score to evaluate the Multiple Overall Toxicity (MOTox) burden is proposed. The MOTox approach investigates the personalised evolution of high overall toxicity (high-MOTox) during the treatment. Design Retrospective analysis of the MRC-BO06/EORTC-80931 randomised controlled […]
12/2021 - Feature selection for imbalanced data with deep sparse autoencoders ensemble
Class imbalance is a common issue in many domain applications of learning algorithms. Oftentimes, in the same domains it is much more relevant to correctly classify and profile minority class observations. This need can be addressed by feature selection (FS), that offers several further advantages, such as decreasing computational costs, aiding inference and interpretability. However, […]
Previous page