Machine Learning and Data Mining
Andreas Maunz received his diploma (german equivalent to M. Sc.) in computer science in 2007, and his doctoral degree in 2013. He is a senior principal scientist in research and early development at Roche‘s main site in Basel (CH).
Data mining (clustering, pattern detection, signal processing) and machine learning (gradient boosting, deep learning), and inferential statistics (parametric models with quantification of uncertainty). Clinical trial data, biostatistics, data-driven workflows for quantitative assessment of data quality.
Machine Learning on images and image-derived data (particularly deep learning), image processing (graph cut methods, kernels), advanced statistical models.
- 2018: SABS Graduate Program, Oxford University: “Deep Learning in the Life Sciences”
- 2011: Article in Special Issue of „Machine Learning” (Springer-Verlag), see publications
- 2007: Appearance among the top third of Freiburg CS graduates in 2007.
- 2003 – 2007: Scholarship granted by Hans-Böckler Stiftung.
Research Project Activities
International research projects:
- 2011 – 2013: Toxicological Risk Assessment in the food industry.
Research collaboration with Nestlé SA (Vevey, Switzerland) for structure-based modeling chronic toxicity and carcinogenicity (TD50).
Activity: Responsible for leading the complete modeling in the project using web technology and statistical learners in R.
- 2008 – 2011: Modelling of adverse chemical properties in pre-clinical screening.
Research Project “OpenTox” of the Seventh Framework Programme of the European Union – development of an interoperable programming frameworks for predictive toxicology.
Activity: design, testing and implementation of data mining and prediction modules using Ruby web services and diverse modelling algorithms.
- 2005 – 2010 Research Project “Sens-it-iv” of the Seventh Framework Programme of the European Union – Development of “in vitro” Alternatives to Animal Testing in the risk assessment of allergy Pathogens.
Activity: implementation and operation of an inductive database for experimental data, using Ruby on Rails and statistical toolboxes.
- A. Gomariz, H. Lu, T. Albrecht, A. Maunz, F. Benmansour, J. Luu, A. Valcarel, D. Ferrara, O. Goksel. “Unsupervised Domain Adaptation with Contrastive Learning for OCT Segmentation”, Medical Image Computing and Computer Assisted Interventions (MICCAI), Singapore, (September 18-22, 2022)
- A. Maunz, IL. Jones, J Hernandez-Sanchez, B. Garcia Armendariz, L. Barras, S. Yu. “Machine Learning Approaches to Automated Prediction of Fibrosis Development in Neovascular Age-Related Macular Degeneration Using Optical Coherence Tomography Images”, ARVO Annual Meeting, Denver (CO), USA (May 1–4, 2022)
- A. Neubert, A. Maunz, S. Yu, TL. von Strauss, A. Wenzel, J. Dai. “Machine Learning Approach to Identify Future Treatment Requirement in Pretreated nAMD Patients Based on OCT Images”, ARVO Annual Meeting, Denver (CO), USA (May 1–4, 2022)
- Y. Li, H. Lu, T. Albrecht, A. Maunz, A. Neubert, F. Benmansour, A. Gomariz, J. Luu, D. Ferrara. “Deep Learning to Segment Retinal Layer Disruption on Optical Coherence Tomography in Neovascular Age-Related Macular Degeneration”, ARVO Annual Meeting, Denver (CO), USA (May 1–4, 2022)
- A. Gomariz, H. Lu, Y. Li, T. Albrecht, A. Maunz, F. Benmansour, J. Luu, O. Goksel, D. Ferrara. “A Unified Deep Learning Approach for OCT Segmentation From Different Devices and Retinal Diseases”, ARVO Annual Meeting, Denver (CO), USA (May 1–4, 2022)
- IL. Jones, A. Maunz, T. Albrecht, H. Lu, Y. Li, F. Benmansour, J. Sahni, M. Gliem „Development and External Validation of a Machine Learning Model for Predicting Response to anti-VEGF Treatment in Patients with neovascular AMD“, ARVO Annual Meeting, Baltimore (MD), USA (May 03 – 07, 2020).
