Artificial Intelligence is Reshaping Pharmaceutical Industry Research
In Brief
Major pharmaceutical firms like Amgen, Bayer, and Novartis are harnessing AI to accelerate clinical trials, cut costs, and revolutionize drug development.
With AI’s help, the industry aims to cut years off the typical drug development timeline, making innovative treatments more accessible.
The most resource-intensive and costly phase of drug development – recruiting patients for clinical trials – has long been a bottleneck in the pharmaceutical industry.
It often takes years to identify suitable candidates, and the process can incur expenses exceeding a billion dollars from drug discovery to market launch. However, in recent years, pharmaceutical companies have been exploring AI’s potential to discover breakthrough drugs, and some AI-selected compounds are currently in development.
Pharmaceutical giants are now training AI systems to sift through extensive databases of public health records, prescription data, medical insurance claims, and internal data to pinpoint trial participants. This approach has, in some instances, halved the time needed to enroll patients.
Major pharmaceutical firms such as Amgen, Bayer, and Novartis are tapping into AI to accelerate patient recruitment for clinical trials and reduce testing costs, significantly accelerating drug development and potentially saving millions of dollars.
Leveraging AI to Streamline Medical Processes
AI’s growing role in human drug trials is transforming the process, as it empowers pharma companies to efficiently identify trial candidates by scanning extensive healthcare data.
Amgen’s AI tool, Atomic, identifies and ranks clinics and doctors based on their past performance in recruiting trial participants, potentially reducing the enrollment period for mid-stage trials by half. Amgen aims to employ AI in most of its studies by 2024, expecting that AI will cut two years from the typical decade-long drug development timeline by 2030.
Bayer’s use of AI reduced the number of participants needed for a late-stage trial, saving time and money. In addition, Bayer plans to employ real-world patient data, mined with the help of AI, to create an external control arm for a study involving children, potentially eliminating the need for a placebo group. While this approach is unconventional, it has been used in rare disease trials, with Amgen’s drug Blincyto receiving U.S. approval using this method.
Access to extensive and high-quality data is crucial for AI systems to design drugs accurately. Smaller companies face significant challenges in obtaining the necessary data for AI-driven drug discovery.
Centralized data repositories, like European Health Data Space (EHDS), could improve the situation by granting researchers access to datasets held by public authorities and pharmaceutical companies.
Microsoft’s DeepSpeed4Science Advances AI in Scientific Research
Microsoft recently launched DeepSpeed4Science initiative to apply deep learning in natural sciences, including drug development and renewable energy. DeepSpeed, an open-source AI framework, aims to accelerate and scale up deep learning processes.
DeepSpeed4Science strives to address the challenges of scientific discoveries, building upon the capabilities of DeepSpeed. It enables automated training of models like ChatGPT, offering a 15x speedup compared to state-of-the-art reinforcement learning from human feedback (RLHF) systems. RLHF systems learn tasks through interaction with human teachers, but they can be computationally expensive and require substantial human feedback.
DeepSpeed4Science is also collaborating with AI-driven science model specialists, including climate science and molecular dynamics simulation experts, to support scientific research.
AI Giant Nvidia Supports Startups Advancing Drug Discovery with Generative AI
Last week, Generate:Biomedicines, an AI-driven biotech company, closed a Series C funding round, raising $237 million. The investment was led by NVentures, the venture capital arm of Nvidia.
The company leverages machine learning to create clinical protein complexes and enzymes, including antibodies designed for specific epitopes and functional antibodies that interact with cell surface receptors. It uses a machine learning platform, The Generate Platform, which has been trained on extensive datasets encompassing natural protein structures, sequences, and proprietary data.
With the funds, Generate:Biomedicines plans to further develop The Generate Platform, aiming to submit multiple Investigational New Drug applications (INDs) in 2024 and initiate several clinical trials annually thereafter.
AI’s Use in Pharma Sparks Concerns
Despite the potential benefits of AI in streamlining drug trials, some scientists and regulators express concerns about relying too heavily on AI-generated external control arms, emphasizing the importance of maintaining rigorous standards for drug safety and effectiveness.
Nonetheless, AI’s ability to rapidly analyze real-world patient data at scale is proving to be a game-changer in the pharmaceutical industry, revolutionizing the drug development process.
Besides, skepticism lingers due to past high-profile failures and concerns about AI-designed medicines’ safety, efficacy, and regulatory compliance. The pharmaceutical sector faces a critical challenge: ensuring that AI-developed drugs can navigate the same rigorous regulatory pathways as traditional medications.
If successful, AI has the potential to revolutionize the industry by drastically shortening drug development timelines, identifying new molecules, and increasing patient access to innovative treatments.
AI’s rapid analysis of real-world patient data has the potential to reshape the industry, accelerating drug development, identifying novel molecules, and improving patient access to treatments. Even though the sector faces challenges like ensuring that AI-developed drugs meet rigorous regulatory standards, AI could usher in a new era of pharmaceutical innovation.
Disclaimer
In line with the Trust Project guidelines, please note that the information provided on this page is not intended to be and should not be interpreted as legal, tax, investment, financial, or any other form of advice. It is important to only invest what you can afford to lose and to seek independent financial advice if you have any doubts. For further information, we suggest referring to the terms and conditions as well as the help and support pages provided by the issuer or advertiser. MetaversePost is committed to accurate, unbiased reporting, but market conditions are subject to change without notice.
About The Author
Agne is a journalist who covers the latest trends and developments in the metaverse, AI, and Web3 industries for the Metaverse Post. Her passion for storytelling has led her to conduct numerous interviews with experts in these fields, always seeking to uncover exciting and engaging stories. Agne holds a Bachelor’s degree in literature and has an extensive background in writing about a wide range of topics including travel, art, and culture. She has also volunteered as an editor for the animal rights organization, where she helped raise awareness about animal welfare issues. Contact her on agnec@mpost.io.
More articles
Agne is a journalist who covers the latest trends and developments in the metaverse, AI, and Web3 industries for the Metaverse Post. Her passion for storytelling has led her to conduct numerous interviews with experts in these fields, always seeking to uncover exciting and engaging stories. Agne holds a Bachelor’s degree in literature and has an extensive background in writing about a wide range of topics including travel, art, and culture. She has also volunteered as an editor for the animal rights organization, where she helped raise awareness about animal welfare issues. Contact her on agnec@mpost.io.
