Generative molecular design has predominantly been anchored in two-dimensional (2D) methodologies. Despite the growing integration of three-dimensional (3D) post-processing techniques, the development of inherently 3D-generative models remains nascent. This discrepancy introduces a significant gap in predictive models for target-specific objectives operating in the 2D world and the 3D-target binding site of the hit or lead compound.
Recent advancements have seen first ventures into the realm of 3D-generative modeling. However, the synthesizability of the generated molecules remains a major bottleneck, significantly hampering the practical application of these methods. With the wealth of internal data and project-specific filters to restrict the chemical space explored, this bottleneck can be mitigated in the pharmaceutical industry.
For this PostDoc grant, we invite you to submit your research plan that focuses on the development and combination of 3D-generative models and potency predictions for drug design. A successful research proposal to our question will focus on these topics:
- How to develop a 3D-generative algorithm for pharmaceutical drug design by using or combining novel machine learning approaches?
- How would you integrate machine learning, physics-based methods in an early-stage of a project with limited experimental data points?
- In addition, how would you combine various computational chemistry methods that can leverage data to enhance potency predictions?
With your solution, you will be able to benefit from the ecosystem of a large pharmaceutical player and at the same time contribute to better drug design with improved predictive models. Apply now to join Boehringer Ingelheim as part of the prestigious PostDoc grant program opn2TALENTS.
As a winner of this call, you will have the unique opportunity to pursue your own submitted research project as a fully resourced two-years PostDoc (with the option for a one-year extension), in the Computational Chemistry group at Boehringer Ingelheim, Biberach, Germany. As part of an international team of world-class scientists working on computational drug design you will learn the processes and challenges of drug discovery in the pharmaceutical industry from the inside.
At Boehringer Ingelheim, you will have access to a fully equipped state-of-the-art research facility including access to all relevant tools and HPC-enabled technologies. You will benefit from mentoring through our internal experts, have the chance to attend international conferences, and publish your results in high-ranking journals. You will be part of the vibrant PostDoc and data science and AI community at Boehringer Ingelheim in Biberach.
In addition, you can benefit from the rich packages for employee benefit. Our most important asset in achieving our global vision is our people. We prioritize the growth of our people through mentoring, coaching, skill-building, leadership development, and academic support. Our infrastructure promotes wellness with sports groups, health counseling, onsite medical services, and regular check-ups. Achieve work-life balance with flexible work hours, remote working, childcare support, counseling, and convenient amenities. We ensure financial health with employer loans, private insurances, access to discounts, and a company pension scheme. You can also benefit from our excellent healthy on-site catering and the opportunity for take-away meals. We offer relocation support and interim accommodation to make joining us easy.
Your proposal outlining your own research plan should contain a clear description of the planned combination of computational chemistry methods focused on 3D-based generative modelling, and a strategy of training potency models with fewer data points and tailored reward functions towards design objectives while generating molecules in 3D.
Additional requirements:
- Doctoral degree (PhD) in computational (medicinal) chemistry, computer-aided drug design or a related field. Track record of scientific innovation, as demonstrated by scientific publications, patents, relevant presentations, or software code.
- Demonstrated experience in structure- and ligand-based drug design methods (e.g., docking, QSAR, classic molecular dynamics, etc.)
- Familiar with all aspects of protein-ligand interactions.
- Solid python programming knowledge and good code quality is a must.
- Additional knowledge on machine learning (e.g., scikit-learn, Pytorch, and generative chemistry) and free energy calculations is beneficial.
- Outstanding creativity, critical thinking, and analytical as well as problem-solving skills.
- Enthusiastic, self-motivated, and result-driven with a strong desire to achieve scientific excellence and the will to challenge the status quo.
- Strong communication and presentation skills, capable of conveying project information in a clear manner to discipline experts
Please use our PostDoc grant application template to provide a 4–5-page non-confidential proposal (available for download here). Please complement with your CV, publication list, and recommendation letters.
If confidential data exists that would strengthen the proposal, please indicate that information is available to share under a Confidential Disclosure Agreement (CDA). If we find the non-confidential concept proposal sufficiently interesting, we will execute a CDA for confidential discussions.
All incoming applications accompanied by a research plan will be evaluated by a scientific jury, and, upon selection, you as the winner will have the opportunity to pursue your research project as defined by yourself as part of your PostDoc studies at Boehringer Ingelheim. An attractive package including salary, expenses, and additional company benefits will apply.
We can only accept research proposals if they arrive by the submission deadline on May 13, 2025, 11.59 pm PST.
