Data Mining and AI-Assisted Optimization of Potential-Controlled Membrane Affinity Chromatography
- Institute
- Lehrstuhl für Bioseparation Engineering (TUM-ED)
- Type
- Content
- Description
Affinity membrane chromatography enables highly efficient capture of biomolecules, but the development of robust next-generation separation processes increasingly requires structured use of experimental, analytical, and simulation data. At the Chair of Bioseparation Engineering (BioSE), a new platform technology for potential-controlled affinity membrane chromatography (pcMAC) is under active development, generating heterogeneous datasets from chromatography runs, electrochemical control, module testing, and bioanalytical characterization.
This master’s thesis focuses on the data mining and AI-assisted optimization of pcMAC process data. The student will develop a structured workflow to integrate historical and newly generated datasets from ÄKTA/UNICORN exports, electrochemical measurements, simulation outputs, process metadata, and offline analytics into a machine-readable data infrastructure.
The work includes data harmonization, automated feature extraction, multivariate data analysis, and predictive modeling. Relevant process features may include UV peak properties, pressure response, conductivity and pH shifts, current and charge profiles, recovery, artefact indicators, and module-specific metadata. Based on these features, statistical and machine-learning approaches will be used to identify process patterns and support the selection of suitable voltage profiles, buffer conditions, and operating windows.
Depending on project progress, the developed models may be used to propose experimentally testable process conditions for pcMAC optimization. The project therefore combines data science, process analytics, chromatography, and downstream bioprocess development to transform complex pcMAC datasets into actionable process knowledge.
The project is embedded in a highly innovative and confidential research context with strong relevance for future automation, scale-up, and technology transfer.
The work is primarily conducted at the laboratories of the Munich Institute of Integrated Materials, Energy, and Process Engineering (MEP) and at the former Biotechnikum in the Mechanical Engineering Building (MW). Data analysis and programming work can be performed flexibly depending on project needs.
Supervision is provided by Eike K. Theel, who has extensive experience in experimental downstream processing, chromatography systems, automation, and data-driven process development. Close scientific guidance and regular meetings ensure structured progress and application-driven development.
Please submit a CV, a current transcript of records, and a short motivation statement (1–2 sentences) describing your interest in the topic and your preferred starting date to the contact address below.
For questions or further information, you are very welcome to contact me directly. I am also happy to discuss alternative or related thesis topics within the broader field of data-driven bioprocess development, automation, and bioseparation engineering.
Contact: Eike K. Theel (he/him) Chair of Bioseparation Engineering (BioSE), TUM E-mail: eike.theel@tum.de Phone: +49 89 289 52764
- Requirements
- Background in biotechnology, bioprocess engineering, bioinformatics, data science, chemical engineering, computer science, or a related field.
- Interest in downstream processing, chromatography, process analytics, automation, and data-driven optimization.
- Basic experience with Python-based data analysis is advantageous; familiarity with pandas, scikit-learn, DoE, machine learning, or simulation tools is helpful but not mandatory.
- Motivation to work independently at the interface of experimental bioprocessing, process data analysis, and AI-assisted model development.
- Possible start
- sofort
- Contact
-
Eike Kristian Theel
Room: 5414.01.1013
Phone: 08928915761
eike.theeltum.de