Multiclass multiple kernel learning (2010)
Alexander Zien, Cheng Soon Ong
In many applications it is desirable to learn from several kernels. “Multiple kernel learning” (MKL) allows the practitioner to optimize over linear combinations of kernels. By enforcing sparse...
Non-Sparse Regularization and Efficient Training with Multiple Kernels (2010)
Kloft, Marius, Brefeld, Ulf, Sonnenburg, Soeren, Zien, Alexander
Learning linear combinations of multiple kernels is an appealing strategy when the right choice of features is unknown. Previous approaches to multiple kernel learning (MKL) promote sparse kernel...
A Multi-Class Support Vector Machine Based on Scatter Criteria (2009)
Jenssen, Robert, Kloft, Marius, Zien, Alexander, Sonnenburg, Sören, Müller, Klaus-Robert
We re-visit Support Vector Machines (SVMs) and provide a novel interpretation thereof in terms of weighted class means and scatter theory. The gained theoretical insight can be translated into a...
The Feature Importance Ranking Measure (2009)
Zien, Alexander, Kraemer, Nicole, Sonnenburg, Soeren, Raetsch, Gunnar
Most accurate predictions are typically obtained by learning machines with complex feature spaces (as e.g. induced by kernels). Unfortunately, such decision rules are hardly accessible to humans and...
mGene.web: a web service for accurate computational gene finding (2009)
Schweikert, Gabriele, Behr, Jonas, Zien, Alexander, Zeller, Georg, Ong, Cheng Soon, Sonnenburg, Sören, ...
We describe mGene.web, a web service for the genome-wide prediction of protein coding genes from eukaryotic DNA sequences. It offers pre-trained models for the recognition of gene structures...
The Feature Importance Ranking Measure (2009)
Zien, Alexander, Krämer, Nicole, Sonnenburg, Sören, Rätsch, Gunnar
Most accurate predictions are typically obtained by learning machines with complex feature spaces (e.g., as induced by kernels). Unfortunately, such decision rules are hardly accessible to humans and...
mGene: Accurate SVM-based gene finding with an application to nematode genomes (2009)
Schweikert, Gabriele, Zien, Alexander, Zeller, Georg, Behr, Jonas, Dieterich, Christoph, Ong, Cheng Soon, ...
We present a highly accurate gene-prediction system for eukaryotic genomes, called mGene. It combines in an unprecedented manner the flexibility of generalized hidden Markov models (gHMMs) with the...
The Feature Importance Ranking Measure (2009)
Zien, Alexander, Krämer, Nicole, Sonnenburg, Sören, Raetsch, Gunnar
Most accurate predictions are typically obtained by learning machines with complex feature spaces (as e.g. induced by kernels). Unfortunately, such decision rules are hardly accessible to humans and...
The Feature Importance Ranking Measure (2009)
Zien, Alexander, Krämer, N, Sonnenburg, Sören, Rätsch, Gunnar
Efficient and Accurate Lp-Norm Multiple Kernel Learning (2009)
Kloft, Marius, Brefeld, Ulf, Sonnenburg, Sören, Laskov, Pavel, Müller, Klaus-Robert, Zien, Alexander
Learning linear combinations of multiple kernels is an appealing strategy when the right choice of features is unknown. Previous approaches to multiple kernel learning (MKL) promote sparse kernel...
mGene: A Novel Discriminative Gene Finding System (2009)
Schweikert, Gabriele, Zeller, Georg, Zien, Alexander, Behr, Jonas, Ong, Cheng Soon, Philips, Petra, ...
We present a highly accurate gene prediction system for eukaryotic genomes, called mGene. It combines in an unprecedented manner the flexibility of generalized hidden Markov models with the...
mGene: Accurate SVM-based gene finding with an application to nematode genomes (2009)
Schweikert, Gabriele, Zien, Alexander, Zeller, Georg, Behr, Jonas, Dieterich, Christoph, Ong, Cheng Soon, ...
We present a highly accurate gene-prediction system for eukaryotic genomes, called mGene. It combines in an unprecedented manner the flexibility of generalized hidden Markov models (gHMMs) with the...
mGene: Accurate SVM-based gene finding with an application to nematode genomes (2009)
Schweikert, Gabriele, Zien, Alexander, Zeller, Georg, Behr, Jonas, Dieterich, Christoph, Ong, Cheng Soon, ...
We present a highly accurate gene-prediction system for eukaryotic genomes, called mGene. It combines in an unprecedented manner the flexibility of generalized hidden Markov models (gHMMs) with the...
