Christian L. Müller

christian_8048

Christian L. Müller

Research Interests

I am a research scientist and project leader in computational statistics and optimization in the Numerical Algorithms group at the Flatiron Institute.

I am interested in developing computational statistical tools that are applicable in data-driven research in biology and microbial ecology.

On the computational side I work on:

  • High-dimensional variable selection schemes such as the LASSO and the TREX
  • Black-box (a.k.a. gradient-free, derivative-free, direct search) optimization and sampling algorithms such as CMA-ES, Gaussian Adaptation, and adaptive MCMC
  • Proximal algorithms and their application in statistics
  • Statistical and spectral methods to analyze complex networks
  • Statistical tools to describe energy and fitness landscapes

My biological applications include:

  • Inference of microbial interaction networks from 16S rRNA data
  • Inference of transcriptional regulatory networks from high-throughput measurements
  • Robustness of parameter spaces in biological networks 
  • Protein conformation spaces and prediction of deleterious mutations in proteins

A recent CV can be found here (pdf).

I co-organize a mini-symposium on Proximal Algorithms for High-dimensional Statistics as part of the SIAM Conference of Optimization 2017 which will take place on the 22th-25th of May 2017 at the Sheraton Vancouver Wall Centre, Vancouver. Information and registration can be found here.

We have organized  the second workshop on statistical and computational challenges in microbiome research which took place on the 16th-17th of February 2017 at the Broad Institute, Cambridge. Information and registration can be found here (#SACMDA2).

We have organized the first workshop on statistical and computational challenges in microbiome research on the 25th-26th of February 2016 at the Simons Foundation, New York. Further information can be found here.

If you’re interested in working with me at the Flatiron Institute, I have a postdoc (Flatiron Fellow) position available (see here for further information). Please contact me via cmueller[at]simonsfoundation.org for further information.

Selected Publications

Please find below a list of representative publications (more complete list is available on my ResearchGate profile). Some of the accompanying code can be found in my personal github repository. My Erdös number is 3 (P.E., Pavel Valtr, Bernd Gärtner).

Recent manuscripts under review/in preparation

Asmus J,  Müller CL, Sbalzarini IF. Lp-Adaptation: Simultaneous Design Centering and Robustness Estimation of Electronic and Biological Systems. To appear Scientific Reports, 2017

Müller CL, Bonneau R, Kurtz ZD. Generalized Stability Approach for Regularized Graphical Models. https://arxiv.org/abs/1605.07072 [code]

Bien J, Gaynanova I, Lederer J, Müller CL. Theory for the TREX. submitted. [overview]

Äijö, T, Müller CL, Bonneau R, Temporal probabilistic modeling of bacterial compositions derived from 16S rRNA sequencing. http://biorxiv.org/content/early/2016/09/22/076836  [code]

Lederer J, Müller CL. Topology adaptive graph estimation in high dimensions. arXiv preprint arXiv:1410.7279, 2014. [code]

Cázáls F, Robert C, Roth A, Müller CL, Towards Morse Theory for Point Cloud Data. HAL preprint, 2013.

Recent highlights

Combettes PL, Müller CL. Perspective Functions: Proximal Calculus and Applications in High Dimensional Statistics. J. Math. Anal. Appl., 2017  [code]

Raviram R, Rocha PP, Müller CL, Miraldi ER, Fu Y, Swanzey E, Badri S, Proudhon C, Snetkova V, Bonneau R, Skok JA. 4C-ker: A method to reproducibly identify genome-wide interactions captured by 4C-Seq experiments. PLoS Comput Biol 2016; 12(3): e1004780.[code]

Baugh EH, Simmons-Edler R, Müller CL, Alford RF, Volfovsky N, Lash AE, Bonneau R. Robust Classification of Protein Variation Using Structural Modeling and Large-Scale Data Integration Nucl. Acids Res. 2016; 44 (6): 2501-2513[code]

High-dimensional statistics

Bien J, Gaynanova I, Lederer J, Müller CL. Non-convex Global Minimization and False Discovery Rate Control for the TREX. To appear J. Comp. Graph. Stats. 2017  arXiv preprint arXiv:1604.06815  [code]

Hill SM et al., HPN-DREAM Consortium, Inferring causal molecular networks: empirical assessment through a community-based effort. Nature Methods, 2016.

Kurtz ZD*, Müller CL*, Miraldi ER*, Littman DR, Blaser MJ, Bonneau RA. Sparse and compositionally robust inference of microbial ecological networks. PLoS Comput Biol. 2015;11(5):e1004226  (* joint first authors) [code]

Lederer J*, Müller CL*. Don’t fall for tuning parameters: Tuning-free variable selection in high dimensions with the TREX. Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015. (* joint first authors).  [code]

Optimization and Monte Carlo sampling

Stich SU, Müller CL, Gärtner B. Variable Metric Random Pursuit. Math Program A, May 24, 2015.

Müller CL. Stochastic methods for single objective global optimization. In: AAIA Computational Intelligence in Aerospace Sciences, 2014. 63-112.

Stich SU, Müller CL, Gärtner B. Optimization of convex functions with Random Pursuit. SIAM J Optim 2013;23(2):1284-1309.

