Machine Learning for Synthetic Chemistry
Postdoc to use machine learning to analyze and develop synthetic chemistry for the Navy, including pathway design and data augmentation.
This grant is no longer accepting proposals
NRC Research Associateship Programs has archived this opportunity.
Funder: NRC Research Associateship Programs
Due Dates: May 1, 2025 (Application Deadline)
Funding Amounts: $99,200 stipend plus $3,000 travel allowance; typical postdoctoral fellowship duration 2-3 years.
Summary: Postdoctoral fellowship to apply machine learning techniques to analyze and develop synthetic chemistry pathways relevant to the U.S. Navy.
Key Information: Open to U.S. citizens and permanent residents with a Ph.D.; requires prior programming experience and basic synthetic chemistry knowledge; relocation and health insurance benefits included.
Description
This postdoctoral research opportunity at the Naval Research Laboratory (NRL) focuses on applying machine learning algorithms to the analysis and development of synthetic chemistries of interest to the U.S. Navy. The research initially involves:
- Assessing data availability in commercial reaction databases and other sources.
- Designing custom machine representations for relevant chemical transformations.
- Implementing scripts for data retrieval, formatting, and visualization to be validated by human experts.
Subsequent research phases may include:
- Training data augmentation strategies such as on-the-fly generation of no-go reactions.
- Developing neural networks for generating single-step retrosynthetic transformations.
- Creating neural networks for feasibility ranking of synthetic pathways proposed by machines or humans.
The ultimate goal is to integrate these approaches with sequential decision-making algorithms to design multistep retrosynthetic pathways for chemical compounds relevant to Navy interests.
Applicants should have experience with high-level programming languages (e.g., Python, MATLAB), familiarity with UNIX/Linux environments, and a basic understanding of synthetic chemistry principles. While in-depth machine learning expertise is highly desirable, it is not strictly required.
Keywords
Retrosynthesis, computer-assisted synthesis planning, machine learning, deep learning, neural networks, tree search, TensorFlow, Keras, Scikit-learn, Rdkit, Python, theoretical chemistry.
