Machine Learning in Oncology
Our mission is the application and collaboration driven development of interpretable and statistically sound machine learning methods for understanding disease heterogeneity. As part of the DKTK/DKFZ and hosted by Frankfurt University we thrive to use machine learning for accelerating progress in personalised oncology.
We build on probabilistic machine learning to address computational challenges in three areas: translational single-cell genomics, computational proteomics and the integration of multi-omics data.
Machine Learning (ML), Precision Oncology, Multi-omics data integration
Machine learning, Bioinformatics, Probabilistic modeling, Metric learning, Omics data analysis
Calibration, Out-of-domain Generalization, Hyperparameter Optimization
Probabilistic Machine Learning, Multi-omics Data Integration, Survival Analysis
Mixture of Factor Analyzers with Informative Priors for Explaining Latent Clusters in Biomedical Applications
Post-hoc Uncertainty Calibration of Neural Networks via Kernel Density Estimation
Machine Learning (ML), Deep Learning, Probabilistic Modeling
Encoding Pathway Gene Sets with Sparse Priors for Inferring Explainable Latent Variables
Simulation and Evaluation of Distribution Shifts on Tumor Images
Hidden Functional Activity in JOANA
In the summer term 2021 we offered Introduction to AI, have a look at the Vorlesungsvereichnis here.
In the winter term 2021/2022 we offer a seminar on AI in Medicine. Please contact me directly if you are interested/have any questions. Further information will be provided via moodle: https://moodle.studiumdigitale.uni-frankfurt.de/moodle/course/view.php?id=2046. The course is now open for self-registration - please only register in moodle if you are assigned to this seminar.
We are always interested in talented MSc and BSc students interested in machine learning for genomics data and offer topics for MSc theses and BSc theses. If you’re interested, just contact us and we’ll have an informal chat!