A Multi-Class Support Vector Machine Based on Scatter Criteria (2009)
Jenssen, R, Kloft, M, Zien, Alexander, Sonnenburg, Sören, Müller, Klaus
Efficient and Accurate Lp-Norm MKL (2009)
Kloft, M, Brefeld, U, Sonnenburg, Sören, Laskow, P, Mueller, Klaus, Zien, Alexander
mGene: Accurate SVM-based gene finding with an application to nematode genomes (2009)
Schweikert, Gabriele, Zien, Alexander, Zeller, Georg, Behr, Jonas, Dieterich, Christoph, Ong, Cheng Soon, ...
We present a highly accurate gene-prediction system for eukaryotic genomes, called mGene. It combines in an unprecedented manner the flexibility of generalized hidden Markov models (gHMMs) with the...
mGene: Accurate SVM-based gene finding with an application to nematode genomes (2009)
Schweikert, Gabriele, Zien, Alexander, Zeller, Georg, Behr, Jonas, Dieterich, Christoph, Ong, Cheng Soon, ...
We present a highly accurate gene-prediction system for eukaryotic genomes, called mGene. It combines in an unprecedented manner the flexibility of generalized hidden Markov models (gHMMs) with the...
2004/03/01 15:03 1 A primer on molecular biology 1.1 The Cell Life (2008)
Modern molecular biology provides a rich source of challenging machine learning problems. This tutorial chapter aims to provide the necessary biological background knowledge required to communicate...
Olivier Chapelle, Bernhard Schölkopf, Alexander Zien, London England
All rights reserved. No part of this book may be reproduced in any form by any electronic or mechanical means (including photocopying, recording, or information storage and retrieval) without...
Sonnenburg, Sören, Zien, Alexander, Philips, Petra, Rätsch, Gunnar
Motivation: At the heart of many important bioinformatics problems, such as gene finding and function prediction, is the classification of biological sequences. Frequently the most accurate...
Zien, Alexander, Sonnenburg, Sören, Philips, Petra, Rätsch, Gunnar
Motivation: At the heart of many important bioinformatics problems, such as gene finding and function prediction, is the classification of biological sequences. Frequently the most accurate...
Positional Oligomer Importance Matrices (2007)
Zien, Alexander, Sonnenburg, Sören, Philips, Petra, Raetsch, Gunnar
At the heart of many important bioinformatics problems, such as gene finding and function prediction, is the classification of biological sequences, above all of DNA and proteins. In many cases, the...
An Automated Combination of Kernels for Predicting Protein Subcellular Localization (2007)
Zien, Alexander, Ong, Cheng Soon
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...
Computing Positional Oligomer Importance Matrices (POIMs) (2007)
Zien, Alexander, Philips, Petra, Sonnenburg, Sören
We show how to efficiently compute Positional Oligomer Importance Matrices (POIMs) which are a novel and powerful way to extract, rank, and visualize higher order (i.e. oligo-nucleotide)...
Core to the Centralization method [1] for the normalization of gene expression data is the estimation of most consistent sample scaling factors based on possibly inconsistent pairwise estimates....
Daniel Hanisch, Alexander Zien, Ralf Zimmer, Thomas
Motivation: Large scale gene expression data are often analyzed by clustering genes based on gene expression data alone, though a-priori knowledge in the form of biological networks is available. The...
Alexander Zien, Juliane Fluck, Ralf Zimmer, Thomas Lengauer
yx We estimate the number of microarrays that is required in order to gain reliable results from a common type of study: the pairwise comparison of different classes of samples. Current knowlegde...
Training and Approximation of a Primal Multiclass Support Vector Machine (2007)
Zien, Alexander, De Bona, Fabio, Ong, Cheng Soon
We revisit the multiclass support vector machine (SVM) and generalize the formulation to convex loss functions and joint feature maps. Motivated by recent work [Chapelle, 2006] we use logistic loss...
Transductive Support Vector Machines for Structured Variables (2007)
Zien, Alexander, Brefeld, Ulf, Scheffer, Tobias
We study the problem of learning kernel machines transductively for structured output variables. Transductive learning can be reduced to combinatorial optimization problems over all possible...
Multiclass Multiple Kernel Learning (2007)
Zien, Alexander, Ong, Cheng Soon
In many applications it is desirable to learn from several kernels. “Multiple kernel learning” (MKL) allows the practitioner to optimize over linear combinations of kernels. By enforcing sparse...
