Matthias Rupp

Machine learning for atomistic systems

Publications

Journal articles

  1. Li Li, John C. Snyder, Isabelle M. Pelaschier, Jessica Huang, Uma-Naresh Niranjan, Paul Duncan, Matthias Rupp, Klaus-Robert Müller, Kieron Burke: Understanding Machine-Learned Density Functionals, International Journal of Quantum Chemistry, 116(11): 819–833, Wiley, 2016. [doi]
  2. Matthias Rupp, Raghunathan Ramakrishnan, O. Anatole von Lilienfeld: Machine Learning for Quantum Mechanical Properties of Atoms in Molecules, Journal of Physical Chemistry Letters, 6(16): 3309–3313, American Chemical Society, 2015. [doi]
  3. Matthias Rupp: Special Issue on Machine Learning and Quantum Mechanics, International Journal of Quantum Chemistry, 115(16): 1003–1004, Wiley, 2015. [doi]
  4. Matthias Rupp: Machine Learning for Quantum Mechanics in a Nutshell, International Journal of Quantum Chemistry, 115(16): 1058–1073, Wiley, 2015. [doi] [supplement]
  5. Kevin Vu, John C. Snyder, Li Li, Matthias Rupp, Brandon F. Chen, Tarek Khelif, Klaus-Robert Müller, Kieron Burke: Understanding Kernel Ridge Regression: Common Behaviors from Simple Functions to Density Functionals, International Journal of Quantum Chemistry, 115(16): 1115–1128, Wiley, 2015. [doi]
  6. John C. Snyder, Matthias Rupp, Klaus-Robert Müller, Kieron Burke: Nonlinear Gradient Denoising: Finding Accurate Extrema from Inaccurate Functional Derivatives, International Journal of Quantum Chemistry, 115(16): 1102–1114, Wiley, 2015. [doi]
  7. O. Anatole von Lilienfeld, Raghunathan Ramakrishnan, Matthias Rupp, Aaron Knoll: Fourier Series of Atomic Radial Distribution Functions: A Molecular Fingerprint for Machine Learning Models of Quantum Chemical Properties, International Journal of Quantum Chemistry, 115(16): 1084–1093, Wiley, 2015. [doi]
  8. Raghunathan Ramakrishnan, Pavlo O. Dral, Matthias Rupp, O. Anatole von Lilienfeld: Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach, Journal of Chemical Theory and Computation, 11(5): 2087–2096, American Chemical Society, 2015. [doi]
  9. Raghunathan Ramakrishnan, Pavlo Dral, Matthias Rupp, O. Anatole von Lilienfeld: Quantum Chemistry Structures and Properties of 134 kilo Molecules, Scientific Data, 1: 140022, Nature Publishing Group, 2014. [doi] [pdf]
  10. Matthias Rupp, Matthias R. Bauer, Rainer Wilcken, Andreas Lange, Michael Reutlinger, Frank M. Boeckler, Gisbert Schneider: Machine Learning Estimates of Natural Product Conformational Energies, PLoS Computational Biology, 10(1): e1003400, Public Library of Science, 2014. [doi] [pdf]
  11. John C. Snyder, Matthias Rupp, Katja Hansen, Leo Blooston, Klaus-Robert Müller, Kieron Burke: Orbital-free Bond Breaking via Machine Learning, Journal of Chemical Physics, 139(22): 224104, American Institute of Physics, 2013. [doi] [pdf]
  12. Katja Hansen, Grégoire Montavon, Franziska Biegler, Siamac Fazli, Matthias Rupp, Matthias Scheffler, O. Anatole von Lilienfeld, Alexandre Tkatchenko, Klaus-Robert Müller: Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies, Journal of Chemical Theory and Computation, 9(8): 3543–3556, American Chemical Society, 2013. [doi]
