September 22, 2022

Don’t take antibiotics every time you have a cold. But the resistance crisis has an AI solution

These technologies are already working together to accelerate the discovery of new antimicrobial drugs. A subset of next-generation AIs, called generative models, produce hypotheses about the final molecule needed for a specific new drug. These AI models not only search for known molecules with relevant properties, such as the ability to bind to and neutralize a virus or bacteria, they are powerful enough to learn the characteristics of the underlying data and can suggest new molecules that have not yet been synthesized. This design, as opposed to research capacity, is particularly transformative because the number of possible suitable molecules is greater than the number of atoms in the universe, which is prohibitively expensive for research tasks.

Generative AI can navigate this vast chemical space to discover the right molecule faster than any human using conventional methods. AI modeling is already supporting research that could help patients with Parkinson’s disease, Diabetes and chronic pain. For example, antimicrobial peptides (AMPs), i.e. small protein-like compounds, are one solution that is being intensively studied. These molecules hold great promise as next-generation antibiotics because they are inherently less susceptible to resistance and are produced naturally as part of the innate immune system of living organisms.

In recent studies published in Nature Biomedical Engineering, 2021the AI-assisted search for new, effective and non-toxic peptides produced 20 promising new candidates in just 48 days, a striking reduction compared to conventional development times for new compounds.

Among these were two new candidates used against Klebsiella pneumoniae, a bacterium frequently found in hospitals that causes pneumonia and bloodstream infections and which has become increasingly resistant to conventional classes of antibiotics. Obtaining such a result with conventional research methods would take years.

SAP already used for commercial purposes

Collaborative work between IBM, Unilever and STFC, which hosts one of IBM’s research centers Discovery Accelerators at the Hartree Center in the UK, recently helped researchers better understand SAPs. Unilever has already used this new knowledge to create consumer products that enhance the effects of these natural defense peptides.

And, in this Biophysical Journal paper, researchers demonstrated how small molecule additives (low molecular weight organic compounds) are able to make AMPs much more potent and effective. Using advanced simulation methods, IBM researchers, in combination with experimental studies from Unilever, have also identified new molecular mechanisms that may be responsible for this increased potency. This is a first-of-its-kind proof of principle that scientists will implement in ongoing collaborations.

Driving materials discovery with generative AI models and advanced computer simulations is part of a much broader IBM Research strategy called Accelerated Discovery, where we use emerging computer technologies to drive the scientific method and its application. to discover. The goal is to dramatically accelerate the pace of discovery of new materials and drugs, whether in preparation for the next global crisis or to quickly address the current one and inevitable future ones.

It is just one piece of the loop comprising the Revised Scientific Method, a state-of-the-art transformation of the traditional linear approach to materials discovery. Generally speaking, the AI ​​learns the desired properties of a new material. Then another type of AI, IBM’s Deep Search, combs through the existing knowledge about how that specific material is made, i.e. all the previous research hidden in patents and papers.

Generative models have the potential to create a new molecule

Following this, generative models create a possible new molecule based on the existing data. Once that’s done, we use a high-performance computer to simulate this new candidate molecule and the reactions it should have with its neighbors to make sure it works as expected. In the future, a quantum computer could further improve these molecular simulations.

The last step consists of AI-based laboratory tests to experimentally validate the predictions and develop real molecules. At IBM, we do this with a tool called RoboRXN, a small refrigerator-sized chemistry lab that combines AI, cloud computing and robots to help researchers create new molecules anywhere and whenever. The combination of these approaches is well suited to solving general “reverse design” problems. Here, the task is to find or create a material with a desired property or function for the first time, as opposed to calculating or measuring the properties of a large number of candidates.

Proof that AI can go beyond the limits of classical computing

The antibiotic crisis is a particularly urgent example of a global reverse design challenge requiring a real paradigm shift to how we discover materials. Rapid advances in quantum computing and the development of quantum machine learning techniques now create realistic prospects for extending the reach of artificial intelligence beyond the confines of classical computing. Early examples show promising quantum advantages in model training speed, classification tasks, and prediction accuracy.

Overall, combining the most powerful emerging AI techniques (possibly with quantum acceleration) to learn characteristics related to antimicrobial activity with molecular-scale physical modeling to reveal modes of action is, arguably, the most promising way to create these essential compounds faster than ever before.

The article originally appeared in the World Economic Forum.


Read also : CGPA instead of notes, side entry – Modi govt SoP to bring parity to the board