PhD position - Molecular simulation and machine-learning predictive chromatography modeling

Organisation/Company Forschungszentrum Jülich

Research Field All Researcher Profile First Stage Researcher (R1) Final date to receive applications 19 Jan 2038 - 03:14 (UTC) Country Germany Type of Contract To be defined Job Status Other Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

IBG-4 - Bioinformatik

Area of research:

PHD Thesis

Your Job:

Chromatography modeling, while crucial for modern bipporcess development, still heavily relies on empirical determination of key model parameters. By combining protein structure descriptors, molecular simulations, and machine learning, this PhD project seeks to predict ion-exchange isotherm parameters directly from molecular properties. These predictions will be integrated into the open-source CADET simulation framework, enabling fully predictive process simulations without extensive experimental calibration.

Embedded in the Helmholtz Graduate School for Data Science in Life, Earth and Energy (HDS-LEE), the project offers an interdisciplinary research environment at the interface of bioengineering, computational biophysics, and data-driven modeling, with strong links to open-source software development and industrially relevant applications.

• Development of molecular descriptors from protein structures and simulations
• Design and training of QSPR and machine learning models to predict ion-exchange isotherm parameters
• Integration of predicted parameters into the CADET chromatography simulation framework
• Simulation and analysis of batch and gradient elution processes using predictive isotherms
• Curation and analysis of experimental chromatography data for model training and validation
• Collaboration with experimental and industrial partners
• Dissemination of results through high-quality publications and open-source software contributions

• Master’s degree in chemical engineering, biotechnology, computational biophysics, bioinformatics, data science, or a closely related discipline with a strong academic record
• Genuine interest in data-driven and physics-based modeling, molecular simulations, and their application to bioprocesses and bioseparations
• Proficiency in at least one programming language, preferably Python; experience with scientific computing, numerical modeling, or machine-learning frameworks is an asset
• Strong analytical skills with a solid understanding of data evaluation, modeling, and interpretation of complex datasets
• Ability to work independently as well as collaboratively in an interdisciplinary and international research environment
• Very good written and oral communication skills in English; knowledge of German is beneficial but not required
• High motivation for academic development, demonstrated by academic transcripts and references, and interest in publishing and presenting scientific results

We work on the very latest issues that impact our society and are offering you the chance to actively help in shaping the change! We offer ideal conditions for you to complete your doctoral degree:

• Outstanding research environment and infrastructure:
  The position is embedded at Forschungszentrum Jülich (FZJ), one of Europe’s largest interdisciplinary research centers, offering access to world-class computational resources (HPC), state-of-the-art research software, and close integration with experimental and modeling groups across institutes and Helmholtz programs.
• Structured doctoral training and international visibility:
  The PhD candidate will be part of the HDS-LEE graduate school, benefiting from a structured qualification program, dedicated mentoring, transferable-skills training, and funding for international conferences, research stays, and networking within the Helmholtz Association.
• Unique combination of science-to-impact opportunities:
  The project combines molecular biophysics, machine learning, and industrially relevant bioprocess modeling with strong links to open-source platforms (e.g., CADET) and academic–industrial collaborations, offering a rare opportunity to develop skills that…