Transductive support vector machines for structured variables (2007)
Alexander Zien, Ulf Brefeld, Tobias Scheffer
We study the problem of learning kernel machines transductively for structured output variables. Transductive learning can be reduced to combinatorial optimization problems over all possible...
Multiclass multiple kernel learning (2007)
In many applications it is desirable to learn from several kernels. “Multiple kernel learning” (MKL) allows the practitioner to optimize over linear combinations of kernels. By enforcing sparse...
Alexander Zien, Friedrich Miescher Lab
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...
Multiclass multiple kernel learning (2007)
In many applications it is desirable to learn from several kernels. “Multiple kernel learning” (MKL) allows the practitioner to optimize over linear combinations of kernels. By enforcing sparse...
Transductive support vector machines for structured variables (2007)
Alexander Zien, Ulf Brefeld, Tobias Scheffer
We study the problem of learning kernel machines transductively for structured output variables. Transductive learning can be reduced to combinatorial optimization problems over all possible...
Semi-Supervised Support Vector Machines and Application to Spam Filtering (2006)
After introducing the semi-supervised support vector machine (aka TSVM for "transductive SVM"), a few popular training strategies are briefly presented. Then the assumptions underlying...
Towards the Inference of Graphs on Ordered Vertices (2006)
Zien, Alexander, Raetsch, Gunnar, Ong, Cheng Soon
We propose novel methods for machine learning of structured output spaces. Specifically, we consider outputs which are graphs with vertices that have a natural order. We consider the usual adjacency...
ARTS: Accurate Recognition of Transcription Starts in Human (2006)
Sonnenburg, Sören, Zien, Alexander, Raetsch, Gunnar
We develop new methods for finding transcription start sites (TSS) of RNA Polymerase II binding genes in genomic DNA sequences. Employing Support Vector Machines with advanced sequence kernels, we...
A Continuation Method for Semi-Supervised SVMs (2006)
Chapelle, Olivier, Chi, Mingmin, Zien, Alexander
Semi-Supervised Support Vector Machines (S3VMs) are an appealing method for using unlabeled data in classification: their objective function favors decision boundaries which do not cut clusters....
Alexander Zien, Er Zien, Cheng Soon Ong, Cheng Soon Ong
Abstract. Protein subcellular localization is a crucial ingredient to many important inferences about cellular processes, including prediction of protein function and protein interactions. While many...
A Continuation Method for Semi-Supervised SVMs (2006)
Olivier Chapelle, Mingmin Chi, Alexander Zien
Semi-Supervised Support Vector Machines (S 3 VMs) are an appealing method for using unlabeled data in classification: their objective function favors decision boundaries which do not cut clusters....
ARTS: accurate recognition of transcription starts in human (2006)
Sonnenburg, Sören, Zien, Alexander, Rätsch, Gunnar
We develop new methods for finding transcription start sites (TSS) of RNA Polymerase II binding genes in genomic DNA sequences. Employing Support Vector Machines with advanced sequence kernels, we...
Kernels for Predicting Protein Subcellular Localization (2006)
Alexander Zien, Cheng Soon Ong, Er Zien, Cheng Soon Ong
Abstract. Protein subcellular localization is a crucial ingredient to many important inferences about cellular processes, including prediction of protein function and protein interactions. While many...
A continuation method for semi-supervised svms (2006)
Olivier Chapelle, Mingmin Chi, Alexander Zien
Semi-Supervised Support Vector Machines (S3VMs) are an appealing method for using unlabeled data in classification: their objective function favors decision boundaries which do not cut clusters....
Large Margin Non-Linear Embedding (2005)
Zien, Alexander, Quinonero Candela, Joaquin
It is common in classification methods to first place data in a vector space and then learn decision boundaries. We propose reversing that process: for fixed decision boundaries, we ``learn'' the...
Semi-Supervised Classification by Low Density Separation (2005)
Olivier Chapelle, Alexander Zien
We believe that the cluster assumption is key to successful semi-supervised learning. Based on this, we propose three semi-supervised algorithms: 1. deriving graph-based distances that emphazise low...
Large margin non-linear embedding (2005)
Alexander Zien, Joaquin Quiñonero Candela
It is common in classification methods to first place data in a vector space and then learn decision boundaries. We propose reversing that process: for fixed decision boundaries, we “learn ” the...
