24.07.2025

Modeling and simulation of Expanded Bed Chromatography

Internship: Modeling and simulation of Expanded Bed Chromatography
read more

Kontakt: n.kohn@tum.de

24.07.2025

Master Thesis: Modeling SNP-Conditioned Cellular Phenotypes via Flow Matching in the labs of Prof. Fabian Theis and Dr. Matthias Heinig

Context

Advances in high-throughput single-cell profiling and large-scale phenotypic screens have unlocked unprecedented insights into cellular heterogeneity and the effects of experimental perturbations. Tools like CellFlow (Klein et al. 2025), a generative framework based on flow matching, have demonstrated powerful capabilities in predicting cellular responses to perturbations such as drug treatments, gene knockouts, or cytokine stimulations.

In parallel, population-scale genomics projects such as OneK1K (Yazar et al. 2022), which combine genetic variation (e.g., SNPs) with single-cell RNA-seq data, provide a rich substrate for exploring how genetic variation modulates cellular phenotypes. This thesis will integrate these two directions, leveraging CellFlow to model how SNP-defined genetic backgrounds influence cellular responses to perturbations, with a particular focus on QTL-associated variants and epistatic interactions.

Thesis Goals and Research Questions

The primary objective of this thesis is to extend CellFlow to incorporate individual-specific genetic variation, particularly common SNPs, as conditioning variables. This enables predictive modeling of single-cell phenotypes under both genetic and experimental perturbation contexts, with applications ranging from fundamental questions in gene regulation, genetic risk prediction and genotype-informed response prediction. A longer-term goal is to position this framework as a tool for modeling cellular phenotypes relevant to disease predisposition, therapeutic response, and inter-individual variability. Specific questions include:

• Can we model epistatic interactions between SNPs in terms of their effect on phenotypic response trajectories?
• Can we identify causal variants and study gene-environment interactions?
• How well can CellFlow predict phenotypes for unseen SNP combinations or rare alleles, particularly under perturbation conditions?
• Can SNP-conditioned models reveal genotype-dependent variation in cellular responses that align with known or hypothesized disease mechanisms?
• To what extent can SNP-conditioned models be generalized or transferred across genetically diverse populations or cell types?

Methodology and Scope

• Adapt the CellFlow architecture to ingest SNP-based sample covariates, including QTLs and epistatic variant pairs.
• Use genotype-informed embeddings (e.g., one-hot encoding, gene embeddings inferred from ESM3 (Hayes et al. 2025), learned SNP embeddings inferred from DNA language models (Nguyen et al. 2023; Hingerl et al. 2025), or integration with known functional annotations (Zheng et al. 2024)).
• Evaluate on datasets such as OneK1K, eQTL Consortium, or sc-eQTLGen.
• Compare against baseline models, such as:
  • Conditional VAEs
  • Epistasis prediction models

Candidate Profile

• Strong background in machine learning, computational biology, or bioinformatics
• Familiarity with deep generative models
• Experience with single-cell RNA-seq data and basic statistical genetics
• Programming skills in Python, PyTorch or JAX, and data science tools

How to Apply

Send an email to matthias.heinig@tum.de, dominik.klein@helmholtz-munich.de, and lucas.arnoldt@tum.de with the following information:

• Your CV
• A brief introduction outlining your background and motivation
• Your preferred start date
• Academic transcripts

We look forward to receiving your email!

References

• Klein et al. (2025). CellFlow enables generative single-cell phenotype modeling with flow matching. bioRxiv; DOI: 10.1101/2025.04.11.648220
• Yazar et al. (2022). Single-cell eQTL mapping identifies cell type–specific genetic control of autoimmune disease. Science, 376 (6589); DOI: 10.1126/science.abf3041
• Hayes et al. (2025). Simulating 500 million years of evolution with a language model. Science, 387 (6736); DOI: 10.1126/science.ads0018
• Nguyen et al. (2023). HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution. arXiv; DOI: 10.48550/arXiv.2306.15794
• Hingerl et al. (2025). scooby: Modeling multi-modal genomic profiles from DNA sequence at single-cell resolution. bioRxiv; DOI: 10.1101/2024.09.19.613754
• Zheng et al. (2024). Leveraging functional genomic annotations and genome coverage to improve polygenic prediction of complex traits within and between ancestries. Nature Genetics, 56; DOI: 10.1038/s41588-024-01704-y

Kontakt: Lucas Arnoldt; TUM School of Computation, Information and Technology; lucas.arnoldt@tum.de

22.07.2025

Computational Modeling of Motivation and Emotion (Internship/Thesis)