  13. Volker Hähnke, Matthias Rupp, Alexander K. Hartmann, Gisbert Schneider: Pharmacophore Alignment Search Tool (PhAST): Significance Assessment of Chemical Similarity, Molecular Informatics, 32(7): 625–646, Wiley, 2013. [doi]
  14. Grégoire Montavon, Matthias Rupp, Vivekanand Gobre, Alvaro Vazquez-Mayagoitia, Katja Hansen, Alexandre Tkatchenko, Klaus-Robert Müller, O. Anatole von Lilienfeld: Machine learning of molecular electronic properties in chemical compound space, New Journal of Physics, 15(9): 095003, IOP Publishing, 2013. [doi] [pdf] [dataset]
  15. Matthias Rupp, Alexandre Tkatchenko, Klaus-Robert Müller, O. Anatole von Lilienfeld: Reply to Comment by J.E. Moussa (Physical Review Letters 109(5): 059801, 2012), Physical Review Letters, 109(5): 059802, American Physical Society, 2012. [doi] [pdf] See our original article (Physical Review Letters 108(5): 058301, 2012).
  16. Julia Weber, Matthias Rupp, Ewgenij Proschak: Impact of X-Ray Structure on Predictivity of Scoring Functions: PPARγ Case Study, Molecular Informatics, 31(9): 631–633, Wiley, 2012. [doi]
  17. John C. Snyder, Matthias Rupp, Katja Hansen, Klaus-Robert Müller, Kieron Burke: Finding Density Functionals with Machine Learning, Physical Review Letters, 108(25): 253002, American Physical Society, 2012. [doi] [pdf]
  18. Grigorios Skolidis, Katja Hansen, Guido Sanguinetti, Matthias Rupp: Multi-task learning for pKa prediction, Journal of Computer-Aided Molecular Design, 26(7): 883–895, Springer, 2012. [doi]
  19. Zachary D. Pozun, Katja Hansen, Daniel Sheppard, Matthias Rupp, Klaus-Robert Müller, Graeme Henkelman: Optimizing transition states via kernel-based machine learning, Journal of Chemical Physics, 136(17): 174101, American Institute of Physics, 2012. [doi] Top 20 Most Read in 5/2012
  20. Markus Hartenfeller, Heiko Zettl, Miriam Walter, Matthias Rupp, Felix Reisen, Ewgenij Proschak, Sascha Weggen, Holger Stark, Gisbert Schneider: DOGS: Reaction-Driven De Novo Design of Bioactive Compounds, PLoS Computational Biology, 8(2): e1002380, Public Library of Science, 2012. [doi] [pdf]
  21. Matthias Rupp, Alexandre Tkatchenko, Klaus-Robert Müller, O. Anatole von Lilienfeld: Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning, Physical Review Letters, 108(5): 058301, American Physical Society, 2012. [doi] [pdf] See also comment by J.E. Moussa in Physical Review Letters 109(5): 059801, 2012, and our reply to it.
  22. Katja Hansen, David Baehrens, Timon Schroeter, Matthias Rupp, Klaus-Robert Müller: Visual Interpretation of Kernel-Based Prediction Models, Molecular Informatics, 30(9): 817–826, Wiley, 2011. [doi]
  23. Quan Wang, Kerstin Birod, Carlo Angioni, Sabine Grösch, Tim Geppert, Petra Schneider, Matthias Rupp, Gisbert Schneider: Spherical Harmonics Coefficients for Ligand-Based Virtual Screening of Cyclooxygenase Inhibitors, PLoS ONE, 6(7): e21554, Public Library of Science, 2011. [doi] [pdf]
