Master’s project

IBM Zurich Research Laboratory
WorkplaceZurich, Zurich region, Switzerland
Master’s project

Chemical Reservoir Computing

Ref. 2024_003

Project description The brain is the world’s most amazing, energy-efficient computer and runs entirely on chemical reactions. The vision of the EU Project CORENET is to deploy complex chemical reaction networks (CRNs) as computing unit to process information. Fully automated liquid-handling hardware and multi-functional reactors are available to initiate and control chemical reactions by changing composition and steering the evolution of the CRN. As a result, a large number of chemically diverse products is being generated and analyzed by a combination of optical inline spectroscopy (e.g. UV-VIS and FT-IR) and offline mass-spectroscopy (e.g. LC-MS, MS-MS, TIMS-ToF), supported by cheminformatics and metabolomics algorithms.

The goal of this master project is to treat the chemical processor as a reservoir and use it for classification tasks. This work includes:

extraction of compound-specific features from existing analytical data;

creating an output feature vector comprising both qualitative and quantitative information;

establishing a data pipeline to automatically feed in feature vectors for different input parameters covering a large phase space (chemical input + operation input + initial state);

performing in-silico trainings for typical classification problems and different type of CRNs, and search and calculate elementary reaction pathways connecting CRN feedstock reagents with selected compounds verified by MS-MS spectroscopy for reasoning by quantum chemistry.

Besides these data science tasks, interaction with the chemical computer located at IBM Research Europe - Zurich (in Rüschlikon, Switzerland) is desired to iteratively optimize the chemical protocols used for the operation of the wet-chemistry system. In addition to the static input variation of the CRN, dynamic operation combined with real-time read-out may be targeted. Furthermore, theoretical quantum chemistry models should be applied to reason about the evolution of the CRN by suggesting and calculating elementary reaction pathways connecting species in the network with experimentally validated compounds.

Requirements Applicants are expected to hold a bachelor’s degree in computer, data or mathematical science, theoretical chemistry or an engineering discipline and to have a broad interest in data science, chemistry, automatization and artificial intelligence. A background in statistics and machine learning as well as hands-on experience with data analysis in Python, R, or MATLAB is required. Excellent communication and presentation skills would be of added value. If you are enthusiastic, willing to learn and explore, and want to become part of an open, collaborative and multi-cultural team dedicated to scientific excellence, then please apply below.

Diversity IBM is committed to diversity at the workplace. With us you will find an open, multicultural environment. Excellent flexible working arrangements enable all genders to strike the desired balance between their professional development and their personal lives.

How to apply If you are interested in this position and you fulfill all the requirements, please submit your application including a motivation letter, a complete curriculum vitae and the names of at least two references.

For technical questions, please contact please contact Dr. Emanuel Lörtscher, !--

[1] M. Dueñas-Diez and J. Pérez-Mercader, "How chemistry computes: language recognition by non-biochemical chemical automata. From finite automata to turing machines," IScience, vol. 19, pp. 514-526, 2019.
[2] Wozniak, Stanislaw, et al. "Deep learning incorporating biologically inspired neural dynamics and in-memory computing." Nat. Mach. Intell., vol. 2, June 2020, pp. 325-36, doi:10.1038/s42256-020-0187-0.
[3] Maass, Wolfgang. "Liquid state machines: motivation, theory, and applications." Computability in context: computation and logic in the real world (2011): 275-296.

!-- -------- Use this side column for images ----------------

Footer links



Terms of use
In your application, please refer to and reference JobID 2837224.