Personal tools
Home → Rätsch Lab → People → Research Topics
 

Research Topics

Machine Learning
Machine Learning offers tools for computational analyses of complex phenomena. Given a set of labeled observations, one trains a learning machine to be able to make accurate predictions about future observations.
Computational Transcriptomics
For the analysis of data from whole-genome tiling arrays and mRNAs sequenced with next-generation sequencing technology, the group has developed sophisticated machine learning methods to preprocess array data, to align short (potentially spliced) reads to the genome, and to identify new transcripts and splice forms. Profiling the whole Arabidopsis transcriptome in different tissues, developmental stages, under abiotic stresses, and in RNA-processing mutants, we found thousands of new transcripts potentially implicated in transcriptional regulation and reprogramming during development and in response to stress.
Computational Genome Annotation
The group’s major contribution to Genomics has been the development of a novel and very accurate gene finding system that uses the latest advances in Machine Learning.
Sequence Variation
Analyzing a huge set of hybridization data from resequencing tiling arrays with discriminative state-of-the-art machine learning methods, we revealed hundreds of thousands polymorphisms (SNPs, deletions and highly polymorphic regions) in the genome of 20 varieties of two model plant organisms, Arabidopsis thaliana and Oryza sativa (rice). This inventory of sequence variation constitutes an unprecedented resource for further functional and large-scale evolutionary studies and is a fundamental step towards answering the key question: How is genetic variation linked to complex traits?