Large margin non-linear embedding (2005)
Alexander Zien, Joaquin Quiñonero Candela
It is common in classification methods to first place data in a vector space and then learn decision boundaries. We propose reversing that process: for fixed decision boundaries, we “learn ” the...
Semi-Supervised Classification by Low Density Separation (2004)
Chapelle, Olivier, Zien, Alexander
We believe that the cluster assumption is key to successful semi-supervised learning. Based on this, we propose three semi-supervised algorithms: 1. deriving graph-based distances that emphazise low...
Microarrays: How many do you need? (2003)
Zien, Alexander, Fluck, Juliane, Zimmer, Ralf, Lengauer, Thomas
Microarrays: how many do you need (2003)
Alexander Zien, Juliane Fluck, Ralf Zimmer, Thomas Lengauer
We estimate the number of microarrays that is required in order to gain reliable results from a common type of study: the pairwise comparison of different classes of samples. We show that current...
Prediction on Spike Data Using Kernel Algorithms (2003)
Jan Eichhorn, Andreas Tolias, Alexander Zien, Er Zien, Malte Kuss, Carl Edward Rasmussen, ...
We report and compare the performance of different learning algorithms based on data from cortical recordings. The task is to predict the orientation of visual stimuli from the activity of a...
Confidence measures for protein fold recognition (2002)
Sommer,Ingolf, Zien,Alexander, Öhsen Von,Niklas, Zimmer,Ralf, Lengauer,Thomas
Co-clustering of biological networks and gene expression data (2002)
Hanisch,Daniel, Zien,Alexander, Zimmer,Ralf, Lengauer,Thomas
Microarrays: How Many Do You Need? (2002)
Zien, Alexander, Fluck, Juliane, Zimmer, Ralf, Lengauer, Thomas, Myers, Gene, Hannenhalli, Sridhar, ...
Confidence measures for protein fold recognition (2002)
Sommer, Ingolf, Zien, Alexander, Öhsen Von, Niklas, Zimmer, Ralf, Lengauer, Thomas
Co-clustering of biological networks and gene expression data (2002)
Hanisch, Daniel, Zien, Alexander, Zimmer, Ralf, Lengauer, Thomas
Confidence measures for protein fold recognition (2002)
Sommer, Ingolf, Zien, Alexander, Von Öhsen, Niklas, Zimmer, Ralf, Lengauer, Thomas
Motivation: We present an extensive evaluation of different methods and criteria to detect remote homologs of a given protein sequence. We investigate two associated problems: first, to develop a...
Co-clustering of biological networks and gene expression data (2002)
Hanisch, Daniel, Zien, Alexander, Zimmer, Ralf, Lengauer, Thomas
Motivation: Large scale gene expression data are often analysed by clustering genes based on gene expression data alone, though a priori knowledge in the form of biological networks is available. The...
Centralization: a new method for the normalization of gene expression data (2001)
Zien, Alexander, Aigner, Thomas, Zimmer, Ralf, Lengauer, Thomas
Microarrays measure values that are approximately proportional to the numbers of copies of different mRNA molecules in samples. Due to technical difficulties, the constant of proportionality between...
Analysis of Gene Expression Data with Pathway Scores (2000)
Alexander Zien, Robert Küffner, Er Zien, Robert Ku Ner, Ralf Zimmer, Thomas Lengauer
Wepresent a new approachfortheevaluation of gene expression data. The basic idea is to generate biologically possible pathways and to score them with respect to gene expression measurements. We...
mGene.web: a web service for accurate computational gene finding
Schweikert, Gabriele, Behr, Jonas, Zien, Alexander, Zeller, Georg, Ong, Cheng Soon, Sonnenburg, Sören, ...
We describe mGene.web, a web service for the genome-wide prediction of protein coding genes from eukaryotic DNA sequences. It offers pre-trained models for the recognition of gene structures...
Sonnenburg, Sören, Zien, Alexander, Philips, Petra, Rätsch, Gunnar
Motivation: At the heart of many important bioinformatics problems, such as gene finding and function prediction, is the classification of biological sequences. Frequently the most accurate...
mGene: Accurate SVM-based gene finding with an application to nematode genomes
Schweikert, Gabriele, Zien, Alexander, Zeller, Georg, Behr, Jonas, Dieterich, Christoph, Ong, Cheng Soon, ...
We present a highly accurate gene-prediction system for eukaryotic genomes, called mGene. It combines in an unprecedented manner the flexibility of generalized hidden Markov models (gHMMs) with the...