- A. Maunz, F. Benmansour, Y. Li, T. Albrecht, YP. Zhang, F. Arcadu, Y. Zheng, S. Madhusudan, J. Sahni „Diagnostic Accuracy of a Machine-Learning Algorithm to Detect and Classify Choroidal Neovascularization based on SD-OCT in Neovascular Age-Related Macular Degeneration (nAMD)“, ARVO Annual Meeting, Baltimore (MD), USA (May 03 – 07, 2020).
- J. Dai, A. Thalhammer, M. Kawczynski, N. Anegondi, X. Wang, A. Maunz, T. Bengtsson, S. Gao, J. Willis „Accurately Identify nAMD Patients with Low Anti-VEGF Treatment Need by Deep Learning“, ARVO Annual Meeting, Baltimore (MD), USA (May 03 – 07, 2020).
- J. Sahni, A. Maunz, F. Arcadu, YP. Zhang. Y. Li, T. Albrecht, A. Thalhammer, F. Benmansour. „Machine Learning Approach to Predict Response to anti-VEGF Treatment in Patients with Neovascular Age-Related Macular Degeneration using SD-OCT“, ARVO Annual Meeting, Vancouver, Canada (April 28 – May 02, 2019).
- F. Arcadu, F. Benmansour, A. Maunz, J. Willis, M. Prunotto, Z. Haskova. „Deep Learning Algorithm for Patient-Level Prediction of Diabetic Retinopathy Response to Vascular Endothelial Growth Factor Inhibition“, ARVO Annual Meeting, Vancouver, Canada (April 28 – May 02, 2019).
- F. Arcadu, J. Willis, A. Maunz, J. Michon, Z. Haskova, F. Benmansour. „Deep Learning Predicts OCT Measures of Diabetic Macular Thickening From Color Fundus Photographs“, 42nd Annual Macula Society Meeting, ARVO Annual Meeting, Vancouver, Canada (April 28 – May 02, 2019).
- F. Arcadu, F. Benmansour, A. Maunz, J. Michon, Z. Haskova, D. McClintock, J. Willis, M. Prunotto. „Automated Image Quality Evaluation of Color Fundus Photographs Using Deep Learning Architecture“, ARVO Imaging in the Eye Conference 2018, Honolulu (HI), USA (April 28, 2018)
- Maunz A, Ulrich E, Sternberger L, Blumenroehr C. Custom Scientific Visualizations in TIBCO Spotfire for Better Informed Decisions“, 15th Annual Bio-IT World Conference & Expo, Boston, USA, April 5-7, 2016.
- Amrein K, Vercruysse M, Prunotto M, Wolf L, Schmucki R, Racek T, Clausen I, Blum Marti R, Araujo Del Rosario A, Benmansour F, Maunz A, Jensen Zoffmann S. „Mode of action characterization of antibiotics using expression profile fingerprint“, Modern Phenotypic drug development, the path forward (Keystone Symposium), Big Sky, Montana, USA, April 2—6, 2016.
- Maier A, Dhar S, Maunz A, Zeitouni B, Peille A-L, Giesemann T, Fiebig HH. „High-throughput analysis of 3D tumor colony formation of primary cell suspensions derived from xenografts to identify efficacy of anti-tumor agents in single agent or combination therapy“, 27th AACR-NCI-EORTC
International Conference on Molecular Targets and Cancer Therapeutics, Boston, MA, USA, November 5-9, 2015, abstract B70
- Maunz A, Gilsdorf M, Fournier S, Blumenröhr C, Horstmöller R, Schmiedle J. „Visual Analysis of Gene Interaction Networks using Hive Plots“, VIZBI 2015, The 6th International Meeting on Visualizing Biological Data, Broad Institute of MIT and Harvard (March 25-27 2015).
