Sort by
Refine Your Search
-
Listed
-
Employer
-
Field
-
components in time and space, from single molecules to native tissue environments. The project The industrial PhD student will develop AI and machine learning models to predict drug metabolism, a critical area
-
methods, including modern machine learning methods, to draw inferences from register data. A third project “Integrative machine and deep learning models for predictive analysis in complex disease areas“ is
-
flow phenomena. The goal is to integrate theoretical and experimental fluid dynamics with modern computational tools to analyze and predict multiphase flow behavior. The project also involves applying
-
evaluating designed backbones and predicting the functional effects of protein variants. In addition, the doctoral student will be part of the DDLS initiative, and participate in the DDLS Research School
-
immunity and develop diagnostic approaches that accurately predict therapy benefit and enable successful individualized cancer therapy planning. Contemporary AI-based approaches show great promise to advance
-
or predictive modelling of pathogen biology or host-microbe systems for which multidimensional, genome-scale experimental data are now available or it may use population-scale genetic, clinical, or public health
-
of variation in protein structure and function, using simple measures such as overall hydrophobicity, in addition to modern protein structural prediction techniques. The student will then be responsible
-
in humans and in animal models. Environmental factors have been reported to predict the risks of developing SUDs too. For instance, epidemiological data have shown that impoverished social environments
-
processing conditions. This will enable prediction of health benefits as well as sensory properties as taste and texture attributes. The main objectives of the PhD project are: To systematically characterise
-
clinical prediction of progression remains difficult, leading to over- and undertreatment of women with particularly early breast cancer. Over the past decade, spatial tissue analysis techniques have been