Despite advances in biotechnology, there are still more than 7,000 diseases today with no effective treatment. There also continue to be disparities in global health as treatments for many infectious diseases do not attract sufficient research funding and pharmaceutical attention.
The global population is facing a growing burden of various diseases, such as cardiovascular diseases, diabetes, cancer, respiratory diseases, and neurological disorders, which is significantly fueling the demand for new and innovative drugs. Due to the rapid growth of biopharmaceuticals, the exponentially growing biopharmaceutical industry will drive the drug discovery market in the coming years.
While pharmaceutical companies are dominating the global drug discovery market, the contract research organizations (CROs) segment is estimated to be the most opportunistic one. The accelerating growth of several small and medium-sized CROs across the globe, owing to the rising demand for their services among pharmaceutical companies, is exponentially boosting the growth of the drug discovery market. Research is the most common activity in the drug discovery process, and small and medium pharmaceutical companies with low financial capabilities generally tend to acquire CRO services, which in turn fuels the growth of this segment.
Expected to grow to $158.67 billion in 2027 at a compound annual growth rate of 12.7 percent, the global drug discovery market is additionally navigating new frontiers with artificial intelligence (AI), synthetic data, and strategic partnerships.
Drug discovery is a complex and time-consuming endeavor that traditionally relies on labor and resource-intensive techniques, such as trial-and-error experimentation and high-throughput screening. However, AI techniques such as machine learning (ML) and natural language processing are offering the potential to accelerate and improve this process by enabling more efficient and accurate exploration of large molecular design space.
As a result, global players in the drug discovery market, such as Pfizer, GlaxoSmithKline, Merck & Co., Agilent Technologies, Eli Lilly and Company, F. Hoffmann-La Roche, Bayer AG, Abbott Laboratories, AstraZeneca, Shimadzu Corp., Evotec SE, Boehringer Ingelheim, Novartis, Johnson & Johnson and WIL Research Laboratories etc., are exploring the use of various new technologies to reduce the time required for drug discovery.
AI and Drug Discovery-Tools and Techniques
AI involves several methods, such as reasoning, knowledge representation, solution search, and a fundamental paradigm of ML that comprises algorithms to recognize patterns within a set of data that has been further classified. A subfield of ML is deep learning (DL), which engages gradient descent in architecturally different models such as artificial neural networks (ANNs) and Transformers using supervised or unsupervised training procedures.
There are different types of ANNs used in deep learning, such as multilayer perceptron (MLP) networks, recurrent neural networks (RNNs), and convolutional neural networks (CNNs). At the same time, popular Transformer architectures involve elements such as multi[1]head self-attention (MHSA), layer normalization (LN), and positional embeddings (PE).
Several tools have also been developed based on the networks that form the core architecture of AI systems. One such tool developed using AI technology is the IBM Watson platform in the US. It was designed to assist in the analysis of a patient’s medical information and its correlation with a vast database, resulting in suggestions for treatment strategies for cancer.
One key application of AI is the prediction of the efficacy and toxicity of potential drug compounds. Based on the analysis of a large amount of experimental data, AI algorithms can identify relevant and predictive molecular features that may not be apparent to human researchers. This advanced analytical capability facilitates the discovery of novel bioactive compounds, promising minimized clinical side effects. Moreover, AI-driven methods significantly accelerate the drug discovery process, outpacing traditional approaches with their efficiency and precision.
Another important application of AI in drug discovery is the identification of drug–drug interactions that take place when several drugs are combined for the same or different diseases in the same patient, resulting in altered effects or adverse reactions. This issue can be identified by AI-based approaches by analyzing large datasets of known drug interactions and recognizing the patterns and trends.
Added to the key applications of AI in drug discovery is the design of novel compounds with specific properties and activities. For example, a deep learning (DL) algorithm has recently been trained on a dataset of known drug compounds and their corresponding properties to propose new therapeutic molecules with desirable characteristics such as solubility and activity, demonstrating the potential of these methods for the rapid and efficient design of new drug candidates.
Key Advancements by Frontrunners
The CPHI Report’s AI findings, which were released ahead of CPHI Barcelona, the world’s largest pharma event, held at Fira Barcelona (October 24-26th, 2023), point to the technology having a transformational impact on all parts of drug discovery and development within the next 24 months.
The CPHI Report features insights from 250 global pharma companies and is a key barometer of the industry’s future growth prospects. For the first time in the report’s history, pharmaceutical ‘AI companies’ (26%) have overtaken ‘late stage’ (20%) and ‘early stage’ (19%) biotechs as the industry’s most appealing investment option for venture capitals.
Significantly, the rate of change is accelerating, with 62% forecasting that the first fully AI drug discovered and developed therapy will be approved by the US FDA within the next five years, and 20% believe this can be achieved in under two years. By 2030, over half (52%) of new drugs approved will be discovered or developed using AI.