- Vorgrimmler D, Rautenberg M, Gütlein, M, Maunz A, Gebele D, and Helma C. „Lazar – A Modular Predictive Toxicology Framework“, OpenTox Euro 2013 – Innovation in Predictive Toxicology, Johannes
Gutenberg University of Mainz (30 September – 2 October 2013).
- A. Maunz, IL. Jones, J. Hernandez-Sanchez, B. Garcia Armendariz, L. Barras, S. Yu. “Machine Learning to Predict Fibrosis Development in Neovascular Age-Related Macular Degeneration”, Ophthalmic AI Summit, website, talk recording (June 18, 2022)
- A. Maunz, IL. Jones, J. Dai. “Development and Validation of a Machine Learning Model for Predicting 3-Month Best-Corrected Visual Acuity After Monthly Ranibizumab Treatment in Patients With Neovascular AMD”, ARVO Virtual Meeting (May 1–7, 2021)
- A. Maunz. “Machine Learning to Predict Response to Treatment in eye Diseases using Tomography Scans of the Retina”, Biodata World Congress (November 9-12, 2020)
- F. Arcadu, F. Benmansour, A. Maunz, J. Willis, M. Prunotto, Z. Haskova. „Deep Learning Algorithm to Predict Diabetic Retinopathy Progression on the Individual Patient Level“, ARVO Annual Meeting, Vancouver, Canada (April 28 – May 02, 2019).
- A. Adamis, F. Arcadu, F. Benmansour, A. Maunz, J. Michon, Z. Haskova, D. McClintock, M. Prunotto, J. Willis. „Deep Learning Predicts OCT Measures of Diabetic Macular Thickening From Color Fundus Photographs“, 42nd Annual Macula Society Meeting, Bonita Springs (FL), USA (February 13-16, 2019).
- S. Zoffmann, A. Maunz, L. Wolf, F. Benmansour, M. Vercruysse, K. Amrein, M. Burcin, M. Prunotto. „Machine Learning Powered Antibiotics Phenotypic Drug Discovery“, Keystone Symposium on Phenotypic Drug Discovery, Breckenridge (CO), USA (March 03-07, 2019).
- Maunz A, Wolf L, Jensen Zoffmann S, Prunotto M, Amrein K, Vercruysse M, Blum Marti R, Zhu S, Ding H, Benmansour F. „Automating a high content screening assay“, 15th Annual Bio-IT World
Conference & Expo, Boston, USA, April 5-7, 2016.
- Helma C, Maunz A, „Vorstellung des Tools Lazar (Lazy Structure-Activity Relationships)“, Read-Across und Grouping zur Füllung von Datenlücken unter REACH, DGPT Jahrestagung 2013, Halle/Saale (05. – 07. März 2013).
- A. Maunz, C. Helma, and S. Kramer: Large Scale Graph Mining using Backbone Refinement Classes. In 7th International Workshop on Mining and Learning with Graphs, Leuven, Belgium (02-04 July 2009).
The submitted abstract was one of eight that were selected for oral presentation (21 accepted in total) at the conference. Following the conference, the work was selected for publication in the joint
MLG/SRL/ILP workshop special issue of the Machine Learning Journal (among five other works out of 83).
- Maunz A, Helma C. „New Lazar Developments“, presented at the eCheminfo Community of Practice InterAction Meeting, Autumn 2008, Bryn Mawr College, Philadelphia (13-17 October 2008).
- Maunz A: „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 (April 2008).
- A. Maunz, F. Benmansour, Y. Li, T. Albrecht, YP. Zhang, F. Arcadu, Y. Zheng, S. Madhusudhan, J. Sahni “Accuracy of a Machine Learning Algorithm to Detect and Classify Choroidal Neovascularization on Spectral-Domain Optical Coherence Tomography” Journal of Personalized Medicine 6, 11, Jun 2021.
- M. Zarbin, L. Hill, A. Maunz, M. Gliem, I. Stoylov “Anti-VEGF-resistant subretinal fluid is Associated with Better Vision and Reduced Risk of Macular Atrophy” British Journal of Ophthalmology Published Online First: 26 May 2021.
