Collaborative intelligence: How AI partnerships are shaping the future of drug development

The digitisation of medical records is catalysing the use of AI in various sectors of healthcare, including clinical trials, precision medicine, and drug discovery, thereby supporting biotech and pharmaceutical companies in their quest for more efficient and personalised medical solutions. This blog post explores the transformative role of AI in fostering collaborations within and beyond these industries, highlighting its impact on drug discovery and the development of personalised medicines, while also addressing the challenges and ethical considerations involved.

AI applications in drug discovery

In recent years, the use of AI within drug development has grown rapidly, already achieving important milestones such as:

• Exscientia celebrated the first-ever AI-designed drug molecule entering human clinical trials.
• DeepMind's AlphaFold predicted protein structures for 330,000 proteins, including all 20,000 proteins in the human genome, marking a transformative leap in structural biology.
• Insilico Medicine initiated Phase I clinical trials for the first-ever AI-discovered molecule based on an AI-discovered novel target.
• AbSci became the first entity to create and validate new antibodies using generative AI.
• The FDA granted its first Orphan Drug Designation to a drug discovered and designed using AI.

AI is currently being used across multiple different aspects of drug development, supporting the work of both biotechs and pharma, as well as other areas of the healthcare sector. AI is having a particular impact in the following areas:

Target identification: AI is trained on extensive datasets, including omics, phenotypic data, and disease associations, to understand biological mechanisms and identify new proteins or genes relevant to drug development.

Molecular simulations: Reducing the need for physical testing, AI enables high-fidelity molecular simulations entirely in silico (via a computer simulation), saving costs associated with traditional chemistry methods.

Prediction of drug properties: AI systems help predict key properties like toxicity, bioactivity, and physicochemical characteristics of molecules. There are numerous examples of this, such as:

• A machine learning (ML) algorithm called DeepTox outperformed all other methods by identifying specific features within molecules and could efficiently predict the toxicity of a molecule based on predefined features.
• The Similarity Ensemble Approach (SEA) was used to evaluate the safety target prediction of 656 marketed drugs against 73 unintended targets that might produce adverse effects.
• eToxPred was developed using an ML-based approach and applied to estimate the toxicity and synthesis feasibility of small organic molecules. It showed accuracy as high as 72%.

Drug design and repurposing: AI is able to find new drug candidates, either through screening existing molecules or finding entirely new candidates. For example, a deep learning algorithm has recently been trained on a dataset of known drug compounds to propose new therapeutic molecules. AI also contributes to theoretical drug design by suggesting synthesis pathways for hypothetical drug compounds. In some cases, AI can also suggest modifications to compounds to make them even easier to manufacture, which is particularly useful for pharmaceutical companies.

Candidate prioritisation: Once promising compounds are identified, AI has the capability to rank and prioritise them for further assessment and can often do this and more quickly and effectively than researchers can.

Predicting side effects: AI is currently being used to predict side effects for certain drugs and to work out optimal dosages for drug combinations, reducing the risk of adverse events and making medications safer for patients.

Supporting clinical trials: AI helps with clinical trials by improving patient recruitment through analysis of patient data, optimising trial design, offering real-time monitoring with wearable AI devices, and allowing for more efficient data analysis. It is also able to identify patient subgroups likely to respond to specific treatments which can improve success rates of studies.

Examples of AI collaborations in drug development

Synergistic collaborations around the use of AI are pivotal in driving innovative breakthroughs in drug development and patient care; below, we share examples in which these collaborations are making significant impacts.

AstraZeneca: AstraZeneca stands out as an early adopter of AI, utilising knowledge graphs and image analysis for disease insights and biomarker identification. AstraZeneca has already announced collaborations with AI specialists like Eko and Mila, demonstrating a commitment to using AI for drug discovery.

Pfizer: Pfizer's $120 million investment in biotechnology innovation through the Pfizer Breakthrough Growth Initiative has effectively used AI to conduct COVID-19 vaccine trials and streamline distribution. The company is working on a collaboration with XtalPi to develop a hybrid physics and AI-powered software platform for accurate molecular modelling of drug-like small molecules. Pfizer also has a partnership with a biotech company called Insilico Medicine to mine data for drug targets.

Janssen: In addition to working with Pfizer on real-world disease data collaborations, AI company ConcertAI announced that it was expanding its partnership with Janssen to improve study design and diversify clinical trials with the help of AI. Janssen has also partnered with the Cambridge-based software solutions provider Nference to leverage AI for identifying and selecting novel targets and disease subsets.

Exscientia: Biotech company Exscientia has already shown promise after its collaboration with GSK. Together, the pair developed the first-ever AI-powered treatment for COPD, which has already progressed to human trials. Now, Exscientia is also working with other pharmaceutical companies including Roche, Bayer and Sanofi to utilise AI in drug development.

Challenges in implementing AI solutions in drug development

While the integration of AI into drug development promises to revolutionise various facets of the process, it also introduces a range of unique challenges. One primary hurdle is the availability and quality of data, which is vital for training AI models. AI-based approaches often demand extensive datasets but the accessibility and quality of available data is still limited in many cases, which can reduce the reliability of AI-driven results.

Ethical considerations are also a major discussion point at the moment. Main concerns surround fairness and bias, particularly when training data is skewed or not representative or real-world populations, which it often is in clinical research. The potential implications of biassed AI programs include a range of negative effects, from inaccurate drug development decisions to unequal access to medical treatments. To address these ethical concerns, some are using strategies such as data augmentation (generating synthetic data to supplement existing datasets) and the use of explainable AI (XAI) methods to provide interpretable and transparent explanations for the predictions made by ML algorithms.

The relationships being built between pharmaceutical and biotech companies to bring AI into drug development will be beneficial for improving collaboration in the future. This will support new and improved medicines becoming available, shared knowledge that can be built on across the sectors, and a better understanding of patient health and disease. Despite the benefits that AI collaborations can bring to drug development, it's crucial to recognise its role as a complementary tool rather than a replacement for traditional experimental methods and human expertise. The challenge lies in effectively combining the power of AI with human expertise to optimise and accelerate the drug discovery and development processes.

Conclusion

The use of AI across biotech and pharma is making drug development easier and more cost-effective, offering new ways to find and test drug candidates and providing support throughout the clinical trial process. Key pharma and biotech industry players are already collaborating technology companies to utilise AI in major aspects of their drug development processes. While AI is not a complete substitute for traditional methods, its use alongside human knowledge and expertise can help improve drug development across both pharma and biotech and create better options for patient care in the future.

To learn more about how Sano is incorporating AI into the work we do to streamline precision medicine trials, get in touch below.