The Silicon Review
The primary goal of drug discovery research is to identify medicines that have a beneficial effect on the body – in other words, medications that can help prevent or treat a specific disease. Although there are many different types of drugs, many are small chemically synthesized molecules. These are capable of binding specifically a target molecule present in the disease. Traditional drug discovery methods are target-driven, which means that a known target is used to screen for small molecules that interact with it or affect its function in cells. However, due to the complexity of cellular interactions and a lack of knowledge of intricate cellular pathways, these methods are minimal. AI in drug discovery market can overcome these obstacles by detecting novel interactions and determining the functional significance of various cellular pathway components.
Exscientia is one such global pharmatech company using patient-first artificial intelligence (AI) to discover better drugs, faster. The company is on a mission to encode, automate, and transform every stage of the drug design and development process, by combining the latest AI techniques with experimental innovation, to enable the design of patient centric drug candidates with an improved probability of success. Its validated platform has delivered the first three AI-designed drugs to enter clinical trials and is the first AI system proven to improve clinical outcomes in oncology. It has significantly accelerated pre-clinical drug discovery, with 10x productivity improvement in delivering a drug candidate compared with industry standards. By actively applying AI to precision engineer medicines more rapidly and efficiently, Exscientia allows the best ideas of science to rapidly become the best medicines for patients.
Revolutionizing Drug Discovery Using Precision AI-based Methodologies
Precision Target: Target selection is a key to creating success in drug discovery. Selecting each target is a significant decision and the future success of any molecule will depend on that initial decision. The company combines global genetic data and literature with specific readouts from primary patient tissue, generated in its own laboratories. By bringing together complementary layers of data, they are able to build precise views of disease-relevant target space. This comprehensive strategy allows them to work on both first in class and validated targets, within a single unified framework. They can apply the same strategic approaches to diseases areas where individual target mechanisms are unclear yet. In these situations, drug discovery can be conducted at a cell, tissue or whole organism level by measuring changes in a high-content image or a phenotypic response. In their own laboratories they can also use single cell phenotypic screening in primary patient tissue to identify novel target space for small molecule discovery.
Precision Design: Drug design is engineering at the molecular scale. Every position of every atom and every bond determines the future success of a molecule. For each project Exscientia collect all relevant experimental information irrespective of data type. This can cover target-driven pharmacology, ADME, 3D structure, high content data, and phenotypic readouts. All these different sources of data can be used to build a coherent set of machine learning models for AI-design. This approach is highly advantageous and they refer to it as a data agnostic approach. It was the first company to demonstrate that AI algorithms can outperform human experts when given the same drug discovery optimization challenge. They formalized each drug discovery project as a learning challenge, where each project has a distinct set of issues to be solved. The faster the systems learn, the more efficiently compounds with a profile suitable for clinical assessment are identified. This benefits the human researchers freeing their time to work on other strategic aspects of each project.
Precision Experiment: Only with continual feedback between experiment and prediction can machine learning models be refined and deliver against complex therapeutic profiles. Novel targets need high-quality seed data generated quickly for its algorithms whilst established targets may require experiment to uncover new binding sites and additional chemotypes. Fragment-based screening is ideal for Project Seeding and can be implemented by two complementary high-precision experiments. The company conducts experimental research on primary patient tissue at single cell resolution. With this they screen small molecules, quantify responses in cancer cell tissue and uncover potential novel target space.
Precision Medicine: First integrated system to demonstrate improved clinical outcomes in oncology using live patient tissue and the power of AI. Exscientia’s EXALT1 is the ﬁrst-ever prospective interventional study of its kind. Predictions made by the platform proposed which therapy would be most effective for late stage hematological cancer patients based on testing drug responses ex vivo in their own tissue samples. EXALT-1 demonstrated real-world patient selection capabilities by achieving a 55 percent overall response rate and statistically significant improvement in progression free survival over the prior line of therapy for patients that were treated following the platform’s recommendation.
The Pre-Eminent Leader
Andrew Hopkins is the Chief Executive Officer Exscientia. He is one of the most distinguished and cited scientists in modern drug discovery. As part of his role as founder and CEO of Exscientia, he invented and championed an automated and algorithmic approach to drug design and drug discovery. Prior to that, he spent 14 years at Pfizer and in academia, pioneering cutting-edge projects using data mining and machine learning in the pharmaceutical industry. His papers, published in Nature journals, are widely considered as pivotal points in the new paradigm of modern drug discovery.