Müller CL, Sbalzarini IF. Gaussian adaptation revisited: an entropic view on covariance matrix adaptation. In: Di Chio C, Cagnoni S, Cotta, C, et al., Applications of Evolutionary Computation: EvoApplications 2010. Berlin and Heidelberg, Germany: Springer; 2010:432-441. [code]

Müller CL, Baumgartner B, Sbalzarini IF. Particle swarm CMA evolution strategy for the optimization of multi-funnel landscapes. Proc. IEEE Congress on Evolutionary Computation (CEC), May 18-21, 2009; Trondheim, Norway[code]

Fitness and energy landscapes

Müller CL, Sbalzarini IF. Energy landscapes of atomic clusters as black box optimization benchmarks. Evol Comput. 2012;20(4):543R573. [code]

Müller CL, Sbalzarini IF. Global characterization of the CEC 2005 fitness landscapes using fitness-distance analysis. In: Di Chio C, Cagnoni S, Cotta C, et al., eds. Applications of Evolutionary Computation: EvoApplications 2011. Berlin and Heidelberg, Germany: Springer; 2011:294-303.

Biological data analysis and modeling

Mahana, D, Trent CM, Kurtz, ZD, Bokulich, NA, Battaglia T,Chung, J, Müller CL, Li, H, Bonneau RA, Blaser MJ. Antibiotic perturbation of the murine gut microbiome enhances the adiposity, insulin resistance, and liver disease associated with high-fat diet Genome Medicine, 8:48, 2016.

Plessis A, Hafemeister C, Wilkins O, Gonzaga ZJ, Meyer RS, Pires I, Müller CL, Septiningsih EM, Bonneau R, Purugganan M. Multiple abiotic stimuli are integrated in the regulation of rice gene expression under field conditions. eLIFE 2015.

Tchourine K*, Poultney CS*, Wang L*, Silva GM, Manohar S, Mueller CL, Bonneau R, and Vogel C. One third of dynamic protein expression profiles can be predicted by a simple rate equation. Mol Biosyst. 2014;10:2850-2862. (* joint first authors)

Billerbeck S, Calles B, Müller CL, de Lorenzo V, Panke S. Towards Functional Orthogonalisation of Protein Complexes: Individualisation of GroEL Monomers Leads to Distinct Quasihomogeneous Single Rings. Chembiochem. 2013;14(17):2310-2321.

Müller CL, Sbalzarini IF, van Gunsteren WF, Zagrovic B, Hünenberger PH. In the eye of the beholder: inhomogeneous distribution of high resolution shapes within the random walk ensemble. J Chem Phys. 2009;130(21):214904.

Theses

Müller CL. Black-box landscapes: characterization, optimization, sampling and application to geometric configuration problems [Dissertation]. Zürich, Switzerland: ETH Zürich; 2010.

Müller CL. Parameter sensitivity analysis in behavioral and analog circuit simulations of neuro-fuzzy models [Diploma thesis]. Tübingen, Germany: University of Tübingen; 2006.

Müller CL. die erde dreht sich zu laut: gedichte von der schwedischen oberfläche [Certificate thesis]. Tübingen, Germany: University of Tübingen; 2005.

Müller CL. High order accurate numerical solution of the linearized Euler equations for sound propagation in the atmosphere [Master’s thesis]. Uppsala, Sweden: Uppsala University, 2004.

Active Collaborations

Jacob Bien, Department BSCB, Cornell University, USA, High-dimensional statistics.

Patrick Combettes, NC State, USA, Proximal algorithms.

Martin Blaser, New York School of Medicine, USA, Microbiome data analysis.

Johannes. Lederer, Statistics Department, UW Seattle, USA, High-dimensional statistics.

Ivo F. Sbalzarini, Max-Planck-Institute for Cell Biology, Dresden, Germany, Markov Chain Monte Carlo, Optimization.

Thomas J. Fuchs, Memorial Sloan Kettering Cancer Center, New York, USA, Approximate Bayesian Computation .

Frederic Cazals, INRIA Sophia-Antipolis, Sophia-Antipolis, France, Computational topological analysis of high-dimensional sampled landscapes.

Bojan Zagrovic, Max F. Perutz Laboratories and University of Vienna, Vienna, Austria, Conformation space analysis of chain molecules.

Co-Principal Supervision of Students

PhD theses (since 2010):

Sebastian Stich (completed, with Dr. Bernd Gärtner, ETH Zürich) now at UC Louvain, Belgium

Josefine Asmus (ongoing, with Dr. Ivo F. Sbalzarini, MPI Dresden)

Master/diploma theses (2006-2010, ETH Zürich):

Ana Tusek, Benedikt Baumgartner, Christian Fiegl, Georg Ofenbeck, Markus König, Daniel Zünd, (with Ivo F. Sbalzarini), Thomas Lampart (with Peter Widmayer)

Bachelor/semester theses (2006-2010, ETH Zürich):

Johannes Lederer, Yannick Misteli, Patrick Plattner (with Ivo F. Sbalzarini)

Mentoring  of Graduate Students (since 2013, NYU):

Evan Baugh, Zachary Kurtz, Ramya Raviram

Josh Fass (Principal supervisor John Chodera, MSKCC)