The working unit AG Personality & Motivation (Prof. Dr. Markus Quirin) of TUM School of Medicine & Health offers an Internship (and/or BSc/MSc thesis) Working in the area of Computational Modeling of Motivation & Emotion: Psychology Engineering - Robotics - Computational Neuroscience We look for: a motivated student with a background in engineering (control systems, cybernetics, dynamic systems), AI, robotics, or (neuro)computational (e.g., cognitive) modeling with an interest in psychology. The length of the internship is 3 months at maximum but may be a step into a thesis, publication, or other form of cooperation. Note that the internship is unpaid. We offer: • Working on an exciting project of simulating human mind (i.e., motivation, emotion, cognition & personality). • The chance to start an academic career in this field of research. • A young, open-minded, and international team. • Diverse and challenging tasks at the forefront of interdisciplinary research. • In-depth insights and strong involvement in our research activities. • A relatively flexible work arrangement regarding location and time, so your studies are not compromised. • The possibility to integrate your bachelor's/master's thesis or project studies with the specified topic. Requests for supervising theses or research internships in this area are possible regardless of the advertised position. Process of Application: Please send the following application documents in a PDF document via email to m.quirin@tum.de: • brief statement of motivation • Curriculum Vitae (especially degrees, grades, practical and academic experiences) • transcript of records (updated) Please use the following subject line: "Internship/Thesis on Modeling the Mind". We look forward to receiving your application!
read more

Kontakt: m.quirin@tum.de

22.07.2025

Project studies/work (e.g., WI000684), research internships (e.g., MCTS0047, POL30001) in "AI chatbots in healthcare: Ethical considerations".

The Chair of Business Ethics and the Institute for Ethics in AI (Prof. Dr. Christoph Lütge) offers project studies/work (e.g., WI000684), research internships (e.g., MCTS0047, POL30001) in the following areas: AI chatbots in healthcare: Ethical considerations Background. As AI-empowered decision-support systems become more widespread and accessible to the public, individuals are increasingly delegating their decisions to these tools, including those involving ethical considerations, such as decisions in healthcare. For example, algorithms can guide the allocation of scarce medical resources, such as donated organs (Meier et al., 2022). ChatGPT, specifically, has demonstrated promise in improving triage accuracy in emergency departments (Kaboudi et al., 2024) and can serve as a personal therapist by delivering mental health support to individuals in real-time (Alanezi, 2024). This growing integrating into highly sensitive and personal decision-making brings substantial societal implications and risks, such as emerging responsibility gaps, the reinforcement of existing biases, limitations on data privacy, or moral deskilling (e.g., Hagendorff, 2024; Poszler & Lange, 2024). Goal & tasks. During the project work, students will concentrate on tasks related to the use of AI chatbots in decision-making processes within triage and mental health contexts. Potential tasks may include: • Networking and partner identification: Locating leading researchers, professionals, practitioners, technology companies, and startups active in the field • Literature review: Systematically identifying key publications and synthesizing the current state of research • Qualitative research: Supporting the design, execution, and analysis of semi-structured interviews and focus groups Student Profile. • Bachelor or Master level • Any disciplines and departments/schools (Please verify with your school if they permit supervision by us/TUM SOT) • Proficiency in English • Skills and/or strong interest in any of the following fields: artificial intelligence, LLMs and AI chatbots, ChatGPT, AI ethics, medical ethics, healthcare (specifically, triage and mental health), moral psychology, qualitative or quantitative research. Details. Supervisor: Dr. Franziska Poszler Starting date: as soon as possible Time commitment: flexible: Full-time or part-time How to apply. If you are interested, please send your CV along with your module number and earliest possible start date to Dr. Franziska Poszler (franziska.poszler@tum.de). We are looking forward to your application!
read more

Kontakt: franziska.poszler@tum.de

22.07.2025

Masterarbeiten: Entwicklung potenzialgesteuerter Affinitäts-Membranchromatographie & digitaler Prozessmodelle

Spannende Masterarbeiten am BioSE Lehrstuhl der TUM zur Antikörperaufreinigung mit potenzialgesteuerter Membranchromatographie (pcAMC). Mögliche Schwerpunkte: Labor, Simulation, digitaler Zwilling, Analytik. Flexible Rahmenbedingungen mit wöchentlicher Betreuung. Start jederzeit, mind. 6 Monate.
read more

Kontakt: eike.theel@tum.de

21.07.2025

Thesis Projects in World Models

read more

Kontakt: xingcheng.zhou@tum.de

18.07.2025

Abschlussarbeiten, Bachelor- und Masterarbeiten

read more

Kontakt: vasilije.rakcevic@tum.de

18.07.2025

[Forschungspraxis/Masterthesis] BLDC Custom actuator Electronics Hacking

read more

Kontakt: vasilije.rakcevic@tum.de

18.07.2025

CAD Sketch of Parallel Elastic Actuator

[Forschungspraxis/Master Thesis] System prototyping & Control Characterization of Novel Elastic Actuator

read more

Kontakt: vasilije.rakcevic@tum.de

18.07.2025

Master Thesis in AI Agents

read more

Kontakt: yakov.golovanev@gmail.com