Abstract & Details
Description
Award ID: 2449589
Transporters with Transformers The proposal aims to overcome limitations in biomanufacturing by designing proteins known as transporters, proteins that act like molecular doors that control how molecules move in and out of cells. Transporters limit how well cells can produce the valuable chemicals used in products like fragrances, polymers, and food because transporters are selective in the cargo they release from a cell. Identifying the right transporter for a specific molecule is slow and inefficient. By applying artificial intelligence, this project will create user-friendly tools that allow researchers to design transporters for many different chemicals, making bioproduction faster and more cost-effective. This innovation will support domestic manufacturing, reduce reliance on high-risk supply chains, and drive economic growth using resources like plant waste to create commodity molecules. In addition to advancing science, the project will foster collaboration between industry and academia, train the next generation of researchers, and contribute to building a resilient U.S. bioeconomy. The proposal addresses a critical bottleneck in bioproduction: the inefficient transport of small molecules across cell membranes, which limits titers, rates, and yields (TRY) in microbial production systems. By leveraging advancements in AI and machine learning (ML), this project will develop computational tools to design transporters with improved specificity and activity. These tools will incorporate protein language models, structural modeling, and data-driven predictions to identify and optimize transporter-substrate specificity. The research will focus on two target molecules chosen for their economic significance in industries such as polymers, food supplements, and agricultural chemicals. The project will validate these models in real-world bioproduction strains and integrate the findings into a publicly accessible web application, enabling widespread adoption of transporter design methodologies. Beyond enhancing TRY, this work has broader implications for drug delivery systems and other applications involving cellular transport mechanisms. By integrating experimental validation with AI-based design, the project will establish a pipeline for improving biomanufacturing efficiency and supply chain resilience. Furthermore, this project will advance fermentation-based synthetic methods and promote the adoption of U.S. based bioproduction technologies. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
NSF Program Director: Waleed Nasser
Transporters with Transformers The proposal aims to overcome limitations in biomanufacturing by designing proteins known as transporters, proteins that act like molecular doors that control how molecules move in and out of cells. Transporters limit how well cells can produce the valuable chemicals used in products like fragrances, polymers, and food because transporters are selective in the cargo they release from a cell. Identifying the right transporter for a specific molecule is slow and inefficient. By applying artificial intelligence, this project will create user-friendly tools that allow researchers to design transporters for many different chemicals, making bioproduction faster and more cost-effective. This innovation will support domestic manufacturing, reduce reliance on high-risk supply chains, and drive economic growth using resources like plant waste to create commodity molecules. In addition to advancing science, the project will foster collaboration between industry and academia, train the next generation of researchers, and contribute to building a resilient U.S. bioeconomy. The proposal addresses a critical bottleneck in bioproduction: the inefficient transport of small molecules across cell membranes, which limits titers, rates, and yields (TRY) in microbial production systems. By leveraging advancements in AI and machine learning (ML), this project will develop computational tools to design transporters with improved specificity and activity. These tools will incorporate protein language models, structural modeling, and data-driven predictions to identify and optimize transporter-substrate specificity. The research will focus on two target molecules chosen for their economic significance in industries such as polymers, food supplements, and agricultural chemicals. The project will validate these models in real-world bioproduction strains and integrate the findings into a publicly accessible web application, enabling widespread adoption of transporter design methodologies. Beyond enhancing TRY, this work has broader implications for drug delivery systems and other applications involving cellular transport mechanisms. By integrating experimental validation with AI-based design, the project will establish a pipeline for improving biomanufacturing efficiency and supply chain resilience. Furthermore, this project will advance fermentation-based synthetic methods and promote the adoption of U.S. based bioproduction technologies. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
NSF Program Director: Waleed Nasser
| Status | Closed |
|---|---|
| Effective start/end date | 01/01/25 → 06/30/25 |
Lead and Sub-Awardee Organization(s)
Funding
- (USPRD) Use-Inspired Acceleration of Protein Design: $6,908,604.00
Active Fiscal Year
- FY2025
Start Fiscal Year
- FY2025
TIP Programs
- (USPRD) Use-Inspired Acceleration of Protein Design
Key Technology Areas
- Artificial Intelligence
- (confidence score: 97%)
- Biotechnology
- (confidence score: 100%)
Technology Foci
- Synthetic Biology
- (confidence score: 100%)
- Bio-manufacturing
- (confidence score: 92%)
- Biotechnology - Other than SynBio
- (confidence score: 100%)
- Genomics and bioinformatics
- (confidence score: 100%)
- Artificial Intelligence (Broad)
- (confidence score: 100%)
Congressional District at Award
- District n. 14 of California
Current Congressional District
- District n. 14 of California
United States
- California
Core Based Statistical Area (CBSA)
- San Francisco-Oakland-Fremont, CA
County
- County: Alameda, CA
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint. Learn more about Elsevier's Fingerprint Engine here: https://beta.elsevier.com/products/elsevier-fingerprint-engine