Phd and Postdoc Positions

**Heidelberg University** is a comprehensive university with a strong focus on research and international standards. With around 30,000 students and 8,400 employees, including numerous top researchers, it is a globally recognised institution that is also of outstanding economic importance for the Rhine-Neckar metropolitan region.

The University has recently established a new Faculty of Engineering Sciences at the interface of material science, molecular biotechnology and computational science.

The **ZMBH** has a long tradition of conducting cutting-edge research in molecular and cell biology, as well as biomedicine. In the years to come, we anticipate rapid advancements and new technologies in the fields of synthetic DNA, artificial intelligence (AI), and all natural sciences. These advancements will collectively drive progress in synthetic and molecular biology, presenting entirely new possibilities for biomedicine, bioengineering, and biomanufacturing. With the CZS Center SynGen Initiative the ZMBH is on a mission to contribute to these developments with fundamental, theoretical or applied research towards programmable biology.

The new **CZS Center SynGen** supported by the Carl-Zeiss-Stiftung promotes research and development at the participating Universities in Heidelberg, Karlsruhe and Mainz to develop an internationally visible research focus on Synthetic Genomics.

Our Junior group develops Deep Genomic Sequence-to-Function (DGS2F) models to explore how genomic sequences influence gene regulatory functions. These highly scalable models integrate various data modalities that measure different aspects of gene regulation in a high-throughput manner. Our research is at the forefront of advancing these models′ foundational understanding of gene regulation. We are pursuing three exciting directions: 1) Scaling up current models with single-cell data across diverse species and data types, 2) Incorporating readily available cell type-specific data to train the next generation of cell type-agnostic models, capable of predicting for unseen cell types and conditions, and 3) Developing new generative models to leverage DGS2F’s foundational knowledge for creating synthetic regulatory elements with tailored properties for biotechnology.

**PhD and PostDoc positions (f/m/d)**

Joining our junior research group offers a collaborative and international work environment where you can gain hands-on experience and develop crucial research skills. The role provides invaluable opportunities for professional growth, equipping you with technical expertise at the intersection of AI and genomics, essential for a successful research career. You′ll have the freedom to explore and develop your own research ideas, fostering innovative thinking and enhancing problem-solving skills in a supportive setting that builds your confidence as an independent researcher. The position comes with flexible working hours, German statutory health insurance, company pension scheme, annual special payments, 30 days of vacation, and a subsidised job ticket for public transit.

Currently we have three different **Projects**:
**1. Developing multi-modal Deep Neural Networks to learn the cis-regulatory code at single-cell resolution**

The cis-regulatory code governs when, where, and how much of gene products are created in cells, enabling the formation of various cell types from a single genome. Variants disrupting this code can lead to genetic diseases. Experimentally measuring all cis-regulatory sequence variations is nearly impossible. However, deep sequence-to-function models can learn the relationship between genomic sequences and their regulatory function from massive collections of genome-wide high-throughput datasets. In this process, they gain knowledge about the regulatory sequence grammar of our cells which can be used to predict the effects of unseen regulatory sequences. However, current state-of-the-art models have limitations, particularly in understanding complex sequence grammar arising from the complex multi-layered regulatory processes and the interplay of distal sequence elements. Improving these models’ foundational understanding of gene regulation involves enhancing cell type resolution, integrating various data modalities, and using cross-species data. This poses significant engineering challenges, and new model architectures are needed to effectively manage and learn from the large, and diverse datasets. This project will develop multi-modal sequence-to-function models and new explainable AI methods in pytorch or similar deep learning environments to determine the cis-regulatory code of multi-cellular species.

**2. Generating cell type specific synthetic regulatory nucleotide sequences with generative sequence-to-function models**

Genomic sequence-to-function models can learn the cis-regulatory language from a large set of genome-wide measurements. Combining these deep sequence-to-function models with generative p