  24. Iurii Sushko, Sergii Novotarskyi, Robert Körner, Anil Kumar Pandey, Matthias Rupp, Wolfram Teetz, Stefan Brandmaier, Ahmed Abdelaziz, Volodymyr V. Prokopenko, Vsevolod Y. Tanchuk, Roberto Todeschini, Alexandre Varnek, Gilles Marcou, Peter Ertl, Vladimir Potemkin, Maria Grishina, Johann Gasteiger, Christof Schwab, Igor I. Baskin, Vladimir A. Palyulin, Eugene V. Radchenko, William J. Welsh, Vladyslav Kholodovych, Dmitriy Chekmarev, Artem Cherkasov, Joao Aires-de-Sousa, Qing-You Zhang, Andreas Bender, Florian Nigsch, Luc Patiny, Antony Williams, Valery Tkachenko, Igor V. Tetko: Online chemical modeling environment (OCHEM): web platform for data storage, model development and publishing of chemical information, Journal of Computer Aided Molecular Design, 25(6): 533–554, Springer, 2011. [doi]
  25. Matthias Rupp, Robert Körner, Igor V. Tetko: Predicting the pKa of small molecules, Combinatorial Chemistry & High Throughput Screening, 14(5): 307–327, Bentham, 2011. [doi] [pdf]
  26. Matthias Rupp, Robert Körner, Igor V. Tetko: Estimation of acid dissociation constants using graph kernels, Molecular Informatics, 29(10): 731–740, Wiley, 2010. [doi]
  27. Volker Hähnke, Matthias Rupp, Mireille Krier, Friedrich Rippmann, Gisbert Schneider: Pharmacophore alignment search tool (PhAST): Influence of Canonical Atom Labeling on Similarity Searching, Journal of Computational Chemistry, 31(15): 2810–2826, Wiley, 2010. [doi]
  28. Matthias Rupp, Gisbert Schneider: Graph kernels for molecular similarity, Molecular Informatics, 29(4): 266–273, Wiley, 2010. [doi]
  29. Ramona Steri, Petra Schneider, Alexander Klenner, Matthias Rupp, Manfred Schubert-Zsilavecz, Gisbert Schneider: Target profile prediction: Cross-activation of peroxisome proliferator-activated receptor (PPAR) and farnesoid X receptor (FXR), Molecular Informatics, 29(4): 287–292, Wiley, 2010. [doi]
  30. Ramona Steri, Matthias Rupp, Ewgenij Proschak, Timon Schroeter, Heiko Zettl, Katja Hansen, Oliver Schwarz, Lutz Müller-Kuhrt, Klaus-Robert Müller, Gisbert Schneider, Manfred Schubert-Zsilavecz: Truxillic acid derivatives act as peroxisome proliferator-activated receptor γ activators, Bioorganic & Medicinal Chemistry Letters, 20(9): 2920–2923, Elsevier, 2010. [doi]
  31. Matthias Rupp, Timon Schroeter, Ramona Steri, Heiko Zettl, Ewgenij Proschak, Katja Hansen, Oliver Rau, Oliver Schwarz, Lutz Müller-Kuhrt, Manfred Schubert-Zsilavecz, Klaus-Robert Müller, Gisbert Schneider: From machine learning to natural product derivatives selectively activating transcription factor PPARγ, ChemMedChem, 5(2): 191–194, Wiley, 2010. [doi]
  32. Matthias Rupp, Petra Schneider, Gisbert Schneider: Distance phenomena in high-dimensional chemical descriptor spaces: Consequences for similarity-based approaches, Journal of Computational Chemistry, 30(14): 2285–2296, Wiley, 2009. [doi]
  33. Ewgenij Proschak, Matthias Rupp, Swetlana Derksen, Gisbert Schneider: Shapelets: Possibilities and limitations of shape-based virtual screening, Journal of Computational Chemistry, 29(1): 108–114, Wiley, 2008. [doi]
  34. Matthias Rupp, Ewgenij Proschak, Gisbert Schneider: Kernel approach to molecular similarity based on iterative graph similarity, Journal of Chemical Information and Modeling, 47(6): 2280–2286, American Chemical Society, 2007. [doi]