- F. Arcadu, F. Benmansour, A. Maunz, J. Willis, Z. Haskova, M. Prunotto “Deep learning algorithm predicts diabetic retinopathy progression in individual patients”. npj Digital Medicine 2, 92, Sep 2019.
- F. Arcadu, J. Willis, A. Maunz, J. Michon, Z. Haskova, M. Prunotto, F. Benmansour. “Deep Learning Predicts OCT Measures of Diabetic Macular Thickening From Color Fundus Photographs”. Investigative Ophthalmology and Visual Science, 60:852–857, Mar 2019.
- S. Zoffmann, M. Vercruysse, F. Benmansour, A. Maunz, L. Wolf, R. Blum Marti, T. Heckel, H. Ding, H. Truong, M. Prummer, R. Schmucki, C. Mason, K. Bradley, A. I. Jacob, C. Lerner, A. Araujo del Rosario, M. Burcin, K. Amrein, and M. Prunotto. “Machine Learning-Powered Antibiotics Phenotypic Drug Discovery”. Nature Scientific Reports, 9:5013, 2019.
- A. Moisan, M. Gubler, J. D. Zhang, Y. Tessier, K. Dumong Erichsen, S. Sewing, R. Gerard, B. Avignon, S. Huber, F. Benmansour, X. Chen, R. Villasenor, A. Braendli-Baiocco, M. Festag, A. Maunz, T. Singer, F. Schuler, and A. B. Roth. “Inhibition of EGF Uptake by Nephrotoxic Antisense Drugs In Vitro and Implications for Preclinical Safety Profiling”. Molecular Therapy Nucleic Acids, 6:89–105, Mar 2017.
- Batke M, Gütlein M, Partosch F, Gundert-Remy U, Helma C, Kramer S, Maunz A, Seeland M, and Bitsch A. “Innovative Strategies to Develop Chemical Categories using a Combination of Structural and Toxicological Properties” Frontiers in Pharmacology, 7:321, 2016.
- Lo Piparo E, Maunz A, Helma C, Vorgrimmler D, Schilter B. (2014) “Automated and Reproducible Read-Across like Models for Predicting Carcinogenic Potency” Regulatory Toxicology and Pharmacology 70(1).
- Seeland M, Maunz A, Karwath A, Kramer S. “Extracting Information from Support Vector Machines for Pattern-Based Classification” Proceedings of the 29th Symposium On Applied Computing, SAC ’14, pages 129–135, New York, NY, USA, 2014. ACM. [pdf, bib]
- Maunz A, Vorgrimmler D, Helma C. “Out-of-Bag Discriminative Graph Mining” Proceedings of the 28th Symposium On Applied Computing, SAC ’13, 109–114, New York, NY, USA, 2013. ACM. [pdf, bib]
- Maunz A, Gütlein M, Rautenberg M, Vorgrimmler D, Gebele D, Helma C. “Lazar: A Modular Predictive Toxicology Framework” Frontiers in Pharmacology 4:38, 2013. [pdf]
- Batke M, Bitsch A, Gundert-Remy U, Guetlein M, Helma Ch, Kramer S, Maunz A, Partosch F, Seeland M, Stahlmann R. “New Strategies to develop Chemical Categories in the Context of REACH-Work in progress” Toxicology Letters, 221:84, 2013.
- Maunz A, Helma C, and Kramer S. “Efficient Mining for Structurally Diverse Subgraph Patterns in Large Molecular Databases” Machine Learning, 83:2, 193-218, Springer Netherlands, 2011. [pdf]
- Maunz A, Helma C, Cramer T, and Kramer S. “Latent Structure Pattern Mining” ECML/PKDD 2010: Machine Learning and Knowledge Discovery in Databases, 6322, 353-368, Springer Berlin / Heidelberg, 2011. [pdf, poster pdf]
- Suenderhauf, C, Hammann, F, Maunz, A, Helma, C, and Huwyler, J. “Combinatorial QSAR Modeling of Human Intestinal Absorption” Molecular Pharmaceutics, 8(1):213-224, 2011.
