Molecular Manipulation Lab

Machine learning for the identification of molecular conformations

We can overcome the information gap by acquiring large amounts of data while manipulating the molecule a small region around its current conformation. As long as this manipulation is fully reversible, the conformation is essentially not changed. We will implement machine learning solutions (such as (un)supervised learning, kernel ridge regression, support vector machines etc.) for the various data analysis tasks required in this context. Supervised machine learning which, based on wavelet analysis, detects discontinuities in the experimental signals that indicate (irreversible) conformational relaxations. Unsupervised machine learning to structure small segments of experimental data into larger units. Acquiring large amounts of simulation data using a reliable and accurate molecular mechanics model. Supervised machine learning (support vector machine) to determine the shape of the region within which manipulation is reversible for experimental and simulated data. Kernel regression to interpolate measured and simulated data in each region. An algorithm to assign experimental regions to simulated ones on a bipartite graph via measurements of manifold distances. This creates a map of all possible manipulation processes.

White Paper: Understanding Many-Particle Systems with Machine Learning, Inst. of Pure and Appl. Mathematics (IPAM) (2017)

January 19th, 2023

MomaLab is part of the Orbital Cinema project!

September 8th, 2022

Warmest congratulations to Taner Esat for winning the Gerhard Ertl Young Investigator Award for his outstanding work in surface science, particularly metastable standing molecules.

April 7th, 2022

Want to make your own standing molecule? "Design Principles for Metastable Standing Molecules" Read at J. Phys. Chem. C

October 10th, 2021

We finally knocked it down: "The stabilization potential of a standing molecule" Read at Science Advances Press release

October 22nd, 2020

Introducing machine learning to the nanoscale: "Autonomous robotic nanofabrication with reinforcement learning" Read at Science Advances Press release

July 2020

Our Helmholtz-AI project MomoNano (together with HZB and TU-Berlin) successfully competed for a three year funding by the Helmholtz Association.

September 2nd, 2020

"The theory of scanning quantum dot microscopy" Read at J Phys. Cond. Mat.
Meet us at
▶   "...home"