-
to biological challenges, is required. Some degree of experience and understanding of probabilistic modeling and/or deep learning is required, as is a desire to deepen this understanding. The candidate must
-
and accepted to the PhD program at Stockholm University. Project description Project title: “Deep learning modeling of spatial biology data for expression profile-based drug repurposing”. A new exciting
-
the molecular level. While structural predictions using deep learning methods like AlphaFold have revolutionized our understanding of sequence dependent molecular structure, we currently have much more limited
-
data analysis, programming, and biology. You will be part of a collaborative research team with deep experimental and analytical expertise, with access to advanced tumor models and state-of-the-art
-
variability in risk factor susceptibility, treatment response, disease pathogenesis, and clinical diagnosis (biostatistics, machine/deep learning), ii) Investigating causal processes and disease mechanisms
-
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
-
. The long-term goal is to enable targeted interventions for the right individuals, based on their lifestyle, disease trajectories, and molecular profiles. To achieve this, we will apply deep learning models
-
, and will apply deep learning to integrate the analysis flows. The PhD student will develop the method and apply to numerous in-house samples of environmental sequences, pushing the boundaries of RNA
-
information. The techniques include image registration, segmentation, and regression/classification, often include deep learning-base implementations. Together with experts in epidemiology, genetic, and multi
-
in Python programming. Experience with machine learning methods, bioinformatics, and data science. Familiarity with generative AI tools for protein design and protein language models. Knowledge