Topics In Demand
Notification
New

No notification found.

Empowering Medicine: Unleashing the Potential of Generative AI in Drug Discovery & Development
Empowering Medicine: Unleashing the Potential of Generative AI in Drug Discovery & Development

115

0

The landscape of Generative AI is a dynamic and constantly evolving realm, encompassing diverse industries and offering transformative solutions that push the boundaries of innovation. Among its numerous applications, Generative AI has found a compelling niche in the domain of Drug Discovery & Development. This specialized and groundbreaking application has the potential to revolutionize research, reshape healthcare, and unlock new frontiers in the sector.

 

Generative AI in Drug Discovery & Development

 

The traditional drug discovery process is a time-consuming and costly endeavour, requiring extensive experimentation with chemical compounds to identify potential drug candidates. Generative AI, particularly through the application of Generative Adversarial Networks (GANs), has emerged as a powerful tool to streamline and accelerate this critical phase of drug discovery & development.

The GANs architecture consists of two differentiable functions – a generator and a discriminator - that work in harmony towards achieving the final goal of refining the system. While the role of generator is to take random noises as input and work towards imitating the data distribution, the role of discriminator is to distinguish between the fake and real samples. The training continues till the time GAN is no longer able to distinguish between the generated data and the real data. However, there are some challenges associated with the use of GANs in drug discovery & development. Hence, other methods of drug discovery & development, involving the use of GANs, are emerging in the space. One such method is Quantum GAN.

 

 

 

 

 

 

 

 

Source: American Chemical Society

In quantum GAN, generators and discriminators are trained on quantum computers. Studies have shown that quantum generators outperform the classical GAN in the drug properties of generated compounds and the goal-directed benchmark. Furthermore, quantum discriminators of GAN, with just tens of learnable parameters, outperform the classical counterpart in generated molecule properties and KL-divergence score. Quantum generators with hybrid generators, which are constituted of parameterized quantum circuits that give a feature vector of qubit size dimension, offer higher training efficiency and better molecular graphs than the classical counterpart.

These transformative approaches enable researchers to rapidly generate a diverse set of potential drug candidates, expediting the identification of molecules with high therapeutic potential. Consequently, Generative AI significantly reduces the time and resources required for early-stage drug discovery, offering a more efficient and cost-effective path towards novel drug development.

 

Success Story

 

Insilico Medicine, a Hong Kong-based biotech startup, has developed the first fully generative AI drug for idiopathic pulmonary fibrosis (IPF), a chronic disease, causing scarring in the lungs. The disease affects around 100,000 people in the US and can lead to death within two to five years if untreated. The drug, INS018_055, is the first fully generative AI drug to reach human clinical trials, specifically Phase II trials with patients. The discovery process began in 2020 with the goal of creating a "moonshot" medicine to overcome challenges with the existing treatments. Insilico has two other partially AI-generated drugs in clinical stage: a Covid-19 drug in phase one and a cancer drug, specifically a USP1 inhibitor for solid tumor treatment.

The IPF drug's current study is a randomized, double-blind, placebo-controlled trial taking place over 12 weeks in China, with plans to expand the testing population to 60 subjects at 40 sites in the U.S. and China. If successful, the drug will go on to another study with a larger cohort and potentially reach phase III studies with hundreds of participants.

 

What does this mean?

 

The convergence of Generative AI and niche applications in Drug Discovery & Development promises a revolution in the field of medicine. Through cutting-edge technologies like GANs, Generative AI accelerates drug discovery by efficiently generating novel molecular structures, minimizing time and costs associated with traditional methods. As Generative AI continues to advance, we can envision a future where medical treatments are customized, regenerative medicine reaches new heights, and breakthrough discoveries reshape the landscape of healthcare and life sciences. The transformative potential of Generative AI in this application underscores its role as a catalyst for innovation, propelling medicine towards a realm of unprecedented possibilities.


That the contents of third-party articles/blogs published here on the website, and the interpretation of all information in the article/blogs such as data, maps, numbers, opinions etc. displayed in the article/blogs and views or the opinions expressed within the content are solely of the author's; and do not reflect the opinions and beliefs of NASSCOM or its affiliates in any manner. NASSCOM does not take any liability w.r.t. content in any manner and will not be liable in any manner whatsoever for any kind of liability arising out of any act, error or omission. The contents of third-party article/blogs published, are provided solely as convenience; and the presence of these articles/blogs should not, under any circumstances, be considered as an endorsement of the contents by NASSCOM in any manner; and if you chose to access these articles/blogs , you do so at your own risk.


images
Dhiraj Sharma
Principal Analyst

© Copyright nasscom. All Rights Reserved.