https://bio.nikkeibp.co.jp/atcl/news/p1/23/05/02/10648/
Moderna and IBM announced on April 20, 2023 that they have entered into an agreement to collaborate on the design of safe and effective mRNA medicines. Under the agreement, Moderna plans to leverage next-generation technologies such as quantum computing and generative AI (Generative AI) to accelerate progress in mRNA drug research and development. Over the past several years, IBM has been working on Generative AI to improve our understanding of molecular behavior and facilitate the design of promising molecules. The agreement will enable Moderna to use the technology built by IBM for the development of therapeutics, and will be backed by IBM. The company plans to first learn how to apply quantum computing and then work collaboratively to determine how to apply quantum approaches to the company’s scientific challenges. computing to its full potential, Moderna is investing money and assembling a dedicated team to address this area. Under the agreement, IBM will grant Moderna access to quantum computing systems and provide expertise to support the application of quantum technology to the life sciences. Quantum Network. The two companies will apply MoLFormer, an AI-based model for predicting molecular properties, to examine the properties of mRNA drug candidates to optimize mRNA molecules and the lipid nanoparticles that encase them. The goal is to design mRNA drugs with optimized safety and efficacy.
MoLFormer-XL is a software of IBM that has been pretrained on 1.1 billion molecules represented as machine-readable strings of text. From these simple and accessible chemical representations, it turns out that a transformer can extract enough information to infer a molecule’s form and function. Instead of training a model on thousands to millions of examples of molecules with detailed structural and property information, IBM can leverage a dataset that is at least 1,000 times larger. From this mountain of examples, IBM found that MoLFormer-XL could more easily learn a variety of downstream property prediction tasks. IBM reports our results in the latest issue of Nature Machine Intelligence.
MoLFormer-XL can predict a molecule’s physical properties, like its solubility, its biophysical properties, like its anti-viral activity, and its physiological properties, like its ability to cross the blood-brain barrier. It could even predict quantum properties, like a molecule’s bandgap energies, an indicator of how well it converts sunlight to energy.
https://research.ibm.com/blog/what-is-generative-AI
https://research.ibm.com/blog/molecular-transformer-discovery