Improving safety of AI research for engineering biology

Phys.org  July 8, 2024
The development of high-throughput methods like massively parallel reporter assays, data-rich microscopy techniques, computational protein structure prediction and design, and the development of whole-cell models are able to generate huge volumes of data. An international team of researchers (UK, USA – University of Washington) presented a community-developed framework for assessing hazards posed by using data-centric methods to engineer biology
and demonstrated its application to two synthetic biology case studies. They showed the diversity of considerations that arise in common types of bioengineering projects and provided some guidelines and mitigating steps. According to the researchers understanding potential issues and dangers when working with data and proactively addressing them will be essential for ensuring the appropriate use of emerging data-intensive AI methods and help increase the trustworthiness of their applications in synthetic biology… read more. Open Access TECHNICAL ARTICLE