Advancing Oncology Drug Development with Precision Medicine

Traditionally a disease has been defined by its clinical presentation and observable characteristics, not by the underlying molecular mechanisms, pathways and biological processes specific to a particular patient.

This can lead to classifying what are often highly heterogeneous medical conditions as a single disease.

In recent years, the healthcare industry has made significant steps in further understanding and targeting the underlying molecular cause of disease, however there is much more to be done. Consequently, patients with the same disease diagnosis tend to receive the same treatment. This kind of one-size-fits-all treatment strategy inadequately accounts for inter-individual variability between patients or the stage of their disease course. The result is that a large number of patients fail to respond to the treatments they are prescribed for.

One obvious example is cancer, which is a heterogeneous disease, with both between-patient variability and differences in the characteristics of disease within a given patient, making developing long-term cures challenging in many cancer types. Over the past decades, there have been major advances in developing cancer therapeutics; patients who receive targeted therapies have benefitted from improved survival [1,2,3]. However, there is still a huge unmet need for patients who either do not respond to existing treatments or develop resistance to them.

Our Precision Medicine team is working to change this by starting drug discovery from endotypes - groups of patients with the same underlying cause of disease.  By stratifying patients, we believe we have a better chance at identifying responder patients, designing more effective clinical trials and developing new therapies for complex and heterogeneous diseases like cancer.

Our team takes a multi-disciplinary approach to leverage the vast collection of patient-level data produced by recent developments in technology. We apply machine learning, bioinformatics, biological knowledge, and translational medicine to advance our drug discovery programs with a data driven approach. We use unsupervised machine learning techniques to capture patient heterogeneity and uncover different underlying biological mechanisms within the disease. We then incorporate these new insights into our core biomedical knowledge graph for drug target identification.

Our approach has been used in multiple discovery programs in disease areas such as neurology and oncology. Recently we announced our collaboration with Novartis Global Drug Development, where we are investigating new indications and responders for Novartis oncology medicines currently in clinical development. With this initiative, we combine expertise from both parties to further expedite the process of delivering the next generation of cancer therapies to the clinic.  

Our focus on precision medicine is important because we are translating scientific discoveries into real-world practice more efficiently, to more precisely target medicines for the patients who need them most.

Pijika Watcharapichat, Senior Research Scientist, Health Informatics

More Posts

You Might Also Like

Intern at BenevolentAI part I: meet our 2020 intern cohort
What impactful work did our interns get up to across Engineering, Data Science, ML and business operations this summer? Get to know them and their work in our tech internships blog.
Nov 26, 2020
FDA grants Emergency Use Authorisation for baricitinib in hospitalised COVID-19 patients nine months after initial hypothesis was published by BenevolentAI
BenevolentAI scientists first identified baricitinib as a potential treatment for COVID-19 in early February 2020 using Benevolent's AI tools and biomedical knowledge graph.
Nov 20, 2020
NeurIPS 2020: Meet the BenevolentAI team
BenevolentAI is happy to announce it is sponsoring NeurIPS 2020. Join us to hear about data diversity and ML applied drug discovery, and to learn about careers in the field.
Nov 17, 2020
Careers with Impact: 5 learnings from machine learning applied drug discovery
Last week, we brought together four of our exceptional colleagues for a panel discussion on careers in machine learning applied drug discovery. Here are some of our main takeaways:
Nov 17, 2020
Data published in Science Advances shows baricitinib reduces COVID-19 morbidity and mortality
Research published in Science Advances supports BenevolentAI’s AI-generated hypothesis from late January for baricitinib as a treatment for COVID-19.
Nov 13, 2020
Sir Nigel Shadbolt joins BenevolentAI as a non-executive director
BenevolentAI strengthens its Board with the appointment of AI pioneer Sir Nigel Shadbolt as Non-Executive Director.
Nov 3, 2020