RESCUE: Rare Earth Self-Driving Cellular Uptake Engineering (DRAFT)

Rare earths are vital for U.S. economic and national security, underpinning technologies such as magnets, energy storage, electronics, and renewable energy systems, yet their domestic supply chain faces significant extraction challenges. The separation of individual rare earths remains a significant challenge in industrial extraction and refining due to their chemical similarity. Brookhaven National Laboratory (BNL) and the University of Illinois Urbana-Champaign (UIUC) propose to integrate artificial intelligence (AI), laboratory automation, and metabolic and protein engineering to advance foundational science for designing high-affinity metal uptake transporters and metabolic pathways for selective uptake  and intracellular storage of critical rare earths from tailings, mine ash, and electronic waste. By enabling microbes to selectively uptake and store a single rare earth type, researchers aim to simplify extraction and separation processes, followed by cell lysis to recover purified rare earths. In this one-year pilot, researchers will focus on AI-driven, self-optimizing automation to engineer high-affinity metal transporters for selective uptake of terbium (Tb), a critical rare earth for magnets, electronics, and semiconductors.

Over the next 5 years, the developed framework will be extended to engineer metabolic pathways for enhanced extraction, storage, and uptake systems for additional rare earths, contributing to U.S. resilience in the rare earth supply chain. In the long term, this capability provides a framework to address a wider set of BER problems. Below are 12-month short-term and 5-year long-term objectives and expected outcomes.

12-Month Objectives

• Aim 1: Develop AI Models for Protein Engineering. The team will create AI models integrating knowledge graphs, large language models (LLMs), and protein foundation models to predict and design RE-binding proteins.
• Aim 2: Establish an AI-Driven Automation Framework. The team will develop an AI-driven closed-loop automation framework for engineering microbes with high-affinity Tb-uptake transporters. This includes automated library construction, cloning, cell culture, fitness selection with real-time data feedback to AI for iterative optimization.
• Aim 3: Advance Rare Earth–Extraction Science via High-Throughput Characterization. To validate and further improve the AI automation framework, researchers will establish a high-throughput characterization workflow integrating X-ray imaging, spectroscopy, and structural techniques at the National Synchrotron Light Source-II (NSLS-II).
• Expected Outcome: By the end of the 12-month pilot, the team will deliver a prototype framework integrating AI, automation, and characterization to demonstrate selective Tb uptake and separation in engineered microbes, validated by quantitative binding and structural data.

5-Year Objectives

Building on the established year 1 knowledge and framework, the team will (1) Engineer rare earth–specific biosynthetic pathways to improve the delivery of rare earths to uptake transporters. (2) Engineer intracellular storage pathways to increase rare earth accumulation in cells. (3) Extend uptake systems to additional rare earths, such as praseodymium (Pr), neodymium (Nd), and Dysprosium (Dy). (4) Develop biohybrid and biochemical strategies to convert uptake rare earths into value-added materials and catalysts. (5) Integrate AI, automation, and data workflows with DOE BER facilities and data infrastructure to support broader biotechnology and biological discovery within BER’s mission.