AI’s impact on the future of pharma and drug discovery

The rise of artificial intelligence has been popular within the life sciences industry and in particular pharma. Find out why and what it means for the future of drug development.  

The recent surge in activity in deploying AI capabilities in pharmaceutical R&D shows no sign of abating, with ‘big pharma’ investing significant capital in streamlining or accelerating the drug discovery process and applying AI methods to identifying new targets and medicines. If AI delivers on its promise, then there will be a material increase in the rate of new medicines coming to market. This could lead to a corresponding up-tick in the demands on manufacturing. Running in parallel is the question of how the same technologies can be applied to increase efficiency and improve outcomes in manufacturing as well as how AI technology might help improve efficiencies within these businesses. 

AI meets ‘big pharma’

Major pharmaceutical companies are data-rich and expert at developing new medicines starting from an implicated gene, protein, process or pathogen. They have powerful computational tools at their disposal and are early adopters of new technology. The leading AI companies have developed tools capable of analysing vast data sets, including natural language documents. The convergence of the two means that the deployment of leading-edge AI to pharmaceutical R&D is accelerating.

Pharma-AI collaborations are being structured in different ways. For example, the AI partner may simply offer consultancy, and a technology platform for use with the pharma partner’s data, or the AI partner may wish to conduct its own pharmaceutical R&D and hence may wish to take learnings from and reserve usage rights in the collaboration outputs.

Intellectual Property

AI technologies evolve through use. Training an existing model on new data gives rise to a new model whose properties and behaviour are modified by that training data. Where the AI platform and data belong to different parties, the question arises as to which party should own the new intellectual property in the trained model and any derived data. There is no set rule. As with the fee and any royalty structure, this is ultimately a commercial discussion between the parties. 

Where AI technologies are used, for example, to prioritise follow-up research efforts, the downstream creative and technical input may generate IP which is distinct from the output of the AI system. The ownership and exploitation rights attaching to each should be dealt with clearly and separately.

Data Usage, Privacy and Ethics

Usage rights for the confidential/proprietary information need to be considered. Are there any restrictions on the data being used? Is the data personal data or PII?

AI is particularly suited to the analysis of genetic data. Analysis and application of privacy laws, including around whether data can be anonymised, is essential. The UK Information Commissioner’s Office has set out an auditing framework for artificial intelligence. The European Commission’s High-Level Expert Group on AI, Ethics Guidelines for Trustworthy AI (April 2019) – seven essentials has a strong focus on privacy and data governance as well as transparency and ethical application of AI. 

There will be more law and guidance emanating from regulators across the globe in these areas. 

Technology and cyber-security

AI technologies reside on servers, whether on-premise or in the cloud. It is critical that a detailed analysis takes place, early on, as to the technology set-up, data flows, and security arrangements. The analysis is broadly the same as for other technology projects, but is a critical step given the large amounts of data and the potential sensitivity of the data and the results, especially if any personal data being used is voluminous and not anonymised.

Future prospects

AI technologies are now used at every stage in pharmaceutical R&D, as is evidenced by the numerous high-value deals between ‘big pharma’ and providers of AI technologies. As a recent example, Eversheds Sutherland advised global biopharmaceutical company AstraZeneca on its long-term collaboration with BenevolentAI to use AI and machine learning for the discovery and development of potential new treatments for chronic kidney disease (CKD) and idiopathic pulmonary fibrosis (IPF). 

Further to this, even if the prospect of machines inventing medicines is some way off, the use of AI to improve efficiency and speed up drug discovery is a realistic prospect today. AI technologies may also be utilised in areas of manufacturing which are amenable to predictive modelling and predictive support, such as process optimisation. 

The use of such AI tools within smart factories and smart manufacturing is enabling less down-time in the manufacturing process and driving stronger results. And AI tools are also beginning to be deployed on a more wide-spread basis within the ‘back office’ such as within accounting technology. As AI tools and computing power become more accessible and affordable, as with any technology, it will become very much part of the process within pharma and manufacturing – the future will be ‘AI-enabled’.