Understanding Biology in the Age of Artificial Intelligence
10AM – 11AM
Head of Cellular Genetics, Wellcome Sanger Institute, University of Cambridge
“Mapping the human body: one cell at a time”
The 37 trillion cells of the human body have a remarkable array of specialised functions, and must cooperate and collaborate in time and space to construct a functioning human. Harnessing cutting edge single cell genomics, my lab has been attempting to understand this cellular diversity, how it is generated during development and how it goes wrong in disease. My talk will explore the importance of computational methods (including machine learning and artificial intelligence) in our work. This highlights how an exciting synergy between ‘wet’ and ‘dry’ science is driving new discoveries in the cellular composition and tissue microenvironments of the human body.
11AM – 12PM
Professor of Structural Bioinformatics, Department of Statistics, University of Oxford
“How far are we from designing an antibody therapeutic on a computer?”
Immune receptor proteins play a key role in the immune system, our response to vaccines and have shown great promise as biotherapeutics. The development of new vaccines or biotherapeutics typically takes many years and requires over $1bn in investment. Computational methods and in particular machine learning have shown great promise for increasing the speed and reducing the cost of biotherapeutic development. In this talk I will describe some of the novel computational tools we are pioneering in the area of biotherapeutics from accurate rapid structure prediction to understanding the diverse binding preferences between different types of immune receptor proteins to allow us to better design them.
1PM – 2PM
Vice President of Research (AI for Science, Reliable and Responsible AI), DeepMind
“Leveraging AI for Biology”
Scientific advances over the last several centuries have not only expanded our understanding of the world, but have also raised the standard of living for many people across the globe. However, there are still massive challenges facing humanity, as evidenced by climate change and the COVID-19 pandemic. The sophistication and complexity of biological systems is a particular challenge faced by Science today. The scientific community has gathered vast amounts of information about biological systems, from information about the shape and function of constituent elements such as proteins, to large genomic projects that capture the representation of biological systems. However, it is impossible for any individual mind to comprehend this data. In this talk, I will discuss the potential of AI (and techniques like Machine Learning) to analyze and understand this biological data and improve our ability to make predictions about the behaviour of such systems. I will also discuss resulting systems like AlphaFold and the impact they can have on biological research.
2PM – 3PM
Vice President of Artificial Intelligence, BenevolentAI
“Large Language Models in Drug Discovery”
Despite the remarkable capabilities demonstrated by large language models, many companies are struggling with whether - and how - to integrate them into an existing workflow. Here, I’ll discuss multiple scenarios in which BenevolentAI is integrating large (and small) language models into our processes, according to their unique strengths and weaknesses. To overcome issues with accuracy and latency, we consider smaller, specialised language models for many natural language-based use cases. In contrast, our experience suggests that large language models are well suited for binding specialised tools and data into a single cohesive workflow, requiring much less technical knowledge to use effectively. This combination of specialist and generalist models allows users to seamlessly combine diverse sets of tools on-the-fly in a problem-specific manner.
3:15PM – 4:15PM
Assistant Professor of Philosophy, Irène Curie Fellow, Eindhoven University of Technology
“ML in science and biology: Just a toy?”
More and more sciences are turning to machine learning (ML) technologies to solve long-standing problems or make new discoveries—ranging from medical science to fundamental physics and biology. The ever-growing fingerprint ML modeling has on the production of scientific knowledge and understanding comes with opportunity and also pressing challenges. In this talk, I discuss how philosophy of science and epistemology can help us understand the potential and limits of ML used for science. Specifically, I will argue that ML models in science function in a similar way that highly idealized toy models do. Thinking of ML models as toy models can help to shed light on the scope of ML’s potential for scientific understanding.
Train: For visitors arriving from outside the Greater Cambridge area, travel via Cambridge Railway station is likely to be the easiest transport option. The station is approximately 15 minutes walk from the department. There are also taxis available at the station. Note that rail strikes may affect train availability around the conference.
Bus: Various bus routes connect the Greater Cambridge area to the Department of Chemistry, including the Citi 1, Citi 7, and Universal bus routes. Check the local bus schedules and routes to find the most convenient option for you.
Bicycle: Traveling by bicycle can also be a convenient option, and the Department of Chemistry offers ample bicycle parking facilities.
Car: If you prefer to drive, you can reach the Department of Chemistry by car. Unfortunately the department cannot offer any parking for this event, however, paid parking is available nearby at the Grand Arcade.