While there are still no AI-designed drugs in the market, there are a number of companies across the globe with their drugs in advanced clinical trials. The first AI-designed drug candidate to enter clinical trials was reported by UK-based Exscientia in early 2020, a pivotal moment in AI drug discovery. Since then, several global companies, including Insilico Medicine, Evotec, and Schrödinger, have announced phase I trials. Several candidates have had their clinical development accelerated through AI-enabled solutions.
Insilico Medicine, a US and Hong Kong-based startup, is combining two rapidly developing technologies, i.e. quantum computing and generative AI, to explore lead candidate discovery in drug development and demonstrate the potential advantages of quantum generative adversarial networks in generative chemistry.
On the other hand, researchers at the University of Toronto used an Al-powered protein structure database to uncover a novel treatment pathway for liver cancer. Apparently, the potential drug was created in just 30 days!
Quoting another example, we have NVIDIA, a Silicon Valley giant, recently collaborating with Genentech, a member of the Roche Group, to accelerate drug discovery using Generative AI. This appears to be a first-of-its-kind collaboration aiming to optimize each company’s platform and deliver potential medicines to patients faster.
In a new move that underscores the pharmaceutical industry’s commitment to harnessing the power of AI for drug discovery, we recently saw Sanofi entering into a $140 million multi-year research collaboration with French pharma tech company Aqemia. Further, German life sciences firm Merck has launched its first-ever AI solution to integrate drug discovery and synthesis, combining generative AI, machine learning and computer-aided drug design.
In addition to these developments, we are also seeing the increasing participation of non-pharma companies in this space. For instance, Google Cloud has launched two new AI-powered solutions that aim to help biotech and pharmaceutical companies accelerate drug discovery and advance precision medicine; Deloitte has launched an AI incubator to harness the power of India’s tech innovation and talent capabilities; Accenture has made a strategic investment, through Accenture Ventures, in QuantHealth, an AI-powered clinical trial design company that simulates clinical trials in the cloud, allowing pharmaceutical and biotech companies to develop treatments for patients more quickly and cost-effectively.
With so many developments taking place, one cannot help noticing that these are not restricted to one or two regions. The US and Europe are leading the way, but many Asian Pacific countries, including China, Japan, Singapore, Korea, and India, are making tremendous efforts.
Challenges and Limitations
According to a Boston Consulting Group (BCG) analysis, in 2022, around 20 AI-intensive companies had 158 drug candidates in discovery and preclinical development. Although these are noteworthy developments, concerns are being raised that such developments need further authentication. A study published in the journal Nature states that these findings need to be reported in the peer-reviewed literature and authenticated by researchers unaffiliated with the companies involved.
Adding on, AI-based approaches typically require a large volume of information for the AI models to be trained. In many cases, the amount of data accessible may be limited, or the data may be of low quality or inconsistent, which can affect the accuracy and reliability of the results. Another challenge is the ethical consideration since AI-based approaches may raise concerns about fairness and bias. If the data used to train an ML algorithm is biased or unrepresentative, the resulting predictions may not be accurate or fair.
Experts have also pointed out that even if AI does reduce the time and cost involved in getting a compound into, and perhaps through, preclinical testing, most drug candidates will still fail at later stages. But anything that can speed up the process represents a win-win situation.
That is why the role of collaboration between AI researchers and pharmaceutical scientists is crucial in the development of innovative and effective treatments for various diseases. Both industry and academia need to leverage each other’s strengths to determine how AI can be used to the best effect.
Another main point of AI implementation in drug discovery, or any other application, is the apprehension of replacing humans, leading to job loss. According to a recent report of 750 business leaders using AI from ResumeBuilder, 37% say the technology replaced workers in 2023. Meanwhile, 44% report that there will be layoffs in 2024 due to AI efficiency. While layoffs are a reality, AI technology is also enabling business leaders to restructure and redefine the jobs we do. Nevertheless, human intervention is mandatory for any AI platform’s successful implementation, development, and operation.
Future Perspectives
Amidst numerous challenges and limitations, the drug discovery process requires compelling evidence for decision-making because it directly affects public health. Nevertheless, the industry and academia have demonstrated the benefits of drug discovery with AI technology through their tremendous research work.
The immediate priority is to create AI technology tailored for drug discovery to achieve meaningful progress. AI specialists must grasp the nuances of drug discovery data and strive to create relevant and transparent algorithms that elucidate the mechanisms of action, thereby supporting informed decision-making.
Other domain experts will need to generate biological and chemical data with minimal experimental errors and store them in unified platforms for further improvements to the AI systems. Also, it will be crucial for all stakeholders to be open to working together and actively communicating to construct a concrete framework for a new revolution in drug discovery.
Author Details
Saurabh Singal, Founder - Molecule AI and KnowDis
Publication Details
This article appeared in American Pharmaceutical Review:Vol. 27, No. 2March 2024Pages: 31-33
Subscribe to our e-Newsletters
Stay up to date with the latest news, articles, and events. Plus, get special
offers from American Pharmaceutical Review delivered to your inbox!
Sign up now!