A Standard Enabled Synthetic Biology Workflow to Produce AI-Ready Data

This project addresses a critical challenge in synthetic biology: the lack of standardized, machine-accessible experimental data and metadata, which limits reproducibility, data sharing, and the development of predictive models. Without consistent ways to capture and integrate experimental information across laboratories and platforms, it is difficult to reliably design biological systems or apply artificial intelligence (AI) to accelerate discovery. This project will develop and demonstrate data-driven workflows that improve the reliability, transparency, and reuse of biological data. By enabling researchers to generate and share high-quality, standardized datasets, this project will advance the national interest by promoting scientific progress, supporting innovation in biotechnology, and strengthening the foundation for AI-enabled biological engineering. The resulting tools, data resources, and training materials will support both research and education, fostering an open science ecosystem that benefits academic, industrial, and government stakeholders. This project will integrate standardized synthetic biology data workflows with advanced laboratory automation systems at the National Institute of Standards and Technology (NIST). It will extend and connect open-source software tools—including Excel2SBOL for data capture, SBOLCanvas for genetic circuit design, iBioSim for modeling, the Experimental Data Connector (XDC) for data and metadata ingestion, and Flapjack for experimental analysis—using community data standards and the SynBioHub genetic design repository. The team will develop and validate protocols for calibration and characterization of genetic parts and devices across diverse experimental contexts, generating high-quality, machine-actionable datasets. These data will be used to construct and benchmark predictive models of gene expression, including hybrid biophysical and machine learning (ML) approaches that explain variation across conditions. All data and metadata will be encoded using FAIR (findable, accessible, interoperable, reusable) principles to ensure effective data sharing and reproducibility. This project will produce standardized workflows, datasets, and models that can be adopted by other biofoundries and research groups, advancing the integration of biotechnology and artificial intelligence. This award is funded by a collaboration between NSF, the National Institute of Standards and Technology, and Schmidt Sciences. 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 Award ID: 2622619 | Program: 01002627DB NSF RESEARCH & RELATED ACTIVIT,4082CYXXDB NSF TRUST FUND | Principal Investigator: Chris Myers | Institution: University of Colorado at Boulder, BOULDER, CO | Award Amount: $250,000 View on NSF Award Search: https://www.nsf.gov/awardsearch/show-award/?AWD_ID=2622619 View on Research.gov: https://www.research.gov/awardapi-service/v1/awards/2622619.html