Book chapters

  1. Matthias Rupp: Graph kernels. In Matthias Dehmer, Subhash Basak (editors): Machine Learning Approach for Network Analysis: Novel Graph Classes for Classification Techniques, Wiley, chapter 8, p. 217-243, 2012. [doi]

Conferences and workshops

  1. Matthias Rupp: Many-Body Tensor Representation, Working Conference on Materials and Data Analysis, Harvard University, Cambridge, Massachusetts, USA, March 27–31, 2017.
  2. Matthias Rupp: Many-Body Tensor Representation for Machine Learning of Materials, March Meeting of the American Physical Society, New Orleans, Louisiana, USA, March 13–17, 2017.
  3. Matthias Rupp: Accurate Machine Learning Predictions for Materials Properties, International Workshop on Machine Learning for Materials Science, Aalto University, Espoo, Finland, 2017.
  4. Haoyan Huo, Matthias Scheffler, Matthias Rupp: Many-Body Tensor Representation for Machine Learning of Solids, The 57th Sanibel Symposium, St. Simons Island, Georgia, USA, February 19–24, 2017.
  5. Matthias Rupp: New Data, Validation, Code and Representation for Interpolation Across Chemical Compound Space, Institute for Pure and Applied Mathematics (IPAM) Workshop on Machine Learning Meets Many-Particle Problems, Los Angeles, California, September 26–30, 2016.
  6. Matthias Rupp: Atomistic Machine Learning Models, Probing Potential Energy Surfaces IV (PPES IV), Zermatt, Switzerland, April 10–15, 2016.
  7. Matthias Rupp: Challenges in Development of Accurate and Efficient Atomistic Machine Learning Models, CECAM Workshop on Big Data of Materials Science–Critical Next Steps, Lausanne, Switzerland, November 30–December 4, 2015.
  8. Matthias Rupp: Machine Learning for Quantum Mechanical Properties of Atoms in Molecules, 18th Asian Workshop on First-Principles Electronic Structure Calculations, Tokyo, Japan, November 9–11, 2015.
  9. Matthias Rupp: Predicting Results of Quantum Mechanical Calculations: Challenges for Machine Learning, Frontiers in Data-Driven Science and Technology: Recent Advances in Machine Learning and Applications, Nagoya, Japan, November 5–6, 2015.
  10. Matthias Rupp: Quantum Mechanical Properties of Atoms in Molecules via Machine Learning, Ψk 2015 Conference, San Sebastián, Spain, September 6–10, 2015. [pdf]
  11. Matthias Rupp: Quantum Mechanics / Machine Learning Models, Hands-on Workshop Density Functional Theory and Beyond: First-principles Simulations of Molecules and Materials, Berlin, Germany, July 13–23, 2015. [pdf]
  12. Matthias Rupp, Raghunathan Ramakrishnan, O. Anatole von Lilienfeld: Representing Atoms in Molecules, CECAM/Ψk Workshop From Many-Body Hamiltonians to Machine Learning and Back, Berlin, Germany, May 11–13, 2015.
  13. Matthias Rupp: Properties of Atoms in Molecules via Machine Learning, Workshop on Machine Learning for Many-Particle Systems, Institute for Pure and Applied Mathematics (IPAM), Los Angeles, California, February 23–27, 2015. 
  14. Matthias Rupp: Properties of Atoms in Molecules via Machine Learning, CECAM/Ψk Research Conference on Frontiers of First-Principles Simulations: Materials Design and Discovery, Berlin, Germany, February 1–5, 2015. 
  15. Pavlo O. Dral, Raghunathan Ramakrishnan, Matthias Rupp, Walter Thiel, O. Anatole von Lilienfeld: Combining Semiempirical Quantum Mechanics with Machine Learning: Towards Hybrid Quantum Mechanics/Machine Learning (QM/ML), 50th Symposium on Theoretical Chemistry (STC 2014), Vienna, Austria, September 14–18, 2014. [pdf]
  16. Matthias Rupp: Quantum Mechanics / Machine Learning Models, Institute for Pure and Applied Mathematics, Hands-on Summer School on Electronic Structure Theory for Materials and (Bio)molecules (IPAM GSS2014), Los Angeles, California, USA, July  21–August 1, 2014, 2014. [pdf]
  17. Matthias Rupp: Quantum Mechanics / Machine Learning Models. Recent Successes and Challenges, White Nights of Materials Science: From Physics and Chemistry to Data Analysis, and Back, St. Petersburg, Russia, June 16–20, 2014.
  18. Matthias Rupp: Hybrid Quantum Mechanics/Machine Learning Models, HP2C/PASC Materials Simulation Junior Retreat, Boldern, Männedorf, Switzerland, July 09–12, 2013.
