Generative artificial intelligence software used for chemical and protein design has repurposing potential. We propose careful discussion in the biotech community on security considerations of such technologies and serious consideration of restrictions to control who can access the software and what applications it is used for.
UrbinaF, LentzosF, InvernizziC, et al.Dual use of artificial-intelligence-powered drug discovery. Nat Mach Intell, 2022; 4(3):189–191; doi: 10.1038/s42256-022-00465-9
4.
LentzosF.How to protect the world from ultra-targeted biological weapons. Bull At Sci 2020.
5.
World Health Organization. Global guidance framework for the responsible use of the life sciences. World Health Organization; 2022. Available from: https://www.who.int/publications/i/item/9789240056107 [Last accessed: May24, 2023].
6.
RevillJ, ZhangV, Garzon MacedaM, (eds). Stakeholder Perspectives on the Biological Weapons Convention. United Nations Institute for Disarmament Research: Geneva, Switzerland; 2022.
TuckerJB, HooperC. Protein engineering: Security implications. The increasing ability to manipulate protein toxins for hostile purposes has prompted calls for regulation. EMBO Rep, 2006; 7(Spec No):S14–S17; doi: 10.1038/sj.embor.7400677
9.
CaoL, CoventryB, GoreshnikI, et al.Design of protein-binding proteins from the target structure alone. Nature, 2022; 605(7910):551–560; doi: 10.1038/s41586-022-04654-9
10.
CaoL, GoreshnikI, CoventryB, et al.De novo design of picomolar SARS-CoV-2 miniprotein inhibitors. Science, 2020; 370(6515):426–431; doi: 10.1126/science.abd9909
11.
EkinsS, LentzosF, BrackmannM, et al.There's a ‘ChatGPT’ for biology. What could go wrong?. Bull At Sci, 2023.
12.
FerruzN, SchmidtS, HockerB. ProtGPT2 is a deep unsupervised language model for protein design. Nat Commun, 2022; 13(1):4348; doi: 10.1038/s41467-022-32007-7
13.
MadaniA, KrauseB, GreeneER, et al.Large language models generate functional protein sequences across diverse families. Nat Biotechnol, 2023; doi: 10.1038/s41587-022-01618-2
14.
WatsonJL, JuergensD, BennettNR, et al.Broadly applicable and accurate protein design by integrating structure prediction networks and diffusion generative models. bioRxiv, 2022;2022.12.09.519842; doi: 10.1101/2022.12.09.519842
15.
WangJ, LisanzaS, JuergensD, et al.Deep learning methods for designing proteins scaffolding functional sites. bioRxiv, 2021;2021.11.10.468128; doi: 10.1101/2021.11.10.468128
16.
SgarbossaD, LupoU, BitbolA-F. Generative power of a protein language model trained on multiple sequence alignments. eLife, 2023; 12:e79854; doi: 10.7554/eLife.79854
17.
WickyBIM, MillesLF, CourbetA, et al.Hallucinating symmetric protein assemblies. Science, 2022; 378(6615):56–61; doi: 10.1126/science.add1964
18.
UrbinaF, LentzosF, InvernizziC, et al.A teachable moment for dual use. Nat Mach Intell, 2022; 4:607; doi: 10.1038/s42256-022-00465-9
19.
UrbinaF, LentzosF, InvernizziC, et al.Preventing AI from creating biochemical threats. J Chem Inf Model, 2023; 63:691–694; doi: 10.1021/acs.jcim.2c01616
20.
ColeyCW, ThomasDA, 3rd, LummissJAM, et al.A robotic platform for flow synthesis of organic compounds informed by AI planning. Science, 2019; 365(6453):eaax1566; doi: 10.1126/science.aax1566
21.
HartrampfN, SaebiA, PoskusM, et al.Synthesis of proteins by automated flow chemistry. Science, 2020; 368(6494):980–987; doi: 10.1126/science.abb2491
22.
PettersenEF, GoddardTD, HuangCC, et al.UCSF ChimeraX: Structure visualization for researchers, educators, and developers. Protein Sci, 2021; 30(1):70–82; doi: 10.1002/pro.3943
23.
DauparasJ, AnishchenkoI, BennettN, et al.Robust deep learning-based protein sequence design using ProteinMPNN. Science, 2022; 378(6615):49–56; doi: 10.1126/science.add2187
24.
VaradiM, AnyangoS, DeshpandeM, et al.AlphaFold Protein Structure Database: Massively expanding the structural coverage of protein-sequence space with high-accuracy models. Nucleic Acids Res, 2022; 50(D1):D439–D444; doi: 10.1093/nar/gkab1061
