Andreas Maunz, Dipl.-Inf.

Room: 207

Albert-Ludwigs-Universität Freiburg
Institute for Physics
Hermann-Herder-Str. 3

79104 Freiburg, Germany

E-Mail: andreas@maunz.de

Office Phone: +49-761-203-8442

Research Interests:

Graph Mining

Inductive Databases

QSAR Models

"Classical" Data Mining

Probabilistic Reasoning

Research:

Generally: In toxicology, the aim is to understand the biochemical mechanisms involved and the degree to which chemicals induce toxicological activity in living organisms with respect to a well-defined endpoint. This mostly involves chemical expe knowledge, tailored to specific biochemical interactions (top-down). Quite conflicting, statistical approaches use general toxic endpoints and activity values gathered for a wide range of structures and are primarily driven by information inherently present in the data (bottom-up). My aim is the development of powerful, yet universally applicable algorithms that narrow this gap.

Specifically: I am mainly concerned with structural alerts, i.e. structural motifs in chemical structures associated with biological activity. The objective is to establish an inductive database of compounds and activity values that users can query for fragments relevant to the endpoint of interest, providing, among others, frequency and statistical constraints. For this purpose, efficient subgraph enumeration including pruning techniques for statistical and frequency constraints are

employed.

Awards:

2003 - 2007: Scholarship granted by Hans-Böckler Stiftung.

2007: Appearance among the top third of Freiburg CS graduates in 2007.

Activities:

Workshops:

A. Maunz. Elaborate Graph Mining: Exploiting Structural Invariants and Latent Information in Graph Databases to predict REACH-relevant Endpoints, presented at the OpenTox InterAction Meeting, Summer 2011, Technical University Munich, Munich, Germany (9-12 August 2011).

A. Maunz, C. Helma, T. Cramer, and S. Kramer. Latent Structure Pattern Mining, presented at the eCheminfo Community of Practice InterAction Meeting, Summer 2010, Oxford University, Oxford, UK (01-05 August 2010).

A. Maunz, C. Helma. New Lazar Developments, presented at the eCheminfo Community of Practice InterAction Meeting, Autumn 2008, Bryn Mawr College, Philadelphia, USA (13-17 October 2008).

A. Maunz. Instance-based Regression Models for Quantitative Biological Activities using Support Vector Machines and Multilinear Models, presented at the Scarlet Workshop on in silico methods for carcinogenicity and mutagenicity, Milano, Italy (April 2008).

(Co)-Reviewing:

ECML/PKDD 2010, ICDM 2010, KDD 2011, Journal of Intelligent Information Systems, Journal of Chemical Information and Modelling.

Publications:

Maunz, A, Gütlein, M, Rautenberg, M, Vorgrimmler, D, Gebele, D, and Helma, C (2013).
Lazar: A Modular Predictive Toxicology Framework
Frontiers in Pharmacology, 4(00038).

Maunz, A, Vorgrimmler, D, and Helma, C (2013).
Out-of-Bag Discriminative Graph Mining
In: Proceedings of the 28th Symposium On Applied Computing, accepted.

Maunz, A, Helma, C, and Kramer, S (2011).
Efficient Mining for Structurally Diverse Subgraph Patterns in Large Molecular Databases
In: Machine Learning, vol. 83(2), pp. 193-218, Springer Netherlands.

Suenderhauf, C, Hammann, F, Maunz, A, Helma, C, and Huwyler, J (2011).
Combinatorial QSAR Modeling of Human Intestinal Absorption
Molecular Pharmaceutics, 8(1):213-224.

Hardy, B, Douglas, N, Helma, C, Rautenberg, M, Jeliazkova, N, Jeliazkov, V, Nikolova, I, Benigni, R, Tcheremenskaia, O, Kramer, S, Girschick, T, Buchwald, F, Wicker, J, Karwath, A, Gütlein, M, Maunz, A, Sarimveis, H, Melagraki, G, Afantitis, A, Sopasakis, P, Gallagher, D, Poroikov, V, Filimonov, D, Zakharov, A, Langunin, A, Gloriozova, T, Novikov, S, Skvortsova, N, Druzhilovsky, D, Chawla, S, Gosh, I, Ray, S, Patel, H, and Escher, S (2010).
Collaborative Development of Predictive Toxicology Applications
Journal of Cheminformatics, 2(7).

Maunz, A and Helma, C (2010).
Prediction of Toxic Effects of Pharmaceutical Agents
In: Pharmaceutical Data Mining: Approaches and Applications for Drug Discovery, ed. by Konstantin V. Balakin, Sean Ekins. Wiley, New York, NY, USA, chap. 5, pp. 145-176. (ISBN: 978-0-470-19608-3).

Maunz, A, Helma, C, Cramer, T, and Kramer, S (2010).
Latent Structure Pattern Mining
In: Balcazar, Jose; Bonchi,Francesco; Gionis, Aristides; Sebag, Michele: ECML/PKDD 2010: Machine Learning and Knowledge Discovery in Databases, vol. 6322, pp. 353-368, Berlin / Heidelberg, Springer.

Hammann, F, Gutmann, H, Jecklin, U, Maunz, A, Helma, C, and Drewe, J (2009).
Development of Decision Tree Models for Substrates, Inhibitors, and Inducers of p-Glycoprotein
Current Drug Metabolism, 10(4):339-346.

Maunz, A, Helma, C, and Kramer, S (2009).
Large Scale Graph Mining using Backbone Refinement Classes
In: KDD '09: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 617-626, New York, NY, USA, ACM.

Maunz, A and Helma, C (2008).
Prediction of Chemical Toxicity with Local Support Vector Regression and Activity-Specific Kernels
SAR and QSAR in Environmental Research, 19(5-6):413-431.

Short Scientific CV:

Current Status

2008 - now: PhD student at Technische Universität München. Advisor: Prof. Dr. techn. Stefan Kramer.

Degrees

July 2007: Diplom (german M. Sc.) in Computer Science at Albert-Ludwigs-Universität Freiburg. Advisor: Prof. Dr. Rolf Backofen.

Employment

2004 - 2005: Cooperation with the Machine Learning and Natural Language Processing Lab in Freiburg as student worker.

2005 - 2007: Cooperation with the EU FP 7 project Sens-it-iv.

2007 - now: Scientific position at Freiburg University (Institute for Computer Science, Institute for Physics, Center for Data Analysis and Modeling).

2008 - now: Cooperation with the EU FP 7 project OpenTox.

Personal tools

Sections