ARCHIVE Snapshot of the Rätsch lab website (Tübingen, then New York) as of February 2016: preserved, not maintained. The group today: bmi.inf.ethz.ch
Personal tools
Home → Rätsch Lab → People → Research Topics → Computational Genome Annotation → Protein Subcellular Localization
 
Document Actions

Protein Subcellular Localization

We use "Multiple Kernel Learning" (MKL), an extension to support vector machines (SVMs) to combine and select diverse data sources, to predict the subcellular localization of proteins.

Protein subcellular localization is a crucial ingredient to many important inferences about cellular processes, including prediction of protein function and protein interactions. We propose a new class of protein sequence kernels which considers all motifs including motifs with gaps. This class of kernels allows the inclusion of pairwise amino acid distances into their computation. We utilize an extension of the multiclass support vector machine (SVM) method which directly solves protein subcellular localization without resorting to the common approach of splitting the problem into several binary classification problems. To automatically search over families of possible amino acid motifs, we optimize over multiple kernels at the same time. We compare our automated approach to four other predictors on three different datasets, and show that we perform better than the current state of the art. Furthermore, our method provides some insights as to which features are most useful for determining subcellular localization, which are in agreement with biological reasoning.

More details, including references, papers, datasets, and software, can be found on our project web page.

People specializing in this area

Alumnae and Alumni

Cheng Soon Ong, Ph.D./The Australian National University

Cheng Soon Ong, Ph.D./The Australian National University

More about Cheng Soon Ong, Ph.D./The Australian National University...
Alexander Zien, Ph.D.

Alexander Zien, Ph.D.

Several types of evidence are available for predicting the subcellular localization of proteins. My colleague Cheng Soon Ong and me devise several useful kernel functions from the primary sequence and automatically combine them with a multiclass version of multiple kernel learning (MCMKL) for suppoert vector machines (SVMs). The resulting accuracy compares favorably to several established existing predictors.
More about Alexander Zien, Ph.D....

Publications