mcfly
Helps you find a suitable neural network configuration for deep learning on time series.
Identification and prioritization of cancer-causing structural variations in whole genomes
Cancer affects millions of people worldwide. With the advent of novel DNA sequencing technologies, genome sequencing has now started to become part of a routine workflow for cancer diagnostics and potentially enables fine-tuned treatment strategies tailored towards individual cancer patients. In spite of the massive genomic data production, systematic and comprehensive analysis of these data, in particular regarding the detection and interpretation of structural variation, are lagging behind due to computational and algorithmic limitations.
In this project, we will create novel analytical and computational frameworks that lead to fast, cost-efficient and comprehensive detection and annotation of structural variations in cancer genomes. We particularly focus on previously neglected variations occurring in unexplored regions of the cancer genome. Our methods will serve as an important component in future genome-first-based clinical-decision making for cancer patients and is essential to drive discovery of novel cancer genes and mechanism from modern-day whole genome sequencing data.
Sharing TADPOLE’s algorithms for reuse and evaluation
Advancing our understanding of molecular mechanisms of health and disease
Scoring 3D protein-protein interaction models using deep learning
Deep learning algorithms for more accurate implants
Vast amounts of data to improve cancer treatment decisions
Gaining insights from wearable movement sensors
Prediction models based on EEG characteristics
Combining molecular simulation and eScience technologies
Better biomarkers through datasharing
A sustainable infrastructure for translational medical research
Helps you find a suitable neural network configuration for deep learning on time series.
Highly portable parallel workflow to detect structural variants in cancer genomes.
Genome-wide detection of structural variants using deep learning
Highly portable parallel workflow to generate artificial genomes with structural variants.
If you are using remote machines to do your computations, and don’t feel like learning and implementing many different APIs, Xenon is the tool for you.
A command line interface for the Xenon library that allows you to use remote machines to do your computations.
Python library for YAML type inference, schema checking and syntactic sugar.