In our previous blog, we noted how the increasing utilization of AI across different phases of the drug discovery process has proven the strategic value of the technology in addressing some of the core efficiency and productivity challenges involved.
As a result, AI in drug discovery and development has finally cut through the hype and become an industry-wide reality. A key milestone in this process has been the launch of clinical trials for the first developed completely using AI.
Currently, the rapid evolution of AI-powered protein folding algorithms, such as AlphaFold, RoseTTAFold and RaptorX6, promises to dramatically accelerate experimental structural biology, protein engineering and drug discovery.
In fact, AI is expected to underpin a Million-X Drug Discovery future, wherein the ability of these technologies to exponentially scale up protein structure prediction and potential chemical compound generation will increase the opportunity for drug discovery by a million times.
Apart from sheer scale, AI-driven drug development also facilitates several other strategic outcomes such as access to larger datasets, reduced drug discovery costs, optimised drug designs, accelerated drug repurposing or repositioning, enabling the discovery of new and hidden drug targets, and turning previously undruggable targets into druggable ones
There is a range of applications for AI across the drug development pipeline. Here’s a quick overview of how AI can transform some of the key stages of drug design:
Drug discovery typically begins with the identification of targets for a disease of interest, a step that requires high-throughput screening of large chemical libraries to locate relevant activity assays. Though HTS has its advantages, it may not always be appropriate or even adequate, especially in the big data era when chemical libraries have expanded beyond a billion molecules.
This is where AI-powered Virtual Screening (VS) methods are being used to complement HTS to accelerate the exploratory research process in the discovery of potential drug components. AI-based VS is increasingly being used to complement HTS due to its ability to rapidly screen millions of compounds, at a fraction of the cost associated with HTS and predict potential ligands with as much as 85% accuracy.
Lead optimization (LO) is an essential yet expensive and time-consuming phase in preclinical drug discovery. The fundamental utility of the LO process is to enhance the desirable properties of a compound while eliminating deficiencies and adverse side effects in its structure. However, this is a complex multiparameter optimization problem where several competing objectives have to be precisely balanced in order to arrive at optimal drug candidates.
Done right, LO can significantly reduce the chances of attrition in pre-clinical as well as clinical stages of drug development. And reducing the iterations required for optimization in the DMTA cycle can help accelerate the drug development process.
Deep learning generative models are now being successfully used to accelerate the obtention of lead compounds while simultaneously ensuring that these compounds also conform to the requisite biological objectives. Generative modelling platforms, with integrated predictive models for calculating various ADMET endpoints, can now significantly shorten the DMTA cycle required to select and design compounds that satisfy all defined LO criteria.
The integration of AI and drug synthesis has been accelerating in recent times, significantly improving the design and synthesis of drug molecules. AI-driven computer-aided synthesis tools are being widely used in retrosynthetic analysis, reaction prediction and automated synthesis. For instance, these tools can be applied to the retrosynthetic analysis of target compounds to design multiple synthetic routes that can help the synthesis and optimization of hit compounds during drug discovery.
AI in computer-aided synthesis planning (CASP) is enabling chemists to objectively identify the most efficient and cost-effective synthetic route for a target molecule, thereby accelerating the ‘make’ phase of the DMTA cycle. The emergence of intelligent and automated technologies for continuous-flow chemical synthesis promises a future of fully autonomous synthesis.
AI in drug synthesis is not only accelerating the drug discovery and development process but is also improving the quality of synthesised molecules and significantly increasing the success rate.
These are just a few examples of the potential for AI in drug discovery and development. In fact, companies are using AI to address key challenges across the R&D pipeline and across the life sciences value chain.
In the future, according to one research paper, drug discovery will entail a centralised closed-loop ML-controlled workflow where the system autonomously generates hypotheses, synthesises lead candidates, tests them, and stores the data.
The paper postulates that eliminating the human interface between the key components of data analysis, computational prediction, and experimentation, could “reduce the bottlenecks and standards discrepancies and also eliminate human biases in hypothesis generation”.
Fully autonomous drug discovery may well be the future but in the near term, at least the human component will remain essential in the drug discovery and development process. There is still a lot of value to be had by optimising the current humans-in-the-loop approach to AI in drug design.
Currently, AI algorithms are augmenting human intelligence by independently extracting and learning from patterns in vast volumes of complex big data. AI technologies like NLP are helping catalyse insights from unstructured data sources like scientific literature, clinical trials, EHRs, social media posts that have thus far remained completely underutilised.
Most importantly though, AI in drug discovery has grown far beyond hype and hypothesis. As we mentioned in the previous blog, today the AI-driven drug discovery space is rife with activity as big pharma, big tech and big VC-funded scrappy startups jostle for position in the next big innovation cycle in drug discovery and development.
Autonomous drug discovery may well be the collective end goal, but to get there AI technologies will first have to address some persistent issues related to productivity, efficiency and cost-effectiveness in drug discovery and development.