Connecting and Building Collaborations between AI and Synthetic Biology Communities
2023 Fall Symposium: Artificial Intelligence for Synthetic Biology
November 15, 2023 | Virtual
Thank you for a fantastic symposium! The recording is available upon request.
We held several successful versions of this symposium at the AAAI Spring (2021, 2022) and Fall Symposia (2018, 2019) series. An article was published in Communications of the ACM based on the 2019 symposium.
This symposium continues the ongoing series to connect and build mutually beneficial collaborations between the AI and the synthetic biology communities. We are particularly interested in discussions and seek to spur actions by the community including in the following areas:
- Implications of large language models to synthetic biology,
- Ethics and safety concerns of lower barrier of entry to both AI and Synthetic Biology,
- Prospects of generative AI for synthetic biology, and
- Implications of the possibility of implementing neural network through circuits-like functions.
The symposium will include: very brief introduction to each domain to ensure the easy accessibility of attendees to both backgrounds, focused groups studying the open problems and challenges in the intersection of AI and Synthetic Biology, insightful contributed talks, and panel discussions with a wide range of speakers.
Synthetic biology is the systematic design and engineering of biological systems. Synthetic biology holds the potential for revolutionary advances in medicine, environmental remediation, and many more. For example, some synthetic biologists are trying to develop cellular programs that will identify and kill cancer cells, while others are trying to design plants that will extract harmful pollutants like arsenic from the ground.
Many times the design of synthetic organisms occurs at a low level (e.g., DNA level) in a manual process that becomes unmanageable as the size and complexity of a design grows. This is analogous to writing a computer program in assembly language, which also becomes difficult quickly as the size of the program grows. Many of the emerging techniques and tools in synthetic biology produce large amounts of data. Understanding and processing this data provides more avenues for AI techniques to make a big impact.
Data driven modeling of biological systems also presents opportunities to apply AI techniques. Work is needed to help predict the outcome of genetic modifications, identify root causes of failure in circuits, and predict the effect of a circuit on a host organism.
Currently most organism engineering workflows have little automation and rely heavily on domain expertise, only some of which is shared in publications. Tools that support or carry out information integration and informed decision making can improve the efficiency and speed of organism engineering, and enable better results.
A broad set of AI techniques can advance the progress of synthetic biology, and help realize these goals.
Please register using this Google Form to receive the Zoom information for the meeting. If you can’t access Google Forms, please contact the organizers.
|Date / Time
|Activity / Title
|Author(s) / Speaker(s)
|Wednesday, November 15, 2023
|09:30 – 09:45 EST
|Welcome and Introduction
|09:45 – 10:20 EST
|Keynote: The Convergence of Artificial Intelligence and the Life Sciences: Safeguarding Technology, Rethinking Governance, and Preventing Catastrophe
|10:20 – 10:45 EST
|Paper: A Comprehensible Framework to Active Learning Genome-Scale Metabolic Networks
|Lun Ai, Shi-Shun Liang, Stephen Muggleton and Geoff Baldwin
|10:45 – 11:10 EST
|Paper: Active learning for developing synthetic Ser/Thr signal transduction systems
|Noam Grunfeld, Erel Levine and Elizabeth Libby
|11:10 – 11:50 EST
|Panel: AI Synbio security concerns and opportunities
|Joel Bader (JHU), Chris Bettinger (DARPA), Nick Guido (MIT LL), Michael Patterson (IARPA)
|11:50 -12:45 EST
|12:45 – 13:20 EST
|Keynote: Data Integrity: A Looming Crisis for AI in Life Sciences?
|13:20 – 13:45 EST
|Paper: Machine learning models for enzyme kinetic parameter prediction
|Veda Sheersh Boorla and Costas D. Maranas
|13:45 – 14:10 EST
|Paper: Prospects for uses of generative AI in evaluations of truth and causality
|14:10 – 14:35 EST
|Paper: Retrobiosynthesis, Biosecurity, and Large Language Models
|Prasanna Muthukumar, Nicholas Roehner, Kemper Talley, Sean Colbath and Jacob Beal
|14:35 – 15:00 EST
|Discussion and Closing Remarks
Dr. Nicole Wheeler
The Convergence of Artificial Intelligence and the Life Sciences: Safeguarding Technology, Rethinking Governance, and Preventing Catastrophe
Significant advances in artificial intelligence (AI) offer tremendous benefits for modern bioscience and bioengineering. However, AI-bio capabilities—AI tools and technologies that enable the engineering of living systems—also could be accidentally or deliberately misused to cause significant harm, with the potential to cause a global biological catastrophe. I will present the findings of NTI | bio’s new report, “The Convergence of Artificial Intelligence and the Life Sciences: Safeguarding Technology, Rethinking Governance, and Preventing Catastrophe,” which draws on interviews with more than 30 experts in the field and makes recommendations about governance approaches for AI-bio capabilities to reduce biological risks without unduly hindering scientific advances.
Mr. Charles Fracchia
Data Integrity: A Looming Crisis for AI in Life Sciences?
As digital and biological technologies continue to interact in increasingly productive ways in industry, government, and academia, it has become imperative for us to examine its use and assumptions. The recent acceleration and democratization of machine learning techniques are already revolutionizing key biological processes such as molecular structure prediction, protein-ligand modeling, ADME/tox prediction, gene network modeling, large language model reasoning, hypothesis extraction and generation, and closed-loop automated laboratory execution, among others.
Data integrity is one of the critical components that underpins all modern biological research, development, manufacturing, clinical research, packaging, and distribution. Unfortunately, very little progress has been made on modernizing critical data integrity provisions, particularly in the face of an increasingly adversarial environment in the digital sphere, and a rise in geopolitical importance of the sector.
In this keynote, we will discuss the current state of data integrity in life sciences, how it might threaten the application of AI to our sector, and end with a few suggestions on how we can mitigate these issues.
Papers and Talks
August 11, 2023 August 25, 2023
Submission URL: https://easychair.org/conferences/?conf=fss230
Initial submissions are 2 page abstracts consisting of
- Challenge Overview (1 par)
- Diagram of solution (1/2 page)
- Technical Discussion of solution/results (1 page)
- Conclusion next/steps (1/2 page)
Aaron Adler (Raytheon BBN), Mohammed Ali Eslami (Netrias, LLC), Fusun Yaman (Raytheon BBN), Mingfei Sun (The University of Manchester), James Comolli (MIT Lincoln Laboratory)
AAAI Code of Conduct
All persons, organizations and entities that attend AAAI conferences and events are subject to the standards of conduct set forth on the AAAI Code of Conduct for Events and Conferences. AAAI expects all community members to formally endorse this code of conduct, and to actively prevent and discourage any undesired behaviors. Everyone should feel empowered to politely engage when they or others are disrespected, and to raise awareness and understanding of this code of conduct. AAAI event participants asked to stop their unacceptable behavior are expected to comply immediately. Sponsors are also subject to this code of conduct in their participation in AAAI events. For more information about AAAI’s Code of Professional Ethics and Conduct, please also see www.aaai.org/Conferences/code-of-ethics-and-conduct.php.