Personal tools
Home Rätsch Lab People Gabriele Schweikert, Ph.D.
Gabriele Schweikert, Ph.D.
Document Actions

Gabriele Schweikert, Ph.D.

  • Postdoc (Alumna)


I studied Physics at the University of Bayreuth, the Technical University Munich, Germany and - for an Erasmus exchange year - at Univeriste Piere et Marie Curie (Paris VI), France. During my Diploma thesis (Master's equivalent) in Wolfgang Baumeister's lab at the Max Planck Institute for Biochemistry, Martinsried, Germany, I worked on methods to reduce radiation damage on biological specimen during cryo-electron tomography. I subsequently moved to Tübingen to start a Ph.D. thesis with Bernhard Schölkopf, Detlef Weigel and Gunnar Rätsch. My main focus now is to develop and apply new machine learning techniques for genomic sequence analysis.


A list of publications can be found here.

Research Interests:

Gene Finding:
Domain Adaption for Genomic Sequence Analysis:
My main interested in domain adaptation methods is in their application to sequence analysis and in particular to gene finding. To date gene finding methods require a large amount of labeled data (e.i. previously annotated genes) to train a model for the subsequent prediction of unknown genes in the rest of the genome. To achieve highly accurate predictions, training is performed for each organism separately, e.g. a model learnt on fly genes is not working well to predict genes in a worm genome as the characteristics of the genes have diverged during evolution. However, it is also known that the cellular machineries that are responsible for transcription, processing and translation of genes are highly conserved between organisms. Therefore the tasks of predicting genes in flies and worms are similar albeit different. By applying domain adaptation techniques we try to close the remaining gap.
Inference of Alternative Splicing:
SNP Detection in A. thaliana:
As part of the resequencing project for 20 diverse strains of the model plant Arabidopsis thaliana, I have developed a SVM-based method for accurate detection of single-nucleotide polymorphisms (SNPs) from hybridization data. We have thus identified more than 1 million SNPs. Assessing the effects of the nonredundant SNPs on the annotated protein-coding genes we have found many that have a large impact on gene integrity, e.g. more than 1000 SNPs introduce premature stop codons.