  19. Matthias Rupp, Grégoire Montavon, Vivekanand Gobre, Alvaro Vazquez-Mayagoitia, Katja Hansen, Alexandre Tkatchenko, Klaus-Robert Müller, O. Anatole von Lilienfeld: Machine Learning in Chemical Space: Predicting Electronic Structure Properties, 7th Molecular Quantum Mechanics. Electron Correlation: The Many-Body Problem at the Heart of Chemistry, Lugano, Switzerland, June 2-7, 2013. [pdf]
  20. Grégoire Montavon, Katja Hansen, Siamac Fazli, Matthias Rupp, Franziska Biegler, Andreas Ziehe, Alexandre Tkatchenko, O. Anatole von Lilienfeld, Klaus-Robert Müller: Learning invariant representations of molecules for atomization energy prediction, Advances in Neural Information Processing Systems 25 (NIPS 2012), Lake Tahoe, Nevada, USA, December 3-6, 2012. [pdf]
  21. Matthias Rupp: Kernel-based Machine Learning for Molecular Energy Estimation, CECAM Workshop on Machine Learning in Atomistic Simulations, Lugano, Switzerland, September 10–12, 2012. [pdf]
  22. Matthias Rupp: Modeling of molecular atomization energies using machine learning, 7th German Conference on Chemoinformatics, Goslar, Germany, November 6–8, 2011. [pdf]
  23. Katja Hansen, David Baehrens, Timon Schroeter, Matthias Rupp, Klaus-Robert Müller: Interpretation and explanation of kernel-based prediction models, 242nd Annual Meeting of the American Chemical Society, Denver, Colorado, USA, August 28–September 1, 2011.
  24. Matthias Rupp: From machine learning to novel agonists of the peroxisome proliferator-activated receptor, 24th Annual Conference on Neural Information Processing Systems (NIPS 2010) Workshop on Charting Chemical Space: Challenges and Opportunities for AI and Machine Learning, Whistler, Canada, December 10–11, 2010. [pdf]
  25. Matthias Rupp: Graph kernels for chemoinformatics. A critical discussion, 6th German Conference on Chemoinformatics, Goslar, Germany, November 7–9, 2010. [pdf]
  26. Matthias Rupp, Timon Schroeter, Ramona Steri, Ewgenij Proschak, Katja Hansen, Heiko Zettl, Oliver Rau, Manfred Schubert-Zsilavecz, Klaus-Robert Müller, Gisbert Schneider: Kernel learning for virtual screening: Discovery of a new PPARγ agonist, 5th German C onference on Chemoinformatics, Goslar, Germany, November 8–10, 2009. [pdf] [doi]
  27. Igor Tetko, Iurii Sushko, Sergeii Novotarsky, Robert Körner, Anil Kumar Pandey, Matthias Rupp: Online chemical modeling environment, 1st World Conference on Physico-Chemical Methods in Drug Discovery and Development, Rovinj, Croatia, September 27–October 1, 2009. [pdf]
  28. Matthias Rupp, Petra Schneider, Gisbert Schneider: Distance phenomena in chemical spaces: Consequences for similarity approaches, 4th German Conference on Chemoinformatics, Goslar, Germany, November 9–11, 2008. [pdf]
  29. Timon Schroeter, Matthias Rupp, Katja Hansen, Klaus-Robert Müller, Gisbert Schneider: Virtual screening for PPAR-gamma ligands using the ISOAK molecular graph kernel and Gaussian processes, 4th German Conference on Chemoinformatics, Goslar, Germany, November 9–11, 2008. [pdf]
  30. Matthias Rupp, Ewgenij Proschak, Gisbert Schneider: Molecular similarity for machine learning in drug development, 3rd German Conference on Chemoinformatics, Goslar, Germany, November 11–13, 2007. [pdf] Best poster award
  31. Matthias Rupp, Wolfgang Mergenthaler, Bernhard Mauersberg, Jens Feller: Markov mills, reliable rolls and Monte-Carlo mines: Minimizing the operating costs of grinding mills, Proceedings of the 2005 International Conference on Numerical Analysis and Applied Mathematics (ICNAAM 2005), Rhodes, Greece, September 26–20, 2005. [pdf]

Theses

  1. Matthias Rupp: Kernel methods for virtual screening, PhD dissertation, University of Frankfurt, Germany, 2009. [pdf]
  2. Matthias Rupp: Zeitoptimale Bearbeitungsreihenfolgen für mehrere Schweißroboter: Modelle und Algorithmen, degree dissertation, University of Frankfurt, Germany, 2004. [pdf]

Software

  1. Matthias Rupp: Machine Learning for Quantum Mechanics in a Nutshell, Mathematica implementation, version 2015-07-04. [zip]
  2. Grigorios Skolidis: Multi-task Gaussian process regression, Matlab code, version 2012-05-10. [zip]
  3. Matthias Rupp: Iterative similarity optimal assignment kernel (ISOAK), Java implementation, version 2008-01-15. [mloss] [zip]