We all have an internal clock, but what makes us tick? Scientists at the Earlham Institute at Norwich Research Park in conjunction with IBM Research have developed new artificial intelligence (AI) and machine learning technology to understand how gene expression regulates an organism's circadian clock.

The inner 24-hour cycles – or circadian rhythms – are key to maintaining human, plant and animal health. The word circadian originates from the Latin phrase circa diem which means ‘around a day’.

Circadian rhythms, such as the sleep-wake cycle, are critical to life on Earth, orchestrating an organism’s physiology, biochemistry and metabolism across the 24-hour day-night cycle. This is why being out of kilter can affect our fitness levels, our health or our ability to survive. For example, experiencing jet lag occurs when our body clocks are out of sync because the normal external cues such as light or temperature have changed.

The circadian clock isn’t unique to humans. Plants also have an in-built clock that helps to regulate a huge range of processes – including flowering time, plant metabolism and mineral uptake – by syncing with the rising and setting of the sun. Getting a better understanding of circadian rhythms can help to improve plant growth and yields, not to mention revealing new opportunities to tackle human diseases.

We know that plants are healthier and have higher yields when their circadian clocks are in sync with their external surroundings. Knowing how the clock functions in key crops, such as bread wheat, has clear agricultural potential.

Beyond plants

The research team at the Earlham Institute applied machine learning to predict complex time-based patterns in a specific plant called Arabidopsis thaliana. This plant is popular for scientific modelling and is used often for plant biology and genetics research. By analysing new and published data as well as the plant’s genomes, the researchers trained machine learning models to make predictions about how circadian rhythms regulate the behaviour of genes and what they do.

Lead author Dr Laura-Jayne Gardiner from IBM Research Europe, and formerly of the Earlham Institute, said: “Essentially, our inner rhythm is driven by a circadian clock, which is a biochemical oscillator synchronised with solar time or the position of the sun in the sky.

"In most living things, including animals, plants and fungi, internally synchronised circadian clocks make it possible for an organism to anticipate daily environmental changes corresponding with the day-night cycle – and adjust its biology and behaviour accordingly.”

Prof Anthony Hall, Group Leader at the Earlham Institute, said: “Genes involved in the circadian clock typically show an oscillation between off-on state rhythmic patterns throughout a 24-hour period. This pattern is called circadian rhythmicity.

“Detecting circadian rhythmicity with existing methods is challenging. To measure gene expression throughout the day is not only expensive, but it is also time-consuming for laboratory scientists. Consequently, our knowledge to date of how genes are controlled and regulated in a circadian clock has been limited.”

Artificial intelligence

The team’s development of AI and machine learning technology has now been adapted for wheat to show that the methods used offer accurate analysis of key food crops.

Dr Gardiner explained: “Our machine learning models and their application to crops, where circadian rhythms are critical to maintaining healthy growth and development, could lead to increased yields as agricultural scientists and farmers begin to use the model to understand the inner rhythms of the plants they grow and harvest.

“However, the technology we have developed goes beyond the scope of just plants. We are now looking at different species to investigate the circadian clock and its link to disease in humans, for example, where the dysregulation of the circadian clock has been associated with a range of diseases from depression to cancer.

“What makes our models more informative is our usage of explainable AI algorithms. We want to use the findings from our machine learning models to better understand the predictions they make.”

Ultimately, the application of this model could help farmers and agricultural scientists to develop methods to improve yields for important crops like wheat and, in the future, help to address the causes of some human diseases and conditions.

Find out more about the Earlham Institute at www.earlham.ac.uk