- 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. “Collaborative Development of Predictive Toxicology Applications” Journal of Cheminformatics, 2:7, 2010. [pdf]
- Maunz A, Helma C, and Kramer S (2009). “Large Scale Graph Mining using Backbone Refinement Classes” KDD ’09: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 617-626, New York, NY, USA, ACM. [pdf]
Video lecture: slides 1-3.exe, 4-6.exe, 7-10.exe, 11-15.exe, 16-19.exe, 20-23.exe or view the conference recordings.
- Hammann F, Gutmann H, Jecklin U, Maunz A, Helma C, and Drewe J. “Development of Decision Tree Models for Substrates, Inhibitors, and Inducers of p-Glycoprotein” Current Drug Metabolism, 10:4, 339-346, 2009.
- Maunz A and Helma C. “Prediction of Toxic Effects of Pharmaceutical Agents” 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, 2009. [abstract]
- Maunz A and Helma C. “Prediction of Chemical Toxicity with Local Support Vector Regression and Activity-Specific Kernels” SAR and QSAR in Environmental Research, 19(5-6):413-431, 2008. [pdf]
- Maunz A: “A Quantitative Extension to the Lazar Algorithm for the Prediction of Chemical Properties.” [pdf diplomarbeit.pdf].
- Maunz A: “On the Number of Backbone Refinement Classes”, derivation and proof of a formula for counting the number of BBRCs in a perfect binary tree. Comparison to the total number of subtrees [pdf bbrc-no.pdf].
- Maunz A: “On the Co-Occurrence and Diversity of Backbone Refinement Classes”, euclidean embedding of BBRC features and instances in 2D as well as feature similarity alike to ORIGAMI approach [pdf bbrc-rep.pdf].
- Maunz A: “Support Vectors and the Margin in a Nutshell”, brief outline of support vector theory and the concept of margin. (see ch. 1,2 and 7 of Schölkopf and Smola, 2002) [pdf sv-margin.pdf].
Selected Talks and Tutorials
- A. Maunz, C. Helma, and S. Kramer: Large Scale Graph Mining using Backbone Refinement Classes. In 7th International Workshop on Mining and Learning with Graphs, Leuven, Belgium (02-04 July 2009). The submitted abstract was one of eight (out of 21) that were selected for oral presentation at the conference. Following the conference, the work was selected for publication in the joint MLG/SRL/ILP workshop special issue of the Machine Learning Journal (among five other works out of 83).
Short Scientific CV
I studied computer science from 2001 to 2007 and graduated in June 2007. My Thesis treated the quantitative prediction of toxicological properties of small molecules (eg, carcinogenicity, mutagenicity).
In 2009, I became a Ph.D. student. In this phase I published more than ten articles in conferences and journals, including the two largest international data mining conferences (KDD, ECML / PKDD) and in a special edition of the Machine Learning Journal (Springer Verlag).
From 2011 to 2012, I led a research collaboration with Nestlé for structure-based prediction of chronic toxicity and carcinogenicity. The resulting statistical models were used for establishing levels of safety concern, and for regulatory purposes with the Swiss authorities. The results were published in 2014 in Regulatory Toxicology and Pharmacology.
In December 2013 I received my doctoral degree for my thesis “Graph Mining methods for Predictive Toxicology”. During 2013 and 2014 I worked on the computer-based synergy determination of drug combinations in preclinical screenings of anti-cancer agents at Oncotest GmbH.
In November 2014, I joined Hoffmann-La Roche AG (Basel) in their Pharma Research and Early Development Informatics division. After several years of preclinical high-content screening I started on image analyses using deep learning in clinical ophthalmology, with a focus on neovascular age-related macular degeneration and diabetic macular edema.
- Related to Publications:
- Other material: